[Gluster-users] Invitation: Gluster community meeting @ Tue Jun 23, 2020 2:30pm - 3:30pm (IST) (gluster-users@gluster.org)

2020-06-22 Thread sacharya
BEGIN:VCALENDAR PRODID:-//Google Inc//Google Calendar 70.9054//EN VERSION:2.0 CALSCALE:GREGORIAN METHOD:REQUEST BEGIN:VEVENT DTSTART:20200623T09Z DTEND:20200623T10Z DTSTAMP:20200623T055438Z ORGANIZER;CN=sacha...@redhat.com:mailto:sacha...@redhat.com UID:51cmdqukvf6ab8sm0281doh...@google.com

Re: [Gluster-users] State of Gluster project

2020-06-22 Thread Strahil Nikolov
Hey Erik, I actually ment that there is no point in using controllers with fast storage like SAS SSDs or NVMEs. They (the controllers) usually have 1-2 GB of RAM to buffer writes until the risc processor analyzes the requests and stacks them - thus JBOD (in 'replica 3' )makes much more sen

Re: [Gluster-users] State of Gluster project

2020-06-22 Thread Erik Jacobson
> For NVMe/SSD - raid controller is pointless , so JBOD makes most sense. I am game for an education lesson here. We're still using spinng drives with big RAID caches but we keep discussing SSD in the context of RAID. I have read for many real-world workloads, RAID0 makes no sense with modern S

Re: [Gluster-users] State of Gluster project

2020-06-22 Thread Mahdi Adnan
We had a distributed replicated volume of 3 x 7 HDD, the volume was used for small files workload with heavy IO, we decided to replace the bricks with SSDs because of IO saturation to the disks, so we started by swapping the bricks one by one, and the fun started, some files lost its attributes and

Re: [Gluster-users] Reliable Geo-Replication

2020-06-22 Thread Shwetha Acharya
Hi Felix, Have you deleted the session with reset-sync-time and recreated the session? If yes, the crawling starts from beginning. Which happens in this way: It begins with hybrid crawl, as data is already in master before re creating the geo-rep session. If geo-rep session is craeted before cr

Re: [Gluster-users] State of Gluster project

2020-06-22 Thread Strahil Nikolov
Hi Hubert, keep in mind RH recommends disks of size 2-3 TB, not 10. I guess that has changed the situation. For NVMe/SSD - raid controller is pointless , so JBOD makes most sense. Best Regards, Strahil Nikolov На 22 юни 2020 г. 7:58:56 GMT+03:00, Hu Bert написа: >Am So., 21. Juni 2020 um

Re: [Gluster-users] Reliable Geo-Replication

2020-06-22 Thread Felix Kölzow
Dear Shwetha, sorry, one more question, since I try to collect some more information which may helpful for other gluster-users. Does the suggested command # setfattr -n glusterfs.geo-rep.trigger-sync -v "1" also work regardless of the current mode, i.e. history, hybrid or changelog crawl?

Re: [Gluster-users] Reliable Geo-Replication

2020-06-22 Thread Felix Kölzow
Dear Shwetha, thanks for your reply. I mounted the volume via fuse on the gluster storage server and ran the command: setfattr -n glusterfs.geo-rep.trigger-sync -v "1" Before that, I mounted the volume with my default options: mount -t glusterfs -o acl glusterStorageServer:/volName /mnt/mo

Re: [Gluster-users] Reliable Geo-Replication

2020-06-22 Thread Shwetha Acharya
Hi Felix, File path is the path from mount point. Need not include any other options. Regards,| Shwetha On Mon, Jun 22, 2020 at 3:15 PM Felix Kölzow wrote: > Dear Shwetha, > > > One more alternative would be to triggering sync on indivisual files, > > # setfattr -n glusterfs.geo-rep.trigger-sy

Re: [Gluster-users] Reliable Geo-Replication

2020-06-22 Thread Felix Kölzow
Dear Shwetha, One more alternative would be to triggering sync on indivisual files, # setfattr -n glusterfs.geo-rep.trigger-sync -v "1" So, how to do it exactly and what is ? Is it a gluster mount point with certain mount options or is this the brick path? Furthermore, does it work for direc

Re: [Gluster-users] Reliable Geo-Replication

2020-06-22 Thread Shwetha Acharya
Deleting geo-rep session with reset-sync-time, makes sure that sync time(stime) is reset. Sync time is last time when the sync happened from master to slave. Regards, Shwetha On Mon, Jun 22, 2020 at 2:42 PM Shwetha Acharya wrote: > Hi Felix, > > Index here is stime or sync time. Once we set syn

Re: [Gluster-users] Reliable Geo-Replication

2020-06-22 Thread Shwetha Acharya
Hi Felix, Index here is stime or sync time. Once we set sync time to 0, crawl happens from the beginning, till stime < xtime. (xtime is last modified time of file or directory on master) We can achieve it using following steps: # gluster volume geo-replication master-vol slave-ip::slave-vol stop

Re: [Gluster-users] State of Gluster project

2020-06-22 Thread Hu Bert
Am So., 21. Juni 2020 um 19:43 Uhr schrieb Gionatan Danti : > For the RAID6/10 setup, I found no issues: simply replace the broken > disk without involing Gluster at all. However, this also means facing > the "iops wall" I described earlier for single-brick node. Going > full-Guster with JBODs wou

Re: [Gluster-users] State of Gluster project

2020-06-22 Thread Gionatan Danti
Il 2020-06-22 06:58 Hu Bert ha scritto: Am So., 21. Juni 2020 um 19:43 Uhr schrieb Gionatan Danti : For the RAID6/10 setup, I found no issues: simply replace the broken disk without involing Gluster at all. However, this also means facing the "iops wall" I described earlier for single-brick no

Re: [Gluster-users] State of Gluster project

2020-06-22 Thread Gionatan Danti
Il 2020-06-21 20:41 Mahdi Adnan ha scritto: Hello Gionatan, Using Gluster brick in a RAID configuration might be safer and require less work from Gluster admins but, it is a waste of disk space. Gluster bricks are replicated "assuming you're creating a distributed-replica volume" so when brick

Re: [Gluster-users] Reliable Geo-Replication

2020-06-22 Thread Felix Kölzow
Dear Shwetha, thank you very much for your immediate response. It turns out we have rsync 3.1.2, so this sould be fine. Actually, geo-rep is in xsync mode, but just due to the fact that I deleted the geo-replication and used the reset-sync-time option. If you are looking to still resync, y