Gluster users - Nov 2017 - Fwd: Ignore failed connection messages during copying files with tiering

Hi, All,


We create a GlusterFS cluster with tiers. The hot tier is
distributed-replicated SSDs. The cold tier is a n*(6+2) disperse volume.
When copy millions of files to the cluster, we find these logs:


W [socket.c:3292:socket_connect] 0-tierd: Ignore failed connection attempt
on /var/run/gluster/39668fb028de4b1bb6f4880e7450c064.socket, (No such file
or directory)
W [socket.c:3292:socket_connect] 0-tierd: Ignore failed connection attempt
on /var/run/gluster/39668fb028de4b1bb6f4880e7450c064.socket, (No such file
or directory)
W [socket.c:3292:socket_connect] 0-tierd: Ignore failed connection attempt
on /var/run/gluster/39668fb028de4b1bb6f4880e7450c064.socket, (No such file
or directory)
?

And then the copy process seems to be suspended. The command df hangs in
the client machine. But if I restart glusterd, then the copy process
continues. However, several minutes later the problems happens again. Later
we find the problem seems to happen when creating directories.

The GlusterFS version is 3.11.0. Does anyone knows what?s the problem? Is
it related to tiering?

Thanks,
Paul
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.gluster.org/pipermail/gluster-users/attachments/20171103/f6ab938d/attachment.html>

Hi,


We create a GlusterFS cluster with tiers. The hot tier is
distributed-replicated SSDs. The cold tier is a n*(6+2) disperse volume.
When copy millions of files to the cluster, we find these logs:


W [socket.c:3292:socket_connect] 0-tierd: Ignore failed connection attempt
on /var/run/gluster/39668fb028de4b1bb6f4880e7450c064.socket, (No such file
or directory)
W [socket.c:3292:socket_connect] 0-tierd: Ignore failed connection attempt
on /var/run/gluster/39668fb028de4b1bb6f4880e7450c064.socket, (No such file
or directory)
W [socket.c:3292:socket_connect] 0-tierd: Ignore failed connection attempt
on /var/run/gluster/39668fb028de4b1bb6f4880e7450c064.socket, (No such file
or directory)
?

And then the copy process seems to be suspended. The command df hangs in
the client machine. But if I restart glusterd, then the copy process
continues. However, several minutes later the problems happens again. Later
we find the problem seems to happen when creating directories.

The GlusterFS version is 3.11.0. Does anyone knows what?s the problem? Is
it related to tiering?

Thanks,
Paul
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.gluster.org/pipermail/gluster-users/attachments/20171104/2fcfc40f/attachment.html>