[jira] [Created] (FLINK-10026) Integrate heap based timers in RocksDB backend with incremental checkpoints

Stefan Richter created FLINK-10026: -- Summary: Integrate heap based timers in RocksDB backend with incremental checkpoints Key: FLINK-10026 URL: https://issues.apache.org/jira/browse/FLINK-10026 Proje

[jira] [Created] (FLINK-10028) Introduce ByteArrayData[Input|Output]View

Stefan Richter created FLINK-10028: -- Summary: Introduce ByteArrayData[Input|Output]View Key: FLINK-10028 URL: https://issues.apache.org/jira/browse/FLINK-10028 Project: Flink Issue Type: Imp

[jira] [Closed] (FLINK-9981) Tune performance of RocksDB implementation

[ https://issues.apache.org/jira/browse/FLINK-9981?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9981. - Resolution: Implemented Fix Version/s: 1.6.0 Merged in: master: a20fd1d51b release-1.6: 27

[jira] [Closed] (FLINK-10028) Introduce ByteArrayData[Input|Output]View

[ https://issues.apache.org/jira/browse/FLINK-10028?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-10028. -- Resolution: Implemented Merged in: master: fffd2e8c5c release-1.6: 7aaa0c4 > Introduce ByteAr

[jira] [Closed] (FLINK-9887) Ensure serializer upgrades work with timer service remake

[ https://issues.apache.org/jira/browse/FLINK-9887?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9887. - Resolution: Implemented Merged in: master: 9d273a3 release-1.6: eca1efa > Ensure serializer upgr

[jira] [Created] (FLINK-10040) Decompose RocksDBKeyedStateBackend

Stefan Richter created FLINK-10040: -- Summary: Decompose RocksDBKeyedStateBackend Key: FLINK-10040 URL: https://issues.apache.org/jira/browse/FLINK-10040 Project: Flink Issue Type: Improvemen

[jira] [Created] (FLINK-10041) Extract all different iterators (inner or static inner classes) into full classes

Stefan Richter created FLINK-10041: -- Summary: Extract all different iterators (inner or static inner classes) into full classes Key: FLINK-10041 URL: https://issues.apache.org/jira/browse/FLINK-10041

[jira] [Created] (FLINK-10042) Extract snapshot algorithms from inner classes into full classes

Stefan Richter created FLINK-10042: -- Summary: Extract snapshot algorithms from inner classes into full classes Key: FLINK-10042 URL: https://issues.apache.org/jira/browse/FLINK-10042 Project: Flink

[jira] [Created] (FLINK-10043) Refactor object construction/inititlization/restore code

Stefan Richter created FLINK-10043: -- Summary: Refactor object construction/inititlization/restore code Key: FLINK-10043 URL: https://issues.apache.org/jira/browse/FLINK-10043 Project: Flink

[jira] [Created] (FLINK-10044) Check proper RIA style and introduce it where missing

Stefan Richter created FLINK-10044: -- Summary: Check proper RIA style and introduce it where missing Key: FLINK-10044 URL: https://issues.apache.org/jira/browse/FLINK-10044 Project: Flink Iss

[jira] [Closed] (FLINK-9938) State TTL cleanup during full state scan upon checkpointing

[ https://issues.apache.org/jira/browse/FLINK-9938?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9938. - Resolution: Implemented Merged in: master: ce96c40914 release-1.6: 93bb127be3 > State TTL cleanu

[jira] [Created] (FLINK-10066) Keep only archived version of previous executions

Stefan Richter created FLINK-10066: -- Summary: Keep only archived version of previous executions Key: FLINK-10066 URL: https://issues.apache.org/jira/browse/FLINK-10066 Project: Flink Issue T

[jira] [Created] (FLINK-6984) Do not recover CompletedCheckpointStore on every restore

Stefan Richter created FLINK-6984: - Summary: Do not recover CompletedCheckpointStore on every restore Key: FLINK-6984 URL: https://issues.apache.org/jira/browse/FLINK-6984 Project: Flink Issu

[jira] [Comment Edited] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16060857#comment-16060857 ] Stefan Richter edited comment on FLINK-6964 at 6/23/17 1:03 PM:

[jira] [Commented] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16060857#comment-16060857 ] Stefan Richter commented on FLINK-6964: --- [~cre...@gmail.com] Hanging mean that you c

[jira] [Commented] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16061078#comment-16061078 ] Stefan Richter commented on FLINK-6964: --- Besides potential exceptions, the same logg

[jira] [Commented] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16061143#comment-16061143 ] Stefan Richter commented on FLINK-6964: --- I have added a commit to my branch that int

[jira] [Commented] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16061164#comment-16061164 ] Stefan Richter commented on FLINK-6964: --- I suggest to log Flink runtime at INFO leve

[jira] [Commented] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16061166#comment-16061166 ] Stefan Richter commented on FLINK-6964: --- In particular, JobManager logs are valuable

[jira] [Commented] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16061174#comment-16061174 ] Stefan Richter commented on FLINK-6964: --- I think I already found the problem. A stup

[jira] [Commented] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16061190#comment-16061190 ] Stefan Richter commented on FLINK-6964: --- Alright, it wasn't the precondition. I have

[jira] [Commented] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16061291#comment-16061291 ] Stefan Richter commented on FLINK-6964: --- Those placeholder messages look ok and expe

[jira] [Commented] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16063653#comment-16063653 ] Stefan Richter commented on FLINK-6964: --- [~cre...@gmail.com] I think I have figured

[jira] [Closed] (FLINK-6773) Use compression (e.g. snappy) for full check/savepoints

[ https://issues.apache.org/jira/browse/FLINK-6773?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-6773. - Resolution: Implemented Merged in 5171513a3c. Documentation in 41806ba681. > Use compression (e.g

[jira] [Closed] (FLINK-7063) test instability in OperatorStateBackendTest.testSnapshotAsyncCancel

[ https://issues.apache.org/jira/browse/FLINK-7063?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-7063. - Resolution: Fixed Fixed in 74adb84742. > test instability in OperatorStateBackendTest.testSnapsho

[jira] [Updated] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-6964: -- Priority: Blocker (was: Major) > Fix recovery for incremental checkpoints in StandaloneComplete

[jira] [Commented] (FLINK-7164) Extend integration tests for (externalised) checkpoints, checkpoint store

[ https://issues.apache.org/jira/browse/FLINK-7164?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16087309#comment-16087309 ] Stefan Richter commented on FLINK-7164: --- Yes. > Extend integration tests for (exter

[jira] [Closed] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-6964. - Resolution: Fixed Fix Version/s: 1.4.0 Merged in 8cff17fcc9. > Fix recovery for incrementa

[jira] [Created] (FLINK-7213) Introduce state management by OperatorID in TaskManager

Stefan Richter created FLINK-7213: - Summary: Introduce state management by OperatorID in TaskManager Key: FLINK-7213 URL: https://issues.apache.org/jira/browse/FLINK-7213 Project: Flink Issue

[jira] [Created] (FLINK-7220) Update RocksDB dependency to 5.5.1

Stefan Richter created FLINK-7220: - Summary: Update RocksDB dependency to 5.5.1 Key: FLINK-7220 URL: https://issues.apache.org/jira/browse/FLINK-7220 Project: Flink Issue Type: Improvement

[jira] [Commented] (FLINK-7164) Extend integration tests for (externalised) checkpoints, checkpoint store

[ https://issues.apache.org/jira/browse/FLINK-7164?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16092755#comment-16092755 ] Stefan Richter commented on FLINK-7164: --- Yes, this was contained with the fix. > Ex

[jira] [Closed] (FLINK-7164) Extend integration tests for (externalised) checkpoints, checkpoint store

[ https://issues.apache.org/jira/browse/FLINK-7164?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-7164. - Resolution: Implemented Assignee: Stefan Richter Merged with 8cff17fcc9b4bca6499c26fc2a6318c

