Mailing-List: contact commits-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@cassandra.apache.org
Date: Mon, 6 Jul 2015 10:07:05 +0000 (UTC)
From: "Benedict (JIRA)" <jira@apache.org>
To: commits@cassandra.apache.org
Message-ID: <JIRA.12835794.1433527678000.104262.1436177225223@Atlassian.JIRA>
In-Reply-To: <JIRA.12835794.1433527678000@Atlassian.JIRA>
References: <JIRA.12835794.1433527678000@Atlassian.JIRA>
 <JIRA.12835794.1433527678519@arcas>
Subject: [jira] [Commented] (CASSANDRA-9558) Cassandra-stress regression in
 2.2
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/CASSANDRA-9558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14614813#comment-14614813 ] 

Benedict commented on CASSANDRA-9558:
-------------------------------------

bq. The problem does not exist with Cassandra because it's a server, both the producer and the consumer is the event loop.

They aren't, but there is a bound on the number of concurrent connections we can be processing requests for on the server, and so the queue size must itself be bounded. 

I would also suggest imposing a user-configurable bound on the size of your queues in the driver (or the total number of not-yet-sent messages), as there can be a multitude of reasons for the message queues to back up, and that's independently bad for the health of the application process. That wouldn't solve this problem, but it would have likely helped a great deal, and is something to consider as well (especially as we may start blocking receipt of messages to cope with cluster overload, which would translate to a growing application send buffer).

Either way, good catch. Looks like the fix should be simple (let's hope it brings throughput right back up).

> Cassandra-stress regression in 2.2
> ----------------------------------
>
>                 Key: CASSANDRA-9558
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-9558
>             Project: Cassandra
>          Issue Type: Bug
>            Reporter: Alan Boudreault
>            Assignee: Andy Tolbert
>             Fix For: 2.2.0 rc2
>
>         Attachments: 2.1.log, 2.2.log, CASSANDRA-9558-2.patch, CASSANDRA-9558-ProtocolV2.patch, atolber-CASSANDRA-9558-stress.tgz, atolber-trunk-driver-coalescing-disabled.txt, stress-2.1-java-driver-2.0.9.2.log, stress-2.1-java-driver-2.2+PATCH.log, stress-2.1-java-driver-2.2.log, stress-2.2-java-driver-2.2+PATCH.log, stress-2.2-java-driver-2.2.log
>
>
> We are seeing some regression in performance when using cassandra-stress 2.2. You can see the difference at this url:
> http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=stress_regression.json&metric=op_rate&operation=1_write&smoothing=1&show_aggregates=true&xmin=0&xmax=108.57&ymin=0&ymax=168147.1
> The cassandra version of the cluster doesn't seem to have any impact. 
> //cc [~tjake] [~benedict]


--
This message was sent by Atlassian JIRA
(v6.3.4#6332)