[Gluster-devel] Slow fs

Pranith Kumar Karampuri pkarampu at redhat.com
Fri Nov 15 13:37:38 UTC 2013


It means either so many files are in constant modification or they need self-heal. Are the numbers decreasing periodically?

Pranith
----- Original Message -----
> From: "Emmanuel Dreyfus" <manu at netbsd.org>
> To: "Pranith Kumar Karampuri" <pkarampu at redhat.com>
> Cc: "Emmanuel Dreyfus" <manu at netbsd.org>, "Vijay Bellur" <vbellur at redhat.com>, gluster-devel at nongnu.org
> Sent: Friday, November 15, 2013 6:58:58 PM
> Subject: Re: [Gluster-devel] Slow fs
> 
> On Fri, Nov 15, 2013 at 05:57:07AM -0500, Pranith Kumar Karampuri wrote:
> > Emmanuel,
> >         Could you let us know the number of files present in
> >         <brick-dir>/.glusterfs/xattrop/indices directory on all the
> >         bricks.
> 
> silo:/export/wd2a	41
> hangar:/export/wd1a	14636
> hangar:/export/wd3a	40
> hangar:/expot/wd1a	16138
> 
> I understand too much is bad, but what are theses, why are they so many,
> and how can I fix it?
> 
> --
> Emmanuel Dreyfus
> manu at netbsd.org
> 




More information about the Gluster-devel mailing list