I recently setup a new octopus cluster and was testing the autoscale feature. Used ceph-ansible so its enabled by default. Anyhow, I have three other clusters that are on nautilus, so I wanted to see if it made sense to enable it there on the main pool. Here is a print out of the autoscale status: POOL SIZE TARGET SIZE RATE RAW CAPACITY RATIO TARGET RATIO EFFECTIVE RATIO BIAS PG_NUM NEW PG_NUM AUTOSCALE default.rgw.buckets.non-ec 0 2.0 55859G 0.0000 1.0 32 on default.rgw.meta 9298 3.0 55859G 0.0000 1.0 32 on default.rgw.buckets.index 18058M 3.0 55859G 0.0009 1.0 32 on default.rgw.control 0 3.0 55859G 0.0000 1.0 32 on default.rgw.buckets.data 9126G 2.0 55859G 0.3268 1.0 4096 1024 off .rgw.root 3155 3.0 55859G 0.0000 1.0 32 on rbd 155.5G 2.0 55859G 0.0056 1.0 32 on default.rgw.log 374.4k 3.0 55859G 0.0000 1.0 64 on For this entry: default.rgw.buckets.data 9126G 2.0 55859G 0.3268 1.0 4096 1024 off I have it disabled because it showed a warn message, but its recommending a 1024 PG setting. When I use the online ceph calculator at ceph.io, its saying the 4096 setting is correct. So why is autoscaler saying 1024? There are 6 osd servers with 10 OSDs each ( all SSD ). 60 TB total. Pool LS output: pool 1 '.rgw.root' replicated size 3 min_size 1 crush_rule 0 object_hash rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 8800 lfor 0/0/344 flags hashpspool stripe_width 0 application rgw pool 2 'default.rgw.control' replicated size 3 min_size 1 crush_rule 0 object_hash rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 8799 lfor 0/0/346 flags hashpspool stripe_width 0 application rgw pool 3 'default.rgw.meta' replicated size 3 min_size 1 crush_rule 0 object_hash rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 8798 lfor 0/0/350 flags hashpspool stripe_width 0 application rgw pool 4 'default.rgw.log' replicated size 3 min_size 1 crush_rule 0 object_hash rjenkins pg_num 64 pgp_num 64 autoscale_mode on last_change 8802 lfor 0/0/298 flags hashpspool stripe_width 0 application rgw pool 5 'default.rgw.buckets.index' replicated size 3 min_size 1 crush_rule 0 object_hash rjenkins pg_num 638 pgp_num 608 pg_num_target 32 pgp_num_target 32 autoscale_mode on last_change 10320 lfor 0/10320/10318 owner 18446744073709551615 flags hashpspool stripe_width 0 application rgw pool 7 'default.rgw.buckets.data' replicated size 2 min_size 1 crush_rule 0 object_hash rjenkins pg_num 4096 pgp_num 4096 last_change 9467 lfor 0/0/552 owner 18446744073709551615 flags hashpspool stripe_width 0 application rgw pool 8 'default.rgw.buckets.non-ec' replicated size 2 min_size 1 crush_rule 0 object_hash rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 8797 lfor 0/0/348 owner 18446744073709551615 flags hashpspool stripe_width 0 application rgw pool 9 'rbd' replicated size 2 min_size 1 crush_rule 0 object_hash rjenkins pg_num 32 pgp_num 32 autoscale_mode on last_change 8801 flags hashpspool,selfmanaged_snaps stripe_width 0 application rbd Regards, -Brent Existing Clusters: Test: Ocotpus 15.2.5 ( all virtual on nvme ) US Production(HDD): Nautilus 14.2.11 with 11 osd servers, 3 mons, 4 gateways, 2 iscsi gateways UK Production(HDD): Nautilus 14.2.11 with 18 osd servers, 3 mons, 4 gateways, 2 iscsi gateways US Production(SSD): Nautilus 14.2.11 with 6 osd servers, 3 mons, 4 gateways, 2 iscsi gateways UK Production(SSD): Octopus 15.2.5 with 5 osd servers, 3 mons, 4 gateways _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |