Hi Till,
Thanks for your reply! I will try to add ones later.
Best,
tison.
Till Rohrmann 于2018年7月18日周三 下午2:48写道：
> Hi Tison,
>
> at the moment there is formal way to verify performance improvements. What
> you can do is to provide your measurements by adding the graphs to the PR
> thread and s
Hi Tison,
at the moment there is formal way to verify performance improvements. What
you can do is to provide your measurements by adding the graphs to the PR
thread and specify the setup. Then others could try to verify these numbers
by running their own benchmark.
Cheers,
Till
On Wed, Jul 18,
Hi,
We have 4 jobs with parallelism 3 that are running over 3 task manager with
4 slots per each , each task manager runs on a different VM ,
On Flink 1.3.2 the jobs were evenly distributed per node each job took one
task slot of each task manager .
After upgrading to flink 1.5 , each job is ru
Riley Li created FLINK-9882:
---
Summary: A function access can be private in client
Key: FLINK-9882
URL: https://issues.apache.org/jira/browse/FLINK-9882
Project: Flink
Issue Type: Improvement
Hi Piotr,
Thanks for your replies and professional suggestions!
My initial thought is just as you said in first suggestion. The current
RecordWriter will emit StreamRecord to some subpartition via ChannelSelector or
broadcast events/watermark to all subpartitions directly.
If the ChannelSelecto
Hi all,
Recently I pull 3 PRs about performance improvements[1][2][3]. Unit tests
will verify their correctness, and in the real scenario, we have benchmark
report to confirm that they do help for performance.
I wonder what is the formal way to verify a performance improvement. Is it
to give out
Ashwin Sinha created FLINK-9881:
---
Summary: Typo in a function name in table.scala
Key: FLINK-9881
URL: https://issues.apache.org/jira/browse/FLINK-9881
Project: Flink
Issue Type: Improvement
Ted Yu created FLINK-9880:
-
Summary: Incorrect argument order calling BucketerContext#update
Key: FLINK-9880
URL: https://issues.apache.org/jira/browse/FLINK-9880
Project: Flink
Issue Type: Bug
Hi
Generally speaking this would be a nice optimisation, however it might be
tricky to implement. The thing to keep in mind is that currently interface
allow to interleave broadcasting and normal sending, because of that at any
given time some serialisers can have more data then others. For exa
Hi everyone,
I'd like to announce the program for Flink Forward Berlin 2018.
The program committee [1] assembled a program of about 50 talks on use
cases, operations, ecosystem, tech deep dive, and research topics.
The conference will host speakers from Airbnb, Amazon, Google, ING, Lyft,
Microsof
Nico Kruber created FLINK-9879:
--
Summary: Find sane defaults for (advanced) SSL session parameters
Key: FLINK-9879
URL: https://issues.apache.org/jira/browse/FLINK-9879
Project: Flink
Issue Type
Nico Kruber created FLINK-9878:
--
Summary: IO worker threads BLOCKED on SSL Session Cache while CMS
full gc
Key: FLINK-9878
URL: https://issues.apache.org/jira/browse/FLINK-9878
Project: Flink
I
Florian Schmidt created FLINK-9877:
--
Summary: Add separate docs page for different join types in
DataStream API
Key: FLINK-9877
URL: https://issues.apache.org/jira/browse/FLINK-9877
Project: Flink
Florian Schmidt created FLINK-9876:
--
Summary: ExecutionGraphCoLocationRestartTest
testConstraintsAfterRestart sometimes fails with timeout
Key: FLINK-9876
URL: https://issues.apache.org/jira/browse/FLINK-9876
陈梓立 created FLINK-9875:
--
Summary: Add concurrent creation of execution job vertex
Key: FLINK-9875
URL: https://issues.apache.org/jira/browse/FLINK-9875
Project: Flink
Issue Type: Improvement
C
Florian Schmidt created FLINK-9874:
--
Summary: set_conf_ssl in E2E tests fails on macOS
Key: FLINK-9874
URL: https://issues.apache.org/jira/browse/FLINK-9874
Project: Flink
Issue Type: Bug
Dear community,
this is the weekly community update thread #29. Please post any news and
updates you want to share with the community to this thread.
# Feature freeze Flink 1.6
The Flink community has cut off the release branch for Flink 1.6 [1]. From
now on, the community will concentrate on fi
Hi Sampath,
technically the client does not need to know the
`high-availability.storageDir` to submit a job. However, due to how we
construct the ZooKeeperHaServices it is still needed. The reason behind
this is that we use the same services for the server and the client. Thus,
the implementation
Hi Titus,
have you looked into ProcessFunction? ProcessFunction[1] gives you
access to the two important streaming primitives "time" and "state".
So in your case you can decide flexibly what you want to put into state
and when you want to set and fire a timer (for clean-up) per key.
Regards
Hi Sampath,
It seems Flink CLI for standalone would not access
*high-availability.storageDir.*
What's the exception stack trace in your environment?
Thanks, vino.
2018-07-17 15:08 GMT+08:00 Sampath Bhat :
> Hi vino
>
> Should the flink CLI have access to the path mentioned in
> *high-availabil
Chesnay Schepler created FLINK-9873:
---
Summary: Log actual state when aborting checkpoint due to task not
running
Key: FLINK-9873
URL: https://issues.apache.org/jira/browse/FLINK-9873
Project: Flink
Chesnay Schepler created FLINK-9872:
---
Summary: SavepointITCase#testSavepointForJobWithIteration does not
properly cancell jobs
Key: FLINK-9872
URL: https://issues.apache.org/jira/browse/FLINK-9872
P
Friends, any assistance regarding this?
On Mon, Jul 16, 2018 at 3:44 PM, Titus Rakkesh
wrote:
> Dear All,
>
> We have 2 independent streams which will receive elements in different
> frequency,
>
> DataStream> splittedActivationTuple;
>
> DataStream> unionReloadsStream;
>
> We have a requiremen
Dawid Wysakowicz created FLINK-9871:
---
Summary: Use Description class for ConfigOptions with rich
formatting
Key: FLINK-9871
URL: https://issues.apache.org/jira/browse/FLINK-9871
Project: Flink
Timo Walther created FLINK-9870:
---
Summary: Support field mapping and time attributes for table sinks
Key: FLINK-9870
URL: https://issues.apache.org/jira/browse/FLINK-9870
Project: Flink
Issue T
Hi vino
Should the flink CLI have access to the path mentioned in
*high-availability.storageDir*?
If my flink cluster is on set of machines and i submit my job from flink
CLI from another independent machine by giving necessary details will the
CLI try to access *high-availability.storageDir *path
26 matches
Mail list logo
