Here it is: https://tracker.ceph.com/issues/45439
The balancer problems we saw might be a consequence of the mgr falling
behind, since even after disabling the balancer, the mgr stays
overloaded. I ended up removing all upmaps and leaving the balancer
disabled since it further increases the os
On Fri, May 8, 2020 at 12:10 PM Lomayani S. Laizer wrote:
>
> Hello,
> On my side at point of vm crash these are logs below. At the moment my debug
> is at 10 value. I will rise to 20 for full debug. these crashes are random
> and so far happens on very busy vms. Downgrading clients in host to N
Hello,
On my side at point of vm crash these are logs below. At the moment my
debug is at 10 value. I will rise to 20 for full debug. these crashes are
random and so far happens on very busy vms. Downgrading clients in host to
Nautilus these crashes disappear
Qemu is not shutting down in general b
I have a seemingly strange situation. I have three OSDs that I created with
Ceph Octopus using the `ceph orch daemon add :device` command. All three
were added and everything was great. Then I rebooted the host. Now the daemon’s
won’t start via Docker. When I attempt to run the `docker` command
Could you create a tracker for this and attach an osdmap as well as
some recent balancer output (perhaps at a higher debug level if
possible)?
There are some improvements awaiting backport to nautilus for the
C++/python interface just FYI [0]
You might also look at gathering output using somethin
On Fri, May 8, 2020 at 3:42 AM Erwin Lubbers wrote:
>
> Hi,
>
> Did anyone found a way to resolve the problem? I'm seeing the same on a clean
> Octopus Ceph installation on Ubuntu 18 with an Octopus compiled KVM server
> running on CentOS 7.8. The KVM machine shows:
>
> [ 7682.233684] fn-radoscl
On Wed, Apr 29, 2020 at 5:56 AM Kenneth Waegeman
wrote:
> I read in some release notes it is recommended to have your default data
> pool replicated and use erasure coded pools as additional pools through
> layouts. We have still a cephfs with +-1PB usage with a EC default pool.
> Is there a way t
ceph.conf still *works*, though, for those with existing systems built to
manage it?
While the centralized config is very handy, I’d love to find a way to tie it
into external revision control, so that settings could continue to be managed
in eg. git and applied by automation.
> On Apr 30, 202
Hi list,
I'm in the middle of an OpenStack migration (obviously Ceph backed) and
stumble into some huge virtual machines.
To ensure downtime is kept to a minimum, I'm thinking of using Ceph's
snapshot features using rbd export-diff and import-diff.
However, is it safe (or even supported) to do t
Hi everyone,
After some investigation, it looks like on our large cluster, ceph-mgr
is not able to keep up with the status updates from about 3500 OSDs. By
default OSDs send updates to ceph-mgr every 5 seconds, which, in our
case, turns to about 700 messages/s to ceph-mgr. It looks from gdb
Lin, Igor, Herve,
With the help of the information all of you have provided I have now
reviewed the massive amount of information that is available for just
one of my OSDs. (All 24 were configured with Ceph-Ansible, so all
should be configured the same.)
Like Lin's example below, I see that
Igor,
Thank you for pointing this section out to me. The information there is
useful, but I would comment for John Dover's interest that the section
was hard to find. I'd been on that page several times before, but
became overwhelmed by the time I got that far down. Maybe the 'What do
I ha
Hi,
Did anyone found a way to resolve the problem? I'm seeing the same on a clean
Octopus Ceph installation on Ubuntu 18 with an Octopus compiled KVM server
running on CentOS 7.8. The KVM machine shows:
[ 7682.233684] fn-radosclient[6060]: segfault at 2b19 ip 7f8165cc0a50 sp
7f81397f64
On Thu, May 7, 2020 at 9:41 AM Robert LeBlanc wrote:
> On Thu, May 7, 2020 at 6:22 AM Yan, Zheng wrote:
>
>> On Thu, May 7, 2020 at 1:27 AM Patrick Donnelly
>> wrote:
>> >
>> > Hello Robert,
>> >
>> > On Mon, Mar 9, 2020 at 7:55 PM Robert Ruge
>> wrote:
>> > > For a 1.1PB raw cephfs system cur
On Thu, May 7, 2020 at 6:22 AM Yan, Zheng wrote:
> On Thu, May 7, 2020 at 1:27 AM Patrick Donnelly
> wrote:
> >
> > Hello Robert,
> >
> > On Mon, Mar 9, 2020 at 7:55 PM Robert Ruge
> wrote:
> > > For a 1.1PB raw cephfs system currently storing 191TB of data and 390
> million objects (mostly sma
On Wed, May 6, 2020 at 2:45 PM Patrick Donnelly wrote:
> On Wed, Mar 11, 2020 at 10:41 PM Robert LeBlanc
> wrote:
> >
> > This is the second time this happened in a couple of weeks. The MDS locks
> > up and the stand-by can't take over so the Montiors black list them. I
> try
> > to unblack list
As a follow up, our MDS was locking up under load so I went ahead and tried
it. It seemed that some directories were getting bounced around the MDS
servers and load would transition from one to the other. Initially my guess
was that some of these old clients were sending all requests to one MDS
ser
Thanks for the suggestion!
- Original Message -
> From: "Szabo, Istvan (Agoda)"
> To: "Andrei Mikhailovsky" , "ceph-users"
>
> Sent: Thursday, 7 May, 2020 03:48:04
> Subject: RE: rados buckets copy
> Hi,
>
> You might try s3 browser app, it is quite easy to navigate and copy between
>
Hi XuYun and Martin,
I checked that already. The OSDs in question have 8GB memory limit and the RAM
of the servers is about 50% used. It could be memory fragmentation, which used
to be a problem before bitmap allocator. However, my OSDs are configured to use
bitmap, at least that is what they c
We had got some ping back/front problems after upgrading from filestore to
bluestore. It turned out to be related to insufficient memory/swap usage.
> 2020年5月6日 下午10:08，Frank Schilder 写道：
>
> To answer some of my own questions:
>
> 1) Setting
>
> ceph osd set noout
> ceph osd set nodown
> c
On Wed, May 6, 2020 at 3:29 AM Katarzyna Myrek wrote:
>
> Hi
>
> I have a few questions about bucket versioning.
>
> in the output of command "*radosgw-admin bucket stats --bucket=XXX"* there
> is info about versions:
>
> "ver": "0#521391,1#516042,2#518098,3#517681,4#518423",
> "master_ver
On Thu, May 7, 2020 at 1:27 AM Patrick Donnelly wrote:
>
> Hello Robert,
>
> On Mon, Mar 9, 2020 at 7:55 PM Robert Ruge wrote:
> > For a 1.1PB raw cephfs system currently storing 191TB of data and 390
> > million objects (mostly small Python, ML training files etc.) how many MDS
> > servers sho
Hi Kenneth,
I did a migration from 2 to 3 pool layout recently. The only way to do this
within ceph at the moment seems to be to create a second ceph fs with the new
layout, rsync everything over and delete the old ceph fs. I had enough spare
capacity and room for the extra PGs to do that.
Thi
Hello XuYun,
In my experience, I would always disable swap, it won't do any good.
--
Martin Verges
Managing director
Mobile: +49 174 9335695
E-Mail: martin.ver...@croit.io
Chat: https://t.me/MartinVerges
croit GmbH, Freseniusstr. 31h, 81247 Munich
CEO: Martin Verges - VAT-ID: DE310638492
Com. r
Hello,
I saw there was a clone_range function in librados earlier. But it removed in
version 12 I beleive. I need excatly that function to avoid unnecessary network
traffic.
I need to combine many small objects into one. So clone range would be really
useful for me. I can read from an object
Someone an idea /experience if this is possible ? :)
On 29/04/2020 14:56, Kenneth Waegeman wrote:
Hi all,
I read in some release notes it is recommended to have your default
data pool replicated and use erasure coded pools as additional pools
through layouts. We have still a cephfs with +-1PB
Something like:
rbd perf image iostat
-Original Message-
From: Void Star Nill [mailto:void.star.n...@gmail.com]
Sent: 07 May 2020 04:18
To: ceph-users
Subject: [ceph-users] per rbd performance counters
Hello,
Is there a way to get read/write I/O statistics for each rbd device for
eac
27 matches
Mail list logo
