Mailing-List: contact commits-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@cassandra.apache.org
Date: Thu, 17 Aug 2017 23:34:00 +0000 (UTC)
From: "Jason Brown (JIRA)" <jira@apache.org>
To: commits@cassandra.apache.org
Message-ID: <JIRA.13093973.1502415934000.60132.1503012840286@Atlassian.JIRA>
In-Reply-To: <JIRA.13093973.1502415934000@Atlassian.JIRA>
References: <JIRA.13093973.1502415934000@Atlassian.JIRA> <JIRA.13093973.1502415934413@jira-lw-us.apache.org>
Subject: [jira] [Commented] (CASSANDRA-13756) StreamingHistogram is not
 thread safe
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
archived-at: Thu, 17 Aug 2017 23:34:06 -0000


    [ https://issues.apache.org/jira/browse/CASSANDRA-13756?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16131480#comment-16131480 ] 

Jason Brown commented on CASSANDRA-13756:
-----------------------------------------

+1 on the changes, and please commit if/when the tests pass.

wrt trunk, yes, I think it should be safe due to the snapshots we create and access from {{StatsMetadata}}.

> StreamingHistogram is not thread safe
> -------------------------------------
>
>                 Key: CASSANDRA-13756
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-13756
>             Project: Cassandra
>          Issue Type: Bug
>            Reporter: xiangzhou xia
>            Assignee: Jeff Jirsa
>             Fix For: 3.0.x, 3.11.x
>
>
> When we test C*3 in shadow cluster, we notice after a period of time, several data node suddenly run into 100% cpu and stop process query anymore.
> After investigation, we found that threads are stuck on the sum() in streaminghistogram class. Those are jmx threads that working on expose getTombStoneRatio metrics (since jmx is kicked off every 3 seconds, there is a chance that multiple jmx thread is access streaminghistogram at the same time).  
> After further investigation, we find that the optimization in CASSANDRA-13038 led to a spool flush every time when we call sum(). Since TreeMap is not thread safe, threads will be stuck when multiple threads visit sum() at the same time.
> There are two approaches to solve this issue. 
> The first one is to add a lock to the flush in sum() which will introduce some extra overhead to streaminghistogram.
> The second one is to avoid streaminghistogram to be access by multiple threads. For our specific case, is to remove the metrics we added.  


--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@cassandra.apache.org
For additional commands, e-mail: commits-help@cassandra.apache.org