[Gluster-users] Problem manipulating files when a replica is down
We currently have a small pilot gluster setup as Replica 2 + 1 (arbiter) As a DR test we decided to see that to see what would happen when taking one of the replicas offline. For the first couple of hours everything seemed fine and then one of my colleagues tried to a directory with files via samba from a windows client by using robocopy. At this point it starting to go wrong. The brick went offline, I could force it online but when trying to manipulate files on the volume the brick kept going offline. Some Examples of trying to manipulate the files from the mounted gluster volume: rm -rf a Directory: "Directory not empty" on an empty directory ls -la : "total 0" ( didn't show "." or ".." ) After bringing the partner replica up the brick on the system that was never shutdown kept going offline. In the end I ended up restoring the volume from a gluster snapshot from the night before and then everything seemed fine again. This morning I was made aware that creating a new directory via samba resulted in 5 New folders being created. Restarting glusterd has made the issue go away for now. This is on Centos 7.3 with gluster 3.10.3-1 and samba 4.4.4-14 Can anyone help ? Thanks *Gary Lloyd* I.T. Systems:Keele University Finance & IT Directorate Keele:Staffs:IC1 Building:ST5 5NB:UK +44 1782 733063 <%2B44%201782%20733073> ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Snapshot auto-delete unmount problem
Incase anyone is interested this issue was caused by turning on brick multiplexing. Switching it off made the problem go away... *Gary Lloyd* I.T. Systems:Keele University Finance & IT Directorate Keele:Staffs:IC1 Building:ST5 5NB:UK +44 1782 733063 <%2B44%201782%20733073> On 31 May 2017 at 14:46, Gary Lloyd <g.ll...@keele.ac.uk> wrote: > Here is the glusterd.log file as it has just happened with a manual > removal of a snapshot. > The lvs exist even after the snapshot gets removed. I'm also running samba > on these with shadowcopy. > > Thanks > > *Gary Lloyd* > > I.T. Systems:Keele University > Finance & IT Directorate > Keele:Staffs:IC1 Building:ST5 5NB:UK > +44 1782 733063 <%2B44%201782%20733073> > > > On 31 May 2017 at 12:38, Mohammed Rafi K C <rkavu...@redhat.com> wrote: > >> Can you give us more logs on this issue. Also by any chance did somebody >> unmount the lv's in any cases ? >> >> >> Regards >> >> Rafi KC >> >> On 05/31/2017 03:00 PM, Gary Lloyd wrote: >> >> Hi I am having a problem deleting snapshots, gluster is failing to >> unmount them. I am running centos 7.3 with gluster-3.10.2-1 >> >> here is some log output: >> >> [2017-05-31 09:21:39.961371] W [MSGID: 106057] >> [glusterd-snapshot-utils.c:410:glusterd_snap_volinfo_find] 0-management: >> Snap volume 331ec972f90d494d8a86dd4f69d718b7.glust01-li.run-gluster-snap >> s-331ec972f90d494d8a86dd4f69d718b7-brick1-b not found [Invalid argument] >> [2017-05-31 09:21:51.520811] W [MSGID: 106112] >> [glusterd-snapshot.c:8128:glusterd_handle_snap_limit] 0-management: >> Soft-limit (value = 27) of volume shares1 is reached. Deleting snapshot >> Snap_GMT-2017.05.31-09.20.04. >> [2017-05-31 09:21:51.531729] E [MSGID: 106095] >> [glusterd-snapshot-utils.c:3359:glusterd_umount] 0-management: umounting >> /run/gluster/snaps/4f980da64dec424ba0b48d6d36c4c54e/brick1 failed (No >> such file or directory) [No such file or directory] >> [2017-05-31 09:22:00.540373] E [MSGID: 106038] >> [glusterd-snapshot.c:2895:glusterd_do_lvm_snapshot_remove] 0-management: >> umount failed for path >> /run/gluster/snaps/4f980da64dec424ba0b48d6d36c4c54e/brick1 >> (brick: /run/gluster/snaps/4f980da64dec424ba0b48d6d36c4c54e/brick1/b): >> No such file or directory. >> [2017-05-31 09:22:02.442048] W [MSGID: 106033] >> [glusterd-snapshot.c:3094:glusterd_lvm_snapshot_remove] 0-management: >> Failed to rmdir: /run/gluster/snaps/4f980da64dec424ba0b48d6d36c4c54e/, >> err: Directory not empty. More than one glusterd running on this node. >> [Directory not empty] >> [2017-05-31 09:22:02.443336] W [MSGID: 106039] >> [glusterd-snapshot-utils.c:55:glusterd_snapobject_delete] 0-management: >> Failed destroying lockof snap Snap_GMT-2017.05.31-09.20.04 >> [2017-05-31 09:22:02.444038] I [MSGID: 106144] >> [glusterd-pmap.c:377:pmap_registry_remove] 0-pmap: removing brick >> /run/gluster/snaps/4f980da64dec424ba0b48d6d36c4c54e/brick1/b on port >> 49157 >> >> >> >> Can anyone help ? >> >> Thanks >> >> >> *Gary Lloyd* >> >> I.T. Systems:Keele University >> Finance & IT Directorate >> Keele:Staffs:IC1 Building:ST5 5NB:UK >> >> >> >> ___ >> Gluster-users mailing >> listGluster-users@gluster.orghttp://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] Snapshot auto-delete unmount problem
