[Gluster-users] Memory Consumption Process nfs by Gluster

[Jose Antonio Vico Palomino]

Hello everyone,

Currently one of the production gluster nodes is consuming a lot of 
memory, in particular the gluster NFS process makes great use of SWAP 
memory and does not release it.

It happens to someone else?

# for file in /proc/*/status ; do awk '/VmSwap|Name|Pid/{printf $2 " " 
$3}END{ print ""}' $file; done | sort -k 5 -n -r | less

glusterfs *16818* 1 0 *5283484 kB*
glusterfs 16826 1 0 434184 kB
glusterfsd 14648 1 0 63500 kB

# ps aux | grep 16818
root     16818 48.1 61.7 27419204 20265168 ?   Ssl  Feb27 39412:28 
/usr/sbin/glusterfs -s localhost --volfile-id gluster/nfs -p 
/var/lib/glusterd/nfs/run/nfs.pid -l /var/log/glusterfs/nfs.log -S 
/var/run/gluster/4e5989084b357ad0d2530754e086bd73.socket

# free -m
                        total       used       free     shared 
buffers     cached
Mem:         32073      31710        362          0 0       4291
-/+ buffers/cache:      27418       4655
Swap:         7247       7247          0


The gluster version is*3.7.1-16* under RHEL 6.7


Launching the following commands does not help, as the swap memory is 
re-occupied in full over time.

# sync
# echo 3 > /proc/sys/vm/drop_caches


The swappiness value is currently 60.

# sysctl -a | grep swapp
vm.swappiness = 60

Any idea or similar case?

Thanks.

Greetings,
Jose Antonio Vico Palomino
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20170425/49089416/attachment.html>