Re: [Gluster-users] Fuse vs NFS

On Thu, Jul 18, 2019, 11:06 Sudheer Singh wrote: > Hi , > > I was doing perf testing and found out fuse mount much slower than NFS > mount. I was curious to know what community recommends, mount volumes as > fuse or NFS? > You may need to consider libgfapi instead of fuse. I have seen better

Re: [Gluster-users] Brick missing trusted.glusterfs.dht xattr

Hi Mathew, Could you send me the log file for this mount point after doing the following: 1. gluster v set client-log-level DEBUG 2. unmount and remount the volume 3. stat 4. gluster v set client-log-level INFO Regards, Nithya On Thu, 18 Jul 2019 at 19:49, Matthew Benstead

Re: [Gluster-users] CentOS RPMs for version 5.7

Hi Alan, We came across a python dependency issue which broke 5.7. The issue has been fixed and we are doing 5.8 by skipping 5.7. 5.8 has been tagged, the rpms will be made available soon. Do keep an eye on the list for the announcement of 5.8. Sorry for the inconvenience. Regards, Hari. On

[Gluster-users] CentOS RPMs for version 5.7

Dear list, I noticed that the release notes for Gluster version 5.7 were updated two weeks ago¹, but there are no RPMs for CentOS yet². Did someone forget to push a button or is there some other process we are waiting for? Thank you, ¹

Re: [Gluster-users] Fuse vs NFS

Hello. Seriously? You REALLY thinks, that FUSE (in user space) will be faster then kernel NFS? With best wishes. Victor 2019-06-07 7:29 GMT+03:00, Sudheer Singh : > Hi , > > I was doing perf testing and found out fuse mount much slower than NFS > mount. I was curious to know what community

Re: [Gluster-users] Brick missing trusted.glusterfs.dht xattr

Hi Nithya, No - it was added about a year and a half ago. I have tried re-mounting the volume on the server, but it didn't add the attr: [root@gluster07 ~]# umount /storage/ [root@gluster07 ~]# cat /etc/fstab | grep "/storage" 10.0.231.56:/storage /storage glusterfs

Re: [Gluster-users] Share Experience with Productive Gluster Setup <>

Hi Felix, As I don't have much expertise on hardware side, I would not comment on that segment. Based on your "Requirements", I would say that it looks very much feasible. As you are talking about storing large files, I would say that disperse volume could be a good choice. However,

[Gluster-users] Regarding the recent arrival of emails on list

Hi, while working on https://bugzilla.redhat.com/show_bug.cgi?id=1730962, I did notice that no one was moderating the list since end of April, so I decided to clean the queue (around 200 to 300 mails, most non legitimate, but some where). That's why old emails came suddenly, as I figured that

Re: [Gluster-users] Glusterd2 for production

No, it's not production ready. On Thu, Jul 18, 2019 at 1:33 PM deepu srinivasan wrote: > Hi Users > Is it safe to use glusterd2 for production? > ___ > Gluster-users mailing list > Gluster-users@gluster.org >

Re: [Gluster-users] Memory leak in gluster 5.4

Christian, To debug memory leaks, we need periodic statedumps of respective processes. Please provide the statedumps. I suspect that you are hitting https://bugzilla.redhat.com/show_bug.cgi?id=1694612. This bug is addressed in release-5.6 Thanks, Sanju On Thu, Jul 18, 2019 at 1:30 PM Christian

[Gluster-users] Geo-Replication faulty - changelog register failed - Is a directory

Hello - I am having a problem with geo-replication on glusterv5 that I hope someone can help me with. I have a 7-server distribute cluster as the primary volume, and a 2 server distribute cluster as the secondary volume. Both are running the same version of gluster on CentOS 7:

[Gluster-users] Geo-Replication faulty - Changelog register failed error=[Errno 21] Is a directory

Hello - I am having a problem with geo-replication on glusterv5 that I hope someone can help me with. I have a 7-server distribute cluster as the primary volume, and a 2 server distribute cluster as the secondary volume. Both are running the same version of gluster on CentOS 7:

