[Gluster-users] dealing with gluster outages due to disk timeouts
This is a long-standing problem for me, and I’m wondering how to insulate myself from it…pardon the long-windedness in advance. I use gluster internationally as regional repositories of files, and it’s pretty constantly being rsync’d to (ie, written to solely by rsync, optimized with –inplace or similar). These regional repositories are also being read from, each to the tune of 10-50MB/s. Each gluster pool is anywhere between 4 to 16 servers, each with one brick of RAID6, all pools in a distributed-only config. I’m not currently using distributed-replicated, but even that configuration is not immune to my problem. So, here’s the problem: If one disk on one gluster brick experiences timeouts, all the gluster clients block. This is likely because the rate at which the disks are being exercised by rsyncs (writes and stats) plus reads (client file access) causes an overwhelming backlog of gluster ops, something perhaps is bottlenecked and locking up, but in general it’s fairly useless to me. Running a ‘df’ hangs completely. This has been an issue for me for years. My usual procedure is to manually fail the disk that’s experiencing timeouts, if it hasn’t been ejected already by the raid controller, and remove the load from the gluster file system—it only takes a fraction of a minute before the gluster volume recovers and I can add the load back. Rebuilding parity to the brick’s raid is not the problem—it’s the moments before the disk ultimately fails that causes the backlog of requests that really causes problems. I’m looking for advice as to how to insulate myself from this problem better. My RAID cards don’t support modifying disk timeouts to be incredibly short. I can see disk timeout messages from the raid card, and write an omprog function to fail the disk, but that’s kinda brutal. Maybe I could get a different raid card that supports shorter timeouts or fast disk failures, but if anyone has experience with, say md raid1 not having this problem, or something similar, it might be worth the expense to go that route. If my memory is correct, gluster still has this problem with a distributed-replicated configuration, because writes need to succeed on both leafs before an operation is considered complete, so a timeout on one node is still detrimental. Insight, experience designing around this, tunables I haven’t considered—I’ll take anything. I really like gluster, I’ll keep using it, but this is its Achille’s heel for me. Is there a magic bullet? Or do I just need to fail faster? ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Why not all of my NFS servers are online?
You'd need to check nfs.log & glusterd log file to see why the nfs service didn't come up on both the nodes. Have you ensured that nfs kernel is disabled in both the nodes? Not having nfs service up on all the nodes is certainly not ideal. On Wed, 23 Nov 2016 at 17:25, Jin Li wrote: > Hi all, > > I have the following volume, all bricks are connected fine, but why > not all of the NFS servers are online? (Two of them are offline). Will > the offline NFS servers cause trouble? How could I make sure they are > online? Thanks. > > Please find my volume status. > > > $ sudo gluster volume status gvd > Status of volume: gvd > Gluster process Port Online Pid > > -- > Brick rigel:/mnt/raid6/glusterfs_distributed_export 49155 Y 5553 > Brick betelgeuse:/mnt/raid6/glusterfs_distributed_expor > t 49154 Y 5223 > Brick polaris:/mnt/raid6/glusterfs_distributed_export 49157 Y 5196 > Brick capella:/mnt/raid6/glusterfs_distributed_export 49157 Y 4883 > Brick eridani:/mnt/raid6/glusterfs_distributed_export 49152 Y 3858 > Brick sargas:/mnt/raid6/glusterfs_distributed_export 49152 Y 3886 > Brick toliman:/mnt/raid6/glusterfs_distributed_export 49207 Y 3881 > Brick alphard:/mnt/raid6/glusterfs_distributed_export 49264 Y 3908 > NFS Server on localhost 2049 Y 4898 > NFS Server on eridani 2049 Y 3870 > NFS Server on alphard 2049 Y 3920 > NFS Server on sargas 2049 Y 3898 > NFS Server on toliman 2049 Y 3893 > NFS Server on 172.17.1.1 N/A N N/A > NFS Server on betelgeuse 2049 Y 5235 > NFS Server on polaris N/A N N/A > > > Best regards, > Jin > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://www.gluster.org/mailman/listinfo/gluster-users > -- - Atin (atinm) ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Announcing Gluster 3.9
