[ 
https://issues.apache.org/jira/browse/SOLR-6699?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14195718#comment-14195718
 ] 

Shawn Heisey commented on SOLR-6699:
------------------------------------

In addition to reverting a bunch of recent upgrades in jar versions, the patch 
also seems to revert a lot of other recent dependency work that adjusted the 
"conf" setting on the dependency tags.

[~hprasad], was your checkout fully up to date and completely clean before you 
started modifying it? If you can start with a fresh trunk checkout, that would 
be best.  Check to make sure it's clean with "svn stat" before beginning.

SPDY is supposed to have a lot less latency than HTTP 1.1.  This is primarily 
on websites, where many different components are requested in order to load one 
page, and the server is typically remotely located across the Internet.  I 
suspect that on a LAN, SPDY may not offer as much of a performance boost as it 
does for the web.  Getting those numbers that Otis asked about is the only way 
we'll know if the change is worthwhile.

Does SolrCloud utilize http keepalive for its inter-server connectivity?  If 
not, that should be something for us to look at, even without SPDY.


> To enable SPDY in a SolrCloud setup
> -----------------------------------
>
>                 Key: SOLR-6699
>                 URL: https://issues.apache.org/jira/browse/SOLR-6699
>             Project: Solr
>          Issue Type: Improvement
>            Reporter: Harsh Prasad
>         Attachments: SOLR-6699.patch
>
>
> Solr has lot of inter node communication happening during distributed 
> searching or indexing. Benefits of SPDY is as follows: 
> -Multiple requests can be sent in parallel (multiplexing) and responses can 
> be received out of order.
> -Headers are compressed and optimized.
> This implementation will be using clear-text spdy and not the usual TLS layer 
> spdy.



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

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to