[Gluster-users] Gluster Geo Replication ChangelogException Is a directory

Hello - I am having a problem with geo-replication on glusterv5 that I hope someone can help me with. I have a 7-server distribute cluster as the primary volume, and a 2 server distribute cluster as the secondary volume. Both are running the same version of gluster on CentOS 7:

Re: [Gluster-users] Graceful gluster server retire/poweroff

On 17/07/19 8:50 PM, Strahil Nikolov wrote: Hi Ravi, Can you clarify which script do you use ? Usually I rely on oVirt to shutdown the system properly , but sometimes I have used '/usr/share/glusterfs/scripts/stop-all-gluster-processes.sh' which kills everything (including fuse mounts).

Re: [Gluster-users] Graceful gluster server retire/poweroff

On 16/07/19 3:16 PM, Gionatan Danti wrote: Hi list, I have a replica 3 test cluster and I have a question about how clients behave to an host shutdown. If I suddenly switch off one of the gluster server, the connected clients see a ~42s stall in I/O: this is expected, as it is the default

[Gluster-users] Data Rate and Files transfered in Geo Replication

Hi Users Is there a way to know the stats of geo-replication like the transfer rate, amount of data and number of the file transferred in Geo-Replication? Also, can I know the estimated time left for a checkpoint? ___ Gluster-users mailing list

Re: [Gluster-users] Configure geo replication after volume extension

Thanks a lot, Aravindha. How should the volume rebalance should be done? Should it be done on either side i.e master and slave side or only master side? On Tue, Jul 16, 2019 at 8:18 AM Aravinda wrote: > On Master run `gluster-georep-sshkey generate` and Geo-rep create > command with force

[Gluster-users] Configure geo replication after volume extension

Hi Users Aim: I intend to extend my volume which is basically a 1x3 volume which is in geo-replication Steps I did: I stopped the geo-replication and I extended the volume 1x3 to 2x3 both the master side and slave side. I did the rebalancing on the master side alone. Restarted the geo-replication

[Gluster-users] Webhook for georep status change

Hi Users Is there a webhook that can be configured for a change in georep status change.Like from "checkpoint not completed" to "checkpoint completed"? ___ Gluster-users mailing list Gluster-users@gluster.org

[Gluster-users] Cron rsync -aq --delete /scr/orion/software/linux/ /scratch2/linux/

file has vanished: "/scr/orion/software/linux/fedora/updates/30/Everything/x86_64/Packages/q/.qt5-qtdeclarative-devel-5.12.4-1.fc30.x86_64.rpm.h3U0S8" rsync warning: some files vanished before they could be transferred (code 24) at main.c(1189) [sender=3.1.3]

[Gluster-users] Isolated Client faster than Server+Client

Hi, I have been doing some testing of GlusterFS. I have 2 servers running Gluster 6.3 (although same happening in version 3). 1 Server has 32gb ram the other 4gb. On both servers I also have the volume mounted using the Fuse client and when I run a small of copy 100 x 1kb files it takes about 20

Re: [Gluster-users] Exception in Geo-Replication

Thank you kotresh On Tue, Jul 2, 2019 at 12:38 PM Kotresh Hiremath Ravishankar < khire...@redhat.com> wrote: > You should be looking into the other log file (changes-.log) > for actual failure. > In your case "changes-home-sas-gluster-data-code-misc.log" > > On Tue, Jul 2, 2019 at 12:33 PM deepu

Re: [Gluster-users] Exception in Geo-Replication

Any Update on this issue ? On Mon, Jul 1, 2019 at 4:19 PM deepu srinivasan wrote: > Hi > I am getting this exception while starting geo-replication. Please help. > > [2019-07-01 10:48:02.445475] E [repce(agent > /home/sas/gluster/data/code-misc):122:worker] : call failed: > > Traceback (most

