On Mon, Jun 4, 2018 at 12:37 PM, Reed Dier <reed.dier@xxxxxxxxxxx> wrote: > Hi Caspar, > > David is correct, in that the issue I was having with SSD OSD’s having NVMe > bluefs_db reporting as HDD creating an artificial throttle based on what > David was mentioning, a prevention to keep spinning rust from thrashing. Not > sure if the journal_rotational bit should be 1, but either way, it shouldn’t > affect you being hdd OSDs. Curious how these OSD’s were deployed, per the > below part of the message. > > Copying Alfredo, as I’m not sure if something changed with respect to > ceph-volume in 12.2.2 (when this originally happened) to 12.2.5 (I’m sure > plenty did), because I recently had an NVMe drive fail on me unexpectedly > (curse you Micron), and had to nuke and redo some SSD OSDs, and it was my > first time deploying with ceph-deploy after the ceph-disk deprecation. The > new OSD’s appear to report correctly wrt to the rotational status, where the > others did not. So that appears to be working correctly, just wanted to > provide some positive feedback there. Not sure if there’s an easy way to > change those metadata tags on the OSDs, so that I don’t have to inject the > args every time I need to reweight. Also feels like journal_rotational > wouldn’t be a thing in bluestore? ceph-volume doesn't do anything here with the device metadata, and is something that bluestore has as an internal mechanism. Unsure if there is anything one can do to change this on the OSD itself (vs. injecting args) > > ceph osd metadata |grep ‘id\|model\|type\|rotational’ > > "id": 63, > > "bluefs_db_model": "MTFDHAX1T2MCF-1AN1ZABYY", > > "bluefs_db_rotational": "0", > > "bluefs_db_type": "nvme", > > "bluefs_slow_model": "", > > "bluefs_slow_rotational": "0", > > "bluefs_slow_type": "ssd", > > "bluestore_bdev_model": "", > > "bluestore_bdev_rotational": "0", > > "bluestore_bdev_type": "ssd", > > "journal_rotational": "1", > > "rotational": "0" > > "id": 64, > > "bluefs_db_model": "INTEL SSDPED1D960GAY ", > > "bluefs_db_rotational": "0", > > "bluefs_db_type": "nvme", > > "bluefs_slow_model": "", > > "bluefs_slow_rotational": "0", > > "bluefs_slow_type": "ssd", > > "bluestore_bdev_model": "", > > "bluestore_bdev_rotational": "0", > > "bluestore_bdev_type": "ssd", > > "journal_rotational": "0", > > "rotational": "0" > > > osd.63 being one deployed using ceph-volume lvm in 12.2.2 and osd.64 being > redeployed using ceph-deploy in 12.2.5 using ceph-volume backend. > > Reed > > On Jun 4, 2018, at 8:16 AM, David Turner <drakonstein@xxxxxxxxx> wrote: > > I don't believe this really applies to you. The problem here was with an SSD > osd that was incorrectly labeled as an HDD osd by ceph. The fix was to > inject a sleep seeing if 0 for those osds to speed up recovery. The sleep is > needed to not kill hdds to avoid thrashing, but the bug was SSDs were being > incorrectly identified as HDD and SSDs don't have a problem with thrashing. > > You can try increasing osd_max_backfills. Watch your disk utilization as you > do this so that you don't accidentally kill your client io by setting that > too high, assuming that still needs priority. > > On Mon, Jun 4, 2018, 3:55 AM Caspar Smit <casparsmit@xxxxxxxxxxx> wrote: >> >> Hi Reed, >> >> "Changing/injecting osd_recovery_sleep_hdd into the running SSD OSD’s on >> bluestore opened the floodgates." >> >> What exactly did you change/inject here? >> >> We have a cluster with 10TB SATA HDD's which each have a 100GB SSD based >> block.db >> >> Looking at ceph osd metadata for each of those: >> >> "bluefs_db_model": "SAMSUNG