hsafe
2018-Nov-21 05:59 UTC
[Gluster-users] remote operation failed [Transport endpoint is not connected]
Hello, I am stuck with failure of my gluster 2x replica heal with messages at glustershd.log as : *[2018-11-21 05:28:07.813003] E [MSGID: 114031] [client-rpc-fops.c:1646:client3_3_entrylk_cbk] 0-gv1-client-0: remote operation failed [Transport endpoint is not connected]* When the log hits here In either of the replica nodes; I can see that my command: *watch glsuter volume heal <my volume> statistics *returns no more progress and status unchanged afterward. I am running glusterfs on top of zfs and it is basically a storage for small read-only files. There was a thread with Shyam Ranganathan and Reiner Keller in here where the core of the problem was the storage going out of inods and no space left error which obviously can not be my case as am on top of ZFS. However, the similarity between us is that we were previously on 3.10 and upon various issues with that version we upgraded to 3.12 on Ubuntu 16.04 with kernel 4.4.0-116-generic. Anybody faced issue as above?Can you advise what can be done as it is for over a month with no effective self-heal process completed... Here is my gluster cluster info: *Volume Name: gv1 Type: Replicate Volume ID: f1c955a1-7a92-4b1b-acb5-8b72b41aaace Status: Started Snapshot Count: 0 Number of Bricks: 1 x 2 = 2 Transport-type: tcp Bricks: Brick1: IMG-01:/images/storage/brick1 Brick2: IMG-02:/images/storage/brick1 Options Reconfigured: cluster.self-heal-daemon: enable cluster.eager-lock: off client.event-threads: 4 performance.cache-max-file-size: 8 features.scrub: Inactive features.bitrot: off network.inode-lru-limit: 50000 nfs.disable: true performance.readdir-ahead: on server.statedump-path: /tmp cluster.background-self-heal-count: 32 performance.md-cache-timeout: 30 cluster.readdir-optimize: on cluster.shd-max-threads: 4 cluster.lookup-optimize: on features.cache-invalidation: on features.cache-invalidation-timeout: 600 performance.stat-prefetch: on performance.cache-invalidation: on server.event-threads: 4* Thank you -- Hamid Safe www.devopt.net +989361491768 -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20181121/e7a10043/attachment.html>