[Gluster-users] Exception in Geo-Replication

Hi I am getting this exception while starting geo-replication. Please help. [2019-07-01 10:48:02.445475] E [repce(agent /home/sas/gluster/data/code-misc):122:worker] : call failed: Traceback (most recent call last): File "/usr/libexec/glusterfs/python/syncdaemon/repce.py", line 118, in

[Gluster-users] Any other method for full resync

Hi Guys We deleted the Geo-replication session with "reset-sync-time" and when we run the sync completely from first and the sync was successful (Hope you remember that we got stuck in geo-replication session in its history crawl and did not go past it). It took a long time to sync the data. Is

[Gluster-users] very poor performance on Debian Buster

I run glusterfs server on a sys-V version of Debian Gluster. The machine is an 8-core/256GB/SSD server and I want to copy 400GB to a mounted gluster device. The copy now runs for more than a day and it has only copied 79GB. The network activity is around 4 to 8 Mbit. Is this a known issue of

[Gluster-users] lingering xattrop (heal) files

Hi All, We're using "gluster volume heal ${volname} statistics heal-count" to monitor our systems w.r.t. healing not happening. The reason we're using statistics heal-count and not info is because it's extremely fast in comparison with info. After upgrading to glusterfs 6.1 (from 4.1) we

[Gluster-users] GeoReplication Error - Changelog register failed error - Is a directory

Hello - I am having a problem with geo-replication on gluster that I hope someone can help me with. I have a 7-server distribute cluster as the primary volume, and a 2 server distribute cluster as the secondary volume. Both are running the same version of gluster on CentOS 7:

Re: [Gluster-users] Duplicated brick processes after restart of glusterd

Thank you for the clarification Regards David Spisla Outlook für Android herunterladen David Spisla Software Engineer david.spi...@iternity.com +49 761 59034852 iTernity GmbH Heinrich-von-Stephan-Str. 21 79100 Freiburg Deutschland Website

Re: [Gluster-users] Geo Replication Stop even after migratingto 5.6

Hi Guys Yes, I will try the root geo-rep setup and update you back. Meanwhile is there any procedure for the below-quoted info in the docs? > Synchronization is not complete > > *Description*: GlusterFS geo-replication did not synchronize the data > completely but the geo-replication status

Re: [Gluster-users] Geo Replication Stop even after migratingto 5.6

Hi Any updates on this On Thu, Jun 13, 2019 at 6:59 PM deepu srinivasan wrote: > > > -- Forwarded message - > From: deepu srinivasan > Date: Thu, Jun 13, 2019 at 5:43 PM > Subject: Geo Replication Stop even after migratingto 5.6 > To: , Kotresh Hiremath Ravishankar < >

Re: [Gluster-users] How to resync completely?

Any Updates on this ? On Thu, Jun 13, 2019 at 6:58 PM deepu srinivasan wrote: > Hi Guys > Found the quotes info in the docs. But Is there any procedure as to how to > do this? the doc seems to not convey it. > >> Synchronization is not complete >> >> *Description*: GlusterFS geo-replication did

[Gluster-users] Fwd: Geo Replication Stop even after migratingto 5.6

-- Forwarded message - From: deepu srinivasan Date: Thu, Jun 13, 2019 at 5:43 PM Subject: Geo Replication Stop even after migratingto 5.6 To: , Kotresh Hiremath Ravishankar , Hi Guys Hope you remember the issue I reported for geo replication hang status on History Crawl. So you

[Gluster-users] How to resync completely?