MZ7KM960", >> "bluefs_db_rotational": "0", >> "bluefs_db_type": "ssd", >> "bluefs_slow_model": "ST10000NM0086-2A", >> "bluefs_slow_rotational": "1", >> "bluefs_slow_type": "hdd", >> "bluestore_bdev_rotational": "1", >> "bluestore_bdev_type": "hdd", >> "default_device_class": "hdd", >> "journal_rotational": "1", >> "osd_objectstore": "bluestore", >> "rotational": "1" >> >> Looks to me if i'm hitting the same issue, isn't it? >> >> ps. An upgrade of Ceph is planned in the near future but for now i would >> like to use the workaround if applicable to me. >> >> Thank you in advance. >> >> Kind regards, >> Caspar Smit >> >> 2018-02-26 23:22 GMT+01:00 Reed Dier <reed.dier@xxxxxxxxxxx>: >>> >>> Quick turn around, >>> >>> Changing/injecting osd_recovery_sleep_hdd into the running SSD OSD’s on >>> bluestore opened the floodgates. >>> >>> pool objects-ssd id 20 >>> recovery io 1512 MB/s, 21547 objects/s >>> >>> pool fs-metadata-ssd id 16 >>> recovery io 0 B/s, 6494 keys/s, 271 objects/s >>> client io 82325 B/s rd, 68146 B/s wr, 1 op/s rd, 0 op/s wr >>> >>> >>> Graph of performance jump. Extremely marked. >>> https://imgur.com/a/LZR9R >>> >>> So at least we now have the gun to go with the smoke. >>> >>> Thanks for the help and appreciate you pointing me in some directions >>> that I was able to use to figure out the issue. >>> >>> Adding to ceph.conf for future OSD conversions. >>> >>> Thanks, >>> >>> Reed >>> >>> >>> On Feb 26, 2018, at 4:12 PM, Reed Dier <reed.dier@xxxxxxxxxxx> wrote: >>> >>> For the record, I am not seeing a demonstrative fix by injecting the >>> value of 0 into the OSDs running. >>> >>> osd_recovery_sleep_hybrid = '0.000000' (not observed, change may require >>> restart) >>> >>> >>> If it does indeed need to be restarted, I will need to wait for the >>> current backfills to finish their process as restarting an OSD would bring >>> me under min_size. >>> >>> However, doing config show on the osd daemon appears to have taken the >>> value of 0. >>> >>> ceph daemon osd.24 config show | grep recovery_sleep >>> "osd_recovery_sleep": "0.000000", >>> "osd_recovery_sleep_hdd": "0.100000", >>> "osd_recovery_sleep_hybrid": "0.000000", >>> "osd_recovery_sleep_ssd": "0.000000", >>> >>> >>> I may take the restart as an opportunity to also move to 12.2.3 at the >>> same time, since it is not expected that that should affect this issue. >>> >>> I could also attempt to change osd_recovery_sleep_hdd as well, since >>> these are ssd osd’s, it shouldn’t make a difference, but its a free move. >>> >>> Thanks, >>> >>> Reed >>> >>> On Feb 26, 2018, at 3:42 PM, Gregory Farnum <gfarnum@xxxxxxxxxx> wrote: >>> >>> On Mon, Feb 26, 2018 at 12:26 PM Reed Dier <reed.dier@xxxxxxxxxxx> wrote: >>>> >>>> I will try to set the hybrid sleeps to 0 on the affected OSDs as an >>>> interim solution to getting the metadata configured correctly. >>> >>> >>> Yes, that's a good workaround as long as you don't have any actual hybrid >>> OSDs (or aren't worried about them sleeping...I'm not sure if that setting >>> came from experience or not). >>> >>>> >>>> >>>> For reference, here is the complete metadata for osd.24, bluestore SATA >>>> SSD with NVMe block.db. >>>> >>>> { >>>> "id": 24, >>>> "arch": "x86_64", >>>> "back_addr": "", >>>> "back_iface": "bond0", >>>> "bluefs": "1", >>>> "bluefs_db_access_mode": "blk", >>>> "bluefs_db_block_size": "4096", >>>> "bluefs_db_dev": "259:0", >>>> "bluefs_db_dev_node": "nvme0n1", >>>> "bluefs_db_driver": "KernelDevice", >>>> "bluefs_db_model": "INTEL SSDPEDMD400G4 ", >>>> "bluefs_db_partition_path": "/dev/nvme0n1p4", >>>> "bluefs_db_rotational": "0", >>>> "bluefs_db_serial": " ", >>>> "bluefs_db_size": "16000221184", >>>> "bluefs_db_type": "nvme", >>>> "bluefs_single_shared_device": "0", >>>> "bluefs_slow_access_mode": "blk", >>>> "bluefs_slow_block_size": "4096", >>>> "bluefs_slow_dev": "253:8", >>>> "bluefs_slow_dev_node": "dm-8", >>>> "bluefs_slow_driver": "KernelDevice", >>>> "bluefs_slow_model": "", >>>> "bluefs_slow_partition_path": "/dev/dm-8", >>>> "bluefs_slow_rotational": "0", >>>> "bluefs_slow_size": "1920378863616", >>>> "bluefs_slow_type": "ssd", >>>> "bluestore_bdev_access_mode": "blk", >>>> "bluestore_bdev_block_size": "4096", >>>> "bluestore_bdev_dev": "253:8", >>>> "bluestore_bdev_dev_node": "dm-8", >>>> "bluestore_bdev_driver": "KernelDevice", >>>> "bluestore_bdev_model": "", >>>> "bluestore_bdev_partition_path": "/dev/dm-8", >>>> "bluestore_bdev_rotational": "0", >>>> "bluestore_bdev_size": "1920378863616", >>>> "bluestore_bdev_type": "ssd", >>>> "ceph_version": "ceph version 12.2.2 >>>> (cf0baeeeeba3b47f9427c6c97e2144b094b7e5ba) luminous (stable)", >>>> "cpu": "Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz", >>>> "default_device_class": "ssd", >>>> "distro": "ubuntu", >>>> "distro_description": "Ubuntu 16.04.3 LTS", >>>> "distro_version": "16.04", >>>> "front_addr": "", >>>> "front_iface": "bond0", >>>> "hb_back_addr": "", >>>> "hb_front_addr": "", >>>> "hostname": “host00", >>>> "journal_rotational": "1", >>>> "kernel_description": "#29~16.04.2-Ubuntu SMP Tue Jan 9 22:00:44 >>>> UTC 2018", >>>> "kernel_version": "4.13.0-26-generic", >>>> "mem_swap_kb": "124999672", >>>> "mem_total_kb": "131914008", >>>> "os": "Linux", >>>> "osd_data": "/var/lib/ceph/osd/ceph-24", >>>> "osd_objectstore": "bluestore", >>>> "rotational": "0" >>>> } >>>> >>>> >>>> So it looks like it correctly guessed(?) the >>>> bluestore_bdev_type/default_device_class correctly (though it may have been >>>> an inherited value?), as did bluefs_db_type get set to nvme correctly. >>>> >>>> So I’m not sure why journal_rotational is still showing 1. >>>> Maybe something in the ceph-volume lvm piece that isn’t correctly >>>> setting that flag on OSD creation? >>>> Also seems like the journal_rotational field should have been deprecated >>>> in bluestore as bluefs_db_rotational should cover that, and if there were a >>>> WAL partition as well, I assume there would be something to the tune of >>>> bluefs_wal_rotational or something like that, and journal would never be >>>> used for bluestore? >>> >>> >>> Thanks to both of you for helping diagnose this issue. I created a ticket >>> and have a PR up to fix it: http://tracker.ceph.com/issues/23141, >>> https://github.com/ceph/ceph/pull/20602 >>> >>> Until that gets backported into another Luminous release you'll need to >>> do some kind of workaround though. :/ >>> -Greg >>> >>>> >>>> >>>> Appreciate the help. >>>> >>>> Thanks, >>>> Reed >>>> >>>> On Feb 26, 2018, at 1:28 PM, Gregory Farnum <gfarnum@xxxxxxxxxx> wrote: >>>> >>>> On Mon, Feb 26, 2018 at 11:21 AM Reed Dier <reed.dier@xxxxxxxxxxx> >>>> wrote: >>>>> >>>>> The ‘good perf’ that I reported below was the result of beginning 5 new >>>>> bluestore conversions which results in a leading edge of ‘good’ performance, >>>>> before trickling off. >>>>> >>>>> This performance lasted about 20 minutes, where it backfilled a small >>>>> set of PGs off of non-bluestore OSDs. >>>>> >>>>> Current performance is now hovering around: >>>>> >>>>> pool objects-ssd id 20 >>>>> recovery io 14285 kB/s, 202 objects/s >>>>> >>>>> pool fs-metadata-ssd id 16 >>>>> recovery io 0 B/s, 262 keys/s, 12 objects/s >>>>> client io 412 kB/s rd, 67593 B/s wr, 5 op/s rd, 0 op/s wr >>>>> >>>>> >>>>> What are you referencing when you talk about recovery ops per second? >>>>> >>>>> These are recovery ops as reported by ceph -s or via stats exported via >>>>> influx plugin in mgr, and via local collectd collection. >>>>> >>>>> Also, what are the values for osd_recovery_sleep_hdd and >>>>> osd_recovery_sleep_hybrid, and can you validate via "ceph osd metadata" that >>>>> your BlueStore SSD OSDs are correctly reporting