Go for 3.8 as that's going to be maintained for a while and is a LTM. 3.9's life cycle is short. On Wed, 23 Nov 2016 at 22:32, Dj Merrill wrote: > On 11/23/2016 8:23 AM, Amye Scavarda wrote: > > Gluster > > versions 3.9, 3.8 and 3.7 are all actively maintained. > > > This might be a bit of a silly question, but how would one know which > version of Gluster to use? > > If you wanted to use Gluster as a scratch space for an HPC cluster, and > needed a solid, stable setup for a production environment, what would be > the recommended version to install? > > Thanks, > > -Dj > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://www.gluster.org/mailman/listinfo/gluster-users > -- - Atin (atinm) ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Announcing Gluster 3.9
On 11/23/2016 8:23 AM, Amye Scavarda wrote: Gluster versions 3.9, 3.8 and 3.7 are all actively maintained. This might be a bit of a silly question, but how would one know which version of Gluster to use? If you wanted to use Gluster as a scratch space for an HPC cluster, and needed a solid, stable setup for a production environment, what would be the recommended version to install? Thanks, -Dj ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Announcing Gluster 3.9
The Gluster community is pleased to announce the release of Gluster 3.9. This is a major release that includes a number of changes. Many improvements contribute to better support of Gluster with containers and running your storage on the same server as your hypervisors. Additionally, we've focused on integrating with other projects in the open source ecosystem. This releases marks the completion of maintenance releases for Gluster 3.6. Moving forward, Gluster versions 3.9, 3.8 and 3.7 are all actively maintained. Our full release notes: http://gluster.readthedocs.io/en/latest/release-notes/3.9.0/ Upgrade Guide is available here: http://gluster.readthedocs.io/en/latest/Upgrade-Guide/upgrade_to_3.9/ -- Amye Scavarda | a...@redhat.com | Gluster Community Lead ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Fwd: Weekly Community Meeting - 2016-11-23
(Forgot the gluster-users list) -- Forwarded message -- From: Kaushal M Date: Wed, Nov 23, 2016 at 6:50 PM Subject: Re: Weekly Community Meeting - 2016-11-23 To: Gluster Devel On Tue, Nov 22, 2016 at 6:26 PM, Kaushal M wrote: > Hi All, > > This is a reminder to add your status updates and topics to the > meeting agenda at [1]. > Ensure you do this before the meeting tomorrow. > > Thanks, > Kaushal > > [1]: https://bit.ly/gluster-community-meetings Thank you everyone who attended today's meeting. 4 topics were discussed today, the major one among them being on the release of 3.9 and the beginning of 3.10 cycle. More information can be found in the meeting minutes and logs at [1][2][3][4]. The agenda for next weeks meeting is available at [5]. Please add your updates and topics for discussion to the agenda. Everyone is welcome to add their own topics for discussion. I'll be hosting next weeks meeting, at the same time and same place. Thanks. ~kaushal [1] https://github.com/gluster/glusterfs/wiki/Community-Meeting-2016-11-23 [2] Minutes: https://meetbot.fedoraproject.org/gluster-meeting/2016-11-23/weekly_community_meeting_2016-11-23.2016-11-23-12.01.html [3] Minutes (text): https://meetbot.fedoraproject.org/gluster-meeting/2016-11-23/weekly_community_meeting_2016-11-23.2016-11-23-12.01.txt [4] Log: https://meetbot.fedoraproject.org/gluster-meeting/2016-11-23/weekly_community_meeting_2016-11-23.2016-11-23-12.01.log.html [5] https://bit.ly/gluster-community-meetings ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Files won't heal, although no obvious problem visible