[jira] [Updated] (FLINK-7220) Update RocksDB dependency to 5.5.5

[ https://issues.apache.org/jira/browse/FLINK-7220?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-7220: -- Summary: Update RocksDB dependency to 5.5.5 (was: Update RocksDB dependency to 5.5.1) > Update

[jira] [Updated] (FLINK-7220) Update RocksDB dependency to 5.5.5

[ https://issues.apache.org/jira/browse/FLINK-7220?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-7220: -- Description: The latest release of RocksDB (5.5.5) fixes the issues from previous versions (slow

[jira] [Closed] (FLINK-6412) Stream has already been closed during job cancel

[ https://issues.apache.org/jira/browse/FLINK-6412?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-6412. - Resolution: Fixed Fix Version/s: 1.3.0 Fixed as byproduct of the incremental checkpointing

[jira] [Commented] (FLINK-6964) Fix recovery for incremental checkpoints in StandaloneCompletedCheckpointStore

[ https://issues.apache.org/jira/browse/FLINK-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16094362#comment-16094362 ] Stefan Richter commented on FLINK-6964: --- Yeah, originally I had just a string there

[jira] [Created] (FLINK-7289) Memory allocation of RocksDB can be problematic in container environments

Stefan Richter created FLINK-7289: - Summary: Memory allocation of RocksDB can be problematic in container environments Key: FLINK-7289 URL: https://issues.apache.org/jira/browse/FLINK-7289 Project: Fl

[jira] [Closed] (FLINK-7220) Update RocksDB dependency to 5.5.5

[ https://issues.apache.org/jira/browse/FLINK-7220?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-7220. - Resolution: Fixed Merged in 219ae33d36 > Update RocksDB dependency to 5.5.5 > ---

[jira] [Commented] (FLINK-7220) Update RocksDB dependency to 5.5.5

[ https://issues.apache.org/jira/browse/FLINK-7220?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16104894#comment-16104894 ] Stefan Richter commented on FLINK-7220: --- Yes, I know. Accidentally pushed the wrong

[jira] [Closed] (FLINK-9436) Remove generic parameter namespace from InternalTimeServiceManager

[ https://issues.apache.org/jira/browse/FLINK-9436?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9436. - Resolution: Fixed Merged in: master: 57b950796d > Remove generic parameter namespace from Intern

[jira] [Closed] (FLINK-9423) Implement efficient deletes for heap based timer service

[ https://issues.apache.org/jira/browse/FLINK-9423?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9423. - Resolution: Fixed Merged in: master: ff0b9c1eed > Implement efficient deletes for heap based tim

[jira] [Created] (FLINK-9485) Improving Flink’s timer management for large state

Stefan Richter created FLINK-9485: - Summary: Improving Flink’s timer management for large state Key: FLINK-9485 URL: https://issues.apache.org/jira/browse/FLINK-9485 Project: Flink Issue Type

[jira] [Created] (FLINK-9486) Introduce TimerState in keyed state backend

Stefan Richter created FLINK-9486: - Summary: Introduce TimerState in keyed state backend Key: FLINK-9486 URL: https://issues.apache.org/jira/browse/FLINK-9486 Project: Flink Issue Type: Sub-t

[jira] [Created] (FLINK-9487) Prepare InternalTimerHeap for asynchronous snapshots

Stefan Richter created FLINK-9487: - Summary: Prepare InternalTimerHeap for asynchronous snapshots Key: FLINK-9487 URL: https://issues.apache.org/jira/browse/FLINK-9487 Project: Flink Issue Ty

[jira] [Assigned] (FLINK-9486) Introduce TimerState in keyed state backend

[ https://issues.apache.org/jira/browse/FLINK-9486?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reassigned FLINK-9486: - Assignee: Stefan Richter > Introduce TimerState in keyed state backend > ---

[jira] [Commented] (FLINK-9486) Introduce TimerState in keyed state backend

[ https://issues.apache.org/jira/browse/FLINK-9486?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16497952#comment-16497952 ] Stefan Richter commented on FLINK-9486: --- Hi, I am already creating the issues for p

