[
https://issues.apache.org/jira/browse/IGNITE-9186?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16568571#comment-16568571
]
ASF GitHub Bot commented on IGNITE-9186:
----------------------------------------
GitHub user AMashenkov opened a pull request:
https://github.com/apache/ignite/pull/4484
IGNITE-9186: Omit datastreamer per-thread buffers for already batched.
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/gridgain/apache-ignite ignite-9186
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/ignite/pull/4484.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #4484
----
commit 3fc53117e648593fbbe8ab512ced01b2c14ef267
Author: Andrey V. Mashenkov <andrey.mashenkov@...>
Date: 2018-08-03T17:54:32Z
IGNITE-9186: Omit datastreamer per-thread buffers for already batched data.
----
> Datastreamer may ignores perNodeBuffer size unexpectedly.
> ---------------------------------------------------------
>
> Key: IGNITE-9186
> URL: https://issues.apache.org/jira/browse/IGNITE-9186
> Project: Ignite
> Issue Type: Improvement
> Components: streaming
> Reporter: Andrew Mashenkov
> Assignee: Igor Seliverstov
> Priority: Major
>
> Looks like we have to omit per-thread buffer for batches that are passed to
> data streamer.
> Large per-thread buffer size may have negative affect on latency in some
> cases (small batch or small per-node buffer size).
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
