[Gluster-devel] glusterfs replica volume self heal lots of small file very very slow！！why？how to improve？
Pranith Kumar Karampuri
pkarampu at redhat.com
Wed Oct 15 15:30:05 UTC 2014
On 10/08/2014 07:50 PM, Joe Julian wrote:
> To the author: You're cross posting user questions in the devel
> mailing list. You're not asking development questions. Please don't do
> To Pranith et al:
> On 10/8/2014 1:45 AM, justglusterfs at gmail.com wrote:
>> * then I config :*
>> *cluster.self-heal-window-size is 1024(max value)*
>> *cluster.self-heal-readdir-size is 131072(max value)*
> There's an interesting observation. I would expect an efficiency gain
> if the window size could be increased to match the maximum tcp packet
> size. Yes?
Not sure. I asked for profile information. Lets debug what is happening.
Sorry for the delay in response :-(
> Gluster-devel mailing list
> Gluster-devel at gluster.org
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Gluster-devel