[jira] [Resolved] (FLINK-11796) Remove Snapshotable interface

[ https://issues.apache.org/jira/browse/FLINK-11796?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter resolved FLINK-11796. Resolution: Implemented Fix Version/s: 1.8.0 Merged in: master: e8daa49a

[jira] [Resolved] (FLINK-11804) Make sure the CloseableRegistry used in backend builder is registered with task

[ https://issues.apache.org/jira/browse/FLINK-11804?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter resolved FLINK-11804. Resolution: Fixed Fix Version/s: 1.8.0 Merged in: master: eada52be release-1.8:

[jira] [Resolved] (FLINK-11730) Make HeapKeyedStateBackend follow the builder pattern

[ https://issues.apache.org/jira/browse/FLINK-11730?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter resolved FLINK-11730. Resolution: Implemented Fix Version/s: 1.8.0 Merged in: master: 237d07c7

[jira] [Updated] (FLINK-11743) Sticky E2E tests failed on travis

[ https://issues.apache.org/jira/browse/FLINK-11743?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-11743: --- Priority: Blocker (was: Critical) > Sticky E2E tests failed on travis >

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

[ https://issues.apache.org/jira/browse/FLINK-10044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-10044. -- Resolution: Fixed Assignee: (was: Stefan Richter) > Check proper RIA style and

[jira] [Resolved] (FLINK-11874) Split CheckpointStorage interface to distinguish JM and TM side

[ https://issues.apache.org/jira/browse/FLINK-11874?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter resolved FLINK-11874. Resolution: Implemented Merged in: master: b6b4baf > Split CheckpointStorage interface

[jira] [Resolved] (FLINK-11904) Improve MemoryStateBackendTest by using JUnit's Parameterized

[ https://issues.apache.org/jira/browse/FLINK-11904?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter resolved FLINK-11904. Resolution: Implemented Merged in: master: 6c7ddf3 > Improve MemoryStateBackendTest by

[jira] [Resolved] (FLINK-11903) Improve FileStateBackendTest by using JUnit's Parameterized

[ https://issues.apache.org/jira/browse/FLINK-11903?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter resolved FLINK-11903. Resolution: Implemented Merged in: master: 76b9f8b > Improve FileStateBackendTest by

[jira] [Created] (FLINK-11980) Improve efficiency of iterating KeySelectionListener on notification

Stefan Richter created FLINK-11980: -- Summary: Improve efficiency of iterating KeySelectionListener on notification Key: FLINK-11980 URL: https://issues.apache.org/jira/browse/FLINK-11980 Project:

[jira] [Resolved] (FLINK-11980) Improve efficiency of iterating KeySelectionListener on notification

[ https://issues.apache.org/jira/browse/FLINK-11980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter resolved FLINK-11980. Resolution: Fixed Fix Version/s: 1.9.0 1.8.0 Merged in: master:

[jira] [Created] (FLINK-11952) Introduce Plugin Architecture for loading FileSystems

Stefan Richter created FLINK-11952: -- Summary: Introduce Plugin Architecture for loading FileSystems Key: FLINK-11952 URL: https://issues.apache.org/jira/browse/FLINK-11952 Project: Flink

[jira] [Assigned] (FLINK-11953) Introduce Plugin/Loading system and integrate it with FileSystem

[ https://issues.apache.org/jira/browse/FLINK-11953?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reassigned FLINK-11953: -- Assignee: Stefan Richter > Introduce Plugin/Loading system and integrate it with

[jira] [Assigned] (FLINK-11954) Provide unit test(s) for new plugin infrastructure

[ https://issues.apache.org/jira/browse/FLINK-11954?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reassigned FLINK-11954: -- Assignee: Stefan Richter > Provide unit test(s) for new plugin infrastructure >

[jira] [Created] (FLINK-11955) Modify build to move filesystems from lib to plugins folder

Stefan Richter created FLINK-11955: -- Summary: Modify build to move filesystems from lib to plugins folder Key: FLINK-11955 URL: https://issues.apache.org/jira/browse/FLINK-11955 Project: Flink

[jira] [Created] (FLINK-11953) Introduce Plugin/Loading system and integrate it with FileSystem

