<div dir="ltr"><div><div class="gmail_signature"><div>I have created a 2 brick replicated volume.</div><div><br></div><div><div>gluster> volume status</div><div>Status of volume: storage</div><div>Gluster process TCP Port RDMA Port Online Pid</div><div>------------------------------------------------------------------------------</div><div>Brick master:/glusterfs/bricks/storage/mountpoint 49153 0 Y 5301</div><div>Brick worker1:/glusterfs/bricks/storage/mountpoint 49153 0 Y 3002</div><div><br></div></div><div>The volume is mounted like this:</div><div>On worker1 node /etc/fstab</div><div>worker1:/storage /data/storage/ glusterfs defaults,_netdev 0 0<br></div><div><br></div><div>On master node /etc/fstab</div><div>master:/storage /data/storage/ glusterfs defaults,_netdev 0 0<br></div><div><br></div><div>When I add read load(many small files) on the volume mounted on the master node CPU usage looks like this:</div><div>On master node: glusterfs ~ 50%</div><div>On master node: glusterfsd ~ 25%</div><div><br></div><div>On worker1 node: glusterfsd ~ 50% </div><div><br></div><div>There is no other load on the servers than the read load I start.</div><div>When I inspect the glusterfsd process on worker1 using strace, it seems like it does at least some of the file reading from this node.</div><div><br></div><div>Is this expected behavior? I would think that since it is a replicated volume and read load, it would serve all the requests from the brick on the localhost and not use the network to serve the requests.</div><div><br></div><div>Can anyone help to clarify my understanding of the architecture? </div></div></div>
</div>