So nobody has any clue on this one ??? Should I go with this one to dev mailing list ?
> On 27 Aug 2017, at 01:49, Tomasz Kusmierz <tom.kusmi...@gmail.com> wrote: > > Hi, > for purposes of experimenting I’m running a home cluster that consists of > single node and 4 OSD (weights in crush map are true to actual hdd size). I > prefer to test all new stuff on home equipment before getting egg in the face > at work :) > Anyway recently I’ve upgrade to Luminous, and replaced my ancient 8x 2TB > drives with 2x 8TB drives (with hopes of getting more in near future). While > doing that I’ve converted everything to bluestore. while still on 12.1.1 > > Everything was running smooth and performance was good (for ceph). > > I’ve decided to upgrade recently to 12.1.2 and this is where everything > started acting up. I’m aware that > - single node cluster is not a cluster > - in the end I might need more OSD (old joke right ?) > - I need to switch from spinning rust to SSD > > Before upgrade my “cluster” was only switching to WRN only when I was pumping > a lot of data into it and it would just come up with “slow requests” stuff. > Now while completely static, not doing anything (no read, no write) OSD’s are > committing suicide due to timeout, also before they will commit suicide I > can’t actually access data from cluster, which make me think that while > performing a scrub those are unaccessible. Bellow I’ll attach a log excerpt > just please notice that it happens on deep scrub and normal scrub as well. > > After I’ve discovered that I’ve tried to play around with sysctl.conf and > with ceph.conf ( up to this point sysctl.conf was stock, and ceph.conf was > just adjusted to allow greater OSD full capacity and disable cephx to speed > it up) > > also I’m running 3 pools on top of this cluster (all three have size = 2 > min_size = 2): > cephfs_data pg=256 (99.99% of data used in cluster) > cephfs_metadata pg=4 (0.01% of data used in cluster) > rbd pg=8 but this pool contains no data and I’m considering removing it since > in my use case I’ve got nothing for it. > > Please note that while this logs were produced cephFS was not even mounted :/ > > > > FYI hardware is old and trusted hp proliant DL180 G6 with 2 xeons @2.2GHz > giving 16 cores and 32GB or ECC ram and LSI in HBA mode (2x 6GB SAS) > > > > ( > As a side issue could somebody explain to my why with bluestore that was > supposed to cure cancer write performance still sucks ? I know that filestore > did suffer from writing everything multiple times to same drive, and I did > experience this first hand when after exhausting journals it was just dead > slow, but now while within same host in my current configuration it keeps > choking [flaps 70MB/s -> 10 MB/s -> 70MB/s] and I never seen it even approach > speed of single slowest drive. This server is not a speed daemon, I know, but > when performing a simultaneous read / write for those drives I was getting > around 760MB/s sequential R/W speed. > Right now I’m struggling to comprehend where the bottleneck is while > performing operations within same host ?! network should not be an issue > (correct me if I’m wrong here), dumping a singular blob into pool should > produce a nice long sequence of object placed into drives … > I’m just puzzled why ceph will not exceed combined 40MB/s while still > switching “cluster” into warning state due to “slow responses” > 2017-08-24 20:49:34.457191 osd.8 osd.8 192.168.1.240:6814/3393 503 : cluster > [WRN] slow request 63.878717 seconds old, received at 2017-08-24 > 20:48:30.578398: osd_op(client.994130.1:13659 1.9700016d > 1:b68000e9:::100000ffeef.00000068:head [write 0~4194304 [1@-1]] snapc 1=[] > ondisk+write+known_if_redirected e4306) currently waiting for active > 2017-08-24 20:49:34.457195 osd.8 osd.8 192.168.1.240:6814/3393 504 : cluster > [WRN] slow request 64.177858 seconds old, received at 2017-08-24 > 20:48:30.279257: osd_op(client.994130.1:13568 1.b95e13a4 > 1:25c87a9d:::100000ffeef.0000000d:head [write 0~4194304 [1@-1]] snapc 1=[] > ondisk+write+known_if_redirected e4306) currently waiting for active > 2017-08-24 20:49:34.457198 osd.8 osd.8 192.168.1.240:6814/3393 505 : cluster > [WRN] slow request 64.002653 seconds old, received at 2017-08-24 > 20:48:30.454463: osd_op(client.994130.1:13626 1.b426420e > 1:7042642d:::100000ffeef.00000047:head [write 0~4194304 [1@-1]] snapc 1=[] > ondisk+write+known_if_redirected e4306) currently waiting for active > 2017-08-24 20:49:34.457200 osd.8 osd.8 192.168.1.240:6814/3393 506 : cluster > [WRN] slow request 63.873519 seconds old, received at 2017-08-24 > 20:48:30.583596: osd_op(client.994130.1:13661 1.31551a8 > 1:158aa8c0:::100000ffeef.0000006a:head [write 0~4194304 [1@-1]] snapc 1=[] > ondisk+write+known_if_redirected e4306) currently waiting for active > 2017-08-24 20:49:34.457206 osd.8 osd.8 192.168.1.240:6814/3393 507 : cluster > [WRN] slow request 64.171785 seconds old, received at 2017-08-24 > 20:48:30.285330: osd_op(client.994130.1:13570 1.49610cc6 > 1:63308692:::100000ffeef.0000000f:head [write 0~4194304 [1@-1]] snapc 1=[] > ondisk+write+known_if_redirected e4306) currently waiting for active > ) > > > So some data on main issue: > > > FAIL ON DEEP SCRUB > 2017-08-26 01:50:04.421944 osd.0 osd.0 192.168.1.240:6814/12991 7 : cluster > [INF] 6.5 scrub ok > 2017-08-26 01:50:09.331095 osd.0 osd.0 192.168.1.240:6814/12991 8 : cluster > [INF] 1.1c scrub starts > 2017-08-26 01:51:03.339509 osd.0 osd.0 192.168.1.240:6814/12991 9 : cluster > [INF] 1.1c scrub ok > 2017-08-26 02:21:00.706695 osd.10 osd.10 192.168.1.240:6806/21564 7 : cluster > [INF] 1.d1 scrub starts > 2017-08-26 02:21:34.066183 osd.10 osd.10 192.168.1.240:6806/21564 8 : cluster > [INF] 1.d1 scrub ok > 2017-08-26 02:21:56.943046 osd.8 osd.8 192.168.1.240:6810/22002 7 : cluster > [INF] 1.17 scrub starts > 2017-08-26 02:23:06.341409 osd.8 osd.8 192.168.1.240:6810/22002 8 : cluster > [INF] 1.17 scrub ok > 2017-08-26 02:35:51.099649 