I afraid I do not know how we got to this strange state, I do not know Gluster in detail enough. When does the trusted.afr.dirty flag get set? And when does the trusted.afr.xxx-client-xxx flag get set? From what you are saying, it seems to me that you always expect them to be set / cleared in the same moment. If it helps you, at the end of my message you can find the full volume configuration. Can I help you somehow more in actually discovering what happened / fixing the problem? Thanks for your help, kind regards, Pavel Volume Name: hot Type: Distributed-Replicate Volume ID: 4d09dd56-97b6-4b63-8765-0a08574e8ddd Status: Started Snapshot Count: 0 Number of Bricks: 12 x (2 + 1) = 36 Transport-type: tcp Bricks: Brick1: 10.10.27.10:/opt/data/hdd1/gluster Brick2: 10.10.27.12:/opt/data/hdd1/gluster Brick3: 10.10.27.11:/opt/data/ssd/arbiter1 (arbiter) ... similar triplets here ... Brick34: 10.10.27.12:/opt/data/hdd8/gluster Brick35: 10.10.27.11:/opt/data/hdd8/gluster Brick36: 10.10.27.10:/opt/data/ssd/arbiter12 (arbiter) Options Reconfigured: performance.flush-behind: off performance.write-behind: off performance.open-behind: off performance.nfs.write-behind: off cluster.background-self-heal-count: 1 performance.io-cache: off network.ping-timeout: 1 network.inode-lru-limit: 1024 performance.nfs.flush-behind: off transport.address-family: inet performance.readdir-ahead: on nfs.disable: on cluster.self-heal-daemon: off On 11/23/2016 01:22 PM, Ravishankar N wrote: On 11/23/2016 04:56 PM, Pavel Cernohorsky wrote: Hello, thanks for your reply, answers are in the text. On 11/23/2016 11:55 AM, Ravishankar N wrote: On 11/23/2016 03:56 PM, Pavel Cernohorsky wrote: The "hot-client-21" is, based on the vol-file, the following of the bricks: option remote-subvolume /opt/data/hdd5/gluster option remote-host 10.10.27.11 I have self healing daemon disabled, but when I try to trigger healing manually (gluster volume heal ), I get: "Launching heal operation to perform index self heal on volume has been unsuccessful on bricks that are down. Please check if all brick processes are running.", although all the bricks are online (gluster volume status ). Can you enable the self-heal daemon and try again ? `gluster volume heal ` requires the shd to be enabled. The error message that you get is inappropriate and is being fixed. When I enabled the self heal daemon, I was able to start healing, and the files were actually healed. What does self-heal daemon do in addition to the automated healing when you read the file? The lookup/read code-path doesn't seem to be considering a file with only the afr.dirty xattr being non-zero as a candidate for heal (while the self heal-daemon code-path does) . I'm not sure at this point if it should because just afr.dirty being set on all bricks without any trusted.afr.xxx-client-xxx being set doesn't seem to be something that should be hit under normal circumstances. I'll need to think about this more. The original reason to disable self heal daemon was to be able to control the amount of resources used by the healing, because the "cluster.background-self-heal-count: 1" did not help very much and the amount of both network and disk io consumed was just extreme. And I am also pretty sure we have seen similar problem (not sure about the attributes) before we disabled the shd. When I try to just md5sum the file, to trigger automated healing on file manipulation, I get the result, but the file is not healed anyway. This usually works when I do not get 3 entries for the same file in the heal info. Is the file size for 99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 non-zero on the 2 data bricks (i.e. on 10.10.27.11 and 10.10.27.10) and do they match? Do the md5sums match with what you got on the mount when you calculate it directly on these bricks? The file has non-zero size on both the data bricks, and the md5 sum was the same on both of them before they were healed, after the healing (enabling the shd and healing start) the md5 did not change on either of the data bricks. Mount point reports the same md5 as all the other attempts directly on the bricks. So what is actually happening there? Why was the file blamed (not unblamed after healing?)? That means there was no real heal pending. But because the dirty xattr was set, the shd picked up a brick as a source and did the heal anyway. We would need to find how we ended in the 'only afr.dirty xattr was set' state for the file. -Ravi Thanks for your answers, Pavel ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Files won't heal, although no obvious problem visible
On 11/23/2016 04:56 PM, Pavel Cernohorsky wrote: Hello, thanks for your reply, answers are in the text. On 11/23/2016 11:55 AM, Ravishankar N wrote: On 11/23/2016 03:56 PM, Pavel Cernohorsky wrote: The "hot-client-21" is, based on the vol-file, the following of the bricks: option remote-subvolume /opt/data/hdd5/gluster option remote-host 10.10.27.11 I have self healing daemon disabled, but when I try to trigger healing manually (gluster volume heal ), I get: "Launching heal operation to perform index self heal on volume has been unsuccessful on bricks that are down. Please check if all brick processes are running.", although all the bricks are online (gluster volume status ). Can you enable the self-heal daemon and try again ? `gluster volume heal ` requires the shd to be enabled. The error message that you get is inappropriate and is being fixed. When I enabled the self heal daemon, I was able to start healing, and the files were actually healed. What does self-heal daemon do in addition to the automated healing when you read the file? The lookup/read code-path doesn't seem to be considering a file with only the afr.dirty xattr being non-zero as a candidate for heal (while the self heal-daemon code-path does) . I'm not sure at this point if it should because just afr.dirty being set on all bricks without any trusted.afr.xxx-client-xxx being set doesn't seem to be something that should be hit under normal circumstances. I'll need to think about this more. The original reason to disable self heal daemon was to be able to control the amount of resources used by the healing, because the "cluster.background-self-heal-count: 1" did not help very much and the amount of both network and disk io consumed was just extreme. And I am also pretty sure we have seen similar problem (not sure about the attributes) before we disabled the shd. When I try to just md5sum the file, to trigger automated healing on file manipulation, I get the result, but the file is not healed anyway. This usually works when I do not get 3 entries for the same file in the heal info. Is the file size for 99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 non-zero on the 2 data bricks (i.e. on 10.10.27.11 and 10.10.27.10) and do they match? Do the md5sums match with what you got on the mount when you calculate it directly on these bricks? The file has non-zero size on both the data bricks, and the md5 sum was the same on both of them before they were healed, after the healing (enabling the shd and healing start) the md5 did not change on either of the data bricks. Mount point reports the same md5 as all the other attempts directly on the bricks. So what is actually happening there? Why was the file blamed (not unblamed after healing?)? That means there was no real heal pending. But because the dirty xattr was set, the shd picked up a brick as a source and did the heal anyway. We would need to find how we ended in the 'only afr.dirty xattr was set' state for the file. -Ravi Thanks for your answers, Pavel ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Why not all of my NFS servers are online?
