Re: [ceph-users] ceph balancer do not start
Hi Konstantin, connections coming from qemu vm clients. Best regards Gesendet: Donnerstag, 24. Oktober 2019 um 09:47 Uhr Von: "Konstantin Shalygin" An: ceph-users@lists.ceph.com, "Jan Peters" Betreff: Re: [ceph-users] ceph balancer do not start Hi, ceph features { "mon": { "group": { "features": "0x3ffddff8eeacfffb", "release": "luminous", "num": 3 } }, "osd": { "group": { "features": "0x3ffddff8eeacfffb", "release": "luminous", "num": 40 } }, "client": { "group": { "features": "0x27fddff8ee8cbffb", "release": "jewel", "num": 813 }, "group": { "features": "0x3ffddff8eeacfffb", "release": "luminous", "num": 3 } } } Yes, 0x27fddff8ee8cbffb is not support upmap. This is kernel clients or qemu vms? k ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] ceph balancer do not start
Hi, ceph features { "mon": { "group": { "features": "0x3ffddff8eeacfffb", "release": "luminous", "num": 3 } }, "osd": { "group": { "features": "0x3ffddff8eeacfffb", "release": "luminous", "num": 40 } }, "client": { "group": { "features": "0x27fddff8ee8cbffb", "release": "jewel", "num": 813 }, "group": { "features": "0x3ffddff8eeacfffb", "release": "luminous", "num": 3 } } } Gesendet: Donnerstag, 24. Oktober 2019 um 06:03 Uhr Von: "Konstantin Shalygin" An: ceph-users@lists.ceph.com, "Jan Peters" Betreff: Re: [ceph-users] ceph balancer do not start root at ceph-mgr[http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com]:~# ceph balancer mode upmaproot at ceph-mgr[http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com]:~# ceph balancer optimize myplanroot at ceph-mgr[http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com]:~# ceph balancer show myplan # starting osdmap epoch 409753 # starting crush version 84 # mode upmap ceph osd pg-upmap-items 4.18e 34 13 ceph osd pg-upmap-items 4.36d 24 20 ceph osd pg-upmap-items 7.2 10 15 ceph osd pg-upmap-items 7.3 24 20 4 17 ceph osd pg-upmap-items 7.4 0 16 4 25 ceph osd pg-upmap-items 7.5 19 2 8 13 ceph osd pg-upmap-items 7.7 8 21root at ceph-mgr[http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com]:~# ceph balancer execute myplan Error EPERM: min_compat_client jewel < luminous, which is required for pg-upmap. Try 'ceph osd set-require-min-compat-client luminous' before using the new interfaceroot at ceph-mgr[http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com]:~# ceph osd set-require-min-compat-client luminous Error EPERM: cannot set require_min_compat_client to luminous: 811 connected client(s) look like jewel (missing 0x820); add --yes-i-really-mean-it to do it anywayroot at ceph-mgr[http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com]:~# What is your `ceph features`? k ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] ceph balancer do not start
Hi David, thank you. Unfortunately i have the problem that i can't use the upmap mode at the moment. root@ceph-mgr:~# ceph balancer mode upmap root@ceph-mgr:~# ceph balancer optimize myplan root@ceph-mgr:~# ceph balancer show myplan # starting osdmap epoch 409753 # starting crush version 84 # mode upmap ceph osd pg-upmap-items 4.18e 34 13 ceph osd pg-upmap-items 4.36d 24 20 ceph osd pg-upmap-items 7.2 10 15 ceph osd pg-upmap-items 7.3 24 20 4 17 ceph osd pg-upmap-items 7.4 0 16 4 25 ceph osd pg-upmap-items 7.5 19 2 8 13 ceph osd pg-upmap-items 7.7 8 21 root@ceph-mgr:~# ceph balancer execute myplan Error EPERM: min_compat_client jewel < luminous, which is required for pg-upmap. Try 'ceph osd set-require-min-compat-client luminous' before using the new interface root@ceph-mgr:~# ceph osd set-require-min-compat-client luminous Error EPERM: cannot set require_min_compat_client to luminous: 811 connected client(s) look like jewel (missing 0x820); add --yes-i-really-mean-it to do it anyway root@ceph-mgr:~# Best regards Jan Gesendet: Mittwoch, 23. Oktober 2019 um 05:42 Uhr Von: "David Turner" An: "Jan Peters" Cc: ceph-users Betreff: Re: [ceph-users] ceph balancer do not start Of the top of my head, if say your cluster might have the wrong tunables for crush-compat. I know I ran into that when I first set up the balancer and nothing obviously said that was the problem. Only researching find it for me. My real question, though, is why aren't you using upmap? It is significantly better than crush-compat. Unless you have clients on really old kernels that can't update or that are on pre-luminous Ceph versions that can't update, there's really no reason not to use upmap. On Mon, Oct 21, 2019, 8:08 AM Jan Peters mailto:haseni...