You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@trafficserver.apache.org by "John Plevyak (JIRA)" <ji...@apache.org> on 2010/09/17 16:26:33 UTC

[jira] Created: (TS-445) improve performance for large files

improve performance for large files
-----------------------------------

                 Key: TS-445
                 URL: https://issues.apache.org/jira/browse/TS-445
             Project: Traffic Server
          Issue Type: Improvement
          Components: Cache
    Affects Versions: 2.0.0
            Reporter: John Plevyak
             Fix For: 2.1.3


Currently large files are fragmented to blocks of 64k.  For high speed connections
which can achieve multiple megabytes per second, this means a lot of seeks and
reduced performance.  This should be configurable.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.

[jira] Resolved: (TS-445) improve performance for large files

Posted by "John Plevyak (JIRA)" <ji...@apache.org>.

     [ https://issues.apache.org/jira/browse/TS-445?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

John Plevyak resolved TS-445.
-----------------------------

    Resolution: Fixed

Committed revision 998151.

   # The target size of a contiguous fragment on disk.
   # Acceptable values are powers of 2, e.g. 65536, 131072, 262144, 524288, 1048576, 2097152.
   # Larger could waste memory on slow connections, smaller could waste seeks.
CONFIG proxy.config.cache.target_fragment_size INT 1048576



> improve performance for large files
> -----------------------------------
>
>                 Key: TS-445
>                 URL: https://issues.apache.org/jira/browse/TS-445
>             Project: Traffic Server
>          Issue Type: Improvement
>          Components: Cache
>    Affects Versions: 2.0.0
>            Reporter: John Plevyak
>             Fix For: 2.1.3
>
>
> Currently large files are fragmented to blocks of 64k.  For high speed connections
> which can achieve multiple megabytes per second, this means a lot of seeks and
> reduced performance.  This should be configurable.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.