osd.8 osd.8 192.168.1.240:6810/22002 9 : cluster > [INF] 1.89 scrub starts > 2017-08-26 02:36:42.605600 osd.8 osd.8 192.168.1.240:6810/22002 10 : cluster > [INF] 1.89 scrub ok > 2017-08-26 02:38:27.132698 osd.8 osd.8 192.168.1.240:6810/22002 11 : cluster > [INF] 1.ce scrub starts > 2017-08-26 02:38:49.820489 osd.8 osd.8 192.168.1.240:6810/22002 12 : cluster > [INF] 1.ce scrub ok > 2017-08-26 03:23:27.619669 osd.8 osd.8 192.168.1.240:6810/22002 13 : cluster > [INF] 1.8c scrub starts > 2017-08-26 03:23:49.679403 osd.8 osd.8 192.168.1.240:6810/22002 14 : cluster > [INF] 1.8c scrub ok > 2017-08-26 03:32:19.475812 osd.0 osd.0 192.168.1.240:6814/12991 10 : cluster > [INF] 1.d4 deep-scrub starts > 2017-08-26 03:38:46.708163 mon.0 mon.0 192.168.1.240:6789/0 1201 : cluster > [INF] osd.0 failed (root=default,host=proxmox1) (connection refused reported > by osd.8) > 2017-08-26 03:38:46.759470 mon.0 mon.0 192.168.1.240:6789/0 1207 : cluster > [WRN] Health check failed: 1 osds down (OSD_DOWN) > 2017-08-26 03:38:49.820122 mon.0 mon.0 192.168.1.240:6789/0 1212 : cluster > [WRN] Health check failed: Reduced data availability: 12 pgs inactive > (PG_AVAILABILITY) > 2017-08-26 03:38:49.820165 mon.0 mon.0 192.168.1.240:6789/0 1213 : cluster > [WRN] Health check failed: Degraded data redundancy: 292260/3786364 objects > degraded (7.719%), 38 pgs unclean, 38 pgs degraded (PG_DEGRADED) > 2017-08-26 03:38:51.088934 mon.0 mon.0 192.168.1.240:6789/0 1214 : cluster > [WRN] Health check update: Reduced data availability: 16 pgs inactive > (PG_AVAILABILITY) > 2017-08-26 03:38:51.088975 mon.0 mon.0 192.168.1.240:6789/0 1215 : cluster > [WRN] Health check update: Degraded data redundancy: 392568/3786364 objects > degraded (10.368%), 52 pgs unclean, 52 pgs degraded (PG_DEGRADED) > 2017-08-26 03:38:53.090178 mon.0 mon.0 192.168.1.240:6789/0 1216 : cluster > [WRN] Health check update: Reduced data availability: 29 pgs inactive > (PG_AVAILABILITY) > 2017-08-26 03:38:53.090216 mon.0 mon.0 192.168.1.240:6789/0 1217 : cluster > [WRN] Health check update: Degraded data redundancy: 592033/3786364 objects > degraded (15.636%), 82 pgs unclean, 82 pgs degraded (PG_DEGRADED) > 2017-08-26 03:39:37.928816 mon.0 mon.0 192.168.1.240:6789/0 1220 : cluster > [INF] Health check cleared: OSD_DOWN (was: 1 osds down) > 2017-08-26 03:39:37.941007 mon.0 mon.0 192.168.1.240:6789/0 1221 : cluster > [INF] osd.0 192.168.1.240:6814/15727 boot > 2017-08-26 03:39:39.949551 mon.0 mon.0 192.168.1.240:6789/0 1226 : cluster > [WRN] Health check update: Degraded data redundancy: 436309/3786364 objects > degraded (11.523%), 82 pgs unclean, 60 pgs degraded (PG_DEGRADED) > 2017-08-26 03:39:41.974996 mon.0 mon.0 192.168.1.240:6789/0 1227 : cluster > [WRN] Health check update: Degraded data redundancy: 379236/3786364 objects > degraded (10.016%), 74 pgs unclean, 52 pgs degraded (PG_DEGRADED) > 2017-08-26 03:39:43.120495 mon.0 mon.0 192.168.1.240:6789/0 1228 : cluster > [WRN] Health check update: Degraded data redundancy: 22 pgs unclean > (PG_DEGRADED) > 2017-08-26 03:39:43.120534 mon.0 mon.0 192.168.1.240:6789/0 1229 : cluster > [INF] Health check cleared: PG_AVAILABILITY (was: Reduced data availability: > 29 pgs inactive) > 2017-08-26 03:39:45.121340 mon.0 mon.0 192.168.1.240:6789/0 1230 : cluster > [INF] Health check cleared: PG_DEGRADED (was: Degraded data redundancy: 22 > pgs unclean) > 2017-08-26 03:39:45.121386 mon.0 mon.0 192.168.1.240:6789/0 1231 : cluster > [INF] Cluster is now healthy > 2017-08-26 03:40:11.568499 osd.10 osd.10 192.168.1.240:6806/21564 9 : cluster > [INF] 1.b5 scrub starts > 2017-08-26 03:40:51.874519 osd.10 osd.10 192.168.1.240:6806/21564 10 : > cluster [INF] 1.b5 scrub ok > 2017-08-26 03:41:15.794026 osd.8 osd.8 192.168.1.240:6810/22002 15 : cluster > [INF] 1.77 scrub starts > 2017-08-26 03:42:19.561924 osd.8 osd.8 192.168.1.240:6810/22002 16 : cluster > [INF] 1.77 scrub ok > 2017-08-26 03:42:30.895351 osd.0 osd.0 192.168.1.240:6814/15727 1 : cluster > [INF] 1.d4 deep-scrub starts > 2017-08-26 03:42:30.842869 osd.8 osd.8 192.168.1.240:6810/22002 17 : cluster > [INF] 1.12 scrub starts > 2017-08-26 03:43:15.478366 osd.8 osd.8 192.168.1.240:6810/22002 18 : cluster > [INF] 1.12 scrub ok > 2017-08-26 03:47:17.962016 osd.0 osd.0 192.168.1.240:6814/15727 2 : cluster > [INF] 1.d4 deep-scrub ok > 2017-08-26 03:48:30.668792 osd.10 osd.10 192.168.1.240:6806/21564 11 : > cluster [INF] 1.1 scrub starts > 2017-08-26 03:49:05.879546 osd.10 osd.10 192.168.1.240:6806/21564 12 : > cluster [INF] 1.1 scrub ok > 2017-08-26 03:50:53.709500 osd.10 osd.10 192.168.1.240:6806/21564 13 : > cluster [INF] 1.9d scrub starts > 2017-08-26 03:52:13.278975 osd.10 osd.10 192.168.1.240:6806/21564 14 : > cluster [INF] 1.9d scrub ok > 2017-08-26 04:31:37.144944 osd.10 osd.10 192.168.1.240:6806/21564 15 : > cluster [INF] 1.82 scrub starts > 2017-08-26 04:32:35.917646 osd.10 osd.10 192.168.1.240:6806/21564 16 : > cluster [INF] 1.82 scrub ok > 2017-08-26 04:33:03.930435 osd.9 osd.9 192.168.1.240:6802/32411 36 : cluster > [INF] 1.f4 scrub starts > 2017-08-26 04:34:08.360134 osd.9 osd.9 192.168.1.240:6802/32411 37 : cluster > [INF] 1.f4 scrub ok > > > > FAIL ON NORMAL SCRUB > 2017-08-25 23:28:55.310602 osd.8 osd.8 192.168.1.240:6806/2820 29 : cluster > [INF] 6.3 deep-scrub starts > 2017-08-25 23:28:55.415144 osd.8 osd.8 192.168.1.240:6806/2820 30 : cluster > [INF] 6.3 deep-scrub ok > 2017-08-25 23:29:01.273979 osd.8 osd.8 192.168.1.240:6806/2820 31 : cluster > [INF] 1.d2 scrub starts > 2017-08-25 23:30:47.518484 osd.8 osd.8 192.168.1.240:6806/2820 32 : cluster > [INF] 1.d2 scrub ok > 2017-08-25 23:31:40.311045 osd.8 osd.8 192.168.1.240:6806/2820 33 : cluster > [INF] 1.6e scrub starts > 2017-08-25 23:32:22.150274 osd.8 osd.8 192.168.1.240:6806/2820 34 : cluster > [INF] 1.6e scrub ok > 2017-08-25 23:32:58.297062 osd.9 osd.9 192.168.1.240:6802/7091 32 : cluster > [INF] 1.d5 scrub starts > 2017-08-25 23:35:19.285841 osd.9 osd.9 192.168.1.240:6802/7091 33 : cluster > [INF] 1.d5 scrub ok > 2017-08-25 23:36:38.375447 osd.8 osd.8 192.168.1.240:6806/2820 35 : cluster > [INF] 1.3 scrub starts > 2017-08-25 23:37:25.012116 osd.8 osd.8 192.168.1.240:6806/2820 36 : cluster > [INF] 1.3 scrub ok > 2017-08-25 23:38:29.406144 osd.8 osd.8 192.168.1.240:6806/2820 37 : cluster > [INF] 1.45 scrub starts > 2017-08-25 23:38:53.020365 mon.0 mon.0 192.168.1.240:6789/0 831 : cluster > [INF] osd.9 failed (root=default,host=proxmox1) (connection refused reported > by osd.8) > 2017-08-25 23:38:53.166364 mon.0 mon.0 192.168.1.240:6789/0 832 : cluster > [WRN] Health check failed: 1 osds down (OSD_DOWN) > 2017-08-25 23:38:56.200767 mon.0 mon.0 192.168.1.240:6789/0 837 : cluster > [WRN] Health check failed: Degraded data redundancy: 100309/3786338 objects > degraded (2.649%), 14 pgs unclean, 14 pgs degraded (PG_DEGRADED) > 2017-08-25 23:38:58.155562 mon.0 mon.0 192.168.1.240:6789/0 838 : cluster > [WRN] Health check failed: Reduced data availability: 1 pg inactive > (PG_AVAILABILITY) > 2017-08-25 23:38:58.155601 mon.0 mon.0 192.168.1.240:6789/0 839 : cluster > [WRN] Health check update: Degraded data redundancy: 715775/3786338 objects > degraded (18.904%), 101 pgs unclean, 102 pgs degraded (PG_DEGRADED) > 2017-08-25 23:39:30.172451 mon.0 mon.0 192.168.1.240:6789/0 840 : cluster > [WRN] Health check update: Degraded data redundancy: 715775/3786338 objects > degraded (18.904%), 102 pgs unclean, 102 pgs degraded (PG_DEGRADED) > 2017-08-25 23:39:47.851497 mon.0 mon.0 192.168.1.240:6789/0 843 : cluster > [INF] Health check cleared: OSD_DOWN (was: 1 osds down) > 2017-08-25 23:39:47.864774 mon.0 mon.0 192.168.1.240:6789/0 844 : cluster > [INF] osd.9 192.168.1.240:6802/32411 boot > 2017-08-25 23:39:50.876761 mon.0 mon.0 192.168.1.240:6789/0 849 : cluster > [WRN] Health check update: Degraded data redundancy: 672540/3786338 objects > degraded (17.762%), 96 pgs unclean, 96 pgs degraded (PG_DEGRADED) > 2017-08-25 23:39:52.184954 mon.0 mon.0 192.168.1.240:6789/0 850 : cluster > [WRN] Health check update: Degraded data redundancy: 476349/3786338 objects > degraded (12.581%), 69 pgs unclean, 69 pgs degraded (PG_DEGRADED) > 2017-08-25 23:39:50.533429 osd.0 osd.0 192.168.1.240:6814/16223 13 : cluster > [INF] 1.80 scrub starts > 2017-08-25 23:39:55.056537 mon.0 mon.0 192.168.1.240:6789/0 851 : cluster > [INF] Health check cleared: PG_AVAILABILITY (was: Reduced data availability: > 1 pg inactive) > 2017-08-25 23:39:55.056574 mon.0 mon.0 192.168.1.240:6789/0 852 : cluster > [INF] Health check cleared: PG_DEGRADED (was: Degraded data redundancy: > 476349/3786338 objects degraded (12.581%), 69 pgs unclean, 69 pgs degraded) > 2017-08-25 23:39:55.056591 mon.0 mon.0 192.168.1.240:6789/0 853 : cluster > [INF] Cluster is now healthy > 2017-08-25 23:40:17.806395 osd.0 osd.0 192.168.1.240:6814/16223 14 : cluster > [INF] 1.80 scrub ok > 2017-08-25 23:40:19.775012 osd.9 osd.9 192.168.1.240:6802/32411 1 : cluster > [INF] 1.5a scrub starts > 2017-08-25 23:40:46.458847 osd.9 osd.9 192.168.1.240:6802/32411 2 : cluster > [INF] 1.5a scrub ok > 2017-08-25 23:40:53.807218 osd.9 osd.9 192.168.1.240:6802/32411 3 : cluster > [INF] 1.56 scrub starts > 2017-08-25 23:41:16.197304 osd.9 osd.9 192.168.1.240:6802/32411 4 : cluster > [INF] 1.56 scrub ok > 2017-08-25 23:41:24.814502 osd.9 osd.9 192.168.1.240:6802/32411 5 : cluster > [INF] 1.92 deep-scrub starts > 2017-08-25 23:51:35.881952 osd.9 osd.9 192.168.1.240:6802/32411 6 : cluster > [INF] 1.92 deep-scrub ok > 2017-08-25 23:52:54.476268 osd.10 osd.10 192.168.1.240:6810/4355 39 : cluster > [INF] 1.f2 scrub starts > 2017-08-25 23:53:21.208291 osd.10 osd.10 192.168.1.240:6810/4355 40 : cluster > [INF] 1.f2 scrub ok > 2017-08-25 23:53:47.475879 osd.10 osd.10 192.168.1.240:6810/4355 41 : cluster > [INF] 1.c8 deep-scrub starts > 2017-08-26 00:01:08.611371 osd.10 osd.10 192.168.1.240:6810/4355 42 : cluster > [INF] 1.c8 deep-scrub ok > 20 > > > root@proxmox1:/# ceph pg dump | egrep -v '^(0\.|1\.|2\.|3\.)' | egrep -v > '(^pool\ (0|1|2|3))' | column -t > dumped all > version 9678 > stamp 2017-08-27 01:27:53.321763 > last_osdmap_epoch 0 > last_pg_scan 0 > full_ratio 0 > nearfull_ratio 0 > PG_STAT OBJECTS MISSING_ON_PRIMARY DEGRADED MISPLACED > UNFOUND BYTES LOG DISK_LOG STATE STATE_STAMP VERSION > REPORTED UP UP_PRIMARY ACTING ACTING_PRIMARY > LAST_SCRUB SCRUB_STAMP LAST_DEEP_SCRUB DEEP_SCRUB_STAMP > 6.4 0 0 0 0 0 > 0 0 0 active+clean 2017-08-26 > 22:55:06.289033 0'0 4725:2848 [10,8] 10 [10,8] > 10 0'0 2017-08-26 22:55:06.288961 0'0 > 2017-08-20 23:32:51.270895 > 6.5 0 0 0 0 0 > 0 0 0 active+clean 2017-08-26 > 23:03:07.062129 0'0 4726:2101 [0,10] 0 [0,10] > 0 0'0 2017-08-26 01:50:04.421951 0'0 > 2017-08-22 14:26:19.915612 > 6.6 0 0 0 0 0 > 0 0 0 active+clean 2017-08-27 > 00:46:09.548107 0'0 4726:2344 [10,9] 10 [10,9] > 10 0'0 2017-08-27 00:46:09.548029 0'0 > 2017-08-24 13:08:56.447183 > 6.7 0 0 0 0 0 > 0 0 0 active+clean 2017-08-26 > 22:52:44.635393 0'0 4725:1481 [10,8] 10 [10,8] > 10 0'0 2017-08-25 22:02:26.297723 0'0 > 2017-08-23 15:55:58.299570 > 6.3 0 0 0 0 0 > 0 0 0 active+clean 2017-08-26 > 22:52:44.632667 0'0 4725:1971 [8,10] 8 [8,10] > 8 0'0 2017-08-25 23:28:55.415148 0'0 > 2017-08-25 23:28:55.415148 > 5.0 18661 0 0 0 0 > 12583538 1563 1563 active+clean 2017-08-26 > 22:03:03.809158 4652'1197298 4725:1382436 [10,9] 10 [10,9] > 10 4623'1197263 2017-08-26 19:49:19.819627 4270'1161119 > 2017-08-20 02:04:03.373813 > 6.2 0 0 0 0 0 > 0 0 0 active+clean 2017-08-26 > 22:52:45.677622 0'0 4725:1440 [9,8] 9 [9,8] > 9 0'0 2017-08-26 20:58:34.722865 0'0 > 2017-08-26 20:58:34.722865 > 5.1 18878 0 0 0 0 > 12583048 1573 1573 active+clean 2017-08-26 > 23:03:07.062298 4640'959478 4726:1131301 [0,8] 0 [0,8] > 0 4596'958844 2017-08-26 13:47:19.329350 4393'956123 > 2017-08-25 09:32:09.556396 > 6.1 0 0 0 0 0 > 0 0 0 active+clean 2017-08-26 > 22:52:44.736333 0'0 4725:1615 [8,9] 8 [8,9] > 8 0'0 2017-08-26 01:28:24.476136 0'0 > 2017-08-22 16:20:13.243273 > 