[Gluster-users] Old story - glusterfs memory usage

[Amon Ott]

On Friday 26 March 2010 wrote Amar Tumballi:
> > > To send forceful forgets to glusterfs, do the following.
> > >
> > > bash# echo 3 > /proc/sys/vm/drop_caches
> > >
> > > and see the memory usage after this.
> >
> > I did it almost one year ago, as recommended by a member of the Gluster
> > team,
> > and repeated yesterday, on Raghavednra's request. Nothing happens,
> > the memory usage stays as high as it was before.

I can confirm this problem on our test system. glusterfs goes up to the memory 
limit set for performance/io-cache (1.2 GB here), logs out of memory errors 
and further access fails with "Stale NFS file handle". The above command did 
not help, only remounting did.

So I assume some memory leak in the io-cache filter.

> Have a look at patchsets which are soon going to come soon, which enable us
> to pin point the leaks here:
>
> http://patches.gluster.com/
> http://patches.gluster.com/patch/2971/  <- patchset starts here
>
> With 3.1 we will have more clear answer fo all memory related questions.

Do I have to scrape all related patches out of that server by hand to test it?

Amon Ott
-- 
Dr. Amon Ott - m-privacy GmbH
Am Köllnischen Park 1, 10179 Berlin
Tel: +49 30 24342334
Fax: +49 30 24342336
Web: http://www.m-privacy.de
Handelsregister:
 Amtsgericht Charlottenburg HRB 84946
Geschäftsführer:
 Dipl.-Kfm. Holger Maczkowsky,
 Roman Maczkowsky
GnuPG-Key-ID: EA898571