You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@cassandra.apache.org by "Jason Brown (JIRA)" <ji...@apache.org> on 2018/01/27 17:26:00 UTC
[jira] [Comment Edited] (CASSANDRA-14194) Chain commit log marker
potential performance regression in batch commit mode
[ https://issues.apache.org/jira/browse/CASSANDRA-14194?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16342232#comment-16342232 ]
Jason Brown edited comment on CASSANDRA-14194 at 1/27/18 5:25 PM:
------------------------------------------------------------------
[~aweisberg] don't forget, there was a follow ticket (CASSANDRA-14108) where we cleaned up a few things. I suspect that's the ticket that would have introduced the regression, if any.
That being said, running {{ViewTest}} on my laptop at the following SHAs all completed within the same amount of time (on the 3.0 branch):
* {{eb05025c0a768241ea61fd86db9a88cfd8f6e93e}} - commit before CASSANDRA-13987
* {{05cb556f90dbd1929a180254809e05620265419b}} - CASSANDRA-13987
* {{010c477e4c1b8b452cc0fa33b3fdb6c286e4037d}} - current head of cassandra-3.0 (CASSANDRA-14181)
Now, this doesn't discount [~aweisberg]'s discovery here. Ariel, which branch was this on?
I'll also do some more runs on circleci to compare...
was (Author: jasobrown):
[~aweisberg] don't forget,, there was a follow ticket (CASSANDRA-14108) where we cleaned up a few things.
That being said, running {{ViewTest}} on my laptop at the following SHAs all completed within the same amount of time (on the 3.0 branch):
* {{eb05025c0a768241ea61fd86db9a88cfd8f6e93e}} - commit before CASSANDRA-13987
* {{05cb556f90dbd1929a180254809e05620265419b}} - CASSANDRA-13987
* {{010c477e4c1b8b452cc0fa33b3fdb6c286e4037d}} - current head of cassandra-3.0 (CASSANDRA-14181)
Now, this doesn't discount [~aweisberg]'s discovery here. Ariel, which branch was this on?
I'll also do some more runs on circleci to compare...
> Chain commit log marker potential performance regression in batch commit mode
> -----------------------------------------------------------------------------
>
> Key: CASSANDRA-14194
> URL: https://issues.apache.org/jira/browse/CASSANDRA-14194
> Project: Cassandra
> Issue Type: Bug
> Components: Core, Testing
> Reporter: Ariel Weisberg
> Assignee: Jason Brown
> Priority: Major
> Attachments: jstack.txt
>
>
> CASSANDRA-13987 modified how the commit log sync thread works. I noticed that cql3.ViewTest and ViewBuilderTaskTest have been timing out, but only in CircleCI. When I jstack in CircleCI what I see is that the commit log writer thread is parked and the threads trying to append to the commit log are blocked waiting on it.
> I tested the commit before 13987 and it passed in CircleCI and then I tested with 13987 and it timed out. I suspect this may be a general performance regression and not just a CircleCI issue.
> And this is with write barriers disabled (sync thread doesn't actually sync) so it wasn't blocked in the filesystem.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@cassandra.apache.org
For additional commands, e-mail: commits-help@cassandra.apache.org