Re: [Gluster-users] self-heal trouble after changing arbiter brick
On Fri, Feb 9, 2018 at 11:46 AM, Karthik Subrahmanyawrote: > Hey, > > Did the heal completed and you still have some entries pending heal? > If yes then can you provide the following informations to debug the issue. > 1. Which version of gluster you are running > 2. Output of gluster volume heal info summary or gluster volume > heal info > 3. getfattr -d -e hex -m . output of any one of the > file which is pending heal from all the bricks > > Regards, > Karthik > > On Thu, Feb 8, 2018 at 12:48 PM, Seva Gluschenko > wrote: > >> Hi folks, >> >> I'm troubled moving an arbiter brick to another server because of I/O >> load issues. My setup is as follows: >> >> # gluster volume info >> >> Volume Name: myvol >> Type: Distributed-Replicate >> Volume ID: 43ba517a-ac09-461e-99da-a197759a7dc8 >> Status: Started >> Snapshot Count: 0 >> Number of Bricks: 3 x (2 + 1) = 9 >> Transport-type: tcp >> Bricks: >> Brick1: gv0:/data/glusterfs >> Brick2: gv1:/data/glusterfs >> Brick3: gv4:/data/gv01-arbiter (arbiter) >> Brick4: gv2:/data/glusterfs >> Brick5: gv3:/data/glusterfs >> Brick6: gv1:/data/gv23-arbiter (arbiter) >> Brick7: gv4:/data/glusterfs >> Brick8: gv5:/data/glusterfs >> Brick9: pluto:/var/gv45-arbiter (arbiter) >> Options Reconfigured: >> nfs.disable: on >> transport.address-family: inet >> storage.owner-gid: 1000 >> storage.owner-uid: 1000 >> cluster.self-heal-daemon: enable >> >> The gv23-arbiter is the brick that was recently moved from other server >> (chronos) using the following command: >> >> # gluster volume replace-brick myvol chronos:/mnt/gv23-arbiter >> gv1:/data/gv23-arbiter commit force >> volume replace-brick: success: replace-brick commit force operation >> successful >> >> It's not the first time I was moving an arbiter brick, and the heal-count >> was zero for all the bricks before the change, so I didn't expect much >> trouble then. What was probably wrong is that I then forced chronos out of >> cluster with gluster peer detach command. All since that, over the course >> of the last 3 days, I see this: >> >> # gluster volume heal myvol statistics heal-count >> Gathering count of entries to be healed on volume myvol has been >> successful >> >> Brick gv0:/data/glusterfs >> Number of entries: 0 >> >> Brick gv1:/data/glusterfs >> Number of entries: 0 >> >> Brick gv4:/data/gv01-arbiter >> Number of entries: 0 >> >> Brick gv2:/data/glusterfs >> Number of entries: 64999 >> >> Brick gv3:/data/glusterfs >> Number of entries: 64999 >> >> Brick gv1:/data/gv23-arbiter >> Number of entries: 0 >> >> Brick gv4:/data/glusterfs >> Number of entries: 0 >> >> Brick gv5:/data/glusterfs >> Number of entries: 0 >> >> Brick pluto:/var/gv45-arbiter >> Number of entries: 0 >> >> According to the /var/log/glusterfs/glustershd.log, the self-healing is >> undergoing, so it might be worth just sit and wait, but I'm wondering why >> this 64999 heal-count persists (a limitation on counter? In fact, gv2 and >> gv3 bricks contain roughly 30 million files), and I feel bothered because >> of the following output: >> >> # gluster volume heal myvol info heal-failed >> Gathering list of heal failed entries on volume myvol has been >> unsuccessful on bricks that are down. Please check if all brick processes >> are running. >> >> I attached the chronos server back to the cluster, with no noticeable >> effect. Any comments and suggestions would be much appreciated. >> >> -- >> Best Regards, >> >> Seva Gluschenko >> CTO @ http://webkontrol.ru >> >> ___ >> Gluster-users mailing list >> Gluster-users@gluster.org >> http://lists.gluster.org/mailman/listinfo/gluster-users >> > > ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] self-heal trouble after changing arbiter brick