Hi Guys Found the quotes info in the docs. But Is there any procedure as to how to do this? the doc seems to not convey it. > Synchronization is not complete > > *Description*: GlusterFS geo-replication did not synchronize the data > completely but the geo-replication status displayed is OK. > >

[Gluster-users] add interface(s) for gluster to listen to - how?

hi guys, is it possible to add iface either for global or per volume which gluster would be available through? And if yes then how? many thanks, L. pEpkey.asc Description: application/pgp-keys ___ Gluster-users mailing list Gluster-users@gluster.org

[Gluster-users] Fuse vs NFS

Hi , I was doing perf testing and found out fuse mount much slower than NFS mount. I was curious to know what community recommends, mount volumes as fuse or NFS? -- Thanks, Sudheer ___ Gluster-users mailing list Gluster-users@gluster.org

[Gluster-users] healing of a volume of type disperse

Hi all, I'm pretty new to glusterfs, I managed to setup a dispersed volume (4+2) following the manual using the release 6.1 from centos' repository.. Is it a stable release? Then I forced the volume stop when the application were writing on the mount point.. getting a wanted splitting

Re: [Gluster-users] [Gluster-devel] Improve stability between SMB/CTDB and Gluster (together with Samba Core Developer)

Hello, just a quick heads-up, during this week pretty much all Samba engineers are busy attending the SambaXP conference in Germany, in addition there was a public holiday in India also this week. Not sure about the general availability tomorrow, I would propose to look for a date maybe next

Re: [Gluster-users] Geo Replication stops replicating

Hi Sunny Sorry, that was a typo. I used the following command. > gluster-mountbroker add code-misc sas > On Thu, Jun 6, 2019 at 6:23 PM Sunny Kumar wrote: > You should not have used this one: > > > > gluster-mountbroker remove --volume code-misc --user sas > > -- This one is to remove

Re: [Gluster-users] Geo Replication stops replicating

Hi Sunny Please find the logs attached > The message "E [MSGID: 106061] > [glusterd-mountbroker.c:555:glusterd_do_mount] 0-management: 'option > mountbroker-root' missing in glusterd vol file" repeated 13 times between > [2019-06-06 11:51:43.986788] and [2019-06-06 11:52:32.764546] > > The

Re: [Gluster-users] Geo Replication stops replicating

Hi Kotresh, Sunny Found this log in the slave machine. > [2019-06-05 08:49:10.632583] I [MSGID: 106488] > [glusterd-handler.c:1559:__glusterd_handle_cli_get_volume] 0-management: > Received get vol req > > The message "I [MSGID: 106488] > [glusterd-handler.c:1559:__glusterd_handle_cli_get_volume]

Re: [Gluster-users] Geo Replication stops replicating

Hi Kotresh, Sunny I Have mailed the logs I found in one of the slave machines. Is there anything to do with permission? Please help. On Wed, Jun 5, 2019 at 2:28 PM deepu srinivasan wrote: > Hi Kotresh, Sunny > Found this log in the slave machine. > >> [2019-06-05 08:49:10.632583] I [MSGID:

Re: [Gluster-users] Geo Replication stops replicating

Thankyou Kotresh On Tue, Jun 4, 2019, 11:20 PM Kotresh Hiremath Ravishankar < khire...@redhat.com> wrote: > Ccing Sunny, who was investing similar issue. > > On Tue, Jun 4, 2019 at 5:46 PM deepu srinivasan > wrote: > >> Have already added the path in bashrc . Still in faulty state >> >> On Tue,

Re: [Gluster-users] Geo Replication stops replicating

Hi As discussed I have upgraded gluster from 4.1 to 6.2 version. But the Geo replication failed to start. Stays in faulty state On Fri, May 31, 2019, 5:32 PM deepu srinivasan wrote: > Checked the data. It remains in 2708. No progress. > > On Fri, May 31, 2019 at 4:36 PM Kotresh Hiremath

Re: [Gluster-users] Geo Replication stops replicating

Have already added the path in bashrc . Still in faulty state On Tue, Jun 4, 2019, 5:27 PM Kotresh Hiremath Ravishankar < khire...@redhat.com> wrote: > could you please try adding /usr/sbin to $PATH for user 'sas'? If it's > bash, add 'export PATH=/usr/sbin:$PATH' in > /home/sas/.bashrc > > On

