Discussion:
ERROR is reading parquet data after create table
Herman Tan
2018-09-20 02:02:06 UTC
Permalink
Hi,

I encountered the following error.
The Steps I did are as follows:
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)

The error:
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.

When I re-run this, the number of tasks will vary.

What could be the problem?

Regards,
Herman Tan

More info below:

This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----

create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int) dim_pos_employee_purchase_key
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key end as
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;

drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;

create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;

select *
from dfs.tmp.load_pos_sales_detail_tbl
;

----- ERROR ----------------------------

SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.


[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch parquet
metadata' are complete. Total number of tasks 29, parallelism 16.


[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism 16.


[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism 16.


[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]

----------------------------------------
From Drill log:

2018-09-20 08:58:12,035 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl

2018-09-20 08:58:53,068 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but only
10 tasks for 'Fetch parquet metadata' are complete. Total number of tasks
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:86)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:57)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$toList$2(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetFileMetadata_v3(Metadata.java:340)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:324)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:305)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:124)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.initInternal(ParquetGroupScan.java:254)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(AbstractParquetGroupScan.java:380)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:132)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:102)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:70)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(FileSystemPlugin.java:136)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:116)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:111)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.getGroupScan(DrillTable.java:99)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:89)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:69)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:62)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(DrillScanRule.java:38)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:212)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:652)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:368)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:429)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:369)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToRawDrel(DefaultSqlHandler.java:255)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:318)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getQueryPlan(DrillSqlWorker.java:145)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:83)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error Occurred: Waited for
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE ERROR: Waited
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16.


[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$Builder.build(UserException.java:633)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:253)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetFileMetadata_v3(Metadata.java:340)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:324)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:305)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:124)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.initInternal(ParquetGroupScan.java:254)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(AbstractParquetGroupScan.java:380)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:132)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:102)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:70)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(FileSystemPlugin.java:136)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:116)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:111)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.getGroupScan(DrillTable.java:99)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:89)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:69)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:62)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(DrillScanRule.java:38)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:212)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:652)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:368)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:429)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:369)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToRawDrel(DefaultSqlHandler.java:255)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:318)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getQueryPlan(DrillSqlWorker.java:145)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:83)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:86)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:57)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$toList$2(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of rpc type 3
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl

2018-09-20 09:02:42,615 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but only
10 tasks for 'Fetch parquet metadata' are complete. Total number of tasks
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:86)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:57)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$toList$2(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetFileMetadata_v3(Metadata.java:340)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:324)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:305)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:124)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.initInternal(ParquetGroupScan.java:254)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(AbstractParquetGroupScan.java:380)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:132)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:102)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:70)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(FileSystemPlugin.java:136)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:116)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:111)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.getGroupScan(DrillTable.java:99)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:89)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:69)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:62)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(DrillScanRule.java:38)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:212)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:652)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:368)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:429)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:369)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToRawDrel(DefaultSqlHandler.java:255)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:318)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getQueryPlan(DrillSqlWorker.java:145)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:83)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error Occurred: Waited for
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE ERROR: Waited
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16.


[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$Builder.build(UserException.java:633)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:253)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetFileMetadata_v3(Metadata.java:340)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:324)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:305)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:124)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.initInternal(ParquetGroupScan.java:254)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(AbstractParquetGroupScan.java:380)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:132)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:102)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:70)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(FileSystemPlugin.java:136)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:116)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:111)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.getGroupScan(DrillTable.java:99)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:89)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:69)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:62)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(DrillScanRule.java:38)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:212)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:652)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:368)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:429)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:369)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToRawDrel(DefaultSqlHandler.java:255)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:318)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getQueryPlan(DrillSqlWorker.java:145)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:83)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:86)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:57)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$toList$2(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted


----------------------------------------
----------
Karthikeyan Manivannan
2018-09-20 18:15:08 UTC
Permalink
Hi Herman,

I am not sure what the exact problem here is but can you check to see if
you are not hitting the problem described here:

http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%3CCACwRgneXLXoP2vCYuGsA4Gwd1jGS8F+***@mail.gmail.com%3E

Thanks

Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int) dim_pos_employee_purchase_key
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key end as
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch parquet
metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but only
10 tasks for 'Fetch parquet metadata' are complete. Total number of tasks
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:86)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:57)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$toList$2(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetFileMetadata_v3(Metadata.java:340)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:324)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:305)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:124)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.initInternal(ParquetGroupScan.java:254)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(AbstractParquetGroupScan.java:380)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:132)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:102)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:70)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(FileSystemPlugin.java:136)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:116)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:111)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.getGroupScan(DrillTable.java:99)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:89)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:69)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:62)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(DrillScanRule.java:38)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:212)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:652)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:368)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:429)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:369)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToRawDrel(DefaultSqlHandler.java:255)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:318)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getQueryPlan(DrillSqlWorker.java:145)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:83)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error Occurred: Waited for
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE ERROR: Waited
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$Builder.build(UserException.java:633)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:253)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetFileMetadata_v3(Metadata.java:340)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:324)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:305)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:124)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.initInternal(ParquetGroupScan.java:254)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(AbstractParquetGroupScan.java:380)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:132)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:102)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:70)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(FileSystemPlugin.java:136)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:116)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:111)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.getGroupScan(DrillTable.java:99)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:89)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:69)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:62)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(DrillScanRule.java:38)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:212)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:652)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:368)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:429)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:369)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToRawDrel(DefaultSqlHandler.java:255)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:318)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getQueryPlan(DrillSqlWorker.java:145)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:83)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:86)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:57)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$toList$2(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of rpc type 3
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but only
10 tasks for 'Fetch parquet metadata' are complete. Total number of tasks
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:86)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:57)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$toList$2(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetFileMetadata_v3(Metadata.java:340)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:324)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:305)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:124)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.initInternal(ParquetGroupScan.java:254)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(AbstractParquetGroupScan.java:380)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:132)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:102)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:70)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(FileSystemPlugin.java:136)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:116)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:111)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.getGroupScan(DrillTable.java:99)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:89)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:69)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:62)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(DrillScanRule.java:38)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:212)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:652)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:368)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:429)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:369)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToRawDrel(DefaultSqlHandler.java:255)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:318)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getQueryPlan(DrillSqlWorker.java:145)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:83)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error Occurred: Waited for
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE ERROR: Waited
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$Builder.build(UserException.java:633)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:253)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetFileMetadata_v3(Metadata.java:340)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:324)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:305)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.getParquetTableMetadata(Metadata.java:124)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.initInternal(ParquetGroupScan.java:254)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(AbstractParquetGroupScan.java:380)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:132)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<init>(ParquetGroupScan.java:102)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(ParquetFormatPlugin.java:70)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(FileSystemPlugin.java:136)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:116)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(AbstractStoragePlugin.java:111)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.getGroupScan(DrillTable.java:99)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:89)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:69)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(DrillScanRel.java:62)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(DrillScanRule.java:38)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:212)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:652)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:368)
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:429)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(DefaultSqlHandler.java:369)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToRawDrel(DefaultSqlHandler.java:255)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:318)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:180)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getQueryPlan(DrillSqlWorker.java:145)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:83)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:86)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.apply(TimedCallable.java:57)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$toList$2(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(Collectors.java:97)
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Herman Tan
2018-09-23 06:49:22 UTC
Permalink
Hi Karthik,

Thank you for pointing me to the mail archive in May 2018.
That is exactly the same problem I am facing.