Hey, Did the heal completed and you still have some entries pending heal? If yes then can you provide the following informations to debug the issue. 1. Which version of gluster you are running 2. gluster volume heal info summary or gluster volume heal info 3. getfattr -d -e hex -m . output of any one of the which is pending heal from all the bricks Regards, Karthik On Thu, Feb 8, 2018 at 12:48 PM, Seva Gluschenkowrote: > Hi folks, > > I'm troubled moving an arbiter brick to another server because of I/O load > issues. My setup is as follows: > > # gluster volume info > > Volume Name: myvol > Type: Distributed-Replicate > Volume ID: 43ba517a-ac09-461e-99da-a197759a7dc8 > Status: Started > Snapshot Count: 0 > Number of Bricks: 3 x (2 + 1) = 9 > Transport-type: tcp > Bricks: > Brick1: gv0:/data/glusterfs > Brick2: gv1:/data/glusterfs > Brick3: gv4:/data/gv01-arbiter (arbiter) > Brick4: gv2:/data/glusterfs > Brick5: gv3:/data/glusterfs > Brick6: gv1:/data/gv23-arbiter (arbiter) > Brick7: gv4:/data/glusterfs > Brick8: gv5:/data/glusterfs > Brick9: pluto:/var/gv45-arbiter (arbiter) > Options Reconfigured: > nfs.disable: on > transport.address-family: inet > storage.owner-gid: 1000 > storage.owner-uid: 1000 > cluster.self-heal-daemon: enable > > The gv23-arbiter is the brick that was recently moved from other server > (chronos) using the following command: > > # gluster volume replace-brick myvol chronos:/mnt/gv23-arbiter > gv1:/data/gv23-arbiter commit force > volume replace-brick: success: replace-brick commit force operation > successful > > It's not the first time I was moving an arbiter brick, and the heal-count > was zero for all the bricks before the change, so I didn't expect much > trouble then. What was probably wrong is that I then forced chronos out of > cluster with gluster peer detach command. All since that, over the course > of the last 3 days, I see this: > > # gluster volume heal myvol statistics heal-count > Gathering count of entries to be healed on volume myvol has been successful > > Brick gv0:/data/glusterfs > Number of entries: 0 > > Brick gv1:/data/glusterfs > Number of entries: 0 > > Brick gv4:/data/gv01-arbiter > Number of entries: 0 > > Brick gv2:/data/glusterfs > Number of entries: 64999 > > Brick gv3:/data/glusterfs > Number of entries: 64999 > > Brick gv1:/data/gv23-arbiter > Number of entries: 0 > > Brick gv4:/data/glusterfs > Number of entries: 0 > > Brick gv5:/data/glusterfs > Number of entries: 0 > > Brick pluto:/var/gv45-arbiter > Number of entries: 0 > > According to the /var/log/glusterfs/glustershd.log, the self-healing is > undergoing, so it might be worth just sit and wait, but I'm wondering why > this 64999 heal-count persists (a limitation on counter? In fact, gv2 and > gv3 bricks contain roughly 30 million files), and I feel bothered because > of the following output: > > # gluster volume heal myvol info heal-failed > Gathering list of heal failed entries on volume myvol has been > unsuccessful on bricks that are down. Please check if all brick processes > are running. > > I attached the chronos server back to the cluster, with no noticeable > effect. Any comments and suggestions would be much appreciated. > > -- > Best Regards, > > Seva Gluschenko > CTO @ http://webkontrol.ru > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://lists.gluster.org/mailman/listinfo/gluster-users > ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Thousands of EPOLLERR - disconnecting now
Are you running gluster version <= 3.12? Did you happen to start seeing this flood after rebalance? I'm just trying to eliminate you're not hitting https://bugzilla.redhat.com/show_bug.cgi?id=1484885 . On Fri, Feb 9, 2018 at 4:45 AM, Vijay Bellurwrote: > > On Thu, Feb 8, 2018 at 2:04 PM, Gino Lisignoli > wrote: > >> Hello >> >> I have a large cluster in which every node is logging: >> >> I [socket.c:2474:socket_event_handler] 0-transport: EPOLLERR - >> disconnecting now >> >> At a rate of of around 4 or 5 per second per node, which is adding up to >> a lot of messages. This seems to happen while my cluster is idle. >> > > > This log message is normally seen repetitively when there are problems in > the network layer. Can you please verify if there are any problems in the > network layer? > > Regards, > Vijay > > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://lists.gluster.org/mailman/listinfo/gluster-users > ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] trusted.ec.dirty attribute