Hi I am having a problem deleting snapshots, gluster is failing to unmount them. I am running centos 7.3 with gluster-3.10.2-1 here is some log output: [2017-05-31 09:21:39.961371] W [MSGID: 106057] [glusterd-snapshot-utils.c:410:glusterd_snap_volinfo_find] 0-management: Snap volume 331ec972f90d494d8a86dd4f69d718b7.glust01-li.run-gluster-snaps-331ec972f90d494d8a86dd4f69d718b7-brick1-b not found [Invalid argument] [2017-05-31 09:21:51.520811] W [MSGID: 106112] [glusterd-snapshot.c:8128:glusterd_handle_snap_limit] 0-management: Soft-limit (value = 27) of volume shares1 is reached. Deleting snapshot Snap_GMT-2017.05.31-09.20.04. [2017-05-31 09:21:51.531729] E [MSGID: 106095] [glusterd-snapshot-utils.c:3359:glusterd_umount] 0-management: umounting /run/gluster/snaps/4f980da64dec424ba0b48d6d36c4c54e/brick1 failed (No such file or directory) [No such file or directory] [2017-05-31 09:22:00.540373] E [MSGID: 106038] [glusterd-snapshot.c:2895:glusterd_do_lvm_snapshot_remove] 0-management: umount failed for path /run/gluster/snaps/4f980da64dec424ba0b48d6d36c4c54e/brick1 (brick: /run/gluster/snaps/4f980da64dec424ba0b48d6d36c4c54e/brick1/b): No such file or directory. [2017-05-31 09:22:02.442048] W [MSGID: 106033] [glusterd-snapshot.c:3094:glusterd_lvm_snapshot_remove] 0-management: Failed to rmdir: /run/gluster/snaps/4f980da64dec424ba0b48d6d36c4c54e/, err: Directory not empty. More than one glusterd running on this node. [Directory not empty] [2017-05-31 09:22:02.443336] W [MSGID: 106039] [glusterd-snapshot-utils.c:55:glusterd_snapobject_delete] 0-management: Failed destroying lockof snap Snap_GMT-2017.05.31-09.20.04 [2017-05-31 09:22:02.444038] I [MSGID: 106144] [glusterd-pmap.c:377:pmap_registry_remove] 0-pmap: removing brick /run/gluster/snaps/4f980da64dec424ba0b48d6d36c4c54e/brick1/b on port 49157 Can anyone help ? Thanks *Gary Lloyd* I.T. Systems:Keele University Finance & IT Directorate Keele:Staffs:IC1 Building:ST5 5NB:UK ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Slow performance on samba with small files
Was just reading the small file section of the 3.9 release notes: http://blog.gluster.org/2016/11/announcing-gluster-3-9/ Setting these options does seem to increase transfer speeds on small files by quite alot: # gluster volume set features.cache-invalidation on # gluster volume set features.cache-invalidation-timeout 600 # gluster volume set performance.stat-prefetch on #This one seemed to have the biggest impact in small file performance for me # gluster volume set performance.cache-invalidation on # gluster volume set performance.md-cache-timeout 600 Setting # gluster volume set performance.cache-samba-metadata on # Only for SMB access. Results in my client to keep losing the state of the server and the shares often disappear / become inaccessible and I can only get them back if I logon / logoff the machine, this is with distro Samba 4.4.4. Has anyone here had the same issue, does the version of samba need to be newer to support the feature ? Thanks *Gary Lloyd* I.T. Systems:Keele University Finance & IT Directorate Keele:Staffs:IC1 Building:ST5 5NB:UK +44 1782 733063 <%2B44%201782%20733073> On 8 February 2017 at 11:49, Дмитрий Глушенок <gl...@jet.msk.su> wrote: > For _every_ file copied samba performs readdir() to get all entries of the > destination folder. Then the list is searched for filename (to prevent name > collisions as SMB shares are not case sensitive). More files in folder, > more time it takes to perform readdir(). It is a lot worse for Gluster > because single folder contents distributed among many servers and Gluster > has to join many directory listings (requested via network) to form one and > return it to caller. > > Rsync does not perform readdir(), it just checks file existence with > stat() IIRC. And as modern Gluster versions has default setting to check > for file only at its destination (when volume is balanced) - the check > performs relatively fast. > > You can hack samba to prevent such checks if your goal is to get files > copied not so slow (as you sure the files you are copying are not exists at > destination). But try to perform 'ls -l' on _not_ cached folder with > thousands of files - it will take tens of seconds. This is time your users > will waste browsing shares. > > 8 февр. 2017 г., в 13:17, Gary Lloyd <g.ll...@keele.ac.uk> написал(а): > > Thanks for the reply > > I've just done a bit more testing. If I use rsync from a gluster client to > copy the same files to the mount point it only takes a couple of minutes. > For some reason it's very slow on samba though (version 4.4.4). > > I have tried various samba tweaks / settings and have yet to get > acceptable write speed on small files. > > > *Gary Lloyd* > > I.T. Systems:Keele University > Finance & IT Directorate > Keele:Staffs:IC1 Building:ST5 5NB:UK > +44 1782 733063 <%2B44%201782%20733073> > > > On 8 February 2017 at 10:05, Дмитрий Глушенок <gl...@jet.msk.su> wrote: > >> Hi, >> >> There is a number of tweaks/hacks to make it better, but IMHO overall >> performance with small files is still unacceptable for such folders with >> thousands of entries. >> >> If your shares are not too large to be placed on single filesystem and >> you still want to use Gluster - it is possible to run VM on top of Gluster. >> Inside that VM you can create ZFS/NTFS to be shared. >> >> 8 февр. 2017 г., в 12:10, Gary Lloyd <g.ll...@keele.ac.uk> написал(а): >> >> Hi >> >> I am currently testing gluster 3.9 replicated/distrbuted on centos 7.3 >> with samba/ctdb. >> I have been able to get it all up and running, but writing small files is >> really slow. >> >> If I copy large files from gluster backed samba I get almost wire speed >> (We only have 1Gb at the moment). I get around half that speed if I copy >> large files to the gluster backed samba system, which I am guessing is due >> to it being replicated (This is acceptable). >> >> Small file write performance seems really poor for us though: >> As an example I have an eclipse IDE workspace folder that is 6MB in size >> that has around 6000 files in it. A lot of these files are <1k in size. >> >> If I copy this up to gluster backed samba it takes almost one hour to get >> there. >> With our basic samba deployment it only takes about 5 minutes. >> >> Both systems reside on the same disks/SAN. >> >> >> I was hoping that we would
Re: [Gluster-users] Slow performance on samba with small files
Thanks for the reply I've just done a bit more testing. If I use rsync from a gluster client to copy the same files to the mount point it only takes a couple of minutes. For some reason it's very slow on samba though (version 4.4.4). I have tried various samba tweaks / settings and have yet to get acceptable write speed on small files. *Gary Lloyd* I.T. Systems:Keele University Finance & IT Directorate Keele:Staffs:IC1 Building:ST5 5NB:UK +44 1782 733063 <%2B44%201782%20733073> On 8 February 2017 at 10:05, Дмитрий Глушенок <gl...@jet.msk.su> wrote: > Hi, > > There is a number of tweaks/hacks to make it better, but IMHO overall > performance with small files is still unacceptable for such folders with > thousands of entries. > > If your shares are not too large to be placed on single filesystem and you > still want to use Gluster - it is possible to run VM on top of Gluster. > Inside that VM you can create ZFS/NTFS to be shared. > > 8 февр. 2017 г., в 12:10, Gary Lloyd <g.ll...@keele.ac.uk> написал(а): > > Hi > > I am currently testing gluster 3.9 replicated/distrbuted on centos 7.3 > with samba/ctdb. > I have been able to get it all up and running, but writing small files is > really slow. > > If I copy large files from gluster backed samba I get almost wire speed > (We only have 1Gb at the moment). I get around half that speed if I copy > large files to the gluster backed samba system, which I am guessing is due > to it being replicated (This is acceptable). > > Small file write performance seems really poor for us though: > As an example I have an eclipse IDE workspace folder that is 6MB in size > that has around 6000 files in it. A lot of these files are <1k in size. > > If I copy this up to gluster backed samba it takes almost one hour to get > there. > With our basic samba deployment it only takes about 5 minutes. > > Both systems reside on the same disks/SAN. > > > I was hoping that we would be able to move away from using a proprietary > SAN to house our network shares and use gluster instead. > > Does anyone have any suggestions of anything I could tweak to make it > better ? > > Many Thanks > > > *Gary Lloyd* > > I.T. Systems:Keele University > Finance & IT Directorate > Keele:Staffs:IC1 Building:ST5 5NB:UK > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://lists.gluster.org/mailman/listinfo/gluster-users > > > -- > Dmitry Glushenok > Jet Infosystems > > ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Slow performance on samba with small files
Hi I am currently testing gluster 3.9 replicated/distrbuted on centos 7.3 with samba/ctdb. I have been able to get it all up and running, but writing small files is really slow. If I copy large files from gluster backed samba I get almost wire speed (We only have 1Gb at the moment). I get around half that speed if I copy large files to the gluster backed samba system, which I am guessing is due to it being replicated (This is acceptable). Small file write performance seems really poor for us though: As an example I have an eclipse IDE workspace folder that is 6MB in size that has around 6000 files in it. A lot of these files are <1k in size. If I copy this up to gluster backed samba it takes almost one hour to get there. With our basic samba deployment it only takes about 5 minutes. Both systems reside on the same disks/SAN. I was hoping that we would be able to move away from using a proprietary SAN to house our network shares and use gluster instead. Does anyone have any suggestions of anything I could tweak to make it better ? Many Thanks *Gary Lloyd* I.T. Systems:Keele University Finance & IT Directorate Keele:Staffs:IC1 Building:ST5 5NB:UK ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users