both themselves and their >>>>> journals as non-rotational? >>>>> >>>>> >>>>> This yields more interesting results. >>>>> Pasting results for 3 sets of OSDs in this order >>>>> {0}hdd+nvme block.db >>>>> {24}ssd+nvme block.db >>>>> {59}ssd+nvme journal >>>>> >>>>> ceph osd metadata | grep 'id\|rotational' >>>>> "id": 0, >>>>> "bluefs_db_rotational": "0", >>>>> "bluefs_slow_rotational": "1", >>>>> "bluestore_bdev_rotational": "1", >>>>> "journal_rotational": "1", >>>>> "rotational": “1" >>>>> >>>>> "id": 24, >>>>> "bluefs_db_rotational": "0", >>>>> "bluefs_slow_rotational": "0", >>>>> "bluestore_bdev_rotational": "0", >>>>> "journal_rotational": "1", >>>>> "rotational": “0" >>>>> >>>>> "id": 59, >>>>> "journal_rotational": "0", >>>>> "rotational": “0" >>>>> >>>>> >>>>> I wonder if it matters/is correct to see "journal_rotational": “1” for >>>>> the bluestore OSD’s {0,24} with nvme block.db. >>>>> >>>>> Hope this may be helpful in determining the root cause. >>>> >>>> >>>> If you have an SSD main store and a hard drive ("rotational") journal, >>>> the OSD will insert recovery sleeps from the osd_recovery_sleep_hybrid >>>> config option. By default that is .025 (seconds). >>>> >>>> I believe you can override the setting (I'm not sure how), but you >>>> really want to correct that flag at the OS layer. Generally when we see this >>>> there's a RAID card or something between the solid-state device and the host >>>> which is lying about the state of the world. >>>> -Greg >>>> >>>>> >>>>> >>>>> If it helps, all of the OSD’s were originally deployed with >>>>> ceph-deploy, but are now being redone with ceph-volume locally on each host. >>>>> >>>>> Thanks, >>>>> >>>>> Reed >>>>> >>>>> On Feb 26, 2018, at 1:00 PM, Gregory Farnum <gfarnum@xxxxxxxxxx> wrote: >>>>> >>>>> On Mon, Feb 26, 2018 at 9:12 AM Reed Dier <reed.dier@xxxxxxxxxxx> >>>>> wrote: >>>>>> >>>>>> After my last round of backfills completed, I started 5 more bluestore >>>>>> conversions, which helped me recognize a very specific pattern of >>>>>> performance. >>>>>> >>>>>> pool objects-ssd id 20 >>>>>> recovery io 757 MB/s, 10845 objects/s >>>>>> >>>>>> pool fs-metadata-ssd id 16 >>>>>> recovery io 0 B/s, 36265 keys/s, 1633 objects/s >>>>>> client io 2544 kB/s rd, 36788 B/s wr, 1 op/s rd, 0 op/s wr >>>>>> >>>>>> >>>>>> The “non-throttled” backfills are only coming from filestore SSD >>>>>> OSD’s. >>>>>> When backfilling from bluestore SSD OSD’s, they appear to be throttled >>>>>> at the aforementioned <20 ops per OSD. >>>>> >>>>> >>>>> Wait, is that the current state? What are you referencing when you talk >>>>> about recovery ops per second? >>>>> >>>>> Also, what are the values for osd_recovery_sleep_hdd and >>>>> osd_recovery_sleep_hybrid, and can you validate via "ceph osd metadata" that >>>>> your BlueStore SSD OSDs are correctly reporting both themselves and their >>>>> journals as non-rotational? >>>>> -Greg >>>>> >>>>>> >>>>>> >>>>>> This would corroborate why the first batch of SSD’s I migrated to >>>>>> bluestore were all at “full” speed, as all of the OSD’s they were >>>>>> backfilling from were filestore based, compared to increasingly bluestore >>>>>> backfill targets, leading to increasingly long backfill times as I move from >>>>>> one host to the next. >>>>>> >>>>>> Looking at the recovery settings, the recovery_sleep and >>>>>> recovery_sleep_ssd values across bluestore or filestore OSDs are showing as >>>>>> 0 values, which means no sleep/throttle if I am reading everything >>>>>> correctly. >>>>>> >>>>>> sudo ceph daemon osd.73 config show | grep recovery >>>>>> "osd_allow_recovery_below_min_size": "true", >>>>>> "osd_debug_skip_full_check_in_recovery": "false", >>>>>> "osd_force_recovery_pg_log_entries_factor": "1.300000", >>>>>> "osd_min_recovery_priority": "0", >>>>>> "osd_recovery_cost": "20971520", >>>>>> "osd_recovery_delay_start": "0.000000", >>>>>> "osd_recovery_forget_lost_objects": "false", >>>>>> "osd_recovery_max_active": "35", >>>>>> "osd_recovery_max_chunk": "8388608", >>>>>> "osd_recovery_max_omap_entries_per_chunk": "64000", >>>>>> "osd_recovery_max_single_start": "1", >>>>>> "osd_recovery_op_priority": "3", >>>>>> "osd_recovery_op_warn_multiple": "16", >>>>>> "osd_recovery_priority": "5", >>>>>> "osd_recovery_retry_interval": "30.000000", >>>>>> "osd_recovery_sleep": "0.000000", >>>>>> "osd_recovery_sleep_hdd": "0.100000", >>>>>> "osd_recovery_sleep_hybrid": "0.025000", >>>>>> "osd_recovery_sleep_ssd": "0.000000", >>>>>> "osd_recovery_thread_suicide_timeout": "300", >>>>>> "osd_recovery_thread_timeout": "30", >>>>>> "osd_scrub_during_recovery": "false", >>>>>> >>>>>> >>>>>> As far as I know, the device class is configured correctly as far as I >>>>>> know, it all shows as ssd/hdd correctly in ceph osd tree. >>>>>> >>>>>> So hopefully this may be enough of a smoking gun to help narrow down >>>>>> where this may be stemming from. >>>>>> >>>>>> Thanks, >>>>>> >>>>>> Reed >>>>>> >>>>>> On Feb 23, 2018, at 10:04 AM, David Turner <drakonstein@xxxxxxxxx> >>>>>> wrote: >>>>>> >>>>>> Here is a [1] link to a ML thread tracking some slow backfilling on >>>>>> bluestore. It came down to the backfill sleep setting for them. Maybe it >>>>>> will help. >>>>>> >>>>>> [1] >>>>>> https://www.mail-archive.com/ceph-users@xxxxxxxxxxxxxx/msg40256.html >>>>>> >>>>>> On Fri, Feb 23, 2018 at 10:46 AM Reed Dier <reed.dier@xxxxxxxxxxx> >>>>>> wrote: >>>>>>> >>>>>>> Probably unrelated, but I do keep seeing this odd negative objects >>>>>>> degraded message on the fs-metadata pool: >>>>>>> >>>>>>> pool fs-metadata-ssd id 16 >>>>>>> -34/3 objects degraded (-1133.333%) >>>>>>> recovery io 0 B/s, 89 keys/s, 2 objects/s >>>>>>> client io 51289 B/s rd, 101 kB/s wr, 0 op/s rd, 0 op/s wr >>>>>>> >>>>>>> >>>>>>> Don’t mean to clutter the ML/thread, however it did seem odd, maybe >>>>>>> its a culprit? Maybe its some weird sampling interval issue thats been >>>>>>> solved in 12.2.3? >>>>>>> >>>>>>> Thanks, >>>>>>> >>>>>>> Reed >>>>>>> >>>>>>> >>>>>>> On Feb 23, 2018, at 8:26 AM, Reed Dier <reed.dier@xxxxxxxxxxx> wrote: >>>>>>> >>>>>>> Below is ceph -s >>>>>>> >>>>>>> cluster: >>>>>>> id: {id} >>>>>>> health: HEALTH_WARN >>>>>>> noout flag(s) set >>>>>>> 260610/1068004947 objects misplaced (0.024%) >>>>>>> Degraded data redundancy: 23157232/1068004947 objects >>>>>>> degraded (2.168%), 332 pgs unclean, 328 pgs degraded, 328 pgs undersized >>>>>>> >>>>>>> services: >>>>>>> mon: 3 daemons, quorum mon02,mon01,mon03 >>>>>>> mgr: mon03(active), standbys: mon02 >>>>>>> mds: cephfs-1/1/1 up {0=mon03=up:active}, 1 up:standby >>>>>>> osd: 74 osds: 74 up, 74 in; 332 remapped pgs >>>>>>> flags noout >>>>>>> >>>>>>> data: >>>>>>> pools: 5 pools, 5316 pgs >>>>>>> objects: 339M objects, 46627 GB >>>>>>> usage: 154 TB used, 108 TB / 262 TB avail >>>>>>> pgs: 23157232/1068004947 objects degraded (2.168%) >>>>>>> 260610/1068004947 objects misplaced (0.024%) >>>>>>> 4984 active+clean >>>>>>> 183 active+undersized+degraded+remapped+backfilling >>>>>>> 145 active+undersized+degraded+remapped+backfill_wait >>>>>>> 3 active+remapped+backfill_wait >>>>>>> 1 active+remapped+backfilling >>>>>>> >>>>>>> io: >>>>>>> client: 8428 kB/s rd, 47905 B/s wr, 130 op/s rd, 0 op/s wr >>>>>>> recovery: 37057 kB/s, 50 keys/s, 217 objects/s >>>>>>> >>>>>>> >>>>>>> Also the two pools on the SSDs, are the objects pool at 4096 PG, and >>>>>>> the fs-metadata pool at 32 PG. >>>>>>> >>>>>>> Are you sure the recovery is actually going slower, or are the >>>>>>> individual ops larger or more