[jira] [Created] (FLINK-9489) Checkpoint timers as part of managed keyed state instead of raw keyed state

Stefan Richter created FLINK-9489: - Summary: Checkpoint timers as part of managed keyed state instead of raw keyed state Key: FLINK-9489 URL: https://issues.apache.org/jira/browse/FLINK-9489 Project:

[jira] [Created] (FLINK-9490) Provide backwards compatibility for timer state of Flink 1.5

Stefan Richter created FLINK-9490: - Summary: Provide backwards compatibility for timer state of Flink 1.5 Key: FLINK-9490 URL: https://issues.apache.org/jira/browse/FLINK-9490 Project: Flink

[jira] [Updated] (FLINK-9490) Provide backwards compatibility for timer state of Flink 1.5

[ https://issues.apache.org/jira/browse/FLINK-9490?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-9490: -- Fix Version/s: 1.6.0 Component/s: State Backends, Checkpointing > Provide backwards compa

[jira] [Created] (FLINK-9491) Implement timer service based on RocksDB

Stefan Richter created FLINK-9491: - Summary: Implement timer service based on RocksDB Key: FLINK-9491 URL: https://issues.apache.org/jira/browse/FLINK-9491 Project: Flink Issue Type: Sub-task

[jira] [Updated] (FLINK-9491) Implement timer data structure based on RocksDB

[ https://issues.apache.org/jira/browse/FLINK-9491?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-9491: -- Summary: Implement timer data structure based on RocksDB (was: Implement timer service based o

[jira] [Commented] (FLINK-9506) Flink ReducingState.add causing more than 100% performance drop

[ https://issues.apache.org/jira/browse/FLINK-9506?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16499947#comment-16499947 ] Stefan Richter commented on FLINK-9506: --- >From what I can see, the problem is purel

[jira] [Commented] (FLINK-9506) Flink ReducingState.add causing more than 100% performance drop

[ https://issues.apache.org/jira/browse/FLINK-9506?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16500165#comment-16500165 ] Stefan Richter commented on FLINK-9506: --- [~yow] I had another look at your code and

[jira] [Closed] (FLINK-7866) Weigh list of preferred locations for scheduling

[ https://issues.apache.org/jira/browse/FLINK-7866?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-7866. - Resolution: Fixed Merged in: master: 8868ff5b05 > Weigh list of preferred locations for scheduli

[jira] [Closed] (FLINK-8790) Improve performance for recovery from incremental checkpoint

[ https://issues.apache.org/jira/browse/FLINK-8790?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-8790. - Resolution: Fixed Merged in: master: bbf7ff2273 > Improve performance for recovery from incremen

[jira] [Closed] (FLINK-9440) Allow cancelation and reset of timers

[ https://issues.apache.org/jira/browse/FLINK-9440?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9440. - Resolution: Fixed Fix Version/s: 1.6.0 Merged in: master: a0f4239fae > Allow cancelation

[jira] [Commented] (FLINK-9506) Flink ReducingState.add causing more than 100% performance drop

[ https://issues.apache.org/jira/browse/FLINK-9506?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16510747#comment-16510747 ] Stefan Richter commented on FLINK-9506: --- Hi, I think this discussion has no connect

[jira] [Commented] (FLINK-9506) Flink ReducingState.add causing more than 100% performance drop

[ https://issues.apache.org/jira/browse/FLINK-9506?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16510870#comment-16510870 ] Stefan Richter commented on FLINK-9506: --- [~yow] I would suggest that you discuss it

[jira] [Closed] (FLINK-9506) Flink ReducingState.add causing more than 100% performance drop

[ https://issues.apache.org/jira/browse/FLINK-9506?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9506. - Resolution: Not A Problem > Flink ReducingState.add causing more than 100% performance drop > ---

[jira] [Closed] (FLINK-9487) Prepare InternalTimerHeap for asynchronous snapshots

[ https://issues.apache.org/jira/browse/FLINK-9487?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9487. - Resolution: Implemented Merged in: master: 7e0eafa74d > Prepare InternalTimerHeap for asynchrono

[jira] [Closed] (FLINK-9601) Snapshot of CopyOnWriteStateTable will failed when the amount of record is more than MAXIMUM_CAPACITY

[ https://issues.apache.org/jira/browse/FLINK-9601?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9601. - Resolution: Fixed Merged in: master: 0e9b066aab > Snapshot of CopyOnWriteStateTable will failed

[jira] [Closed] (FLINK-9571) Switch to internal states in StateBinder

[ https://issues.apache.org/jira/browse/FLINK-9571?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9571. - Resolution: Implemented Merged in: master: 0bdde8377c > Switch to internal states in StateBinder

[jira] [Commented] (FLINK-9626) Possible resource leak in FileSystem

[ https://issues.apache.org/jira/browse/FLINK-9626?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16518096#comment-16518096 ] Stefan Richter commented on FLINK-9626: --- I think in general it can be dangerous to

[jira] [Closed] (FLINK-7897) Consider using nio.Files for file deletion in TransientBlobCleanupTask

[ https://issues.apache.org/jira/browse/FLINK-7897?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-7897. - Resolution: Implemented Merged in: master: 8674b69964 > Consider using nio.Files for file delet

[jira] [Closed] (FLINK-7775) Remove unreferenced method PermanentBlobCache#getNumberOfCachedJobs

[ https://issues.apache.org/jira/browse/FLINK-7775?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-7775. - Resolution: Fixed Fix Version/s: 1.6.0 Merged in: master: 4bcf0b99a6 > Remove unreference

[jira] [Created] (FLINK-9702) Improvement in (de)serialization of keys and values for RocksDB state

Stefan Richter created FLINK-9702: - Summary: Improvement in (de)serialization of keys and values for RocksDB state Key: FLINK-9702 URL: https://issues.apache.org/jira/browse/FLINK-9702 Project: Flink

[jira] [Commented] (FLINK-9702) Improvement in (de)serialization of keys and values for RocksDB state

[ https://issues.apache.org/jira/browse/FLINK-9702?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16529733#comment-16529733 ] Stefan Richter commented on FLINK-9702: --- I have a WIP branch that implements many o

[jira] [Closed] (FLINK-9491) Implement timer data structure based on RocksDB

[ https://issues.apache.org/jira/browse/FLINK-9491?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9491. - Resolution: Implemented Merged in: master: c6ad421e2b > Implement timer data structure based on

[jira] [Closed] (FLINK-9513) Wrap state binder with TTL logic

[ https://issues.apache.org/jira/browse/FLINK-9513?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9513. - Resolution: Implemented Merged in: master: afdbf54713 > Wrap state binder with TTL logic > -

[jira] [Commented] (FLINK-7775) Remove unreferenced method PermanentBlobCache#getNumberOfCachedJobs

[ https://issues.apache.org/jira/browse/FLINK-7775?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16532638#comment-16532638 ] Stefan Richter commented on FLINK-7775: --- hi @yanghua it was already merged, please

[jira] [Closed] (FLINK-9736) Potential null reference in KeyGroupPartitionedPriorityQueue#poll()

[ https://issues.apache.org/jira/browse/FLINK-9736?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9736. - Resolution: Not A Bug > Potential null reference in KeyGroupPartitionedPriorityQueue#poll() > ---

[jira] [Commented] (FLINK-9736) Potential null reference in KeyGroupPartitionedPriorityQueue#poll()

[ https://issues.apache.org/jira/browse/FLINK-9736?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16533515#comment-16533515 ] Stefan Richter commented on FLINK-9736: --- [~sihuazhou] Is correct, this heap is alwa

[jira] [Closed] (FLINK-9486) Introduce TimerState in keyed state backend

[ https://issues.apache.org/jira/browse/FLINK-9486?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9486. - Resolution: Implemented Merged in: master: 79b38f8f9a > Introduce TimerState in keyed state back

[jira] [Closed] (FLINK-9011) YarnResourceManager spamming log file at INFO level

[ https://issues.apache.org/jira/browse/FLINK-9011?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9011. - Resolution: Fixed Merge in d5ec911f55. > YarnResourceManager spamming log file at INFO level > --

[jira] [Comment Edited] (FLINK-8836) Duplicating a KryoSerializer does not duplicate registered default serializers

[ https://issues.apache.org/jira/browse/FLINK-8836?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16442589#comment-16442589 ] Stefan Richter edited comment on FLINK-8836 at 4/18/18 2:29 PM:

[jira] [Commented] (FLINK-8836) Duplicating a KryoSerializer does not duplicate registered default serializers

[ https://issues.apache.org/jira/browse/FLINK-8836?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16442589#comment-16442589 ] Stefan Richter commented on FLINK-8836: --- Hi, I have seen a report on the mailing lis

[jira] [Updated] (FLINK-8836) Duplicating a KryoSerializer does not duplicate registered default serializers

[ https://issues.apache.org/jira/browse/FLINK-8836?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-8836: -- Priority: Critical (was: Major) > Duplicating a KryoSerializer does not duplicate registered de

[jira] [Commented] (FLINK-8836) Duplicating a KryoSerializer does not duplicate registered default serializers

[ https://issues.apache.org/jira/browse/FLINK-8836?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16442673#comment-16442673 ] Stefan Richter commented on FLINK-8836: --- That is a very good question, potentially n

[jira] [Reopened] (FLINK-9022) fix resource close in `StreamTaskStateInitializerImpl.streamOperatorStateContext()`

[ https://issues.apache.org/jira/browse/FLINK-9022?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reopened FLINK-9022: --- Assignee: Stefan Richter (was: Sihua Zhou) Reopened because the dispose of backends should

[jira] [Closed] (FLINK-9144) Spilling batch job hangs

[ https://issues.apache.org/jira/browse/FLINK-9144?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9144. - Resolution: Fixed Fixed in: master: 388a083c90 release-1.5: f7e621d322 > Spilling batch job han

[jira] [Closed] (FLINK-9022) fix resource close in `StreamTaskStateInitializerImpl.streamOperatorStateContext()`

[ https://issues.apache.org/jira/browse/FLINK-9022?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9022. - Resolution: Fixed Fixed in master: 777cc1ab53 release-1.5: 01f701ab72 > fix resource close in

[jira] [Commented] (FLINK-8836) Duplicating a KryoSerializer does not duplicate registered default serializers

[ https://issues.apache.org/jira/browse/FLINK-8836?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16443973#comment-16443973 ] Stefan Richter commented on FLINK-8836: --- Serialization will probably work in most ca

[jira] [Assigned] (FLINK-8836) Duplicating a KryoSerializer does not duplicate registered default serializers

[ https://issues.apache.org/jira/browse/FLINK-8836?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reassigned FLINK-8836: - Assignee: Stefan Richter > Duplicating a KryoSerializer does not duplicate registered def

[jira] [Commented] (FLINK-9080) Flink Scheduler goes OOM, suspecting a memory leak

[ https://issues.apache.org/jira/browse/FLINK-9080?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16448183#comment-16448183 ] Stefan Richter commented on FLINK-9080: --- [~rohsing] could you somehow provide your h

[jira] [Closed] (FLINK-8836) Duplicating a KryoSerializer does not duplicate registered default serializers

[ https://issues.apache.org/jira/browse/FLINK-8836?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-8836. - Resolution: Fixed Fix Version/s: 1.4.0 1.6.0 Merged in: master: 321039f

[jira] [Closed] (FLINK-5372) Fix RocksDBAsyncSnapshotTest.testCancelFullyAsyncCheckpoints()

[ https://issues.apache.org/jira/browse/FLINK-5372?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-5372. - Resolution: Fixed Fix Version/s: (was: 1.4.3) 1.6.0 Fixed in: maste

[jira] [Closed] (FLINK-8992) Implement source and operator that validate exactly-once

[ https://issues.apache.org/jira/browse/FLINK-8992?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-8992. - Resolution: Fixed Merged in: master: 31c717697a52af2c64439aaaba2f6a1f97a22159 release 1.5: 8118e

[jira] [Commented] (FLINK-9268) RockDB errors from WindowOperator

[ https://issues.apache.org/jira/browse/FLINK-9268?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16457505#comment-16457505 ] Stefan Richter commented on FLINK-9268: --- This is a known issue with RocksDB, see [h

[jira] [Closed] (FLINK-9270) Upgrade RocksDB to 5.11.3, and resolve concurrent test invocation problem of @RetryOnFailure

[ https://issues.apache.org/jira/browse/FLINK-9270?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9270. - Resolution: Won't Fix Won't fix until we figure out a way around the performance regression of the

[jira] [Closed] (FLINK-9263) Kafka010ITCase failed on travis because of the concurrency problem in DefaultOperateStateBackend

[ https://issues.apache.org/jira/browse/FLINK-9263?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9263. - Resolution: Fixed Merged in: master: c11f11359b release 1.5: de4f283087 > Kafka010ITCase failed

[jira] [Commented] (FLINK-7484) CaseClassSerializer.duplicate() does not perform proper deep copy

[ https://issues.apache.org/jira/browse/FLINK-7484?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16460907#comment-16460907 ] Stefan Richter commented on FLINK-7484: --- [~joshlemer] this looks like a different pr

[jira] [Commented] (FLINK-9290) The job is unable to recover from a checkpoint

[ https://issues.apache.org/jira/browse/FLINK-9290?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16461167#comment-16461167 ] Stefan Richter commented on FLINK-9290: --- [~sihuazhou] yes, looks like it. > The job

[jira] [Commented] (FLINK-9268) RockDB errors from WindowOperator

[ https://issues.apache.org/jira/browse/FLINK-9268?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16461231#comment-16461231 ] Stefan Richter commented on FLINK-9268: --- I don't think that is the cause. The except

[jira] [Commented] (FLINK-9291) Checkpoint failure (CIRCULAR REFERENCE:java.lang.NegativeArraySizeException)

[ https://issues.apache.org/jira/browse/FLINK-9291?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16462025#comment-16462025 ] Stefan Richter commented on FLINK-9291: --- Yes, this is basically a duplicate, just th

[jira] [Commented] (FLINK-9268) RockDB errors from WindowOperator

[ https://issues.apache.org/jira/browse/FLINK-9268?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16462068#comment-16462068 ] Stefan Richter commented on FLINK-9268: --- The 2GB limit actually applies on a per-key

[jira] [Commented] (FLINK-9268) RockDB errors from WindowOperator

[ https://issues.apache.org/jira/browse/FLINK-9268?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16462072#comment-16462072 ] Stefan Richter commented on FLINK-9268: --- Maybe what your are looking for is using a

[jira] [Issue Comment Deleted] (FLINK-9268) RockDB errors from WindowOperator

[ https://issues.apache.org/jira/browse/FLINK-9268?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-9268: -- Comment: was deleted (was: Maybe what your are looking for is using a window with aggregate func

[jira] [Commented] (FLINK-9268) RockDB errors from WindowOperator

[ https://issues.apache.org/jira/browse/FLINK-9268?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16462086#comment-16462086 ] Stefan Richter commented on FLINK-9268: --- Yes, you could have duplicates in AT_LEAST_

[jira] [Commented] (FLINK-9268) RockDB errors from WindowOperator

[ https://issues.apache.org/jira/browse/FLINK-9268?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16462164#comment-16462164 ] Stefan Richter commented on FLINK-9268: --- It is hard to make any assumptions about yo

[jira] [Closed] (FLINK-9269) Concurrency problem in HeapKeyedStateBackend when performing checkpoint async

[ https://issues.apache.org/jira/browse/FLINK-9269?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-9269. - Resolution: Fixed Merged in: master: 14e7d35f26 release-1.5: 3ba21adc0e > Concurrency problem i

<    1   2   3   4   5   6   7   8   9   10   >