Stefan Richter created FLINK-11953: -- Summary: Introduce Plugin/Loading system and integrate it with FileSystem Key: FLINK-11953 URL: https://issues.apache.org/jira/browse/FLINK-11953 Project: Flink

[jira] [Created] (FLINK-11954) Provide unit test(s) for new plugin infrastructure

Stefan Richter created FLINK-11954: -- Summary: Provide unit test(s) for new plugin infrastructure Key: FLINK-11954 URL: https://issues.apache.org/jira/browse/FLINK-11954 Project: Flink Issue

[jira] [Created] (FLINK-11956) Remove shading from filesystems build

Stefan Richter created FLINK-11956: -- Summary: Remove shading from filesystems build Key: FLINK-11956 URL: https://issues.apache.org/jira/browse/FLINK-11956 Project: Flink Issue Type:

[jira] [Closed] (FLINK-11314) Reuse RocksDBWriteBatchWrapper in the flush method of RocksDBMapState

[ https://issues.apache.org/jira/browse/FLINK-11314?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-11314. -- Resolution: Fixed Fix Version/s: 1.8.0 Merged in: master: 1b71e447e0 > Reuse

[jira] [Closed] (FLINK-11315) Make magic number in KvStateSerializer as a constant value to make more readable

[ https://issues.apache.org/jira/browse/FLINK-11315?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-11315. -- Resolution: Fixed Fix Version/s: 1.8.0 Merged in: master: e6a318c420 > Make magic

[jira] [Closed] (FLINK-10431) Extract scheduling-related code from SlotPool

[ https://issues.apache.org/jira/browse/FLINK-10431?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-10431. -- Resolution: Implemented Merged in: master: c60995d60a > Extract scheduling-related code from

[jira] [Closed] (FLINK-11121) Check and update licensing notes for Aliyun FS [FLINK-10865]

[ https://issues.apache.org/jira/browse/FLINK-11121?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-11121. -- Resolution: Fixed Assignee: Stefan Richter Merged in: master: 05a1dd2 > Check and

[jira] [Closed] (FLINK-11311) StreamSource implements StreamOperator interface multiple times.

[ https://issues.apache.org/jira/browse/FLINK-11311?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-11311. -- Resolution: Fixed Merged in: master: e354d0bf70 > StreamSource implements StreamOperator

[jira] [Closed] (FLINK-11008) Speed up upload checkpoint files using multi-thread

[ https://issues.apache.org/jira/browse/FLINK-11008?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-11008. -- Resolution: Implemented Merged in: master: 4c4ce451fc > Speed up upload checkpoint files

[jira] [Closed] (FLINK-11469) fix Tuning Checkpoints and Large State doc

[ https://issues.apache.org/jira/browse/FLINK-11469?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-11469. -- Resolution: Fixed Fix Version/s: 1.8.0 1.7.2

[jira] [Closed] (FLINK-11417) Make access to ExecutionGraph single threaded from JobMaster main thread

[ https://issues.apache.org/jira/browse/FLINK-11417?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-11417. -- Resolution: Implemented Fix Version/s: 1.8.0 Merged in: master: 85bae44 > Make access

[jira] [Closed] (FLINK-10473) State TTL incremental cleanup using Heap backend key iterator

[ https://issues.apache.org/jira/browse/FLINK-10473?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-10473. -- Resolution: Fixed Merged in: master: 592f3a9 > State TTL incremental cleanup using Heap

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

[ https://issues.apache.org/jira/browse/FLINK-10043?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-10043: --- Description: Currently, the constructor of {{RocksDBKeyedStateBackend}} has the following

[jira] [Comment Edited] (FLINK-11775) Introduce MemorySegmentWritable to let DataOutputView direct copy to internal bytes

[ https://issues.apache.org/jira/browse/FLINK-11775?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16815161#comment-16815161 ] Stefan Richter edited comment on FLINK-11775 at 4/11/19 7:59 AM: -

[jira] [Commented] (FLINK-11775) Introduce MemorySegmentWritable to let DataOutputView direct copy to internal bytes

[ https://issues.apache.org/jira/browse/FLINK-11775?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16815161#comment-16815161 ] Stefan Richter commented on FLINK-11775: [~StephanEwen] I found that the implementation in

[jira] [Comment Edited] (FLINK-11775) Introduce MemorySegmentWritable to let DataOutputView direct copy to internal bytes

[ https://issues.apache.org/jira/browse/FLINK-11775?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16815161#comment-16815161 ] Stefan Richter edited comment on FLINK-11775 at 4/11/19 7:58 AM: -

[jira] [Closed] (FLINK-10205) Batch Job: InputSplit Fault tolerant for DataSourceTask

[ https://issues.apache.org/jira/browse/FLINK-10205?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-10205. -- Resolution: Implemented Fix Version/s: 1.9.0 Merged in: master: 4f689b1 > Batch Job:

[jira] [Closed] (FLINK-11953) Introduce Plugin/Loading system and integrate it with FileSystem

[ https://issues.apache.org/jira/browse/FLINK-11953?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-11953. -- Resolution: Implemented Fix Version/s: 1.9.0 Merged in: master: c6307b5990 >

[jira] [Resolved] (FLINK-11954) Provide unit test(s) for new plugin infrastructure

[ https://issues.apache.org/jira/browse/FLINK-11954?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter resolved FLINK-11954. Resolution: Done Work is already done as part of FLINK-11953 > Provide unit test(s) for

[jira] [Commented] (FLINK-11955) Modify build to move filesystems from lib to plugins folder

[ https://issues.apache.org/jira/browse/FLINK-11955?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16817887#comment-16817887 ] Stefan Richter commented on FLINK-11955: [~yanghua] are you commited to working on this issue?

[jira] [Comment Edited] (FLINK-11955) Modify build to move filesystems from lib to plugins folder

[ https://issues.apache.org/jira/browse/FLINK-11955?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16817887#comment-16817887 ] Stefan Richter edited comment on FLINK-11955 at 4/15/19 11:43 AM: --

[jira] [Comment Edited] (FLINK-6755) Allow triggering Checkpoints through command line client

[ https://issues.apache.org/jira/browse/FLINK-6755?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16842210#comment-16842210 ] Stefan Richter edited comment on FLINK-6755 at 5/17/19 2:25 PM: IMO, this

[jira] [Commented] (FLINK-6755) Allow triggering Checkpoints through command line client

[ https://issues.apache.org/jira/browse/FLINK-6755?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16842210#comment-16842210 ] Stefan Richter commented on FLINK-6755: --- IMO, this somehow leads to the more general question about

[jira] [Comment Edited] (FLINK-6755) Allow triggering Checkpoints through command line client

[ https://issues.apache.org/jira/browse/FLINK-6755?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16842210#comment-16842210 ] Stefan Richter edited comment on FLINK-6755 at 5/17/19 2:24 PM: IMO, this

[jira] [Comment Edited] (FLINK-6755) Allow triggering Checkpoints through command line client

[ https://issues.apache.org/jira/browse/FLINK-6755?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16842210#comment-16842210 ] Stefan Richter edited comment on FLINK-6755 at 5/17/19 2:30 PM: IMO, this

[jira] [Commented] (FLINK-8871) Checkpoint cancellation is not propagated to stop checkpointing threads on the task manager

[ https://issues.apache.org/jira/browse/FLINK-8871?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16848118#comment-16848118 ] Stefan Richter commented on FLINK-8871: --- After this quiet intense exchange, I was thinking a bit

[jira] [Comment Edited] (FLINK-8871) Checkpoint cancellation is not propagated to stop checkpointing threads on the task manager

[ https://issues.apache.org/jira/browse/FLINK-8871?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16848118#comment-16848118 ] Stefan Richter edited comment on FLINK-8871 at 5/25/19 9:58 AM: After

[jira] [Commented] (FLINK-12070) Make blocking result partitions consumable multiple times

[ https://issues.apache.org/jira/browse/FLINK-12070?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16855013#comment-16855013 ] Stefan Richter commented on FLINK-12070: I have one more additional question: can you share the

[jira] [Created] (FLINK-12804) Introduce mailbox-based ExecutorService

Stefan Richter created FLINK-12804: -- Summary: Introduce mailbox-based ExecutorService Key: FLINK-12804 URL: https://issues.apache.org/jira/browse/FLINK-12804 Project: Flink Issue Type:

[jira] [Closed] (FLINK-12364) Introduce a CheckpointFailureManager to centralized manage checkpoint failure

[ https://issues.apache.org/jira/browse/FLINK-12364?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-12364. -- Resolution: Implemented Merged in: master: 8c57e5ae > Introduce a CheckpointFailureManager

[jira] [Created] (FLINK-12958) Integrate AsyncWaitOperator with mailbox

Stefan Richter created FLINK-12958: -- Summary: Integrate AsyncWaitOperator with mailbox Key: FLINK-12958 URL: https://issues.apache.org/jira/browse/FLINK-12958 Project: Flink Issue Type:

[jira] [Commented] (FLINK-12481) Make processing time timer trigger run via the mailbox

[ https://issues.apache.org/jira/browse/FLINK-12481?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16838391#comment-16838391 ] Stefan Richter commented on FLINK-12481: Hi [~aitozi] and thanks for offering some help. Can we

[jira] [Created] (FLINK-12591) StatsDReporterTest is unstable

Stefan Richter created FLINK-12591: -- Summary: StatsDReporterTest is unstable Key: FLINK-12591 URL: https://issues.apache.org/jira/browse/FLINK-12591 Project: Flink Issue Type: Bug

[jira] [Closed] (FLINK-12478) Decompose monolithic run-loops in StreamTask implementations into step-wise calls

[ https://issues.apache.org/jira/browse/FLINK-12478?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-12478. -- Resolution: Implemented Merged in: master 022f6cce > Decompose monolithic run-loops in

[jira] [Closed] (FLINK-12480) Introduce mailbox to StreamTask main-loop

[ https://issues.apache.org/jira/browse/FLINK-12480?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-12480. -- Resolution: Implemented Merged in: master 022f6cce > Introduce mailbox to StreamTask

[jira] [Assigned] (FLINK-12482) Make checkpoint trigger/notifyComplete run via the mailbox queue

[ https://issues.apache.org/jira/browse/FLINK-12482?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reassigned FLINK-12482: -- Assignee: Stefan Richter (was: vinoyang) > Make checkpoint trigger/notifyComplete

[jira] [Closed] (FLINK-12483) Support (legacy) SourceFunctions with mailbox

[ https://issues.apache.org/jira/browse/FLINK-12483?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-12483. -- Resolution: Implemented Fix Version/s: 1.9.0 Merged in: master ead91396 > Support

[jira] [Created] (FLINK-12480) Introduce mailbox to StreamTask main-loop

Stefan Richter created FLINK-12480: -- Summary: Introduce mailbox to StreamTask main-loop Key: FLINK-12480 URL: https://issues.apache.org/jira/browse/FLINK-12480 Project: Flink Issue Type:

[jira] [Created] (FLINK-12481) Make processing time timer trigger run via the mailbox

Stefan Richter created FLINK-12481: -- Summary: Make processing time timer trigger run via the mailbox Key: FLINK-12481 URL: https://issues.apache.org/jira/browse/FLINK-12481 Project: Flink

[jira] [Created] (FLINK-12484) Drop unnecessary locking for code-paths that now use the mailbox

Stefan Richter created FLINK-12484: -- Summary: Drop unnecessary locking for code-paths that now use the mailbox Key: FLINK-12484 URL: https://issues.apache.org/jira/browse/FLINK-12484 Project: Flink

[jira] [Created] (FLINK-12477) Change threading-model in StreamTask to a mailbox-based approach

Stefan Richter created FLINK-12477: -- Summary: Change threading-model in StreamTask to a mailbox-based approach Key: FLINK-12477 URL: https://issues.apache.org/jira/browse/FLINK-12477 Project: Flink

[jira] [Created] (FLINK-12479) Make InputProcessors and StreamIterationHead non-blocking

Stefan Richter created FLINK-12479: -- Summary: Make InputProcessors and StreamIterationHead non-blocking Key: FLINK-12479 URL: https://issues.apache.org/jira/browse/FLINK-12479 Project: Flink

[jira] [Created] (FLINK-12478) Decompose monolithic run-loops in StreamTask implementations into step-wise calls

Stefan Richter created FLINK-12478: -- Summary: Decompose monolithic run-loops in StreamTask implementations into step-wise calls Key: FLINK-12478 URL: https://issues.apache.org/jira/browse/FLINK-12478

[jira] [Created] (FLINK-12482) Make checkpoint trigger/notifyComplete run via the mailbox queue

Stefan Richter created FLINK-12482: -- Summary: Make checkpoint trigger/notifyComplete run via the mailbox queue Key: FLINK-12482 URL: https://issues.apache.org/jira/browse/FLINK-12482 Project: Flink

[jira] [Updated] (FLINK-12477) Change threading-model in StreamTask to a mailbox-based approach

[ https://issues.apache.org/jira/browse/FLINK-12477?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-12477: --- Description: This is the umbrella issue to change the threading-model in StreamTask to a

[jira] [Created] (FLINK-12483) Support (legacy) SourceFunctions with mailbox

Stefan Richter created FLINK-12483: -- Summary: Support (legacy) SourceFunctions with mailbox Key: FLINK-12483 URL: https://issues.apache.org/jira/browse/FLINK-12483 Project: Flink Issue

[jira] [Assigned] (FLINK-12480) Introduce mailbox to StreamTask main-loop

[ https://issues.apache.org/jira/browse/FLINK-12480?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reassigned FLINK-12480: -- Assignee: Stefan Richter > Introduce mailbox to StreamTask main-loop >

[jira] [Commented] (FLINK-10855) CheckpointCoordinator does not delete checkpoint directory of late/failed checkpoints

[ https://issues.apache.org/jira/browse/FLINK-10855?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16844829#comment-16844829 ] Stefan Richter commented on FLINK-10855: [~yanghua] Just a heads-up that you pinged the wrong

[jira] [Commented] (FLINK-10855) CheckpointCoordinator does not delete checkpoint directory of late/failed checkpoints

[ https://issues.apache.org/jira/browse/FLINK-10855?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16841428#comment-16841428 ] Stefan Richter commented on FLINK-10855: @vinoyang i guess i cannot. I was just testing the

[jira] [Assigned] (FLINK-12483) Support (legacy) SourceFunctions with mailbox

[ https://issues.apache.org/jira/browse/FLINK-12483?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reassigned FLINK-12483: -- Assignee: Stefan Richter (was: vinoyang) > Support (legacy) SourceFunctions with

[jira] [Closed] (FLINK-10724) Refactor failure handling in check point coordinator

[ https://issues.apache.org/jira/browse/FLINK-10724?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-10724. -- Resolution: Done Fix Version/s: 1.9.0 Merged in: master: c4b0e8f > Refactor failure

[jira] [Closed] (FLINK-12350) RocksDBStateBackendTest doesn't cover the incremental checkpoint code path

[ https://issues.apache.org/jira/browse/FLINK-12350?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-12350. -- Resolution: Fixed Fix Version/s: 1.9.0 Merged in: master: 9aeb4e5 >

[jira] [Reopened] (FLINK-12350) RocksDBStateBackendTest doesn't cover the incremental checkpoint code path

[ https://issues.apache.org/jira/browse/FLINK-12350?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reopened FLINK-12350: > RocksDBStateBackendTest doesn't cover the incremental checkpoint code path >

[jira] [Closed] (FLINK-12350) RocksDBStateBackendTest doesn't cover the incremental checkpoint code path

[ https://issues.apache.org/jira/browse/FLINK-12350?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-12350. -- Resolution: Fixed Fix Version/s: 1.8.1 Merged in: master: 9aeb4e5 release-1.8:

[jira] [Closed] (FLINK-11167) Optimize RocksDBList#put for no empty input

[ https://issues.apache.org/jira/browse/FLINK-11167?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-11167. -- Resolution: Implemented Fix Version/s: 1.9.0 Merged in: master: 03faeb9 > Optimize

[jira] [Commented] (FLINK-13072) RocksDBStateBachend is not thread safe and data loss silently

[ https://issues.apache.org/jira/browse/FLINK-13072?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16879099#comment-16879099 ] Stefan Richter commented on FLINK-13072: [~zicat] All operators in Flink are assumed to be

[jira] [Comment Edited] (FLINK-13072) RocksDBStateBachend is not thread safe and data loss silently

[ https://issues.apache.org/jira/browse/FLINK-13072?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16879099#comment-16879099 ] Stefan Richter edited comment on FLINK-13072 at 7/5/19 9:21 AM: [~zicat]

[jira] [Assigned] (FLINK-13063) AsyncWaitOperator shouldn't be releasing checkpointingLock

[ https://issues.apache.org/jira/browse/FLINK-13063?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reassigned FLINK-13063: -- Assignee: Stefan Richter (was: Piotr Nowojski) > AsyncWaitOperator shouldn't be

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

[ https://issues.apache.org/jira/browse/FLINK-7289?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16874318#comment-16874318 ] Stefan Richter commented on FLINK-7289: --- [~mikekap] I think that is a very good suggestion and

[jira] [Updated] (FLINK-12804) Introduce mailbox-based ExecutorService

[ https://issues.apache.org/jira/browse/FLINK-12804?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-12804: --- Fix Version/s: (was: 1.9.0) 1.10.0 > Introduce mailbox-based

[jira] [Assigned] (FLINK-12958) Integrate AsyncWaitOperator with mailbox

[ https://issues.apache.org/jira/browse/FLINK-12958?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter reassigned FLINK-12958: -- Assignee: (was: Stefan Richter) > Integrate AsyncWaitOperator with mailbox >

[jira] [Closed] (FLINK-12804) Introduce mailbox-based ExecutorService

[ https://issues.apache.org/jira/browse/FLINK-12804?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-12804. -- Resolution: Implemented Merged in: master: 6cf98b671d > Introduce mailbox-based

[jira] [Created] (FLINK-13248) Enhance mailbox executor with yield-to-downstream functionality

Stefan Richter created FLINK-13248: -- Summary: Enhance mailbox executor with yield-to-downstream functionality Key: FLINK-13248 URL: https://issues.apache.org/jira/browse/FLINK-13248 Project: Flink

[jira] [Updated] (FLINK-12958) Integrate AsyncWaitOperator with mailbox

[ https://issues.apache.org/jira/browse/FLINK-12958?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter updated FLINK-12958: --- Labels: (was: pull-request-available) > Integrate AsyncWaitOperator with mailbox >

[jira] [Closed] (FLINK-12730) Combine BitSet implementations in flink-runtime

[ https://issues.apache.org/jira/browse/FLINK-12730?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-12730. -- Resolution: Implemented Merged in: master: 14c4b23 > Combine BitSet implementations in

[jira] [Closed] (FLINK-12693) Store state per key-group in CopyOnWriteStateTable

[ https://issues.apache.org/jira/browse/FLINK-12693?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-12693. -- Resolution: Implemented Merged in: master: 8f47b38 > Store state per key-group in

[jira] [Commented] (FLINK-13072) RocksDBStateBachend is not thread safe and data loss silently

[ https://issues.apache.org/jira/browse/FLINK-13072?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16881149#comment-16881149 ] Stefan Richter commented on FLINK-13072: [~zicat] After reading my previous comment, do you

[jira] [Closed] (FLINK-13063) AsyncWaitOperator shouldn't be releasing checkpointingLock

[ https://issues.apache.org/jira/browse/FLINK-13063?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-13063. -- Resolution: Fixed Release Note: This changes the default chaining behavior of the

[jira] [Commented] (FLINK-13249) Distributed Jepsen test fails with blocked TaskExecutor

[ https://issues.apache.org/jira/browse/FLINK-13249?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16884960#comment-16884960 ] Stefan Richter commented on FLINK-13249: [~gaoyunhaii] thanks for the input, I think what you

[jira] [Commented] (FLINK-13249) Distributed Jepsen test fails with blocked TaskExecutor

[ https://issues.apache.org/jira/browse/FLINK-13249?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16885002#comment-16885002 ] Stefan Richter commented on FLINK-13249: [~gaoyunhaii] That is also how I understood your

[jira] [Commented] (FLINK-13249) Distributed Jepsen test fails with blocked TaskExecutor

[ https://issues.apache.org/jira/browse/FLINK-13249?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16885059#comment-16885059 ] Stefan Richter commented on FLINK-13249: [~till.rohrmann] alright, I think then we have a

[jira] [Commented] (FLINK-12296) Data loss silently in RocksDBStateBackend when more than one operator(has states) chained in a single task

[ https://issues.apache.org/jira/browse/FLINK-12296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16825138#comment-16825138 ] Stefan Richter commented on FLINK-12296: [~klion26] In general I think it is a good idea to

[jira] [Created] (FLINK-12143) Mechanism to ship plugin jars in the cluster

Stefan Richter created FLINK-12143: -- Summary: Mechanism to ship plugin jars in the cluster Key: FLINK-12143 URL: https://issues.apache.org/jira/browse/FLINK-12143 Project: Flink Issue Type:

[jira] [Commented] (FLINK-11775) Introduce MemorySegmentWritable to let DataOutputView direct copy to internal bytes

[ https://issues.apache.org/jira/browse/FLINK-11775?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16813295#comment-16813295 ] Stefan Richter commented on FLINK-11775: [~lzljs3620320] I think in general the performance

[jira] [Closed] (FLINK-10712) RestartPipelinedRegionStrategy does not restore state

[ https://issues.apache.org/jira/browse/FLINK-10712?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-10712. -- Resolution: Fixed Fix Version/s: 1.9.0 Merged in: master: c3a9293 >

[jira] [Closed] (FLINK-12212) Clarify documentation about async checkpointing

[ https://issues.apache.org/jira/browse/FLINK-12212?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-12212. -- Resolution: Fixed Fix Version/s: 1.9.0 Merged in: master: 046d752c6e > Clarify

[jira] [Commented] (FLINK-11955) Modify build to move filesystems from lib to plugins folder

[ https://issues.apache.org/jira/browse/FLINK-11955?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16818833#comment-16818833 ] Stefan Richter commented on FLINK-11955: Great, thanks! I would suggest to use option 1, because

[jira] [Commented] (FLINK-12296) Data loss silently in RocksDBStateBackend when more than one operator(has states) chained in a single task

[ https://issues.apache.org/jira/browse/FLINK-12296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16824945#comment-16824945 ] Stefan Richter commented on FLINK-12296: I guess this is one remaining relic from how backends

[jira] [Commented] (FLINK-12296) Data loss silently in RocksDBStateBackend when more than one operator(has states) chained in a single task

[ https://issues.apache.org/jira/browse/FLINK-12296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16826787#comment-16826787 ] Stefan Richter commented on FLINK-12296: [~klion26] I was just taking a look into the code and

[jira] [Comment Edited] (FLINK-12296) Data loss silently in RocksDBStateBackend when more than one operator(has states) chained in a single task

[ https://issues.apache.org/jira/browse/FLINK-12296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16826787#comment-16826787 ] Stefan Richter edited comment on FLINK-12296 at 4/26/19 9:00 AM: -

[jira] [Commented] (FLINK-13249) Distributed Jepsen test fails with blocked TaskExecutor

[ https://issues.apache.org/jira/browse/FLINK-13249?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16885981#comment-16885981 ] Stefan Richter commented on FLINK-13249: My tendency is also more towards having a

[jira] [Closed] (FLINK-11662) Discarded checkpoint can cause Tasks to fail

[ https://issues.apache.org/jira/browse/FLINK-11662?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-11662. -- Resolution: Fixed Fix Version/s: 1.9.0 Merged in: master: b760d55 > Discarded

[jira] [Closed] (FLINK-13256) Periodical checkpointing is stopped after failovers

[ https://issues.apache.org/jira/browse/FLINK-13256?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-13256. -- Resolution: Fixed Merged in: master: 1ec34249a0 release-1.9: b7bfafca14 > Periodical

[jira] [Closed] (FLINK-13249) Distributed Jepsen test fails with blocked TaskExecutor

[ https://issues.apache.org/jira/browse/FLINK-13249?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Stefan Richter closed FLINK-13249. -- Resolution: Fixed Merged in: master: 23bd23b325 release-1.9: 3eff6387b5 > Distributed Jepsen

[jira] [Created] (FLINK-13325) Add test case for FLINK-13249

Stefan Richter created FLINK-13325: -- Summary: Add test case for FLINK-13249 Key: FLINK-13325 URL: https://issues.apache.org/jira/browse/FLINK-13325 Project: Flink Issue Type: Sub-task

[jira] [Commented] (FLINK-13072) RocksDBStateBachend is not thread safe and data loss silently

[ https://issues.apache.org/jira/browse/FLINK-13072?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16881825#comment-16881825 ] Stefan Richter commented on FLINK-13072: I think it is surely not a bad idea to improve or

<    4   5   6   7   8   9   10   >