Mailing-List: contact commits-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@cassandra.apache.org
Date: Tue, 12 May 2015 19:29:00 +0000 (UTC)
From: "Brandon Williams (JIRA)" <jira@apache.org>
To: commits@cassandra.apache.org
Message-ID: <JIRA.12829281.1431456199000.92153.1431458940137@Atlassian.JIRA>
In-Reply-To: <JIRA.12829281.1431456199000@Atlassian.JIRA>
References: <JIRA.12829281.1431456199000@Atlassian.JIRA>
 <JIRA.12829281.1431456199298@arcas>
Subject: [jira] [Updated] (CASSANDRA-9364) Add a warning when a high setting
 for rpc_max_threads is specified for HSHA
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


     [ https://issues.apache.org/jira/browse/CASSANDRA-9364?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Brandon Williams updated CASSANDRA-9364:
----------------------------------------
    Attachment: 9364.txt

Patch to warn when over cores * 2 + 1024, which covers all the cases of this I've seen.

> Add a warning when a high setting for rpc_max_threads is specified for HSHA
> ---------------------------------------------------------------------------
>
>                 Key: CASSANDRA-9364
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-9364
>             Project: Cassandra
>          Issue Type: Improvement
>            Reporter: Brandon Williams
>             Fix For: 2.0.15, 2.1.x
>
>         Attachments: 9364.txt
>
>
> In CASSANDRA-7594 we allowed configuring this.  The problem is this was ignored for HSHA previously, so some people go through this scenario:
> 1. start with sync and 4000 threads
> 2. switch to HSHA, pre-7594
> 3. upgrade to a version after 7594, without changing this setting
> 4. experience awful performance due to insane thread contention


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