[Gluster-users] glusterfs replica volume self heal dir very slow！！why？

[justglusterfs at gmail.com]

   Hi   Paul Robert Marino  and   Roman
  thank you very much  for you  advise！
  
  to  Paul Robert Marino：
  In fact，  I use XFS as the underlying filesystem in my test cases。
  NOW,  According to your advise， I will increse the background self heal count to test， I will do a feedback after my test，  
  in addition，Do you know  change XFS which options can improve  lots of small file performance？。   
  
  thank you very much！I'm looking forward to your reply！
   



justglusterfs at gmail.com
 
发件人： Paul Robert Marino
发送时间： 2014-09-08 00:15
收件人： justglusterfs at gmail.com; gluster-devel
抄送： gluster-users
主题： Re: [Gluster-users] glusterfs replica volume self heal dir very slow！！why？
Its the small files there is an overhead on any operation on small lots of small file this is not unique to Gluster. Also are you using XFS As the underlying filesystem if you are not that would play a big part ext has issues with performance when dealing with small file due to its over reliance on inodes for read operations.
I would advise you to experiment with incrementing the background self heal count a little at a time till you achieve optimal performance. Unfortunately I can't give you hard numbers because this kind of tuning is more of an art than a science because of the number of possible variables which come into play depending on your hardware configuration and exact use case.


-- Sent from my HP Pre3



On Sep 5, 2014 4:16 AM, justglusterfs at gmail.com <justglusterfs at gmail.com> wrote: 

Hi all：
      I do the  following test：
     I create a glusterfs  replica volume (replica count is 2 ) with two server node(server A and server B)， then  mount the volume in client node，
    then， I  shut down the network of server A node， in  client node， I copy a dir（which has a lot of small files）， the dir size is 2.9GByte，
    when  copy finish， I start the network of server A node，   now， glusterfs  self-heal-daemon start heal dir  from  server B to  server  A， 
    in the  end，  I find the self-heal-daemon   heal the  dir use  40 minutes，  It's too slow！  why？

   I   find out   related options  with  self-heal， as  follow：
   cluster.self-heal-window-size
   cluster.self-heal-readdir-size
   cluster.background-self-heal-count

  I  want  to ask， modify  the above options can improve  the  performance of heal dir？  if possible， please give a reasonable value about above options。
  
  thanks！


justglusterfs at gmail.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20140909/bbecd9b3/attachment.html>