[ceph-users] Re: Ceph v15.2.14 - Dirty Object issue

Did you try options from cache-sizing or other-tunables ? - Dhairya On Fri, Mar 3, 2023 at 5:39 AM wrote: > Hi, we have a cluster with this ceph df > > --- RAW STORAGE

[ceph-users] Re: Theory about min_size and its implications

> but what is the problem with only one active PG? > someone pointed out "split brain" but I am unsure about this. I think Paxos will ensure that split-brain doesn’t happen by virtue of needing >50% of the mon quorum to be up. > i think what happens in the worst case is this: > only 1 PG is

[ceph-users] Ceph v15.2.14 - Dirty Object issue

Hi, we have a cluster with this ceph df --- RAW STORAGE --- CLASS SIZE AVAILUSED RAW USED %RAW USED hdd240 GiB 205 GiB 29 GiB35 GiB 14.43 hddvm 1.6 TiB 1.2 TiB 277 GiB 332 GiB 20.73 TOTAL 1.8 TiB 1.4 TiB 305 GiB 366 GiB 19.91 --- POOLS --- POOL

[ceph-users] Theory about min_size and its implications

Hi! it is unclear for us what min_size means besides what it does. i hope someone can clear this up :) scenario: size is 3 and min_size is 2 2 rooms with 100 OSDs each and this crush rule "op": "take", "item": -10, "item_name": "default"

[ceph-users] Re: ceph 16.2.10 - misplaced object after changing crush map only setting hdd class

Hi, and thanks for the answer. I install the 16.2.10. I do not check for the shadow's one before doing the crush map modification. So it is expected in order that it sees like a new route for the algorithm to calculate position of pgs and datas ? Best regards.

[ceph-users] Re: Very slow backfilling

I see autoscale_mode on all pools and I'm guessing this is your largest pool bkp365-ncy.rgw.buckets.data, with 32 pg. I would definitely turn off autoscale and increase pg_num/pgp_num. Someone with more experience than I can chime in, but I would think something like 2048 would be much better. On

[ceph-users] Re: Interruption of rebalancing

Thanks everyone for the help. I set noout on the cluster, rebooted the node and it came back to rebalancing/remapping where it left off. CEPH is fantastic. > >From: Jeffrey Turmelle >> > >Sent: March 1, 2023 2:47 PM > >To: ceph-users@ceph.io

[ceph-users] Re: Interruption of rebalancing

Hey Jeff, As long as you set the maintenance flags (noout/norebalance) you should be good to take the node down with a reboot Regards, Bailey >From: Jeffrey Turmelle >Sent: March 1, 2023 2:47 PM >To: ceph-users@ceph.io >Subject: [ceph-users] Interruption of rebalancing > >I

[ceph-users] Re: Very slow backfilling

root@hbgt-ceph1-mon3:/# ceph osd df ID CLASS WEIGHTREWEIGHT SIZE RAW USE DATA OMAP META AVAIL%USE VAR PGS STATUS 1hdd 17.34140 1.0 17 TiB 6.3 TiB 5.3 TiB 11 KiB 23 GiB 11 TiB 36.17 1.39 17 up 3hdd 17.34140 1.0 17 TiB

[ceph-users] Re: Very slow backfilling

Forgot to do a reply all. What does ceph osd df ceph osd dump | grep pool return? Are you using auto scaling? 289pg with 272tb of data and 60 osds, that seems like 3-4 pg per osd at almost 1TB each. Unless I'm thinking of this wrong. On Thu, Mar 2, 2023, 17:37 Joffrey wrote: > My Ceph

[ceph-users] Re: Very slow backfilling

My Ceph Version is 17.2.5 and all configuration about osd_scrub* are defaults. I tried some updates on osd-max-backfills but no change. I have many HDD with NVME for db and all are connected in a 25G network. Yes, it's the same PG since 4 days. I got a failure on a HDD and get many days of

[ceph-users] Re: Interruption of rebalancing

Den tors 2 mars 2023 kl 08:09 skrev Eugen Block : > if your failure domain is "host" and you have enough redundancy (e.g. > replicated size 3 or proper erasure-code profiles and rulesets) you > should be able to reboot without any issue. Depending on how long the > reboot would take, you could set

[ceph-users] Very slow backfilling

Hi, I have many 'not {deep-}scrubbed in time' and a1 PG remapped+backfilling and I don't understand why this backfilling is taking so long. root@hbgt-ceph1-mon3:/# ceph -s cluster: id: c300532c-51fa-11ec-9a41-0050569c3b55 health: HEALTH_WARN 15 pgs not deep-scrubbed in