Hi,
I have run tests with v0.50 and see the same symptom.
However: I have also the impression that the problem is related
to the frequency at which requests arrive at the OSD.
I have run tests with rbd kernel client using 126 KByte and
512 KByte size for write requests. In the 2nd case, the
Hi,
Almost always one or more osd dies when doing overlapped recovery -
e.g. add new crushmap and remove some newly added osds from cluster
some minutes later during remap or inject two slightly different
crushmaps after a short time(surely preserving at least one of
replicas online). Seems that
On 09/04/2012 07:04 AM, Skowron Sławomir wrote:
Is there any way now, to inject new configuration change, without restarting
daemons ??
Yes, you can use the injectargs command.
$ ceph osd tell 0 injectargs '--debug-osd 20'
What do you want to change? Not everything can be changed while the
Ok, thanks.
Number of workers used for recover, or numer of disk threads.
-Original Message-
From: Wido den Hollander [mailto:w...@widodh.nl]
Sent: Tuesday, September 04, 2012 10:18 AM
To: Skowron Sławomir
Cc: ceph-devel@vger.kernel.org
Subject: Re: Inject configuration change into
On 09/04/2012 10:30 AM, Skowron Sławomir wrote:
Ok, thanks.
Number of workers used for recover, or numer of disk threads.
I think those can be changed while the OSD is running. You could always
give it a try.
Wido
-Original Message-
From: Wido den Hollander
Yes i will try :) thanks.
-Original Message-
From: Wido den Hollander [mailto:w...@widodh.nl]
Sent: Tuesday, September 04, 2012 11:36 AM
To: Skowron Sławomir
Cc: ceph-devel@vger.kernel.org
Subject: Re: Inject configuration change into cluster
On 09/04/2012 10:30 AM, Skowron Sławomir
Valgrind returns nothing.
valgrind --tool=massif --log-file=ceph_mon_valgrind ceph-mon -i 0 log.txt
==30491== Massif, a heap profiler
==30491== Copyright (C) 2003-2011, and GNU GPL'd, by Nicholas Nethercote
==30491== Using Valgrind-3.7.0 and LibVEX; rerun with -h for copyright info
==30491==
On Tue, 4 Sep 2012, Andrey Korolyov wrote:
Hi,
Almost always one or more osd dies when doing overlapped recovery -
e.g. add new crushmap and remove some newly added osds from cluster
some minutes later during remap or inject two slightly different
crushmaps after a short time(surely
On Tue, 4 Sep 2012, Wido den Hollander wrote:
On 09/04/2012 10:30 AM, Skowron S?awomir wrote:
Ok, thanks.
Number of workers used for recover, or numer of disk threads.
I think those can be changed while the OSD is running. You could always give
it a try.
The thread pool sizes can't
On Fri, Aug 31, 2012 at 11:02 PM, Ryan Nicholson
ryan.nichol...@kcrg.com wrote:
Secondly: Through some trials, I've found that if one loses all of his
Monitors in a way that they also lose their disks, one basically loses their
cluster. I would like to recommend a lower priority shift in
On Fri, Aug 31, 2012 at 11:58 PM, Andrew Thompson andre...@aktzero.com wrote:
Looking at old archives, I found this thread which shows that to mount a
pool as cephfs, it needs to be added to mds:
http://permalink.gmane.org/gmane.comp.file-systems.ceph.devel/5685
I started a `rados cppool
On Sun, Sep 2, 2012 at 6:36 AM, Nick Couchman nick.couch...@seakr.com wrote:
One additional piece of info...I did find the -d flag (documented in the
radosgw-admin man page, but not in the radosgw man page) that keeps the
daemon in the foreground and prints messages to stderr. When I use
On 9/4/2012 11:59 AM, Tommi Virtanen wrote:
On Fri, Aug 31, 2012 at 11:58 PM, Andrew Thompson andre...@aktzero.com wrote:
Looking at old archives, I found this thread which shows that to mount a
pool as cephfs, it needs to be added to mds:
On Tue, Sep 4, 2012 at 9:19 AM, Andrew Thompson andre...@aktzero.com wrote:
Yes, it was my `data` pool I was trying to grow. After renaming and removing
the original data pool, I can `ls` my folders/files, but not access them.
Yup, you're seeing ceph-mds being able to access the metadata pool,
This fixes a bug that went in with this commit:
commit f6e0c99092cca7be00fca4080cfc7081739ca544
Author: Alex Elder el...@inktank.com
Date: Thu Aug 2 11:29:46 2012 -0500
rbd: simplify __rbd_init_snaps_header()
The problem is that a new rbd snapshot needs to go either after an
In the on-disk image header structure there is a field block_name
which represents what we now call the object prefix for an rbd
image. Rename this field object_prefix to be consistent with
modern usage.
This appears to be the only remaining vestige of the use of block
in symbols that represent
Reviewed-by: Josh Durgin josh.dur...@inktank.com
On 09/04/2012 11:08 AM, Alex Elder wrote:
In the on-disk image header structure there is a field block_name
which represents what we now call the object prefix for an rbd
image. Rename this field object_prefix to be consistent with
modern usage.
Reviewed-by: Dan Mick dan.m...@inktank.com
On 09/04/2012 11:08 AM, Alex Elder wrote:
In the on-disk image header structure there is a field block_name
which represents what we now call the object prefix for an rbd
image. Rename this field object_prefix to be consistent with
modern usage.
This
Reviewed-by: Josh Durgin josh.dur...@inktank.com
On 09/04/2012 11:08 AM, Alex Elder wrote:
This fixes a bug that went in with this commit:
commit f6e0c99092cca7be00fca4080cfc7081739ca544
Author: Alex Elder el...@inktank.com
Date: Thu Aug 2 11:29:46 2012 -0500
rbd:
Finally applied this one. Great work, Wido!
sage
On Wed, 8 Aug 2012, Wido den Hollander wrote:
The basic documentation about how you can use RBD with CloudStack
Signed-off-by: Wido den Hollander w...@widodh.nl
---
doc/rbd/rbd-cloudstack.rst | 49
On Tue, 4 Sep 2012, S?awomir Skowron wrote:
Valgrind returns nothing.
valgrind --tool=massif --log-file=ceph_mon_valgrind ceph-mon -i 0 log.txt
The fork is probably confusing it. I usually pass -f to ceph-mon (or
ceph-osd etc) to keep it in the foreground. Can you give that a go?
e.g.,
Hi List,
We have added rbd 0.48 support to the proxmox 2.1 kvm distribution
http://www.proxmox.com/products/proxmox-ve
Proxmox setup:
edit the /etc/pve/storage.cfg and add the configuration (gui creation is not
available yet)
rbd: mycephcluster
monhost
22 matches
Mail list logo