You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@drill.apache.org by "Aman Sinha (JIRA)" <ji...@apache.org> on 2015/11/11 02:44:10 UTC
[jira] [Commented] (DRILL-3847) Exception during partition pruning
[ https://issues.apache.org/jira/browse/DRILL-3847?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14999776#comment-14999776 ]
Aman Sinha commented on DRILL-3847:
-----------------------------------
[~vicky] I suppose you ran with the old metadata cache file. Could you try recreating the cache file and running your query again.
> Exception during partition pruning
> ----------------------------------
>
> Key: DRILL-3847
> URL: https://issues.apache.org/jira/browse/DRILL-3847
> Project: Apache Drill
> Issue Type: Bug
> Components: Query Planning & Optimization
> Affects Versions: 1.2.0
> Reporter: Victoria Markman
> Attachments: drillbit.log, drillbit.log
>
>
> * This is happening when I run query below on a table partitioned by cd_demo_sk which resulted in ~1.9 million files in the single directory.
> * Metadata file is present customer_demographics_part_1
> * If cast to varchar is replaced with the star in projection list: query works
> * If cast to varchar replaced with integer columns: query works
> * Same query runs to completion on the original table.
> {code}
> select
> cast(cd_gender as varchar(10)),
> cast(cd_credit_rating as varchar(10)),
> cast(cd_marital_status as varchar(10)),
> cd_dep_count
> from
> customer_demographics_part_1
> where cd_demo_sk = 10000;
> {code}
> drillbit.log
> {code}
> 2015-09-28 20:39:20,653 [29f65bb1-6f25-9d81-3225-c7ae40adbbf3:foreman] WARN o.a.d.e.p.l.partition.PruneScanRule - Exception while trying to prune partition.
> java.lang.ClassCastException: java.util.LinkedHashMap cannot be cast to parquet.io.api.Binary
> at org.apache.drill.exec.store.parquet.ParquetGroupScan.populatePruningVector(ParquetGroupScan.java:403) ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.ParquetPartitionDescriptor.populatePartitionVectors(ParquetPartitionDescriptor.java:96) ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.logical.partition.PruneScanRule.doOnMatch(PruneScanRule.java:212) ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.logical.partition.ParquetPruneScanRule$2.onMatch(ParquetPruneScanRule.java:87) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:228) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:808) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:303) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.calcite.prepare.PlannerImpl.transform(PlannerImpl.java:303) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.logicalPlanningVolcanoAndLopt(DefaultSqlHandler.java:545) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:213) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:248) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:164) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:178) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:905) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:244) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) [na:1.7.0_71]
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) [na:1.7.0_71]
> at java.lang.Thread.run(Thread.java:745) [na:1.7.0_71]
> 2015-09-28 20:39:24,779 [29f65bb1-6f25-9d81-3225-c7ae40adbbf3:foreman] WARN o.a.d.e.p.l.partition.PruneScanRule - Exception while trying to prune partition.
> java.lang.ClassCastException: java.util.LinkedHashMap cannot be cast to parquet.io.api.Binary
> at org.apache.drill.exec.store.parquet.ParquetGroupScan.populatePruningVector(ParquetGroupScan.java:403) ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.ParquetPartitionDescriptor.populatePartitionVectors(ParquetPartitionDescriptor.java:96) ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.logical.partition.PruneScanRule.doOnMatch(PruneScanRule.java:212) ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.logical.partition.ParquetPruneScanRule$1.onMatch(ParquetPruneScanRule.java:60) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:228) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:808) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:303) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.calcite.prepare.PlannerImpl.transform(PlannerImpl.java:303) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.logicalPlanningVolcanoAndLopt(DefaultSqlHandler.java:545) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:213) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:248) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:164) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:178) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:905) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:244) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) [na:1.7.0_71]
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) [na:1.7.0_71]
> at java.lang.Thread.run(Thread.java:745) [na:1.7.0_71]
> 2015-09-28 20:39:26,149 [29f65bb1-6f25-9d81-3225-c7ae40adbbf3:foreman] WARN o.a.d.e.p.l.partition.PruneScanRule - Exception while trying to prune partition.
> java.lang.ClassCastException: java.util.LinkedHashMap cannot be cast to parquet.io.api.Binary
> at org.apache.drill.exec.store.parquet.ParquetGroupScan.populatePruningVector(ParquetGroupScan.java:403) ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.ParquetPartitionDescriptor.populatePartitionVectors(ParquetPartitionDescriptor.java:96) ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.logical.partition.PruneScanRule.doOnMatch(PruneScanRule.java:212) ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.logical.partition.ParquetPruneScanRule$1.onMatch(ParquetPruneScanRule.java:60) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:228) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:808) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:303) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.calcite.prepare.PlannerImpl.transform(PlannerImpl.java:303) [calcite-core-1.4.0-drill-r5.jar:1.4.0-drill-r5]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.logicalPlanningVolcanoAndLopt(DefaultSqlHandler.java:545) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:213) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.convertToDrel(DefaultSqlHandler.java:248) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.handlers.DefaultSqlHandler.getPlan(DefaultSqlHandler.java:164) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.planner.sql.DrillSqlWorker.getPlan(DrillSqlWorker.java:178) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.work.foreman.Foreman.runSQL(Foreman.java:905) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at org.apache.drill.exec.work.foreman.Foreman.run(Foreman.java:244) [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) [na:1.7.0_71]
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) [na:1.7.0_71]
> at java.lang.Thread.run(Thread.java:745) [na:1.7.0_71]
> 2015-09-28 20:40:53,850 [UserServer-1] INFO o.a.drill.exec.rpc.user.UserServer - RPC connection /10.10.88.133:31010 <--> /10.10.88.133:48567 (user client) timed out. Timeout was set to 30 seconds. Closing connection.
> {code}
> Can't attach data, too big.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)