[Gluster-users] Brick Disconnect from Gluster Volume

[Ashayam Gupta]

Hi All,
We are facing Brick Disconnect issue on our setup , please find more info
about the issue below:






*Gluster: 5.3-6 node distributed Cluster -No replication-2 Bricks Per
Node-Ubuntu 18.04*

*-Issue:*
1 of the Brick on 1 node keeps disconnecting , (after every n days)
not very frequently , but observed more than 3-4 times

Nothing much in glusterd or bricks logs
*GlusterD Logs:*
[2019-08-23 10:39:29.811950] E [MSGID: 101191]
[event-epoll.c:671:event_dispatch_epoll_worker] 0-epoll: Failed to dispatch
handler
[2019-08-23 10:39:29.815723] E [MSGID: 101191]
[event-epoll.c:671:event_dispatch_epoll_worker] 0-epoll: Failed to dispatch
handler
[2019-08-23 10:39:38.111188] E [MSGID: 101191]
[event-epoll.c:671:event_dispatch_epoll_worker] 0-epoll: Failed to dispatch
handler
The message "E [MSGID: 101191]
[event-epoll.c:671:event_dispatch_epoll_worker] 0-epoll: Failed to dispatch
handler" repeated 77 times between [2019-08-23 10:39:38.111188] an
d [2019-08-23 10:39:44.990156]

^^ Messages keeps pouring in the logs , this from time when we saw loss of
1 brick,nothing specail about the above logs , but this is what is there in
logs from the time we saw loss of the brick

*DataBrick Logs:*
The message "E [MSGID: 101191]
[event-epoll.c:671:event_dispatch_epoll_worker] 0-epoll: Failed to dispatch
handler" repeated 4788 times between [2019-08-23 10:39:44.993667]

^^ Same here we see this type to logs only


Would be helpful if we can get some pointers about the above issue.

Thanks
Ashayam
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20190830/08169914/attachment.html>