[jira] [Comment Edited] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17837259#comment-17837259 ] Julien Tournay edited comment on FLINK-35073 at 4/15/24 1:32 PM: -

[jira] [Closed] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay closed FLINK-35073. -- Resolution: Workaround > Deadlock in LocalBufferPool when segments become available in the

[jira] [Commented] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17837259#comment-17837259 ] Julien Tournay commented on FLINK-35073: Closing this issue because even though I captured a

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when segments become available in the global pool

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Summary: Deadlock in LocalBufferPool when segments become available in the global pool

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Commented] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17835659#comment-17835659 ] Julien Tournay commented on FLINK-35073: [~a.pilipenko] updated the issue :) I haven't tested

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Affects Version/s: 1.19.0 > Deadlock in LocalBufferPool when >

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Labels: deadlock network (was: ) > Deadlock in LocalBufferPool when >

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Priority: Critical (was: Major) > Deadlock in LocalBufferPool when >

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Component/s: Runtime / Network > Deadlock in LocalBufferPool when >

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Updated] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

[ https://issues.apache.org/jira/browse/FLINK-35073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-35073: --- Description: The reported issue is easy to reproduce in batch mode using hybrid shuffle and

[jira] [Created] (FLINK-35073) Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently

Julien Tournay created FLINK-35073: -- Summary: Deadlock in LocalBufferPool when NetworkBufferPool.internalRecycleMemorySegments is called concurrently Key: FLINK-35073 URL:

[jira] [Comment Edited] (FLINK-31144) Slow scheduling on large-scale batch jobs

[ https://issues.apache.org/jira/browse/FLINK-31144?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17704538#comment-17704538 ] Julien Tournay edited comment on FLINK-31144 at 4/3/23 9:02 AM: Hey

[jira] [Commented] (FLINK-31144) Slow scheduling on large-scale batch jobs

[ https://issues.apache.org/jira/browse/FLINK-31144?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17704538#comment-17704538 ] Julien Tournay commented on FLINK-31144: Hey [~martijnvisser]  this is great! Thanks for sharing

[jira] [Commented] (FLINK-31144) Slow scheduling on large-scale batch jobs

[ https://issues.apache.org/jira/browse/FLINK-31144?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17696100#comment-17696100 ] Julien Tournay commented on FLINK-31144: Awesome! Thanks for volunteering [~JunRuiLi]  I'm

[jira] [Comment Edited] (FLINK-31144) Slow scheduling on large-scale batch jobs

[ https://issues.apache.org/jira/browse/FLINK-31144?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17694551#comment-17694551 ] Julien Tournay edited comment on FLINK-31144 at 2/28/23 2:04 PM: - Hey

[jira] [Commented] (FLINK-31144) Slow scheduling on large-scale batch jobs

[ https://issues.apache.org/jira/browse/FLINK-31144?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17694551#comment-17694551 ] Julien Tournay commented on FLINK-31144: Hey there! I finally found some time to test the fix

[jira] [Commented] (FLINK-31144) Slow scheduling on large-scale batch jobs

[ https://issues.apache.org/jira/browse/FLINK-31144?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17692286#comment-17692286 ] Julien Tournay commented on FLINK-31144: {quote}IMO, It's too hard to decide the threshold for

[jira] [Commented] (FLINK-31144) Slow scheduling on large-scale batch jobs

[ https://issues.apache.org/jira/browse/FLINK-31144?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17691474#comment-17691474 ] Julien Tournay commented on FLINK-31144: Hi [~huwh], Thank you for the quick reply :)

[jira] [Updated] (FLINK-31144) Slow scheduling on large-scale batch jobs

[ https://issues.apache.org/jira/browse/FLINK-31144?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-31144: --- Attachment: image-2023-02-21-10-29-49-388.png > Slow scheduling on large-scale batch jobs

[jira] [Updated] (FLINK-31144) Slow scheduling on large-scale batch jobs

[ https://issues.apache.org/jira/browse/FLINK-31144?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Julien Tournay updated FLINK-31144: --- Description: When executing a complex job graph at high parallelism

[jira] [Created] (FLINK-31144) Slow scheduling on large-scale batch jobs

Julien Tournay created FLINK-31144: -- Summary: Slow scheduling on large-scale batch jobs Key: FLINK-31144 URL: https://issues.apache.org/jira/browse/FLINK-31144 Project: Flink Issue Type: