[jira] [Assigned] (SPARK-23948) Trigger mapstage's job listener in submitMissingTasks
[ https://issues.apache.org/jira/browse/SPARK-23948?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Imran Rashid reassigned SPARK-23948: Assignee: jin xing > Trigger mapstage's job listener in submitMissingTasks > - > > Key: SPARK-23948 > URL: https://issues.apache.org/jira/browse/SPARK-23948 > Project: Spark > Issue Type: New Feature > Components: Scheduler, Spark Core >Affects Versions: 2.3.0 >Reporter: jin xing >Assignee: jin xing >Priority: Major > Fix For: 2.4.0 > > > SparkContext submitted a map stage from "submitMapStage" to DAGScheduler, > "markMapStageJobAsFinished" is called only in > (https://github.com/apache/spark/blob/master/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L933 > and > https://github.com/apache/spark/blob/master/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1314); > But think about below scenario: > 1. stage0 and stage1 are all "ShuffleMapStage" and stage1 depends on stage0; > 2. We submit stage1 by "submitMapStage"; > 3. When stage 1 running, "FetchFailed" happened, stage0 and stage1 got > resubmitted as stage0_1 and stage1_1; > 4. When stage0_1 running, speculated tasks in old stage1 come as succeeded, > but stage1 is not inside "runningStages". So even though all splits(including > the speculated tasks) in stage1 succeeded, job listener in stage1 will not be > called; > 5. stage0_1 finished, stage1_1 starts running. When "submitMissingTasks", > there is no missing tasks. But in current code, job listener is not triggered -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Assigned] (SPARK-23948) Trigger mapstage's job listener in submitMissingTasks
[ https://issues.apache.org/jira/browse/SPARK-23948?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Apache Spark reassigned SPARK-23948: Assignee: (was: Apache Spark) > Trigger mapstage's job listener in submitMissingTasks > - > > Key: SPARK-23948 > URL: https://issues.apache.org/jira/browse/SPARK-23948 > Project: Spark > Issue Type: New Feature > Components: Spark Core >Affects Versions: 2.3.0 >Reporter: jin xing >Priority: Major > > SparkContext submitted a map stage from "submitMapStage" to DAGScheduler, > "markMapStageJobAsFinished" is called only in (); > But think about below scenario: > 1. stage0 and stage1 are all "ShuffleMapStage" and stage1 depends on stage0; > 2. We submit stage1 by "submitMapStage", there are 10 missing tasks in stage1 > 3. When stage 1 running, "FetchFailed" happened, stage0 and stage1 got > resubmitted as stage0_1 and stage1_1; > 4. When stage0_1 running, speculated tasks in old stage1 come as succeeded, > but stage1 is not inside "runningStages". So even though all splits(including > the speculated tasks) in stage1 succeeded, job listener in stage1 will not be > called; > 5. stage0_1 finished, stage1_1 starts running. When "submitMissingTasks", > there is no missing tasks. But in current code, job listener is not triggered -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Assigned] (SPARK-23948) Trigger mapstage's job listener in submitMissingTasks
[ https://issues.apache.org/jira/browse/SPARK-23948?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Apache Spark reassigned SPARK-23948: Assignee: Apache Spark > Trigger mapstage's job listener in submitMissingTasks > - > > Key: SPARK-23948 > URL: https://issues.apache.org/jira/browse/SPARK-23948 > Project: Spark > Issue Type: New Feature > Components: Spark Core >Affects Versions: 2.3.0 >Reporter: jin xing >Assignee: Apache Spark >Priority: Major > > SparkContext submitted a map stage from "submitMapStage" to DAGScheduler, > "markMapStageJobAsFinished" is called only in (); > But think about below scenario: > 1. stage0 and stage1 are all "ShuffleMapStage" and stage1 depends on stage0; > 2. We submit stage1 by "submitMapStage", there are 10 missing tasks in stage1 > 3. When stage 1 running, "FetchFailed" happened, stage0 and stage1 got > resubmitted as stage0_1 and stage1_1; > 4. When stage0_1 running, speculated tasks in old stage1 come as succeeded, > but stage1 is not inside "runningStages". So even though all splits(including > the speculated tasks) in stage1 succeeded, job listener in stage1 will not be > called; > 5. stage0_1 finished, stage1_1 starts running. When "submitMissingTasks", > there is no missing tasks. But in current code, job listener is not triggered -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org