[jira] [Updated] (SPARK-10796) The Stage taskSets may are all removed while stage still have pending partitions after having lost some executors

[ https://issues.apache.org/jira/browse/SPARK-10796?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] SuYan updated SPARK-10796: -- Description: {code} test("Resubmit stage while lost partition in ZombieTasksets or RemovedTaskSets") {

[jira] [Updated] (SPARK-10796) The Stage taskSets may are all removed while stage still have pending partitions after having lost some executors

[ https://issues.apache.org/jira/browse/SPARK-10796?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] SuYan updated SPARK-10796: -- Description: desc: 1. We know a running ShuffleMapStage will have multiple TaskSet: one Active TaskSet,

[jira] [Updated] (SPARK-10796) The Stage taskSets may are all removed while stage still have pending partitions after having lost some executors

[ https://issues.apache.org/jira/browse/SPARK-10796?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] SuYan updated SPARK-10796: -- Description: We meet that problem in Spark 1.3.0, and I also check the latest Spark code, and I think that

[jira] [Updated] (SPARK-10796) The Stage taskSets may are all removed while stage still have pending partitions after having lost some executors

[ https://issues.apache.org/jira/browse/SPARK-10796?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] SuYan updated SPARK-10796: -- Affects Version/s: 1.4.0 1.5.0 > The Stage taskSets may are all removed while stage

[jira] [Updated] (SPARK-10796) The Stage taskSets may are all removed while stage still have pending partitions after having lost some executors

[ https://issues.apache.org/jira/browse/SPARK-10796?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sean Owen updated SPARK-10796: -- Component/s: Scheduler > The Stage taskSets may are all removed while stage still have pending >

[jira] [Updated] (SPARK-10796) The Stage taskSets may are all removed while stage still have pending partitions after having lost some executors

[ https://issues.apache.org/jira/browse/SPARK-10796?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sean Owen updated SPARK-10796: -- Priority: Minor (was: Major) Can you clarify with a simple example? I'm not clear on the situation

[jira] [Updated] (SPARK-10796) The Stage taskSets may are all removed while stage still have pending partitions after having lost some executors

[ https://issues.apache.org/jira/browse/SPARK-10796?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] SuYan updated SPARK-10796: -- Description: We meet that problem in Spark 1.3.0, and I also check the latest Spark code, and I think that

[jira] [Updated] (SPARK-10796) The Stage taskSets may are all removed while stage still have pending partitions after having lost some executors

[ https://issues.apache.org/jira/browse/SPARK-10796?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] SuYan updated SPARK-10796: -- Description: We meet that problem in Spark 1.3.0, and I also check the latest Spark code, and I think that