[UPDATE] I notice that in [node] -> Ceph -> Pool in Used % column the values is decrease over time! Perhaps need wait to adjust it and than see if active+remapped+backfill_wait and active+remapped+backfilling end it's operations... --- Gilberto Nunes Ferreira
Em sáb., 28 de mar. de 2020 às 11:04, Gilberto Nunes < gilberto.nune...@gmail.com> escreveu: > Help with Ceph in PVE 6 > > Hi > > I have a ceph cluster created with 3 server.... > ServerA has 3 SAS 512GB HDD and 1 SAS 1.3 TB > ServerB has 3 SAS 512GB HDD and 1 SAS 1.3 TB > ServerS has 3 SAS 512GB HDD and 1 SAS 1.3 TB > > I have one pool named VMS with size/min 3/2 and pg_num initially created > with 256 but I have increased to 512 and an hour ago to 768 but it's see > hava not effect on it... > > Ceph health apparently is ok but get this with ceph -s command: > > ceph -s > cluster: > id: 93c55c6b-ce64-4e1a-92bc-0bc529d695f2 > health: HEALTH_OK > > services: > mon: 5 daemons, quorum pve3,pve4,pve5,pve7,pve6 (age 15h) > mgr: pve3(active, since 15h), standbys: pve4, pve5, pve7, pve6 > osd: 12 osds: 12 up (since 10m), 12 in (since 10m); 497 remapped pgs > > data: > pools: 1 pools, 768 pgs > objects: 279.34k objects, 1.1 TiB > usage: 3.0 TiB used, 6.2 TiB / 9.1 TiB avail > pgs: 375654/838011 objects misplaced (44.827%) > 494 active+remapped+backfill_wait > 271 active+clean > 3 active+remapped+backfilling > > io: > client: 140 KiB/s rd, 397 KiB/s wr, 12 op/s rd, 64 op/s wr > recovery: 52 MiB/s, 14 objects/s > > > Is there any action I can take to fix this? > > Thanks > --- > Gilberto Nunes Ferreira > > (47) 3025-5907 > (47) 99676-7530 - Whatsapp / Telegram > > Skype: gilberto.nunes36 > > > > _______________________________________________ pve-user mailing list pve-user@pve.proxmox.com https://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-user