<div dir="ltr"><p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US">I have a replication volume as bellows:</span></p><p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US"> </span></p>
<p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive">[root@gluster001 disk]# gluster volume info rep</span></p><p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive"> </span></p>
<p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive">Volume Name: rep</span></p><p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive">Type: Replicate</span></p>
<p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive">Volume ID: 0f7eb8a0-92d7-4911-b766-f23ed870cf3d</span></p><p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive">Status: Started</span></p>
<p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive">Number of Bricks: 1 x 2 = 2</span></p><p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive">Transport-type: tcp</span></p>
<p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive">Bricks:</span></p><p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive">Brick1: gluster001:/disk/sdc</span></p>
<p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US" style="background-color:olive">Brick2: gluster002:/disk/sdb</span><span lang="EN-US"></span></p><p style="font-family:arial,sans-serif;font-size:14px">
<span lang="EN-US"> </span></p><p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US">The sdc and sdb are both raid5 device in 3 SAS disks.</span></p><p style="font-family:arial,sans-serif;font-size:14px">
<span lang="EN-US"> </span></p><p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US">And I have 3 clients (gluster-client001,gluster-client002,gluster-client003) mount on the same replication volume.To test the self-heal function, I clean gluster001:/disk/sdc (rm –rf /disk/sdc/*), and run “gluster volume heal rep full”. I use the iftop to check the process and I get the log :</span></p>
<p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US"> <img src="cid:ii_1407b4e0fb1c912f" alt="ÄÚǶͼƬ 2" width="1032" height="335">The clients are 172.18.4.17, 172.18.4.19 and 172.18.4.20. There are no jobs running on the clients. But from the log, the client 4.17 and 4.19 are reading something from the gluster002 server. And the self-heal process’s performance seems to be affected, only 253Mb/s.</span></p>
<p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US"> </span></p><p style="font-family:arial,sans-serif;font-size:14px"><span lang="EN-US">My Questions, thanks:</span></p><p style="font-family:arial,sans-serif;font-size:14px">
<span lang="EN-US">@1: why/what are the clients 4.17 and 4.19 reading from gluster002? </span></p><span lang="EN-US" style="font-size:12pt;font-family:Cambria">@2: how to accelerate the self-heal?</span><br></div>