Re: [Gluster-users] Geo Replication stops replicating

Hi Kortesh Please find the logs of the above error *Master log snippet* > [2019-06-04 11:52:09.254731] I [resource(worker > /home/sas/gluster/data/code-misc):1379:connect_remote] SSH: Initializing > SSH connection between master and slave... > [2019-06-04 11:52:09.308923] D [repce(worker >

[Gluster-users] Glusterd2 for production

Hi Users Is it safe to use glusterd2 for production? ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users

[Gluster-users] Glusterfs Split-Brain problem

Hi Gluster Community We have a PVE Proxmox cluster with two nodes. These two nodes each have 4 HDDs over which we have a glusterfs to migrate VMs live. A few days ago we had the problem that some disk files in the glusterfs got into a split-brain condition. We were able to secure the

Re: [Gluster-users] Geo Replication stops replicating

Checked the data. It remains in 2708. No progress. On Fri, May 31, 2019 at 4:36 PM Kotresh Hiremath Ravishankar < khire...@redhat.com> wrote: > That means it could be working and the defunct process might be some old > zombie one. Could you check, that data progress ? > > On Fri, May 31, 2019 at

Re: [Gluster-users] Geo Replication stops replicating

Hi When i change the rsync option the rsync process doesnt seem to start . Only a defunt process is listed in ps aux. Only when i set rsync option to " " and restart all the process the rsync process is listed in ps aux. On Fri, May 31, 2019 at 4:23 PM Kotresh Hiremath Ravishankar <

[Gluster-users] Geo Replication Hangs

Hi We were evaluating Gluster geo Replication between two DataCenters, one is in US west and other in US east. We took multiple trials for different file size . The Geo Replication tend to stop replicating, While checking the status it appears to be in Active state, but the slave volume did not

[Gluster-users] Memory leak in gluster 5.4

Hi everyone! I'm using a Gluster 5.4 Setup with 3 Nodes with three volumes (replicated) (one is the gluster shared storage). Each node has 64GB of RAM. Over the time of ~2 month the memory consumption of glusterd grow linear. An the end glusterd used ~45% of RAM the brick processes together ~43%

[Gluster-users] Memory leak in gluster 5.4

Hi everyone! I'm using a Gluster 5.4 Setup with 3 Nodes with three volumes (replicated) (one is the gluster shared storage). Each node has 64GB of RAM. Over the time of ~2 month the memory consumption of glusterd grow linear. An the end glusterd used ~45% of RAM the brick processes together ~43%

[Gluster-users] File not updated on gluster fuse volume when written by another client

I have a cluster with many replica volumes One of the node was rebooted for some reason Then I mounted all volumes from localhost, on the rebooted server I found some contents of file which was updated by other clients does not change. If I remount the volume, the file was updated, but stopped

Re: [Gluster-users] Geo Replication stops replicating

Done. We got the following result . > 1559298781.338234 write(2, "rsync: link_stat > \"/tmp/gsyncd-aux-mount-EEJ_sY/.gfid/3fa6aed8-802e-4efe-9903-8bc171176d88\" > failed: No such file or directory (2)", 128 seems like a file is missing ? On Fri, May 31, 2019 at 3:25 PM Kotresh Hiremath

Re: [Gluster-users] Geo Replication stops replicating

Hi Kotresh We have tried the above-mentioned rsync option and we are planning to have the version upgrade to 6.0. On Fri, May 31, 2019 at 11:04 AM Kotresh Hiremath Ravishankar < khire...@redhat.com> wrote: > Hi, > > This looks like the hang because stderr buffer filled up with errors > messages

Re: [Gluster-users] Geo Replication stops replicating

Hi Kotresh The above-mentioned work around did not work properly. On Fri, May 31, 2019 at 3:16 PM deepu srinivasan wrote: > Hi Kotresh > We have tried the above-mentioned rsync option and we are planning to have > the version upgrade to 6.0. > > On Fri, May 31, 2019 at 11:04 AM Kotresh Hiremath

[Gluster-users] Geo Replication Stops

Hi We were evaluating Gluster geo Replication between two DCs one is in US west and one is in US east. We took multiple trials for different file size. The Geo Replication tends to stop replicating but while checking the status it appears to be in Active state. But the slave volume did not

Re: [Gluster-users] [ovirt-users] Re: Single instance scaleup.