@gmx.de]> wrote:Hello, I use ceph 12.2.12 and would like to activate the ceph balancer. unfortunately no redistribution of the PGs is started: ceph balancer status { "active": true, "plans": [], "mode": "crush-compat" } ceph balancer eval current cluster score 0.023776 (lower is better) ceph config-key dump { "initial_mon_keyring": "AQBLchlbABAA+5CuVU+8MB69xfc3xAXkjQ==", "mgr/balancer/active": "1", "mgr/balancer/max_misplaced:": "0.01", "mgr/balancer/mode": "crush-compat" } What am I not doing correctly? best regards ___ ceph-users mailing list ceph-users@lists.ceph.com[mailto:ceph-users@lists.ceph.com] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] ceph balancer do not start
Hello, I use ceph 12.2.12 and would like to activate the ceph balancer. unfortunately no redistribution of the PGs is started: ceph balancer status { "active": true, "plans": [], "mode": "crush-compat" } ceph balancer eval current cluster score 0.023776 (lower is better) ceph config-key dump { "initial_mon_keyring": "AQBLchlbABAA+5CuVU+8MB69xfc3xAXkjQ==", "mgr/balancer/active": "1", "mgr/balancer/max_misplaced:": "0.01", "mgr/balancer/mode": "crush-compat" } What am I not doing correctly? best regards ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Bluestore Hardwaresetup
Hi, thank you. Networksetup is like that: 2 x 10 GBit LACP for public 2 x 10 GBit LACP for clusternetwork 1 x 1 GBit for management Yes Joe, the sizing for block.db and blockwal would be interesting! Is there another advice for SSDs like blog from Sebastian Han?: https://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/ Best regards Peter Gesendet: Freitag, 16. Februar 2018 um 19:09 Uhr Von: "Joe Comeau" <joe.com...@hli.ubc.ca> An: "Michel Raabe" <rmic...@devnu11.net>, "Jan Peters" <haseni...@gmx.de> Cc: ceph-users@lists.ceph.com Betreff: Re: [ceph-users] Bluestore Hardwaresetup I have a question about block.db and block.wal How big should they be? Relative to drive size or ssd size ? Thanks Joe >>> Michel Raabe <rmic...@devnu11.net> 2/16/2018 9:12 AM >>> Hi Peter, On 02/15/18 @ 19:44, Jan Peters wrote: > I want to evaluate ceph with bluestore, so I need some hardware/configure > advices from you. > > My Setup should be: > > 3 Nodes Cluster, on each with: > > - Intel Gold Processor SP 5118, 12 core / 2.30Ghz > - 64GB RAM > - 6 x 7,2k, 4 TB SAS > - 2 x SSDs, 480GB Network? > On the POSIX FS you have to set your journal on SSDs. What is the best way > for bluestore? > > Should I configure separate SSDs for block.db and block.wal? Yes. Regards, Michel ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Bluestore Hardwaresetup
Hi, thank you. Networksetup is like that: 2 x 10 GBit LACP for public 2 x 10 GBit LACP for clusternetwork 1 x 1 GBit for management Yes Joe, the sizing for block.db and blockwal would be interesting! Is there another advice for SSDs like blog from Sebastian Han?: https://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/ Best regards Peter Gesendet: Freitag, 16. Februar 2018 um 19:09 Uhr Von: "Joe Comeau" <joe.com...@hli.ubc.ca> An: "Michel Raabe" <rmic...@devnu11.net>, "Jan Peters" <haseni...@gmx.de> Cc: ceph-users@lists.ceph.com Betreff: Re: [ceph-users] Bluestore Hardwaresetup I have a question about block.db and block.wal How big should they be? Relative to drive size or ssd size ? Thanks Joe >>> Michel Raabe <rmic...@devnu11.net> 2/16/2018 9:12 AM >>> Hi Peter, On 02/15/18 @ 19:44, Jan Peters wrote: > I want to evaluate ceph with bluestore, so I need some hardware/configure advices from you. > > My Setup should be: > > 3 Nodes Cluster, on each with: > > - Intel Gold Processor SP 5118, 12 core / 2.30Ghz > - 64GB RAM > - 6 x 7,2k, 4 TB SAS > - 2 x SSDs, 480GB Network? > On the POSIX FS you have to set your journal on SSDs. What is the best way for bluestore? > > Should I configure separate SSDs for block.db and block.wal? Yes. Regards, Michel ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] Bluestore Hardwaresetup
Hi everybody, I want to evaluate ceph with bluestore, so I need some hardware/configure advices from you. My Setup should be: 3 Nodes Cluster, on each with: - Intel Gold Processor SP 5118, 12 core / 2.30Ghz - 64GB RAM - 6 x 7,2k, 4 TB SAS - 2 x SSDs, 480GB On the POSIX FS you have to set your journal on SSDs. What is the best way for bluestore? Should I configure separate SSDs for block.db and block.wal? Is there a way to use CacheTiering or a cachepool? Thanks in advance Peter ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com