5.2 18472 0 0 0 0 > 32462655 1592 1592 active+clean 2017-08-26 > 22:52:44.634997 4652'952265 4725:1174014 [10,8] 10 [10,8] > 10 4652'952265 2017-08-26 22:45:06.916647 4270'930889 > 2017-08-23 05:50:46.370503 > 6.0 0 0 0 0 0 > 0 0 0 active+clean 2017-08-26 > 23:03:07.061426 0'0 4726:2441 [10,0] 10 [10,0] > 10 0'0 2017-08-26 21:59:03.746276 0'0 > 2017-08-23 02:26:18.206975 > 5.3 18512 0 0 0 0 > 10928869 1519 1519 active+clean 2017-08-26 > 23:03:07.062484 4639'984496 4726:1199339 [0,8] 0 [0,8] > 0 4531'983789 2017-08-26 00:09:32.283691 4270'975964 > 2017-08-23 16:15:09.546043 > 5 74523 0 0 0 0 > 68558110 6247 6247 > 6 0 0 0 0 0 > 0 0 0 > 1 1821197 0 0 0 0 > 6962542387273 401319 401319 > sum 1895720 0 0 0 0 > 6962610945383 407566 407566 > OSD_STAT USED AVAIL TOTAL HB_PEERS > PG_SUM PRIMARY_PG_SUM > 8 4288G 3163G 7451G [0,9,10] 177 > 93 > 10 4240G 3211G 7451G [0,8,9] 175 > 93 > 0 1984G 809G 2794G [8,9,10] 82 > 37 > 9 2492G 1233G 3725G [0,8,10] 102 > 45 > sum 13005G 8418G 21424G > > > root@proxmox1:~# ceph versions > { > "mon": { > "ceph version 12.1.2 (cd7bc3b11cdbe6fa94324b7322fb2a4716a052a7) > luminous (rc)": 1 > }, > "mgr": { > "ceph version 12.1.2 (cd7bc3b11cdbe6fa94324b7322fb2a4716a052a7) > luminous (rc)": 1 > }, > "osd": { > "ceph version 12.1.2 (cd7bc3b11cdbe6fa94324b7322fb2a4716a052a7) > luminous (rc)": 4 > }, > "mds": { > "ceph version 12.1.2 (cd7bc3b11cdbe6fa94324b7322fb2a4716a052a7) > luminous (rc)": 1 > }, > "overall": { > "ceph version 12.1.2 (cd7bc3b11cdbe6fa94324b7322fb2a4716a052a7) > luminous (rc)": 7 > } > } > > Crush map: > # begin crush map > tunable choose_local_tries 0 > tunable choose_local_fallback_tries 0 > tunable choose_total_tries 50 > tunable chooseleaf_descend_once 1 > tunable chooseleaf_vary_r 1 > tunable chooseleaf_stable 1 > tunable straw_calc_version 1 > tunable allowed_bucket_algs 54 > > # devices > device 0 osd.0 class hdd > device 1 device1 > device 2 device2 > device 3 device3 > device 4 device4 > device 5 device5 > device 6 device6 > device 7 device7 > device 8 osd.8 class hdd > device 9 osd.9 class hdd > device 10 osd.10 class hdd > > # types > type 0 osd > type 1 host > type 2 chassis > type 3 rack > type 4 row > type 5 pdu > type 6 pod > type 7 room > type 8 datacenter > type 9 region > type 10 root > > # buckets > host proxmox1 { > id -2 # do not change unnecessarily > id -3 class hdd # do not change unnecessarily > # weight 20.922 > alg straw > hash 0 # rjenkins1 > item osd.10 weight 7.277 > item osd.9 weight 3.639 > item osd.0 weight 2.729 > item osd.8 weight 7.277 > } > root default { > id -1 # do not change unnecessarily > id -4 class hdd # do not change unnecessarily > # weight 20.922 > alg straw > hash 0 # rjenkins1 > item proxmox1 weight 20.922 > } > > # rules > rule replicated_ruleset { > id 0 > type replicated > min_size 1 > max_size 10 > step take default > step chooseleaf firstn 0 type osd > step emit > } > > # end crush map _______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com