Mailing-List: contact commits-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@cassandra.apache.org
Date: Fri, 13 Jun 2014 01:17:04 +0000 (UTC)
From: "Jonathan Ellis (JIRA)" <jira@apache.org>
To: commits@cassandra.apache.org
Message-ID: <JIRA.12707049.1396911283827.123730.1402622224724@arcas>
In-Reply-To: <JIRA.12707049.1396911283827@arcas>
References: <JIRA.12707049.1396911283827@arcas>
Subject: [jira] [Updated] (CASSANDRA-6995) Execute local ONE/LOCAL_ONE reads
 on request thread instead of dispatching to read stage
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


     [ https://issues.apache.org/jira/browse/CASSANDRA-6995?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Jonathan Ellis updated CASSANDRA-6995:
--------------------------------------

    Fix Version/s:     (was: 2.0.9)
                   3.0

Think we need to retarget this for 3.0.

> Execute local ONE/LOCAL_ONE reads on request thread instead of dispatching to read stage
> ----------------------------------------------------------------------------------------
>
>                 Key: CASSANDRA-6995
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-6995
>             Project: Cassandra
>          Issue Type: Improvement
>          Components: Core
>            Reporter: Jason Brown
>            Assignee: Jason Brown
>            Priority: Minor
>              Labels: performance
>             Fix For: 3.0
>
>         Attachments: 6995-v1.diff, syncread-stress.txt
>
>
> When performing a read local to a coordinator node, AbstractReadExecutor will create a new SP.LocalReadRunnable and drop it into the read stage for asynchronous execution. If you are using a client that intelligently routes  read requests to a node holding the data for a given request, and are using CL.ONE/LOCAL_ONE, the enqueuing SP.LocalReadRunnable and waiting for the context switches (and possible NUMA misses) adds unneccesary latency. We can reduce that latency and improve throughput by avoiding the queueing and thread context switching by simply executing the SP.LocalReadRunnable synchronously in the request thread. Testing on a three node cluster (each with 32 cpus, 132 GB ram) yields ~10% improvement in throughput and ~20% speedup on avg/95/99 percentiles (99.9% was about 5-10% improvement).


--
This message was sent by Atlassian JIRA
(v6.2#6252)