[Gluster-users] High memory usage GlusterFS

[Marius S. Eriksrud]

I have a replicated server-setup, 2 servers and 3 volumes.
Each server has 4GB of RAM, so gluster is using over 50%.
I have tried "echo 2 > /proc/sys/vm/drop_caches", it free up some 
hundred MB's, but it does not take long before it is back. Any ideas?

Memory consumpsion on server 1:
29256 glusterfs --volume-name=vmail /kit/vmail1
52968 glusterfs --volume-name=global /kit/global
166860 /usr/sbin/glusterfsd -p /var/run/glusterfsd.pid -f 
/etc/glusterfs/glusterfsd.vol --log-file 
/var/log/glusterfs/glusterfsd.vol.log
2101844 glusterfs --volume-name=data /kit/data1

Memory consumpsion on server 2:
132784 glusterfs --volume-name=global /kit/global
196996 /usr/sbin/glusterfsd -p /var/run/glusterfsd.pid -f 
/etc/glusterfs/glusterfsd.vol --log-file 
/var/log/glusterfs/glusterfsd.vol.log
557648 glusterfs --volume-name=vmail /kit/vmail1
1586040 glusterfs --volume-name=data /kit/data1

------

glusterfs.vol:
http://pastebin.com/tQJKYhKC

glusterfsd.vol
http://pastebin.com/4BJfq3a5

-- 
Med vennlig hilsen
Marius S. Eriksrud
Webutvikler
Tlf: 99 603 888
marius at konsept-it.no
www.konsept-it.no