[ 
https://issues.apache.org/jira/browse/SOLR-4509?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14224494#comment-14224494
 ] 

Mark Miller commented on SOLR-4509:
-----------------------------------

To sum up the very high level: currently, each connection thread does a stale 
check, and of course, even it if it passes the server could close the 
connection a millisecond later. It's better to remove this stale check that 
every thread has to deal with and have a dedicated thread that handles stale 
connections itself, and in a way that they are closed on the client before they 
are closed on the server. We want the client to handle connection lifecycle. 
Nothing promises you that you will never get a connection reset - but rather, 
it should go from fairly easy to randomly happen for apparently no good reason 
to almost never happening (and perhaps it is a better reason than bad luck 
timing if it does - a reason you might be able to address).

> Disable HttpClient stale check for performance and fewer spurious connection 
> errors.
> ------------------------------------------------------------------------------------
>
>                 Key: SOLR-4509
>                 URL: https://issues.apache.org/jira/browse/SOLR-4509
>             Project: Solr
>          Issue Type: Improvement
>          Components: search
>         Environment: 5 node SmartOS cluster (all nodes living in same global 
> zone - i.e. same physical machine)
>            Reporter: Ryan Zezeski
>            Assignee: Mark Miller
>            Priority: Minor
>             Fix For: 5.0, Trunk
>
>         Attachments: IsStaleTime.java, SOLR-4509-4_4_0.patch, 
> SOLR-4509.patch, SOLR-4509.patch, SOLR-4509.patch, SOLR-4509.patch, 
> baremetal-stale-nostale-med-latency.dat, 
> baremetal-stale-nostale-med-latency.svg, 
> baremetal-stale-nostale-throughput.dat, baremetal-stale-nostale-throughput.svg
>
>
> By disabling the Apache HTTP Client stale check I've witnessed a 2-4x 
> increase in throughput and reduction of over 100ms.  This patch was made in 
> the context of a project I'm leading, called Yokozuna, which relies on 
> distributed search.
> Here's the patch on Yokozuna: https://github.com/rzezeski/yokozuna/pull/26
> Here's a write-up I did on my findings: 
> http://www.zinascii.com/2013/solr-distributed-search-and-the-stale-check.html
> I'm happy to answer any questions or make changes to the patch to make it 
> acceptable.
> ReviewBoard: https://reviews.apache.org/r/28393/



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

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscr...@lucene.apache.org
For additional commands, e-mail: dev-h...@lucene.apache.org

Reply via email to