Re:
https://docs.ceph.com/en/pacific/start/hardware-recommendations/
Anyone who has knowledge and command of the necessary leisure is invited to
look at the Hardware Recommendations page and make complaints to me about
what they see there.
In the next few months, I'll be putting together material
Hi Zac,
I have https://github.com/ceph/ceph/pull/43848 ready for merge.
-- dan
On Thu, Dec 2, 2021 at 9:58 AM John Zachary Dover wrote:
>
> Re:
> https://docs.ceph.com/en/pacific/start/hardware-recommendations/
>
> Anyone who has knowledge and command of the necessary leisure is invited to
> lo
Dear ceph-users,
We want to optimise our crush rules further and to test adjustments
without impact to the cluster, we use crushtool to show the mappings.
eg:
crushtool -i crushmap.16 --test --num-rep 4 --show-mappings --rule
0|tail -n 10
CRUSH rule 0 x 1014 [121,125,195,197]
CRUSH rule 0 x
Dan,
I'm retesting that PR because the arm64 makecheck is failing. inb4: Yes,
it's absurd that such a thing holds up a docs PR.
When that makecheck succeeds, I'll merge this forthwith.
Zac
On Thu, Dec 2, 2021 at 7:17 PM Dan van der Ster wrote:
> Hi Zac,
>
> I have https://github.com/ceph/ceph
Great, thanks!
Re: the other hdd/ssd info, I think we should remove text related to
"journals" -- that's FileStore jargon and not relevant for new
deployments.
On Thu, Dec 2, 2021 at 10:35 AM John Zachary Dover wrote:
>
> Dan,
>
> I'm retesting that PR because the arm64 makecheck is failing. inb
On 02/12/2021 10:20, Simon Oosthoek wrote:
Dear ceph-users,
We want to optimise our crush rules further and to test adjustments
without impact to the cluster, we use crushtool to show the mappings.
eg:
crushtool -i crushmap.16 --test --num-rep 4 --show-mappings --rule
0|tail -n 10
CRUSH ru
Hi Istvan,
Is that 1-1.2 billion 40KB rgw objects? If you are running EC 4+2 on a
42 OSD cluster with that many objects (and a heavily write oriented
workload), that could be hitting rocksdb pretty hard. FWIW, you might
want to look at the compaction stats provided in the OSD log. You can
Hi Eneko,
I don't think this is a memory H/W issue. This reminds me the following
thread:
https://lists.ceph.io/hyperkitty/list/ceph-users@ceph.io/thread/DEOBAUXQBUFL6HNBBNJ3LMQUCQC76HLY/
There was apparently a data corruption in RocksDB which poped up during
DB compaction only. There were n
Hi,
just from checking different lab clusters I can see that the output of
"mgrmap" has changed between versions. The "epoch" value is present in
L and N, but not in O anymore.
Zitat von Manuel Holtgrewe :
Dear all,
when calling `ceph -s --format=json-pretty`, there is no setting
`{"mgr
Am 29.11.21 um 18:23 schrieb Yuri Weinstein:
> Details of this release are summarized here:
>
> https://tracker.ceph.com/issues/53324
> Release Notes - https://github.com/ceph/ceph/pull/44131
>
> Seeking approvals for:
>
> rados - Neha
rados/cephadm looks good. Except for https://tracker.ceph.com/
Hello Konstantin,
cпасибо, thanks a lot. We're going to upgrade the cluster.
Best,
Malte
Am 02.12.21 um 07:43 schrieb Konstantin Shalygin:
Hi,
The fix was backported to 14.2.10
I suggest to upgrade your clusters to 14.2.22
k
Sent from my iPhone
On 1 Dec 2021, at 19:56, Malte Stroem wrote
On 12/2/21 7:14 AM, Szabo, Istvan (Agoda) wrote:
Hi Mark,
Thank you the quick answer.
I'd say the data distribution in the cluster is around 50kb (on 71TB is stored
1.51B objects).
I have 3 giant buckets it is important to mention (both properly pre-sharded
because the cluster is a 4 cluster
Good morning David,
Assuming you need/want to see the data about the other 31 OSDs,
14 is showing:
ID
CLASS
WEIGHT
REWEIGHT
SIZE
RAW USE
Regarding the drive: maybe. On one hand yes, it probably has lower
write endurance than a write oriented drive (optane for instance has
something like 30-60dwpd). On the other hand, there's been some
disagreement on this list regarding how much write endurance actually
matters if your workloa
On Thu, Dec 2, 2021 at 1:15 PM Yuri Weinstein wrote:
>
> Update:
>
> Neha is finalizing reviewing rados and upgrades (I restarted some tests FYI)
> Still need rgw approval - Casey, Matt?
rgw approved
>
> Thx
> YuriW
>
> On Thu, Dec 2, 2021 at 6:08 AM Sebastian Wagner wrote:
> >
> >
> > Am 29.11
On Mon, Nov 29, 2021 at 9:23 AM Yuri Weinstein wrote:
>
> Details of this release are summarized here:
>
> https://tracker.ceph.com/issues/53324
> Release Notes - https://github.com/ceph/ceph/pull/44131
>
> Seeking approvals for:
>
> rados - Neha
Approved, known issues:
- rados/perf failures, sho
Hi,
It would be good to have the full output. Does iostat show the backing
device performing I/O? Additionally, what does ceph -s show for cluster
state? Also, can you check the logs on that OSD, and see if anything looks
abnormal?
David
On Thu, Dec 2, 2021 at 1:20 PM Zach Heise (SSCC) wrote:
Can do
ceph -s:
cluster:
id:
health: HEALTH_OK
services:
mon: 4 daemons, quorum ceph05,ceph04,ceph01,ceph03 (age 4d)
mgr: ceph01.fblojp(active, since 25h), standbys: ceph03.futetp
mds: 1/1 daemons up, 1 standby
osd: 32 osds: 32 up (since 9d), 31 in (si
Experts :
Sorry to bother you , I can't start a new thread from website , have to
seek your help with email .
We met one question :
Cell version : 13.2.5-68-g53a67b5
(53a67b54fa57bcdfe2ce45c460e06adf62fe2eb2) mimic (stable)
Problem : MON can't startup , the cluster down .
19 matches
Mail list logo