I thought of using Drill as an ETL where I load the warehouse parquet
tables from text source files.
Then I query the parquet tables.
It works on some parquet tables but am having problems with large ones that
consist of several files. (I think)
Still investigating.
Anyone in the community have other experience?
Should I work with all text files instead of parquet?


Herman


On Fri, Sep 21, 2018 at 2:15 AM, Karthikeyan Manivannan <
Post by Karthikeyan Manivannan
Hi Herman,
I am not sure what the exact problem here is but can you check to see if
http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%
Thanks
Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key end
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet
Post by Herman Tan
metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number of tasks
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error Occurred: Waited
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE ERROR: Waited
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:253)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of rpc
type 3
Post by Herman Tan
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number of tasks
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error Occurred: Waited
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE ERROR: Waited
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:253)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.<
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.<init>(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Kunal Khatua
2018-09-24 01:08:47 UTC
Permalink
Hi Herman

Assuming that you're doing analytics on your data. If that's the case, parquet format is the way to go. 

That said, could you provide some details about the parquet data you've created, like the schema, parquet version and the tool used to generate. Usually, the schema (and meta) provides most of these details for any parquet file.

It'll be useful to know if there is a pattern in the failure because of which there might be corruption occurring.

Kunal

 
On 9/22/2018 11:49:36 PM, Herman Tan <***@redcubesg.com> wrote:
Hi Karthik,

Thank you for pointing me to the mail archive in May 2018.
That is exactly the same problem I am facing.

I thought of using Drill as an ETL where I load the warehouse parquet
tables from text source files.
Then I query the parquet tables.
It works on some parquet tables but am having problems with large ones that
consist of several files. (I think)
Still investigating.
Anyone in the community have other experience?
Should I work with all text files instead of parquet?


Herman


On Fri, Sep 21, 2018 at 2:15 AM, Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Hi Herman,
I am not sure what the exact problem here is but can you check to see if
http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%
Thanks
Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key end
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet
Post by Herman Tan
metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number of tasks
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error Occurred: Waited
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE ERROR: Waited
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:253)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of rpc
type 3
Post by Herman Tan
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number of tasks
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error Occurred: Waited
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE ERROR: Waited
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:253)
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.transform(
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(TimedCallable.java:214)
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Herman Tan
2018-09-26 07:35:46 UTC
Permalink
Hi Kunal,

----
That said, could you provide some details about the parquet data you've
created, like the schema, parquet version and the tool used to generate.
Usually, the schema (and meta) provides most of these details for any
parquet file.
----

1. The schema is under dfs.tmp, the queries to generate are all documented
below.
2. I don't know how to find the parquet version of the data file
3. The tool used to generate the parquest is apache drill. The CTAS is
detailed below.

Regards,
Herman
____________

*This is the Text data*

This is the folders of the files
Total # of lines about 50 million rows
----------
show files from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
20180825`
;
show files from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----

*This is the view with the metadata defined:*

create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int) dim_pos_employee_purchase_key
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key end as
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;


*This is the CTAS that generates the parquet from the view above:*

drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;

create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;


*This is the select query that generated the error:*

select *
from dfs.tmp.load_pos_sales_detail_tbl
;

----- ERROR ----------------------------

SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
Post by Karthikeyan Manivannan
Hi Herman
Assuming that you're doing analytics on your data. If that's the case,
parquet format is the way to go.
That said, could you provide some details about the parquet data you've
created, like the schema, parquet version and the tool used to generate.
Usually, the schema (and meta) provides most of these details for any
parquet file.
It'll be useful to know if there is a pattern in the failure because of
which there might be corruption occurring.
Kunal
Hi Karthik,
Thank you for pointing me to the mail archive in May 2018.
That is exactly the same problem I am facing.
I thought of using Drill as an ETL where I load the warehouse parquet
tables from text source files.
Then I query the parquet tables.
It works on some parquet tables but am having problems with large ones that
consist of several files. (I think)
Still investigating.
Anyone in the community have other experience?
Should I work with all text files instead of parquet?
Herman
On Fri, Sep 21, 2018 at 2:15 AM, Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Hi Herman,
I am not sure what the exact problem here is but can you check to see if
http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%
Thanks
Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key end
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet
Post by Herman Tan
metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number of
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080 [245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error Occurred: Waited
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16. (null)
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of rpc
type 3
Post by Herman Tan
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number of
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625 [245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error Occurred: Waited
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are complete.
Total number of tasks 29, parallelism 16. (null)
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:567)
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Divya Gehlot
2018-09-27 03:49:11 UTC
Permalink
Hi Herman,
Just to ensure that your parquet file format is not corrupted , Can you
please query a folder like just 2001 or some of the files underneath
.Instead of querying the whole data set at once .