It is not at all good. It should be healed and dirty xattr should be set to all zero. Please provide all the xattrs of all the fragments of this file. Provide gluster v heal info Run gluster v heal and provide glustershd.logs Provide gluster v status --- Ashish - Original Message - From: "Dmitri Chebotarov" <4dim...@gmail.com> To: "gluster-users"Sent: Friday, February 9, 2018 1:12:39 AM Subject: [Gluster-users] trusted.ec.dirty attribute Hi I've got a problem on a EC volume where heal doesn't seem to work for just few files (heal info shows no progress for few days, Warning on the client mount) I ran getfattr -m . -d -e hex / across all servers in the cluster and 'trusted.ec.dirty' attr is non-zero on all files which don't heal. Is it normal? Any way to correct it? It's my understanding it should be trusted.ec.dirty=0x for 'good' files. Out of 12 copies of the files, 11 have the same non-zero value (0x00111592), and 12th file has a different non-zero value. Thank you. ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Thousands of EPOLLERR - disconnecting now
On Thu, Feb 8, 2018 at 2:04 PM, Gino Lisignoliwrote: > Hello > > I have a large cluster in which every node is logging: > > I [socket.c:2474:socket_event_handler] 0-transport: EPOLLERR - > disconnecting now > > At a rate of of around 4 or 5 per second per node, which is adding up to a > lot of messages. This seems to happen while my cluster is idle. > This log message is normally seen repetitively when there are problems in the network layer. Can you please verify if there are any problems in the network layer? Regards, Vijay ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Thousands of EPOLLERR - disconnecting now
Hello I have a large cluster in which every node is logging: I [socket.c:2474:socket_event_handler] 0-transport: EPOLLERR - disconnecting now At a rate of of around 4 or 5 per second per node, which is adding up to a lot of messages. This seems to happen while my cluster is idle. ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] trusted.ec.dirty attribute
Hi I've got a problem on a EC volume where heal doesn't seem to work for just few files (heal info shows no progress for few days, Warning on the client mount) I ran getfattr -m . -d -e hex / across all servers in the cluster and 'trusted.ec.dirty' attr is non-zero on all files which don't heal. Is it normal? Any way to correct it? It's my understanding it should be trusted.ec.dirty=0x for 'good' files. Out of 12 copies of the files, 11 have the same non-zero value (0x00111592), and 12th file has a different non-zero value. Thank you. ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] How to fix an out-of-sync node?
Hi, >From the information you provided, I am guessing that you have a replica 3 volume configured. In that case you can run "gluster volume heal " which should do the trick for you. Regards, Karthik On Thu, Feb 8, 2018 at 6:16 AM, Frizzwrote: > I have a setup with 3 nodes running GlusterFS. > > gluster volume create myBrick replica 3 node01:/mnt/data/myBrick > node02:/mnt/data/myBrick node03:/mnt/data/myBrick > > Unfortunately node1 seemed to stop syncing with the other nodes, but this > was undetected for weeks! > > When I noticed it, I did a "service glusterd restart" on node1, hoping the > three nodes would sync again. > > But this did not happen. Only the CPU load went up on all three nodes + > the access time went up. > > When I look into the physical storage of the bricks, node1 is very > different > node01:/mnt/data/myBrick : 9GB data > node02:/mnt/data/myBrick : 12GB data > node03:/mnt/data/myBrick : 12GB data > > How do I sync data from the healthy nodes Node2/Node3 back to Node1? > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://lists.gluster.org/mailman/listinfo/gluster-users > ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] How to fix an out-of-sync node?
I have a setup with 3 nodes running GlusterFS. gluster volume create myBrick replica 3 node01:/mnt/data/myBrick node02:/mnt/data/myBrick node03:/mnt/data/myBrick Unfortunately node1 seemed to stop syncing with the other nodes, but this was undetected for weeks! When I noticed it, I did a "service glusterd restart" on node1, hoping the three nodes would sync again. But this did not happen. Only the CPU load went up on all three nodes + the access time went up. When I look into the physical storage of the bricks, node1 is very different node01:/mnt/data/myBrick : 9GB data node02:/mnt/data/myBrick : 12GB data node03:/mnt/data/myBrick : 12GB data How do I sync data from the healthy nodes Node2/Node3 back to Node1? ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users