On Thursday 03 November 2011 you wrote:
On Thu, Nov 3, 2011 at 05:02, Amon Ott a@m-privacy.de wrote:
Documentation recommends three monitors. In our special cluster
configuration, this would mean that if accidentially two nodes with
monitors fail (e.g. one in maintenance and one
Hi all,
I used to schedule a cron job to do radosgw-admin --date `date
+%Y-%m-%d` temp remove.
It works fine in v0.36, but got an error in v0.37. See the error message below:
root@ceph1:~# radosgw-admin --date 2011-11-04 temp remove -d
2011-11-04 16:34:27.373509 7f277c6ab760 cls_bucket_list
On Thu, Nov 3, 2011 at 10:38 PM, Tommi Virtanen
tommi.virta...@dreamhost.com wrote:
On Wed, Nov 2, 2011 at 23:58, Atish Kathpal atish.kath...@gmail.com wrote:
Moreover, I am also unable to create new objects and/or get/put the
degraded objects. I re-ran mkcephfs after my reboot.
Well, if you
On Fri, Nov 4, 2011 at 4:23 PM, Henry C Chang henry.cy.ch...@gmail.com wrote:
Hi Atish,
The default replication number of ceph is 2. Thus, If you have only
one node (osd) in your cluster, all pg/objects are surely in degraded
state.
As to the problem that you cannot put/get objects, I guess
On Fri, 4 Nov 2011, Amon Ott wrote:
On Thursday 03 November 2011 you wrote:
On Thu, Nov 3, 2011 at 05:02, Amon Ott a@m-privacy.de wrote:
Documentation recommends three monitors. In our special cluster
configuration, this would mean that if accidentially two nodes with
monitors fail
On Fri, Nov 4, 2011 at 02:53, Atish Kathpal atish.kath...@gmail.com wrote:
So from your reply I understand that a system reboot would have done
nothing to my RADOS objects, it was the re-running of mkcephfs that
degraded my objects. Right?
Correct.
--
To unsubscribe from this list: send the
On Fri, Nov 4, 2011 at 05:18, Atish Kathpal atish.kath...@gmail.com wrote:
Thank you for providing further insights. To correct what you pointed
out regarding the default replica counts, I have now done the
following to my ceph single node cluster:
ceph osd pool set data size 1
ceph osd pool
On Thu, Nov 3, 2011 at 18:45, eric_yh_c...@wistron.com wrote:
Hi, Tommi,
Here is my ceph.conf. The /var/log/ceph folder is created by myself.
[global]
...
log file = /var/log/ceph/$name.log
pid file = /var/run/ceph/$name.pid
That's your problem. You told even clients to
On Fri, Nov 4, 2011 at 1:12 AM, Amon Ott a@m-privacy.de wrote:
I agree that our needs are special. We want to be able to start with 2 and
extend as customer needs grow, or start with 20 and shut some of them down if
load gets low. I now understand that we should start with at least three
On Thu, Nov 3, 2011 at 20:09, Maxim Mikheev mik...@gmail.com wrote:
Is Ceph copy on write system?
Ceph uses btrfs's copy-on-write properties internally, for cheap
snapshots and journaling speed.
As far as I know, Ceph does not currently expose reflink-style
functionality to clients, and there's
On Fri, Nov 4, 2011 at 12:34, Maxim Mikheev mik...@gmail.com wrote:
I have another question. Looks like repository version 0.37 for ubuntu
oneric has brocken dependencies
for ceph-client-tools.
Can you advice how can I install it?
v0.37 renamed ceph-client-tools to ceph-common. Unfortunately,
On Fri, Nov 4, 2011 at 1:47 AM, Henry C Chang henry.cy.ch...@gmail.com wrote:
Hi all,
I used to schedule a cron job to do radosgw-admin --date `date
+%Y-%m-%d` temp remove.
It works fine in v0.36, but got an error in v0.37. See the error message
below:
root@ceph1:~# radosgw-admin --date
Thanks,
Upgrade from 0.34 to 0.37 was not smooth. I was have to clean all
disks. But new version is working well
On Fri 04 Nov 2011 03:54:42 PM EDT, Tommi Virtanen wrote:
On Fri, Nov 4, 2011 at 12:34, Maxim Mikheevmik...@gmail.com wrote:
I have another question. Looks like repository
On Thu, 3 Nov 2011, Christoph Hellwig wrote:
Using sync_file_range means that neither any required metadata gets commited,
nor the disk cache gets flushed. Stop using it for the journal, and add
a comment on why a fsync_range system call would be helpful here.
Sigh... doesn't that mean that
On Nov 3, 2011, Mandell Degerness mand...@pistoncloud.com wrote:
We are currently running all services on each of the three nodes.
(mon, mds, and several osd processes).
Do you also happen to have a ceph.ko mount on the node that showed the
problem? If so, you may be running into a deadlock
15 matches
Mail list logo