Hi all, I have the following volume, all bricks are connected fine, but why not all of the NFS servers are online? (Two of them are offline). Will the offline NFS servers cause trouble? How could I make sure they are online? Thanks. Please find my volume status. $ sudo gluster volume status gvd Status of volume: gvd Gluster process Port Online Pid -- Brick rigel:/mnt/raid6/glusterfs_distributed_export 49155 Y 5553 Brick betelgeuse:/mnt/raid6/glusterfs_distributed_expor t 49154 Y 5223 Brick polaris:/mnt/raid6/glusterfs_distributed_export 49157 Y 5196 Brick capella:/mnt/raid6/glusterfs_distributed_export 49157 Y 4883 Brick eridani:/mnt/raid6/glusterfs_distributed_export 49152 Y 3858 Brick sargas:/mnt/raid6/glusterfs_distributed_export 49152 Y 3886 Brick toliman:/mnt/raid6/glusterfs_distributed_export 49207 Y 3881 Brick alphard:/mnt/raid6/glusterfs_distributed_export 49264 Y 3908 NFS Server on localhost 2049 Y 4898 NFS Server on eridani 2049 Y 3870 NFS Server on alphard 2049 Y 3920 NFS Server on sargas 2049 Y 3898 NFS Server on toliman 2049 Y 3893 NFS Server on 172.17.1.1 N/A N N/A NFS Server on betelgeuse 2049 Y 5235 NFS Server on polaris N/A N N/A Best regards, Jin ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Files won't heal, although no obvious problem visible
Hello, thanks for your reply, answers are in the text. On 11/23/2016 11:55 AM, Ravishankar N wrote: On 11/23/2016 03:56 PM, Pavel Cernohorsky wrote: The "hot-client-21" is, based on the vol-file, the following of the bricks: option remote-subvolume /opt/data/hdd5/gluster option remote-host 10.10.27.11 I have self healing daemon disabled, but when I try to trigger healing manually (gluster volume heal ), I get: "Launching heal operation to perform index self heal on volume has been unsuccessful on bricks that are down. Please check if all brick processes are running.", although all the bricks are online (gluster volume status ). Can you enable the self-heal daemon and try again ? `gluster volume heal ` requires the shd to be enabled. The error message that you get is inappropriate and is being fixed. When I enabled the self heal daemon, I was able to start healing, and the files were actually healed. What does self-heal daemon do in addition to the automated healing when you read the file? The original reason to disable self heal daemon was to be able to control the amount of resources used by the healing, because the "cluster.background-self-heal-count: 1" did not help very much and the amount of both network and disk io consumed was just extreme. And I am also pretty sure we have seen similar problem (not sure about the attributes) before we disabled the shd. When I try to just md5sum the file, to trigger automated healing on file manipulation, I get the result, but the file is not healed anyway. This usually works when I do not get 3 entries for the same file in the heal info. Is the file size for 99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 non-zero on the 2 data bricks (i.e. on 10.10.27.11 and 10.10.27.10) and do they match? Do the md5sums match with what you got on the mount when you calculate it directly on these bricks? The file has non-zero size on both the data bricks, and the md5 sum was the same on both of them before they were healed, after the healing (enabling the shd and healing start) the md5 did not change on either of the data bricks. Mount point reports the same md5 as all the other attempts directly on the bricks. So what is actually happening there? Why was the file blamed (not unblamed after healing?)? Thanks for your answers, Pavel ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Files won't heal, although no obvious problem visible