expensive? >>>>>>> >>>>>>> The objects should not vary wildly in size. >>>>>>> Even if they were differing in size, the SSDs are roughly idle in >>>>>>> their current state of backfilling when examining wait in iotop, or atop, or >>>>>>> sysstat/iostat. >>>>>>> >>>>>>> This compares to when I was fully saturating the SATA backplane with >>>>>>> over 1000MB/s of writes to multiple disks when the backfills were going >>>>>>> “full speed.” >>>>>>> >>>>>>> Here is a breakdown of recovery io by pool: >>>>>>> >>>>>>> pool objects-ssd id 20 >>>>>>> recovery io 6779 kB/s, 92 objects/s >>>>>>> client io 3071 kB/s rd, 50 op/s rd, 0 op/s wr >>>>>>> >>>>>>> pool fs-metadata-ssd id 16 >>>>>>> recovery io 0 B/s, 28 keys/s, 2 objects/s >>>>>>> client io 109 kB/s rd, 67455 B/s wr, 1 op/s rd, 0 op/s wr >>>>>>> >>>>>>> pool cephfs-hdd id 17 >>>>>>> recovery io 40542 kB/s, 158 objects/s >>>>>>> client io 10056 kB/s rd, 142 op/s rd, 0 op/s wr >>>>>>> >>>>>>> >>>>>>> So the 24 HDD’s are outperforming the 50 SSD’s for recovery and >>>>>>> client traffic at the moment, which seems conspicuous to me. >>>>>>> >>>>>>> Most of the OSD’s with recovery ops to the SSDs are reporting 8-12 >>>>>>> ops, with one OSD occasionally spiking up to 300-500 for a few minutes. >>>>>>> Stats being pulled by both local CollectD instances on each node, as well as >>>>>>> the Influx plugin in MGR as we evaluate that against collectd. >>>>>>> >>>>>>> Thanks, >>>>>>> >>>>>>> Reed >>>>>>> >>>>>>> >>>>>>> On Feb 22, 2018, at 6:21 PM, Gregory Farnum <gfarnum@xxxxxxxxxx> >>>>>>> wrote: >>>>>>> >>>>>>> What's the output of "ceph -s" while this is happening? >>>>>>> >>>>>>> Is there some identifiable difference between these two states, like >>>>>>> you get a lot of throughput on the data pools but then metadata recovery is >>>>>>> slower? >>>>>>> >>>>>>> Are you sure the recovery is actually going slower, or are the >>>>>>> individual ops larger or more expensive? >>>>>>> >>>>>>> My WAG is that recovering the metadata pool, composed mostly of >>>>>>> directories stored in omap objects, is going much slower for some reason. >>>>>>> You can adjust the cost of those individual ops some by changing >>>>>>> osd_recovery_max_omap_entries_per_chunk (default: 8096), but I'm not sure >>>>>>> which way you want to go or indeed if this has anything to do with the >>>>>>> problem you're seeing. (eg, it could be that reading out the omaps is >>>>>>> expensive, so you can get higher recovery op numbers by turning down the >>>>>>> number of entries per request, but not actually see faster backfilling >>>>>>> because you have to issue more requests.) >>>>>>> -Greg >>>>>>> >>>>>>> On Wed, Feb 21, 2018 at 2:57 PM Reed Dier <reed.dier@xxxxxxxxxxx> >>>>>>> wrote: >>>>>>>> >>>>>>>> Hi all, >>>>>>>> >>>>>>>> I am running into an odd situation that I cannot easily explain. >>>>>>>> I am currently in the midst of destroy and rebuild of OSDs from >>>>>>>> filestore to bluestore. >>>>>>>> With my HDDs, I am seeing expected behavior, but with my SSDs I am >>>>>>>> seeing unexpected behavior. The HDDs and SSDs are set in crush accordingly. >>>>>>>> >>>>>>>> My path to replacing the OSDs is to set the noout, norecover, >>>>>>>> norebalance flag, destroy the OSD, create the OSD back, (iterate n times, >>>>>>>> all within a single failure domain), unset the flags, and let it go. It >>>>>>>> finishes, rinse, repeat. >>>>>>>> >>>>>>>> For the SSD OSDs, they are SATA SSDs (Samsung SM863a) , 10 to a >>>>>>>> node, with 2 NVMe drives (Intel P3700), 5 SATA SSDs to 1 NVMe drive, 16G >>>>>>>> partitions for block.db (previously filestore journals). >>>>>>>> 2x10GbE networking between the nodes. SATA backplane caps out at >>>>>>>> around 10 Gb/s as its 2x 6 Gb/s controllers. Luminous 