[Gluster-users] Serious performance problem

[Stefan Michael Guenther]

Hello,

we are running a three brick gluster with version 3.2.5 on a Ubuntu 12.04 64bit.

"gluster peer status" tells me:

Number of Peers: 2

Hostname: 10.10.10.3
Uuid: a4481c3c-8a86-40d1-bd3b-04a61dbe70bc
State: Peer in Cluster (Connected)

Hostname: node2
Uuid: c8bd7f1d-b4bc-4672-9b81-757cb0e497f9
State: Peer in Cluster (Connected)


In /var/log/glusterfs# less etc-glusterfs-glusterd.vol.log the following line is written every minute:

[2015-10-26 22:49:55.937575] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (127.0.0.1:53161)

But I learned from the mailing list, that this is a common message and that I shouldn't me concerned about it.

But the problem is, when I copy a 1.2 GB file from /root to /mnt (gluster volume mounted via nfs) this takes more than 24 seconds. Copying the same file to /tmp takes less than one second, according to the time command.

The system and the gluster volumes are on separate discs.

Where and how can I start to debug this problem?

Thanks for any suggestions and hints,

Stefan