On 11/23/2016 03:56 PM, Pavel Cernohorsky wrote: The "hot-client-21" is, based on the vol-file, the following of the bricks: option remote-subvolume /opt/data/hdd5/gluster option remote-host 10.10.27.11 I have self healing daemon disabled, but when I try to trigger healing manually (gluster volume heal ), I get: "Launching heal operation to perform index self heal on volume has been unsuccessful on bricks that are down. Please check if all brick processes are running.", although all the bricks are online (gluster volume status ). Can you enable the self-heal daemon and try again ? `gluster volume heal ` requires the shd to be enabled. The error message that you get is inappropriate and is being fixed. When I try to just md5sum the file, to trigger automated healing on file manipulation, I get the result, but the file is not healed anyway. This usually works when I do not get 3 entries for the same file in the heal info. Is the file size for 99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 non-zero on the 2 data bricks (i.e. on 10.10.27.11 and 10.10.27.10) and do they match? Do the md5sums match with what you got on the mount when you calculate it directly on these bricks? Thanks, Ravi Any clues? What am I doing wrong? Kind regards, Pavel ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Files won't heal, although no obvious problem visible
Hello, I have Gluster 3.8.5-1.fc24 with replica 3 arbiter 1 volume, where gluster heal info reports (simplified): Brick 10.10.27.11:/opt/data/hdd5/gluster /assets/1/286381384/99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 Status: Connected Brick 10.10.27.10:/opt/data/hdd6/gluster /assets/1/286381384/99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 Status: Connected Brick 10.10.27.12:/opt/data/ssd/arbiter8 /assets/1/286381384/99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 Status: Connected Extended attributes of those files on the bricks are (in the same order of bricks): 10.10.27.11: getfattr -m . -d -e hex assets/1/286381384/99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 # file: assets/1/286381384/99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x0001 trusted.bit-rot.version=0x0200583561b500050a4e trusted.gfid=0x5d2793f9b2a74514937ceb1a3bca3e1f 10.10.27.10: getfattr -m . -d -e hex assets/1/286381384/99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 # file: assets/1/286381384/99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x0001 trusted.afr.hot-client-21=0x trusted.bit-rot.version=0x0200583558e2000b1457 trusted.gfid=0x5d2793f9b2a74514937ceb1a3bca3e1f 10.10.27.12: getfattr -m . -d -e hex assets/1/286381384/99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 # file: assets/1/286381384/99705_544c0cd369a84ebcaf095b4a9f6d682a.mp4 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x0001 trusted.afr.hot-client-21=0x trusted.bit-rot.version=0x0200583440580005944b trusted.gfid=0x5d2793f9b2a74514937ceb1a3bca3e1f The "hot-client-21" is, based on the vol-file, the following of the bricks: option remote-subvolume /opt/data/hdd5/gluster option remote-host 10.10.27.11 I have self healing daemon disabled, but when I try to trigger healing manually (gluster volume heal ), I get: "Launching heal operation to perform index self heal on volume has been unsuccessful on bricks that are down. Please check if all brick processes are running.", although all the bricks are online (gluster volume status ). When I try to just md5sum the file, to trigger automated healing on file manipulation, I get the result, but the file is not healed anyway. This usually works when I do not get 3 entries for the same file in the heal info. Any clues? What am I doing wrong? Kind regards, Pavel ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] question about "All subvolumes are down"