12.2.2. >>>>>>>> >>>>>>>> When the flags are unset, recovery starts and I see a very large >>>>>>>> rush of traffic, however, after the first machine completed, the performance >>>>>>>> tapered off at a rapid pace and trickles. Comparatively, I’m getting 100-200 >>>>>>>> recovery ops on 3 HDDs, backfilling from 21 other HDDs, where as I’m getting >>>>>>>> 150-250 recovery ops on 5 SSDs, backfilling from 40 other SSDs. Every once >>>>>>>> in a while I will see a spike up to 500, 1000, or even 2000 ops on the SSDs, >>>>>>>> often a few hundred recovery ops from one OSD, and 8-15 ops from the others >>>>>>>> that are backfilling. >>>>>>>> >>>>>>>> This is a far cry from the more than 15-30k recovery ops that it >>>>>>>> started off recovering with 1-3k recovery ops from a single OSD to the >>>>>>>> backfilling OSD(s). And an even farther cry from the >15k recovery ops I was >>>>>>>> sustaining for over an hour or more before. I was able to rebuild a 1.9T SSD >>>>>>>> (1.1T used) in a little under an hour, and I could do about 5 at a time and >>>>>>>> still keep it at roughly an hour to backfill all of them, but then I hit a >>>>>>>> roadblock after the first machine, when I tried to do 10 at a time (single >>>>>>>> machine). I am now still experiencing the same thing on the third node, >>>>>>>> while doing 5 OSDs at a time. >>>>>>>> >>>>>>>> The pools associated with these SSDs are cephfs-metadata, as well as >>>>>>>> a pure rados object pool we use for our own internal applications. Both are >>>>>>>> size=3, min_size=2. >>>>>>>> >>>>>>>> It appears I am not the first to run into this, but it looks like >>>>>>>> there was no resolution: >>>>>>>> https://www.spinics.net/lists/ceph-users/msg41493.html >>>>>>>> >>>>>>>> Recovery parameters for the OSDs match what was in the previous >>>>>>>> thread, sans the osd conf block listed. And current osd_max_backfills = 30 >>>>>>>> and osd_recovery_max_active = 35. Very little activity on the OSDs during >>>>>>>> this period, so should not be any contention for iops on the SSDs. >>>>>>>> >>>>>>>> The only oddity that I can attribute to things is that we had a few >>>>>>>> periods of time where the disk load on one of the mons was high enough to >>>>>>>> cause the mon to drop out of quorum for a brief amount of time, a few times. >>>>>>>> But I wouldn’t think backfills would just get throttled due to mons >>>>>>>> flapping. >>>>>>>> >>>>>>>> Hopefully someone has some experience or can steer me in a path to >>>>>>>> improve the performance of the backfills so that I’m not stuck in backfill >>>>>>>> purgatory longer than I need to be. >>>>>>>> >>>>>>>> Linking an imgur album with some screen grabs of the recovery ops >>>>>>>> over time for the first machine, versus the second and third machines to >>>>>>>> demonstrate the delta between them. >>>>>>>> https://imgur.com/a/OJw4b >>>>>>>> >>>>>>>> Also including a ceph osd df of the SSDs, highlighted in red are the >>>>>>>> OSDs currently backfilling. Could this possibly be PG overdose? I don’t ever >>>>>>>> run into ‘stuck activating’ PGs, its just painfully slow backfills, like >>>>>>>> they are being throttled by ceph, that are causing me to worry. Drives >>>>>>>> aren’t worn, <30 P/E cycles on the drives, so plenty of life left in them. >>>>>>>> >>>>>>>> Thanks, >>>>>>>> Reed >>>>>>>> >>>>>>>> $ ceph osd df >>>>>>>> ID CLASS WEIGHT REWEIGHT SIZE USE AVAIL %USE VAR PGS >>>>>>>> 24 ssd 1.76109 1.00000 1803G 1094G 708G 60.69 1.08 260 >>>>>>>> 25 ssd 1.76109 1.00000 1803G 1136G 667G 63.01 1.12 271 >>>>>>>> 26 ssd 1.76109 1.00000 1803G 1018G 785G 56.46 1.01 243 >>>>>>>> 27 ssd 1.76109 1.00000 1803G 1065G 737G 59.10 1.05 253 >>>>>>>> 28 ssd 1.76109 1.00000 1803G 1026G 776G 56.94 1.02 245 >>>>>>>> 29 ssd 1.76109 1.00000 1803G 