Hi, Looks like the only way arround would be to create a brand-new volume as replicated on other disks, and start moving the vms all around the place between volumes ? Cheers, Leo On Mon, May 27, 2019 at 1:53 PM Leo David wrote: > Hi, > Any suggestions ? > Thank you very much ! > > Leo > > On

Re: [Gluster-users] [ovirt-users] Re: Single instance scaleup.

Hi, Any suggestions ? Thank you very much ! Leo On Sun, May 26, 2019 at 4:38 PM Strahil Nikolov wrote: > Yeah, > it seems different from the docs. > I'm adding the gluster users list ,as they are more experienced into that. > > @Gluster-users, > > can you provide some hint how to add aditional

[Gluster-users] Gluster Community Meeting (APAC friendly hours)

Bridge: https://bluejeans.com/836554017 Meeting minutes: https://hackmd.io/B4vOpJumRgexzqeQiNPVOw Flash Talk : What is Thin Arbiter? (By Ashish Pandey) Previous Meeting notes: http://github.com/gluster/community Title: Gluster Community Meeting (APAC friendly hours) Bridge:

[Gluster-users] Gluster mounts becoming stale and never recovering

Hi all, We are having a sporadic issue with our Gluster mounts that is affecting several of our Kubernetes environments. We are having trouble understanding what is causing it, and we could use some guidance from the pros! Scenario We have an environment running a single-node Kubernetes with

[Gluster-users] Gluster mounts becoming stale and never recovering

Hi all, We are having a sporadic issue with our Gluster mounts that is affecting several of our Kubernetes environments. We are having trouble understanding what is causing it, and we could use some guidance from the pros! Scenario We have an environment running a single-node Kubernetes with

Re: [Gluster-users] [Gluster-devel] Improve stability between SMB/CTDB and Gluster (together with Samba Core Developer)

Hi Poornima, thats fine. I would suggest this dates and times: May 15th – 17th at 12:30, 13:30, 14:30 IST (9:00, 10:00, 11:00 CEST) May 20th – 24th at 12:30, 13:30, 14:30 IST (9:00, 10:00, 11:00 CEST) I add Volker Lendecke from Sernet to the mail. He is the Samba Expert. Can someone of you

[Gluster-users] No Variation in Gluster geo Replication when sync jobs value is increased.

Hi We were evaluating Gluster geo Replication. We took multiple trials for different file size and different syncjob value. While increasing or decreasing the syncjob value the geo replication didnot increase or decrease its time period for synching.Is this normal or should we change any other

[Gluster-users] Synchronous Client-Side Replication Behavior

What are the guarantees at write completion time with client-side replication and replicated volume types? When the write completes has it successfully been written to all replicas or just one? How does write-behind/flush-behind affect this behavior?

[Gluster-users] geo-replication create push-pem command failure

I'm running gluster 4.1.8 on a two node replicated cluster. I'm trying to get geo-replication setup between one slave node with a running volume on it. Everything is working, I have a passwordless connection between a geogrp user on the slave and the root user on master 1. When I run gluster

Re: [Gluster-users] GlusterFS on ZFS

Thanks Amar. I’m going to see what kind of performance I get with just ZFS cache using Intel Optane and RaidZ10 with 12x drives. If this performs better than AWS GP2, I’m good. If not I’ll look into dmcache. Has anyone used bcache? Have any experience there? Thank you, Cody Hill | Director

[Gluster-users] Share Experience with Productive Gluster Setup <>

Dear Gluster-Community, we try to implement a gluster setup in a productive environment. During the development process, we found this nice thread regarding to gluster storage experience: https://forums.overclockers.com.au/threads/glusterfs-800tb-and-growing.1078674/ This thread seems to