Mailing-List: contact dev-help@lucene.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@lucene.apache.org
Date: Mon, 25 Feb 2013 01:56:13 +0000 (UTC)
From: "Raintung Li (JIRA)" <jira@apache.org>
To: dev@lucene.apache.org
Message-ID: <JIRA.12631999.1360689859830.330827.1361757373157@arcas>
In-Reply-To: <JIRA.12631999.1360689859830@arcas>
References: <JIRA.12631999.1360689859830@arcas>
Subject: [jira] [Commented] (SOLR-4449) Enable backup requests for the
 internal solr load balancer
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/SOLR-4449?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13585565#comment-13585565 ] 

Raintung Li commented on SOLR-4449:
-----------------------------------

Let me describe it clear to make the same page.

Normal case:
Client send 1 request for search, the Servlet will have handle request thread that we call it is request main thread.
Then main thread will start 3 threads to send the request to 3 shards, because this collection has 3 shards.
Main thread block to wait the full 3 threads(shards) response.  
Result:
We need 4 threads in the normal case that don't send the second request.

Your case:
Client send 1 request search .....
Then main thread will start 6 threads to send the request to 3 shards......
Main thread block to wait the 3 threads response, the other 3 threads are stared in the LB
Result:
We need 7 threads in the normal case that don't send the second request.


My case:
Client send 1 request for search, ....
Then this thread will .....
Change: Main thread wait the 3 threads response in the fixed time. Which shard is overtime, main thread submit the second request.
Result:
We need 4 threads in the normal case that don't send the second request.
   

> Enable backup requests for the internal solr load balancer
> ----------------------------------------------------------
>
>                 Key: SOLR-4449
>                 URL: https://issues.apache.org/jira/browse/SOLR-4449
>             Project: Solr
>          Issue Type: New Feature
>          Components: SolrCloud
>            Reporter: philip hoy
>            Priority: Minor
>         Attachments: SOLR-4449.patch
>
>
> Add the ability to configure the built-in solr load balancer such that it submits a backup request to the next server in the list if the initial request takes too long. Employing such an algorithm could improve the latency of the 9xth percentile albeit at the expense of increasing overall load due to additional requests. 

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

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