Thanks,
Divya
Post by Herman Tan
Hi Kunal,
----
That said, could you provide some details about the parquet data you've
created, like the schema, parquet version and the tool used to generate.
Usually, the schema (and meta) provides most of these details for any
parquet file.
----
1. The schema is under dfs.tmp, the queries to generate are all documented
below.
2. I don't know how to find the parquet version of the data file
3. The tool used to generate the parquest is apache drill. The CTAS is
detailed below.
Regards,
Herman
____________
*This is the Text data*
This is the folders of the files
Total # of lines about 50 million rows
----------
show files from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
20180825`
;
show files from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
*This is the view with the metadata defined:*
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int) dim_pos_employee_purchase_key
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key end as
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
*This is the CTAS that generates the parquet from the view above:*
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
*This is the select query that generated the error:*
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
Post by Karthikeyan Manivannan
Hi Herman
Assuming that you're doing analytics on your data. If that's the case,
parquet format is the way to go.
That said, could you provide some details about the parquet data you've
created, like the schema, parquet version and the tool used to generate.
Usually, the schema (and meta) provides most of these details for any
parquet file.
It'll be useful to know if there is a pattern in the failure because of
which there might be corruption occurring.
Kunal
Hi Karthik,
Thank you for pointing me to the mail archive in May 2018.
That is exactly the same problem I am facing.
I thought of using Drill as an ETL where I load the warehouse parquet
tables from text source files.
Then I query the parquet tables.
It works on some parquet tables but am having problems with large ones
that
Post by Karthikeyan Manivannan
consist of several files. (I think)
Still investigating.
Anyone in the community have other experience?
Should I work with all text files instead of parquet?
Herman
On Fri, Sep 21, 2018 at 2:15 AM, Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Hi Herman,
I am not sure what the exact problem here is but can you check to see
if
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%
%3E
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Thanks
Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key
end
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet
Post by Herman Tan
metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29, parallelism
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number of
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of rpc
type 3
Post by Herman Tan
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms, but
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number of
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:266)
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Herman Tan
2018-10-02 08:44:05 UTC
Permalink
Hi Divya and everyone,

The problem has disappeared.
Drill was not restarted.
This appears to be intermittent.
Before I submitted the error report, I ran the script several times and it
failed all the time.
Today I ran it again and it succeeded.
I will restart and test again.

Regards,
Herman
Post by Karthikeyan Manivannan
Hi Herman,
Just to ensure that your parquet file format is not corrupted , Can you
please query a folder like just 2001 or some of the files underneath
.Instead of querying the whole data set at once .
Thanks,
Divya
Post by Herman Tan
Hi Kunal,
----
That said, could you provide some details about the parquet data you've
created, like the schema, parquet version and the tool used to generate.
Usually, the schema (and meta) provides most of these details for any
parquet file.
----
1. The schema is under dfs.tmp, the queries to generate are all
documented
Post by Herman Tan
below.
2. I don't know how to find the parquet version of the data file
3. The tool used to generate the parquest is apache drill. The CTAS is
detailed below.
Regards,
Herman
____________
*This is the Text data*
This is the folders of the files
Total # of lines about 50 million rows
----------
show files from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
20180825`
;
show files from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
*This is the view with the metadata defined:*
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int) dim_pos_employee_purchase_key
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key end
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
*This is the CTAS that generates the parquet from the view above:*
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
*This is the select query that generated the error:*
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
Post by Karthikeyan Manivannan
Hi Herman
Assuming that you're doing analytics on your data. If that's the case,
parquet format is the way to go.
That said, could you provide some details about the parquet data you've
created, like the schema, parquet version and the tool used to
generate.
Post by Herman Tan
Post by Karthikeyan Manivannan
Usually, the schema (and meta) provides most of these details for any
parquet file.
It'll be useful to know if there is a pattern in the failure because of
which there might be corruption occurring.
Kunal
Hi Karthik,
Thank you for pointing me to the mail archive in May 2018.
That is exactly the same problem I am facing.
I thought of using Drill as an ETL where I load the warehouse parquet
tables from text source files.
Then I query the parquet tables.
It works on some parquet tables but am having problems with large ones
that
Post by Karthikeyan Manivannan
consist of several files. (I think)
Still investigating.
Anyone in the community have other experience?
Should I work with all text files instead of parquet?
Herman
On Fri, Sep 21, 2018 at 2:15 AM, Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Hi Herman,
I am not sure what the exact problem here is but can you check to see
if
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%
%3E
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Thanks
Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks
for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key
end
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks
for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet
Post by Herman Tan
metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms,
but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number of
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of rpc
type 3
Post by Herman Tan
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms,
but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number of
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257) ~[na:1.8.0_172]
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Herman Tan
2018-10-02 10:47:48 UTC
Permalink
Hi,

I have restarted drill and run the script again.

select * from dfs.tmp.`load_pos_sales_detail_tbl`;
-- SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 11 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.

The 29 tasks is related to the 29 parquet files in the folder.
To check if any of the parquet files has an error, I ran the following SQL
on each parquet file in the folder. ALL PASSED. (SQL Below).
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_0_0.parquet`;

So it seems that for this table drill can only get the metadata for 11
parquet files before it times out.
The time-out is a calculation and it varies from size of table.
I checked the source code but I cannot find the calculation of the timeout
of "30000 ms".
When I am lucky, drill can resolve the metadata for 29 files in 30000 ms
and it passes.

I plan to use drill for production but this bothers me that there is a
limit on the number of parquet files and the timeout parameter cannot be
tuned.

Does anyone have any ideas?

Regards,
Herman
-------------- SQL BELOW -------------

select * from dfs.tmp.`load_pos_sales_detail_tbl/1_0_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_10_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_10_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_11_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_11_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_12_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_12_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_13_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_13_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_14_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_15_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_15_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_16_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_16_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_1_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_2_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_3_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_4_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_4_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_5_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_5_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_6_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_6_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_7_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_7_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_8_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_8_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_9_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_9_1.parquet`;
Post by Herman Tan
Hi Divya and everyone,
The problem has disappeared.
Drill was not restarted.
This appears to be intermittent.
Before I submitted the error report, I ran the script several times and it
failed all the time.
Today I ran it again and it succeeded.
I will restart and test again.
Regards,
Herman
Post by Karthikeyan Manivannan
Hi Herman,
Just to ensure that your parquet file format is not corrupted , Can you
please query a folder like just 2001 or some of the files underneath
.Instead of querying the whole data set at once .
Thanks,
Divya
Post by Herman Tan
Hi Kunal,
----
That said, could you provide some details about the parquet data you've
created, like the schema, parquet version and the tool used to generate.
Usually, the schema (and meta) provides most of these details for any
parquet file.
----
1. The schema is under dfs.tmp, the queries to generate are all
documented
Post by Herman Tan
below.
2. I don't know how to find the parquet version of the data file
3. The tool used to generate the parquest is apache drill. The CTAS is
detailed below.
Regards,
Herman
____________
*This is the Text data*
This is the folders of the files
Total # of lines about 50 million rows
----------
show files from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
20180825`
;
show files from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
*This is the view with the metadata defined:*
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key end
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
*This is the CTAS that generates the parquet from the view above:*
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
*This is the select query that generated the error:*
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
Post by Karthikeyan Manivannan
Hi Herman
Assuming that you're doing analytics on your data. If that's the case,
parquet format is the way to go.
That said, could you provide some details about the parquet data
you've
Post by Herman Tan
Post by Karthikeyan Manivannan
created, like the schema, parquet version and the tool used to
generate.
Post by Herman Tan
Post by Karthikeyan Manivannan
Usually, the schema (and meta) provides most of these details for any
parquet file.
It'll be useful to know if there is a pattern in the failure because
of
Post by Herman Tan
Post by Karthikeyan Manivannan
which there might be corruption occurring.
Kunal
Hi Karthik,
Thank you for pointing me to the mail archive in May 2018.
That is exactly the same problem I am facing.
I thought of using Drill as an ETL where I load the warehouse parquet
tables from text source files.
Then I query the parquet tables.
It works on some parquet tables but am having problems with large ones
that
Post by Karthikeyan Manivannan
consist of several files. (I think)
Still investigating.
Anyone in the community have other experience?
Should I work with all text files instead of parquet?
Herman
On Fri, Sep 21, 2018 at 2:15 AM, Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Hi Herman,
I am not sure what the exact problem here is but can you check to
see
Post by Herman Tan
if
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%
%3E
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Thanks
Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks
for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else
dim_site_lfl_key
Post by Herman Tan
end
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks
for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet
Post by Herman Tan
metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms,
but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number
of
Post by Herman Tan
Post by Karthikeyan Manivannan
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of
rpc
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
type 3
Post by Herman Tan
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query id
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms,
but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number
of
Post by Herman Tan
Post by Karthikeyan Manivannan
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Herman Tan
2018-10-02 11:29:28 UTC
Permalink
Hi,

I found the hard coded parameter in the source code

https://github.com/apache/drill/blob/8edeb49873d1a1710cfe28e0b49364d07eb1aef4/exec/java-exec/src/main/java/org/apache/drill/exec/store/TimedCallable.java

LINE 52 : private static long TIMEOUT_PER_RUNNABLE_IN_MSECS = 15000;
LINE 210 :timeout = TIMEOUT_PER_RUNNABLE_IN_MSECS * ((tasks.size() -
1)/parallelism + 1);

parallelism param is also hardcoded
https://github.com/apache/drill/blob/master/exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/metadata/Metadata.java
LINE 343: 16

In my case: task size is 29, 15000 * ((29-1)/(16+1)) = 15000 * 2 = 30000
16 runnables executes round robbin on 29 tasks. Each runnable given 30000
ms to timeout.

This is the error message:
Waited for 30000 ms, but only 11 tasks for 'Fetch parquet metadata' are
complete. Total number of tasks 29, parallelism 16.

TimedCallable.java:
LINE 248: final String errMsg = String.format("Waited for %d ms, but
only %d tasks for '%s' are complete." +
" Total number of tasks %d, parallelism %d.", timeout,
futureMapper.count, activity, tasks.size(), parallelism);

Shouldn't these be parameterized in "options" based on the infrastructure?

Regards,
Herman
Post by Herman Tan
Hi,
I have restarted drill and run the script again.
select * from dfs.tmp.`load_pos_sales_detail_tbl`;
-- SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 11 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
The 29 tasks is related to the 29 parquet files in the folder.
To check if any of the parquet files has an error, I ran the following SQL
on each parquet file in the folder. ALL PASSED. (SQL Below).
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_0_0.parquet`;
So it seems that for this table drill can only get the metadata for 11
parquet files before it times out.
The time-out is a calculation and it varies from size of table.
I checked the source code but I cannot find the calculation of the timeout
of "30000 ms".
When I am lucky, drill can resolve the metadata for 29 files in 30000 ms
and it passes.
I plan to use drill for production but this bothers me that there is a
limit on the number of parquet files and the timeout parameter cannot be
tuned.
Does anyone have any ideas?
Regards,
Herman
-------------- SQL BELOW -------------
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_0_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_10_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_10_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_11_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_11_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_12_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_12_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_13_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_13_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_14_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_15_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_15_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_16_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_16_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_1_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_2_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_3_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_4_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_4_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_5_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_5_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_6_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_6_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_7_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_7_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_8_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_8_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_9_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_9_1.parquet`;
Post by Herman Tan
Hi Divya and everyone,
The problem has disappeared.
Drill was not restarted.
This appears to be intermittent.
Before I submitted the error report, I ran the script several times and
it failed all the time.
Today I ran it again and it succeeded.
I will restart and test again.
Regards,
Herman
Post by Karthikeyan Manivannan
Hi Herman,
Just to ensure that your parquet file format is not corrupted , Can you
please query a folder like just 2001 or some of the files underneath
.Instead of querying the whole data set at once .
Thanks,
Divya
Post by Herman Tan
Hi Kunal,
----
That said, could you provide some details about the parquet data you've
created, like the schema, parquet version and the tool used to
generate.
Post by Herman Tan
Usually, the schema (and meta) provides most of these details for any
parquet file.
----
1. The schema is under dfs.tmp, the queries to generate are all
documented
Post by Herman Tan
below.
2. I don't know how to find the parquet version of the data file
3. The tool used to generate the parquest is apache drill. The CTAS is
detailed below.
Regards,
Herman
____________
*This is the Text data*
This is the folders of the files
Total # of lines about 50 million rows
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
Post by Herman Tan
20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
Post by Herman Tan
20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
*This is the view with the metadata defined:*
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key
end as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
*This is the CTAS that generates the parquet from the view above:*
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
*This is the select query that generated the error:*
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
Post by Karthikeyan Manivannan
Hi Herman
Assuming that you're doing analytics on your data. If that's the
case,
Post by Herman Tan
Post by Karthikeyan Manivannan
parquet format is the way to go.
That said, could you provide some details about the parquet data
you've
Post by Herman Tan
Post by Karthikeyan Manivannan
created, like the schema, parquet version and the tool used to
generate.
Post by Herman Tan
Post by Karthikeyan Manivannan
Usually, the schema (and meta) provides most of these details for any
parquet file.
It'll be useful to know if there is a pattern in the failure because
of
Post by Herman Tan
Post by Karthikeyan Manivannan
which there might be corruption occurring.
Kunal
Hi Karthik,
Thank you for pointing me to the mail archive in May 2018.
That is exactly the same problem I am facing.
I thought of using Drill as an ETL where I load the warehouse parquet
tables from text source files.
Then I query the parquet tables.
It works on some parquet tables but am having problems with large
ones
Post by Herman Tan
that
Post by Karthikeyan Manivannan
consist of several files. (I think)
Still investigating.
Anyone in the community have other experience?
Should I work with all text files instead of parquet?
Herman
On Fri, Sep 21, 2018 at 2:15 AM, Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Hi Herman,
I am not sure what the exact problem here is but can you check to
see
Post by Herman Tan
if
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%
%3E
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Thanks
Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10
tasks for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else
dim_site_lfl_key
Post by Herman Tan
end
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10
tasks for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet
Post by Herman Tan
metadata' are complete. Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for 'Fetch
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query
id
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms,
but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number
of
Post by Herman Tan
Post by Karthikeyan Manivannan
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of
rpc
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
type 3
Post by Herman Tan
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query
id
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms,
but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number
of
Post by Herman Tan
Post by Karthikeyan Manivannan
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Herman Tan
2018-11-12 01:01:35 UTC
Permalink
Hi,

I am running into this problem again.
The solution is to define a view that is a "union all" of individual select
queries of single csv files.
Can I request that the hardcoded timeout values be parametrized please?

Herman
Post by Herman Tan
Hi,
I found the hard coded parameter in the source code
https://github.com/apache/drill/blob/8edeb49873d1a1710cfe28e0b49364d07eb1aef4/exec/java-exec/src/main/java/org/apache/drill/exec/store/TimedCallable.java
LINE 52 : private static long TIMEOUT_PER_RUNNABLE_IN_MSECS = 15000;
LINE 210 :timeout = TIMEOUT_PER_RUNNABLE_IN_MSECS * ((tasks.size() -
1)/parallelism + 1);
parallelism param is also hardcoded
https://github.com/apache/drill/blob/master/exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/metadata/Metadata.java
LINE 343: 16
In my case: task size is 29, 15000 * ((29-1)/(16+1)) = 15000 * 2 = 30000
16 runnables executes round robbin on 29 tasks. Each runnable given 30000
ms to timeout.
Waited for 30000 ms, but only 11 tasks for 'Fetch parquet metadata' are
complete. Total number of tasks 29, parallelism 16.
LINE 248: final String errMsg = String.format("Waited for %d ms, but
only %d tasks for '%s' are complete." +
" Total number of tasks %d, parallelism %d.", timeout,
futureMapper.count, activity, tasks.size(), parallelism);
Shouldn't these be parameterized in "options" based on the infrastructure?
Regards,
Herman
Post by Herman Tan
Hi,
I have restarted drill and run the script again.
select * from dfs.tmp.`load_pos_sales_detail_tbl`;
-- SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 11 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
The 29 tasks is related to the 29 parquet files in the folder.
To check if any of the parquet files has an error, I ran the following
SQL on each parquet file in the folder. ALL PASSED. (SQL Below).
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_0_0.parquet`;
So it seems that for this table drill can only get the metadata for 11
parquet files before it times out.
The time-out is a calculation and it varies from size of table.
I checked the source code but I cannot find the calculation of the
timeout of "30000 ms".
When I am lucky, drill can resolve the metadata for 29 files in 30000 ms
and it passes.
I plan to use drill for production but this bothers me that there is a
limit on the number of parquet files and the timeout parameter cannot be
tuned.
Does anyone have any ideas?
Regards,
Herman
-------------- SQL BELOW -------------
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_0_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_10_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_10_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_11_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_11_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_12_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_12_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_13_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_13_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_14_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_15_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_15_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_16_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_16_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_1_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_2_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_3_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_4_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_4_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_5_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_5_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_6_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_6_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_7_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_7_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_8_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_8_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_9_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_9_1.parquet`;
Post by Herman Tan
Hi Divya and everyone,
The problem has disappeared.
Drill was not restarted.
This appears to be intermittent.
Before I submitted the error report, I ran the script several times and
it failed all the time.
Today I ran it again and it succeeded.
I will restart and test again.
Regards,
Herman
Post by Karthikeyan Manivannan
Hi Herman,
Just to ensure that your parquet file format is not corrupted , Can you
please query a folder like just 2001 or some of the files underneath
.Instead of querying the whole data set at once .
Thanks,
Divya
Post by Herman Tan
Hi Kunal,
----
That said, could you provide some details about the parquet data
you've
Post by Herman Tan
created, like the schema, parquet version and the tool used to
generate.
Post by Herman Tan
Usually, the schema (and meta) provides most of these details for any
parquet file.
----
1. The schema is under dfs.tmp, the queries to generate are all
documented
Post by Herman Tan
below.
2. I don't know how to find the parquet version of the data file
3. The tool used to generate the parquest is apache drill. The CTAS
is
Post by Herman Tan
detailed below.
Regards,
Herman
____________
*This is the Text data*
This is the folders of the files
Total # of lines about 50 million rows
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
Post by Herman Tan
20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
Post by Herman Tan
20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
*This is the view with the metadata defined:*
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key
end as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
*This is the CTAS that generates the parquet from the view above:*
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
*This is the select query that generated the error:*
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
Post by Karthikeyan Manivannan
Hi Herman
Assuming that you're doing analytics on your data. If that's the
case,
Post by Herman Tan
Post by Karthikeyan Manivannan
parquet format is the way to go.
That said, could you provide some details about the parquet data
you've
Post by Herman Tan
Post by Karthikeyan Manivannan
created, like the schema, parquet version and the tool used to
generate.
Post by Herman Tan
Post by Karthikeyan Manivannan
Usually, the schema (and meta) provides most of these details for
any
Post by Herman Tan
Post by Karthikeyan Manivannan
parquet file.
It'll be useful to know if there is a pattern in the failure
because of
Post by Herman Tan
Post by Karthikeyan Manivannan
which there might be corruption occurring.
Kunal
Hi Karthik,
Thank you for pointing me to the mail archive in May 2018.
That is exactly the same problem I am facing.
I thought of using Drill as an ETL where I load the warehouse
parquet
Post by Herman Tan
Post by Karthikeyan Manivannan
tables from text source files.
Then I query the parquet tables.
It works on some parquet tables but am having problems with large
ones
Post by Herman Tan
that
Post by Karthikeyan Manivannan
consist of several files. (I think)
Still investigating.
Anyone in the community have other experience?
Should I work with all text files instead of parquet?
Herman
On Fri, Sep 21, 2018 at 2:15 AM, Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Hi Herman,
I am not sure what the exact problem here is but can you check to
see
Post by Herman Tan
if
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%
%3E
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Thanks
Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10
tasks for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else
dim_site_lfl_key
Post by Herman Tan
end
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10
tasks for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
parquet
Post by Herman Tan
metadata' are complete. Total number of tasks 29, parallelism
16.
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query
id
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000
ms, but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total
number of
Post by Herman Tan
Post by Karthikeyan Manivannan
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of
rpc
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
type 3
Post by Herman Tan
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query
id
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000
ms, but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total
number of
Post by Herman Tan
Post by Karthikeyan Manivannan
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Divya Gehlot
2018-10-11 07:25:40 UTC
Permalink
Hi ,
Can somebody clarify on the number of tasks, What I understood from Herman
is if you have 29 parquet files than Drill actually creates 29 tasks .

Herman , Can I know you are running drill on embedded mode or distributed
mode.

I am running Drill in production for multiple sources and I do have many(
like 2 years worth of data) parquet files and never encountered this issue
.
Yeah at times when I have parquet in multi directory hierarchy or parquet
files are small I do get either time out or query is too slow .

Thoughts please?

Thanks,
Divya
Post by Herman Tan
Hi,
I have restarted drill and run the script again.
select * from dfs.tmp.`load_pos_sales_detail_tbl`;
-- SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 11 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
The 29 tasks is related to the 29 parquet files in the folder.
To check if any of the parquet files has an error, I ran the following SQL
on each parquet file in the folder. ALL PASSED. (SQL Below).
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_0_0.parquet`;
So it seems that for this table drill can only get the metadata for 11
parquet files before it times out.
The time-out is a calculation and it varies from size of table.
I checked the source code but I cannot find the calculation of the timeout
of "30000 ms".
When I am lucky, drill can resolve the metadata for 29 files in 30000 ms
and it passes.
I plan to use drill for production but this bothers me that there is a
limit on the number of parquet files and the timeout parameter cannot be
tuned.
Does anyone have any ideas?
Regards,
Herman
-------------- SQL BELOW -------------
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_0_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_10_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_10_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_11_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_11_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_12_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_12_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_13_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_13_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_14_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_15_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_15_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_16_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_16_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_1_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_2_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_3_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_4_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_4_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_5_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_5_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_6_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_6_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_7_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_7_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_8_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_8_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_9_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_9_1.parquet`;
Post by Herman Tan
Hi Divya and everyone,
The problem has disappeared.
Drill was not restarted.
This appears to be intermittent.
Before I submitted the error report, I ran the script several times and
it
Post by Herman Tan
failed all the time.
Today I ran it again and it succeeded.
I will restart and test again.
Regards,
Herman
Post by Karthikeyan Manivannan
Hi Herman,
Just to ensure that your parquet file format is not corrupted , Can you
please query a folder like just 2001 or some of the files underneath
.Instead of querying the whole data set at once .
Thanks,
Divya
Post by Herman Tan
Hi Kunal,
----
That said, could you provide some details about the parquet data
you've
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
created, like the schema, parquet version and the tool used to
generate.
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Usually, the schema (and meta) provides most of these details for any
parquet file.
----
1. The schema is under dfs.tmp, the queries to generate are all
documented
Post by Herman Tan
below.
2. I don't know how to find the parquet version of the data file
3. The tool used to generate the parquest is apache drill. The CTAS
is
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
detailed below.
Regards,
Herman
____________
*This is the Text data*
This is the folders of the files
Total # of lines about 50 million rows
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
*This is the view with the metadata defined:*
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key
end
Post by Herman Tan
Post by Karthikeyan Manivannan
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
;
*This is the CTAS that generates the parquet from the view above:*
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
*This is the select query that generated the error:*
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
Post by Karthikeyan Manivannan
Hi Herman
Assuming that you're doing analytics on your data. If that's the
case,
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
parquet format is the way to go.
That said, could you provide some details about the parquet data
you've
Post by Herman Tan
Post by Karthikeyan Manivannan
created, like the schema, parquet version and the tool used to
generate.
Post by Herman Tan
Post by Karthikeyan Manivannan
Usually, the schema (and meta) provides most of these details for
any
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
parquet file.
It'll be useful to know if there is a pattern in the failure because
of
Post by Herman Tan
Post by Karthikeyan Manivannan
which there might be corruption occurring.
Kunal
Hi Karthik,
Thank you for pointing me to the mail archive in May 2018.
That is exactly the same problem I am facing.
I thought of using Drill as an ETL where I load the warehouse
parquet
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
tables from text source files.
Then I query the parquet tables.
It works on some parquet tables but am having problems with large
ones
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
that
Post by Karthikeyan Manivannan
consist of several files. (I think)
Still investigating.
Anyone in the community have other experience?
Should I work with all text files instead of parquet?
Herman
On Fri, Sep 21, 2018 at 2:15 AM, Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Hi Herman,
I am not sure what the exact problem here is but can you check to
see
Post by Herman Tan
if
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%
%3E
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Thanks
Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not work)
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10
tasks
Post by Herman Tan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else
dim_site_lfl_key
Post by Herman Tan
end
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10
tasks
Post by Herman Tan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
parquet
Post by Herman Tan
metadata' are complete. Total number of tasks 29, parallelism
16.
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query
id
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms,
but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number
of
Post by Herman Tan
Post by Karthikeyan Manivannan
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST of
rpc
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
type 3
Post by Herman Tan
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for query
id
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000 ms,
but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total number
of
Post by Herman Tan
Post by Karthikeyan Manivannan
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Herman Tan
2018-10-11 07:28:12 UTC
Permalink
I am running in single instance embedded mode under windows.
Post by Divya Gehlot
Hi ,
Can somebody clarify on the number of tasks, What I understood from Herman
is if you have 29 parquet files than Drill actually creates 29 tasks .
Herman , Can I know you are running drill on embedded mode or distributed
mode.
I am running Drill in production for multiple sources and I do have many(
like 2 years worth of data) parquet files and never encountered this issue
.
Yeah at times when I have parquet in multi directory hierarchy or parquet
files are small I do get either time out or query is too slow .
Thoughts please?
Thanks,
Divya
Post by Herman Tan
Hi,
I have restarted drill and run the script again.
select * from dfs.tmp.`load_pos_sales_detail_tbl`;
-- SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 11 tasks for
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
The 29 tasks is related to the 29 parquet files in the folder.
To check if any of the parquet files has an error, I ran the following
SQL
Post by Herman Tan
on each parquet file in the folder. ALL PASSED. (SQL Below).
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_0_0.parquet`;
So it seems that for this table drill can only get the metadata for 11
parquet files before it times out.
The time-out is a calculation and it varies from size of table.
I checked the source code but I cannot find the calculation of the
timeout
Post by Herman Tan
of "30000 ms".
When I am lucky, drill can resolve the metadata for 29 files in 30000 ms
and it passes.
I plan to use drill for production but this bothers me that there is a
limit on the number of parquet files and the timeout parameter cannot be
tuned.
Does anyone have any ideas?
Regards,
Herman
-------------- SQL BELOW -------------
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_0_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_10_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_10_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_11_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_11_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_12_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_12_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_13_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_13_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_14_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_15_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_15_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_16_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_16_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_1_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_2_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_3_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_4_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_4_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_5_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_5_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_6_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_6_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_7_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_7_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_8_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_8_1.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_9_0.parquet`;
select * from dfs.tmp.`load_pos_sales_detail_tbl/1_9_1.parquet`;
Post by Herman Tan
Hi Divya and everyone,
The problem has disappeared.
Drill was not restarted.
This appears to be intermittent.
Before I submitted the error report, I ran the script several times and
it
Post by Herman Tan
failed all the time.
Today I ran it again and it succeeded.
I will restart and test again.
Regards,
Herman
Post by Karthikeyan Manivannan
Hi Herman,
Just to ensure that your parquet file format is not corrupted , Can
you
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
please query a folder like just 2001 or some of the files underneath
.Instead of querying the whole data set at once .
Thanks,
Divya
Post by Herman Tan
Hi Kunal,
----
That said, could you provide some details about the parquet data
you've
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
created, like the schema, parquet version and the tool used to
generate.
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Usually, the schema (and meta) provides most of these details for
any
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
parquet file.
----
1. The schema is under dfs.tmp, the queries to generate are all
documented
Post by Herman Tan
below.
2. I don't know how to find the parquet version of the data file
3. The tool used to generate the parquest is apache drill. The CTAS
is
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
detailed below.
Regards,
Herman
____________
*This is the Text data*
This is the folders of the files
Total # of lines about 50 million rows
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
20180825`
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
20180825\2011`
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
*This is the view with the metadata defined:*
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else dim_site_lfl_key
end
Post by Herman Tan
Post by Karthikeyan Manivannan
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
*This is the CTAS that generates the parquet from the view above:*
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
*This is the select query that generated the error:*
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks
for
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks 29,
parallelism 16.
Post by Karthikeyan Manivannan
Hi Herman
Assuming that you're doing analytics on your data. If that's the
case,
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
parquet format is the way to go.
That said, could you provide some details about the parquet data
you've
Post by Herman Tan
Post by Karthikeyan Manivannan
created, like the schema, parquet version and the tool used to
generate.
Post by Herman Tan
Post by Karthikeyan Manivannan
Usually, the schema (and meta) provides most of these details for
any
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
parquet file.
It'll be useful to know if there is a pattern in the failure
because
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
of
Post by Herman Tan
Post by Karthikeyan Manivannan
which there might be corruption occurring.
Kunal
Hi Karthik,
Thank you for pointing me to the mail archive in May 2018.
That is exactly the same problem I am facing.
I thought of using Drill as an ETL where I load the warehouse
parquet
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
tables from text source files.
Then I query the parquet tables.
It works on some parquet tables but am having problems with large
ones
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
that
Post by Karthikeyan Manivannan
consist of several files. (I think)
Still investigating.
Anyone in the community have other experience?
Should I work with all text files instead of parquet?
Herman
On Fri, Sep 21, 2018 at 2:15 AM, Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Hi Herman,
I am not sure what the exact problem here is but can you check
to
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
see
Post by Herman Tan
if
http://mail-archives.apache.org/mod_mbox/drill-user/201805.mbox/%
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
%3E
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Thanks
Karthik
Post by Herman Tan
Hi,
I encountered the following error.
1. Create a view to fix the data type of fields with cast
2. Create table (parquet) using the view
3. Query select * from table (query a field also does not
work)
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10
tasks
Post by Herman Tan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks
29,
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
parallelism 16.
When I re-run this, the number of tasks will vary.
What could be the problem?
Regards,
Herman Tan
This is the folders of the files
Total # of lines, 50 million
----------
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
show files from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825\2011`
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
-----
sales_pos_detail
\pos_details_20180825
\2007
\2008
\2009
\2010
\2011
\pos_details_0.csv
\pos_details_1.csv
\pos_details_2.csv
\pos_details_3.csv
\pos_details_4.csv
\pos_details_5.csv
\pos_details_6.csv
\pos_details_7.csv
\pos_details_8.csv
\2012
\2013
\2014
\2015
\2016
\2017
\2018
\others
-----
create or replace view dfs.tmp.load_pos_sales_detail as
SELECT
-- dimension keys
cast(dim_date_key as int) dim_date_key
,cast(dim_site_key as int) dim_site_key
,cast(dim_pos_header_key as bigint) dim_pos_header_key
,cast(dim_pos_cashier_key as int) dim_pos_cashier_key
,cast(dim_card_number_key as int) dim_card_number_key
,cast(dim_hour_minute_key as int) dim_hour_minute_key
,cast(dim_pos_clerk_key as int) dim_pos_clerk_key
,cast(dim_product_key as int) dim_product_key
,cast(dim_pos_employee_purchase_key as int)
dim_pos_employee_purchase_key
Post by Herman Tan
,cast(dim_pos_terminal_key as int) dim_pos_terminal_key
,cast(dim_campaign_key as int) dim_campaign_key
,cast(dim_promo_key as int) dim_promo_key
,cast( case when dim_site_lfl_key = '' then 0 else
dim_site_lfl_key
Post by Herman Tan
end
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
as
Post by Herman Tan
int) dim_site_lfl_key
-- derived from keys
,dim_date_str
,`year` as `trx_year`
-- Measures
,Product_Sales_Qty
,Product_Sales_Price
,Product_Cost_Price
,Product_Cost_Amt
,Product_Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt
,Product_Sales_Retail_Amt
,Product_Sales_VAT_Amt
,Product_Sales_Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt
from
dfs.`D:\retail_sandbox\pos\sales_pos_detail\pos_details_20180825`
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
;
drop table if exists dfs.tmp.load_pos_sales_detail_tbl
;
create table dfs.tmp.load_pos_sales_detail_tbl AS
SELECT
-- dimension keys
dim_date_key
,dim_site_key
,dim_pos_header_key
,dim_pos_cashier_key
,dim_card_number_key
,dim_hour_minute_key
,dim_pos_clerk_key
,dim_product_key
,dim_pos_employee_purchase_key
,dim_pos_terminal_key
,dim_campaign_key
,dim_promo_key
,dim_site_lfl_key
-- derived from keys
,dim_date_str
,`trx_year`
-- Measures
,Product_Sales_Qty Sales_Qty
,Product_Sales_Price Sales_Price
,Product_Cost_Price Cost_Price
,Product_Cost_Amt Cost_Amt
,Product_Sales_Gross_Amt Sales_Gross_Amt
,Product_Sales_Promo_Disc_Amt Sales_Promo_Disc_Amt
,Product_Sales_Add_Promo_Disc_Amt Add_Promo_Disc_Amt
,Product_Sales_Total_Promo_Disc_Amt Total_Promo_Disc_Amt
,Product_Sales_Retail_Promo_Amt Retail_Promo_Amt
,Product_Sales_Retail_Amt Retail_Amt
,Product_Sales_VAT_Amt VAT_Amt
,Product_Sales_Product_Margin_Amt Product_Margin_Amt
,Product_Sales_Initial_Margin_Amt Initial_Margin_Amt
from dfs.tmp.load_pos_sales_detail
;
select *
from dfs.tmp.load_pos_sales_detail_tbl
;
----- ERROR ----------------------------
SQL Error: RESOURCE ERROR: Waited for 30000 ms, but only 10
tasks
Post by Herman Tan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
'Fetch parquet metadata' are complete. Total number of tasks
29,
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
parquet
Post by Herman Tan
metadata' are complete. Total number of tasks 29, parallelism
16.
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
RESOURCE ERROR: Waited for 30000 ms, but only 10 tasks for
'Fetch
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
parquet metadata' are complete. Total number of tasks 29,
parallelism
Post by Herman Tan
Post by Karthikeyan Manivannan
16.
Post by Karthikeyan Manivannan
Post by Herman Tan
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 on
IORA-G9KY9P2.stf.nus.edu.sg:31010]
----------------------------------------
2018-09-20 08:58:12,035
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for
query
Post by Herman Tan
id
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 08:58:53,068
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000
ms,
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total
number
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
of
Post by Herman Tan
Post by Karthikeyan Manivannan
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 08:58:53,080
[245d0f5a-ae5f-bfa2-ff04-40f7bdd1c2bf:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata'
are
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: f887dcae-9f55-469c-be52-b6ce2a37eeb0 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
2018-09-20 09:02:10,608 [UserServer-1] WARN
o.a.drill.exec.rpc.user.UserServer - Message of mode REQUEST
of
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
rpc
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
type 3
Post by Herman Tan
took longer than 500ms. Actual duration was 2042ms.
2018-09-20 09:02:10,608
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.drill.exec.work.foreman.Foreman - Query text for
query
Post by Herman Tan
id
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc: select *
from dfs.tmp.load_pos_sales_detail_tbl
2018-09-20 09:02:42,615
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
ERROR o.a.d.e.s.parquet.metadata.Metadata - Waited for 30000
ms,
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
but
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
only
Post by Herman Tan
10 tasks for 'Fetch parquet metadata' are complete. Total
number
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
of
Post by Herman Tan
Post by Karthikeyan Manivannan
tasks
Post by Karthikeyan Manivannan
Post by Herman Tan
29, parallelism 16.
java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
2018-09-20 09:02:42,625
[245d0e6f-0dc1-2a4b-12a4-b9aaad4182fc:foreman]
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
INFO o.a.d.e.s.parquet.metadata.Metadata - User Error
Waited
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
for
Post by Herman Tan
30000 ms, but only 10 tasks for 'Fetch parquet metadata' are
complete.
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
Total number of tasks 29, parallelism 16. (null)
org.apache.drill.common.exceptions.UserException: RESOURCE
Waited
Post by Karthikeyan Manivannan
Post by Herman Tan
for 30000 ms, but only 10 tasks for 'Fetch parquet metadata'
are
Post by Herman Tan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
complete.
Post by Herman Tan
Total number of tasks 29, parallelism 16.
[Error Id: 3b079174-f5d0-4313-8097-25a0b3070854 ]
at
org.apache.drill.common.exceptions.UserException$
Builder.build(UserException.java:633)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:253)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetFileMetadata_v3(Metadata.java:340)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:324)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:305)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.metadata.Metadata.
getParquetTableMetadata(Metadata.java:124)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
initInternal(ParquetGroupScan.java:254)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.AbstractParquetGroupScan.init(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractParquetGroupScan.java:380)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:132)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetGroupScan.
init>(ParquetGroupScan.java:102)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.parquet.ParquetFormatPlugin.getGroupScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
ParquetFormatPlugin.java:70)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.dfs.FileSystemPlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
FileSystemPlugin.java:136)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:116)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.AbstractStoragePlugin.getPhysicalScan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
AbstractStoragePlugin.java:111)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillTable.
getGroupScan(DrillTable.java:99)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:89)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:69)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRel.(
DrillScanRel.java:62)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.logical.DrillScanRule.onMatch(
DrillScanRule.java:38)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.calcite.plan.volcano.VolcanoRuleCall.
onMatch(VolcanoRuleCall.java:212)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.calcite.plan.volcano.VolcanoPlanner.
findBestExp(VolcanoPlanner.java:652)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at org.apache.calcite.tools.Programs$RuleSetProgram.run(
Programs.java:368)
Post by Herman Tan
[calcite-core-1.16.0-drill-r6.jar:1.16.0-drill-r6]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:429)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.
DefaultSqlHandler.transform(
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:369)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToRawDrel(DefaultSqlHandler.java:255)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.
convertToDrel(DefaultSqlHandler.java:318)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
DefaultSqlHandler.java:180)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.
getQueryPlan(DrillSqlWorker.java:145)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(
DrillSqlWorker.java:83)
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.runSQL(Foreman.java:567)
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at org.apache.drill.exec.work
.foreman.Foreman.run(Foreman.java:266)
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(
ThreadPoolExecutor.java:1149)
Post by Herman Tan
[na:1.8.0_172]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(
ThreadPoolExecutor.java:624)
Post by Herman Tan
[na:1.8.0_172]
at java.lang.Thread.run(Thread.java:748) [na:1.8.0_172]
Caused by: java.util.concurrent.CancellationException: null
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:86)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.exec.store.TimedCallable$FutureMapper.
apply(TimedCallable.java:57)
Post by Herman Tan
~[drill-java-exec-1.14.0.jar:1.14.0]
at
org.apache.drill.common.collections.Collectors.lambda$
toList$2(Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at java.util.ArrayList.forEach(ArrayList.java:1257)
~[na:1.8.0_172]
Post by Herman Tan
Post by Karthikeyan Manivannan
Post by Karthikeyan Manivannan
Post by Herman Tan
at
org.apache.drill.common.collections.Collectors.toList(
Collectors.java:97)
Post by Herman Tan
~[drill-common-1.14.0.jar:1.14.0]
at org.apache.drill.exec.store.TimedCallable.run(
TimedCallable.java:214)
Post by Karthikeyan Manivannan
Post by Herman Tan
[drill-java-exec-1.14.0.jar:1.14.0]
... 33 common frames omitted
----------------------------------------
----------
Loading...