Hi everyone, I create a replicate volume using two nodes,A board and B board. A board ip:10.32.1.144 B board ip:10.32.0.48 One brick and mount point is on A board Another brick is on B board I found that I can't access the mount point because the disconnection happen between client and two server. The client log is below.(Please notice the red line) [2016-10-31 04:04:08.063543] I [MSGID: 114046] [client-handshake.c:1213:client_setvolume_cbk] 0-c_glusterfs-client-9: Connected to c_glusterfs-client-9, attached to remote volume '/opt/lvmdir/c2/brick'. ... [2016-10-31 04:06:03.626047] W [socket.c:588:__socket_rwv] 0-c_glusterfs-client-9: readv on 10.32.1.144:49391 failed (Connection reset by peer) [2016-10-31 04:06:03.627345] E [rpc-clnt.c:362:saved_frames_unwind] (--> /usr/lib64/libglusterfs.so.0(_gf_log_callingfn-0xb5c80)[0x3fff8ab79f58] ( --> /usr/lib64/libgfrpc.so.0(saved_frames_unwind-0x1b7a0)[0x3fff8ab1dc90] ( --> /usr/lib64/libgfrpc.so.0(saved_frames_destroy-0x1b638)[0x3fff8ab1de10] ( --> /usr/lib64/libgfrpc.so.0(rpc_clnt_connection_cleanup-0x19af8)[0x3fff8ab1fb18] ( --> /usr/lib64/libgfrpc.so.0(rpc_clnt_notify-0x18e68)[0x3fff8ab20808] ) 0-c_glusterfs-client-9: forced unwinding frame type(GlusterFS 3.3) op(FINODELK(30)) called at 2016-10-31 04:06:03.626033 (xid=0x7f5e) [2016-10-31 04:06:03.627395] E [MSGID: 114031] [client-rpc-fops.c:1673:client3_3_finodelk_cbk] 0-c_glusterfs-client-9: remote operation failed [Transport endpoint is not connected] [2016-10-31 04:06:03.628381] I [socket.c:3308:socket_submit_request] 0-c_glusterfs-client-9: not connected (priv->connected = 0) [2016-10-31 04:06:03.628432] W [rpc-clnt.c:1586:rpc_clnt_submit] 0-c_glusterfs-client-9: failed to submit rpc-request (XID: 0x7f5f Program: GlusterFS 3.3, ProgVers: 330, Proc: 30) to rpc-transport (c_glusterfs-client-9) [2016-10-31 04:06:03.628466] E [MSGID: 114031] [client-rpc-fops.c:1673:client3_3_finodelk_cbk] 0-c_glusterfs-client-9: remote operation failed [Transport endpoint is not connected] [2016-10-31 04:06:03.628475] I [MSGID: 108019] [afr-lk-common.c:1086:afr_lock_blocking] 0-c_glusterfs-replicate-0: unable to lock on even one child [2016-10-31 04:06:03.628539] I [MSGID: 108019] [afr-transaction.c:1224:afr_post_blocking_inodelk_cbk] 0-c_glusterfs-replicate-0: Blocking inodelks failed. [2016-10-31 04:06:03.628630] W [fuse-bridge.c:1282:fuse_err_cbk] 0-glusterfs-fuse: 20790: FLUSH() ERR => -1 (Transport endpoint is not connected) [2016-10-31 04:06:03.629149] E [rpc-clnt.c:362:saved_frames_unwind] (--> /usr/lib64/libglusterfs.so.0(_gf_log_callingfn-0xb5c80)[0x3fff8ab79f58] ( --> /usr/lib64/libgfrpc.so.0(saved_frames_unwind-0x1b7a0)[0x3fff8ab1dc90] ( --> /usr/lib64/libgfrpc.so.0(saved_frames_destroy-0x1b638)[0x3fff8ab1de10] ( --> /usr/lib64/libgfrpc.so.0(rpc_clnt_connection_cleanup-0x19af8)[0x3fff8ab1fb18] ( --> /usr/lib64/libgfrpc.so.0(rpc_clnt_notify-0x18e68)[0x3fff8ab20808] ) 0-c_glusterfs-client-9: forced unwinding frame type(GlusterFS 3.3) op(LOOKUP(27)) called at 2016-10-31 04:06:03.624346 (xid=0x7f5a) [2016-10-31 04:06:03.629183] I [rpc-clnt.c:1847:rpc_clnt_reconfig] 0-c_glusterfs-client-9: changing port to 49391 (from 0) [2016-10-31 04:06:03.629210] W [MSGID: 114031] [client-rpc-fops.c:2971:client3_3_lookup_cbk] 0-c_glusterfs-client-9: remote operation failed. Path: /loadmodules_norepl/CXC1725605_P93A001/cello/emasviews (b0e5a94e-a432-4dce-b86f-a551555780a2) [Transport endpoint is not connected] [2016-10-31 04:06:03.629266] I [socket.c:3308:socket_submit_request] 0-c_glusterfs-client-9: not connected (priv->connected = 255) [2016-10-31 04:06:03.629277] I [MSGID: 109063] [dht-layout.c:702:dht_layout_normalize] 0-c_glusterfs-dht: Found anomalies in /loadmodules_norepl/CXC1725605_P93A001/cello/emasviews (gfid = b0e5a94e-a432-4dce-b86f-a551555780a2). Holes=1 overlaps=0 [2016-10-31 04:06:03.629293] W [rpc-clnt.c:1586:rpc_clnt_submit] 0-c_glusterfs-client-9: failed to submit rpc-request (XID: 0x7f62 Program: GlusterFS 3.3, ProgVers: 330, Proc: 41) to rpc-transport (c_glusterfs-client-9) [2016-10-31 04:06:03.629333] W [fuse