1132G 671G 62.79 1.12 270 >>>>>>>> 30 ssd 1.76109 1.00000 1803G 944G 859G 52.35 0.93 224 >>>>>>>> 31 ssd 1.76109 1.00000 1803G 1061G 742G 58.85 1.05 252 >>>>>>>> 32 ssd 1.76109 1.00000 1803G 1003G 799G 55.67 0.99 239 >>>>>>>> 33 ssd 1.76109 1.00000 1803G 1049G 753G 58.20 1.04 250 >>>>>>>> 34 ssd 1.76109 1.00000 1803G 1086G 717G 60.23 1.07 257 >>>>>>>> 35 ssd 1.76109 1.00000 1803G 978G 824G 54.26 0.97 232 >>>>>>>> 36 ssd 1.76109 1.00000 1803G 1057G 745G 58.64 1.05 252 >>>>>>>> 37 ssd 1.76109 1.00000 1803G 1025G 777G 56.88 1.01 244 >>>>>>>> 38 ssd 1.76109 1.00000 1803G 1047G 756G 58.06 1.04 250 >>>>>>>> 39 ssd 1.76109 1.00000 1803G 1031G 771G 57.20 1.02 246 >>>>>>>> 40 ssd 1.76109 1.00000 1803G 1029G 774G 57.07 1.02 245 >>>>>>>> 41 ssd 1.76109 1.00000 1803G 1033G 770G 57.28 1.02 245 >>>>>>>> 42 ssd 1.76109 1.00000 1803G 993G 809G 55.10 0.98 236 >>>>>>>> 43 ssd 1.76109 1.00000 1803G 1072G 731G 59.45 1.06 256 >>>>>>>> 44 ssd 1.76109 1.00000 1803G 1039G 763G 57.64 1.03 248 >>>>>>>> 45 ssd 1.76109 1.00000 1803G 992G 810G 55.06 0.98 236 >>>>>>>> 46 ssd 1.76109 1.00000 1803G 1068G 735G 59.23 1.06 254 >>>>>>>> 47 ssd 1.76109 1.00000 1803G 1020G 783G 56.57 1.01 242 >>>>>>>> 48 ssd 1.76109 1.00000 1803G 945G 857G 52.44 0.94 225 >>>>>>>> 49 ssd 1.76109 1.00000 1803G 649G 1154G 36.01 0.64 139 >>>>>>>> 50 ssd 1.76109 1.00000 1803G 426G 1377G 23.64 0.42 83 >>>>>>>> 51 ssd 1.76109 1.00000 1803G 610G 1193G 33.84 0.60 131 >>>>>>>> 52 ssd 1.76109 1.00000 1803G 558G 1244G 30.98 0.55 118 >>>>>>>> 53 ssd 1.76109 1.00000 1803G 731G 1072G 40.54 0.72 161 >>>>>>>> 54 ssd 1.74599 1.00000 1787G 859G 928G 48.06 0.86 229 >>>>>>>> 55 ssd 1.74599 1.00000 1787G 942G 844G 52.74 0.94 252 >>>>>>>> 56 ssd 1.74599 1.00000 1787G 928G 859G 51.94 0.93 246 >>>>>>>> 57 ssd 1.74599 1.00000 1787G 1039G 748G 58.15 1.04 277 >>>>>>>> 58 ssd 1.74599 1.00000 1787G 963G 824G 53.87 0.96 255 >>>>>>>> 59 ssd 1.74599 1.00000 1787G 909G 877G 50.89 0.91 241 >>>>>>>> 60 ssd 1.74599 1.00000 1787G 1039G 748G 58.15 1.04 277 >>>>>>>> 61 ssd 1.74599 1.00000 1787G 892G 895G 49.91 0.89 238 >>>>>>>> 62 ssd 1.74599 1.00000 1787G 927G 859G 51.90 0.93 245 >>>>>>>> 63 ssd 1.74599 1.00000 1787G 864G 922G 48.39 0.86 229 >>>>>>>> 64 ssd 1.74599 1.00000 1787G 968G 819G 54.16 0.97 257 >>>>>>>> 65 ssd 1.74599 1.00000 1787G 892G 894G 49.93 0.89 237 >>>>>>>> 66 ssd 1.74599 1.00000 1787G 951G 836G 53.23 0.95 252 >>>>>>>> 67 ssd 1.74599 1.00000 1787G 878G 908G 49.16 0.88 232 >>>>>>>> 68 ssd 1.74599 1.00000 1787G 899G 888G 50.29 0.90 238 >>>>>>>> 69 ssd 1.74599 1.00000 1787G 948G 839G 53.04 0.95 252 >>>>>>>> 70 ssd 1.74599 1.00000 1787G 914G 873G 51.15 0.91 246 >>>>>>>> 71 ssd 1.74599 1.00000 1787G 1004G 782G 56.21 1.00 266 >>>>>>>> 72 ssd 1.74599 1.00000 1787G 812G 974G 45.47 0.81 216 >>>>>>>> 73 ssd 1.74599 1.00000 1787G 932G 855G 52.15 0.93 247 >>>>>>>> >>>>>>>> _______________________________________________ >>>>>>>> ceph-users mailing list >>>>>>>> ceph-users@xxxxxxxxxxxxxx >>>>>>>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >>>>>>> >>>>>>> >>>>>>> >>>>>>> _______________________________________________ >>>>>>> ceph-users mailing list >>>>>>> ceph-users@xxxxxxxxxxxxxx >>>>>>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >>>>>> >>>>>> >>>>>> _______________________________________________ >>>>>> ceph-users mailing list >>>>>> ceph-users@xxxxxxxxxxxxxx >>>>>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >>>>> >>>>> >>>> >>> >>> >>> >>> _______________________________________________ >>> ceph-users mailing list >>> ceph-users@xxxxxxxxxxxxxx >>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >>> >> >> _______________________________________________ >> ceph-users mailing list >> ceph-users@xxxxxxxxxxxxxx >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |