clear query| facets| time Search criteria: .   Results from 1 to 10 from 169 (0.0s).
Loading phrases to help you
refine your search...
[FLINK-12203] Refactor ResultPartitionManager to break tie with Task - Flink - [issue]
...At the moment, we have ResultPartitionManager.releasePartitionsProducedBy which uses indexing by task in network environment. These methods are eventually used only by Task which already kno...
http://issues.apache.org/jira/browse/FLINK-12203    Author: Andrey Zagrebin , 2019-04-18, 13:51
[expand - 1 more] - [Discuss][FLINK-8297]A solution for FLINK-8297 Timebased RocksDBListState - Flink - [mail # dev]
...Hi Faxian,True, we can resolve timestamp conflicts putting values into the same row,good point.Then re-ordering in case of internal clock jump changes behaviour comparingwith the list state ...
   Author: Andrey Zagrebin , 2019-04-16, 08:51
[FLINK-10724] Refactor failure handling in check point coordinator - Flink - [issue]
...At the moment failure handling of asynchronously triggered checkpoint in check point coordinator happens in different places. We could organise it similar way as failure handling of synchron...
http://issues.apache.org/jira/browse/FLINK-10724    Author: Andrey Zagrebin , 2019-04-16, 06:13
[FLINK-12199] Refactor IOMetrics to not distinguish between local/remote in/out bytes - Flink - [issue]
...At the moment we have numBytesInLocal/numBytesInRemote in IOMetrics but in the actual usage we just always sum them up. As local/remote is the detail of shuffle service implementation, we ca...
http://issues.apache.org/jira/browse/FLINK-12199    Author: Andrey Zagrebin , 2019-04-16, 05:36
[FLINK-12202] Consider introducing batch metric register in NetworkEnviroment - Flink - [issue]
...As we have some network specific metrics registered in TaskIOMetricGroup (In/OutputBuffersGauge, In/OutputBufferPoolUsageGauge), we can introduce batch metric registering in NetworkEnviromen...
http://issues.apache.org/jira/browse/FLINK-12202    Author: Andrey Zagrebin , 2019-04-15, 15:39
[FLINK-12201] Introduce InputGateWithMetrics in Task to increment in/out byte metrics - Flink - [issue]
...Incrementing of in/out byte metrics in local/remote input channel does not depend on shuffle service and can be moved out of network internals into Task. Task could wrap InputGate provided b...
http://issues.apache.org/jira/browse/FLINK-12201    Author: Andrey Zagrebin , 2019-04-15, 15:27
[expand - 1 more] - [Discuss] Semantics of event time for state TTL - Flink - [mail # user]
...Hi everybody,Thanks a lot for your detailed feedback on this topic.It looks like we can already do some preliminary wrap-up for thisdiscussion.As far as I see we have the following trends:*L...
   Author: Andrey Zagrebin , 2019-04-15, 13:58
[expand - 1 more] - [DISCUSS] A more restrictive JIRA workflow - Flink - [mail # dev]
...@Robert thanks for pointing out and sorry for confusion. The correct text:+1 for option 1.I also do not mind option 2, after 1-2 contributions, any contributor couldjust ask the committer (w...
   Author: Andrey Zagrebin , 2019-04-15, 11:39
[FLINK-12193] Send TM "can be released status" with RM heartbeat - Flink - [issue]
...We introduced a conditional release of Task Executor in Resource Manager in FLINK-10941. At the moment RM directly asks TE every release timeout whether it can be released (all depending con...
http://issues.apache.org/jira/browse/FLINK-12193    Author: Andrey Zagrebin , 2019-04-15, 08:37
[FLINK-12005] [State TTL] Event time support - Flink - [issue]
...The event time is opted for in StateTtlConfig by setting TtlTimeCharacteristic.EventTime.To enable event time support, the updated watermark needs to be passed to the state backend, shared w...
http://issues.apache.org/jira/browse/FLINK-12005    Author: Andrey Zagrebin , 2019-04-08, 14:22