On Thu, Jun 27, 2013 at 6:27 AM, Julien Recurt
wrote:
>
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Hello,
>
> Two question about SWIFT & RadosGW
> At this time i've got no official information but it seems that
> temporary urls are not supported by the RGW
>
> My first question is: does
Dear all,
I am having a bit of problem with mon after the node was rebooted. I found the
following error messages repeating and wonder if someone have seen similar
issue and what may be the solution to solve it:
2013-07-02 09:55:06.455179 7f866f60a700 0 -- 10.4.132.18:0/0 >>
10.4.132.18:6800/
HI lists
Does dumpling version(2013/8/1) have the "Erasure encoding as a storage
backend" function ?
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Hi,
I am having a bit of problem with mon after the node was rebooted. I found the
following error messages repeating and wonder if someone have seen similar
issue and what may be the solution to solve it:
2013-07-02 09:55:06.455179 7f866f60a700 0 -- 10.4.132.18:0/0 >>
10.4.132.18:6800/0 pipe
Hi,
will there be posix acls in ceph Filesystem?
Best regards
Joachim___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Hi Dominik,
What`s about performance on the osd.87 at this moment, do you have any
related measurements?
As for mine version of this issue, seems that quorum has some kind of
degradation over time - when I restarted mons, problem has gone and peering
time lowered by factor of ten or so. Also see
Hi,
I got it.
ceph health details
HEALTH_WARN 3 pgs peering; 3 pgs stuck inactive; 5 pgs stuck unclean;
recovery 64/38277874 degraded (0.000%)
pg 5.df9 is stuck inactive for 138669.746512, current state peering,
last acting [87,2,151]
pg 5.a82 is stuck inactive for 138638.121867, current state pee
Hi,
Some osd.87 performance graphs:
https://www.dropbox.com/s/o07wae2041hu06l/osd_87_performance.PNG
After 11.05 I have restarted it.
Mons .., maybe this is the problem.
--
Regards
Dominik
2013/7/2 Andrey Korolyov :
> Hi Dominik,
>
> What`s about performance on the osd.87 at this moment, do you
Hi all,
I have been able to bind openstack keystone and radosgw and have checked users
created from keystone can make requests on radosgw.
But, how can we handle several tenants and users from keystone? In swift, we
have the option of setting up ACLs in the config file and headers to mark
whi
Hello,
i wanted to import an old backup but want to keep my current snapshots.
Is this possible? If i try to import it tells me the image exists. If i
delete the image it will also delete the snapshots.
Stefan
___
ceph-users mailing list
ceph-users@list
Dear ceph-users,
I've started to play with Ceph deployment based on Chef CookBooks
found at https://github.com/ceph/ceph-cookbooks
I tried to follow
http://eu.ceph.com/docs/wip-msgauth/config-cluster/chef/
and now my configuration process hangs at command
ceph auth get-key client.bootstrap-osd
Hello,
I am using Ubuntu 13.04 with the testing branch (0.65-1) of ceph.
I have had no problem at all setting up a 3 node cluster and I currently have
several vm's booting off of rbd as a test.
Last night I decided to try and setup radosgw along with it, using the
following docs:
https://gith
You're specifying an explicit keyeing when trying to add the new RGW key,
but letting the system pick one when running ceph -s. it's probably finding
and using a different one to do that; you should check your key rings and
their contents. :)
-Greg
On Tuesday, July 2, 2013, Shain Miley wrote:
> H
On Mon, Jul 1, 2013 at 6:48 PM, maoqi1982 wrote:
> HI lists
> Does dumpling version(2013/8/1) have the "Erasure encoding as a storage
> backend" function ?
Nope. We (mostly Loic) have been laying some of the initial
groundwork, but we're all still working on the system design. :)
-Greg
Software E
On Tue, Jul 2, 2013 at 1:22 AM, wrote:
> Hi,
>
> will there be posix acls in ceph Filesystem?
Someday, but not yet. There's a ticket at
http://tracker.ceph.com/issues/27; this is probably a fairly good
entry point for external contributors... ;)
-Greg
Software Engineer #42 @ http://inktank.com |
Just an FYI...the syntax requirements for this step must have changed a bit
recently, after trying every single combination of options, I finally got it to
work using this:
ceph auth add client.radosgw.gateway /etc/ceph/keyring.radosgw.gateway
/etc/ceph/ceph.client.admin.keyring
Thanks,
Shain
Hi - I am quite new to Ceph and would be grateful if you could explain a couple
of items as these are not immediately clear to me from the Ceph documentation:
1) My Ceph cluster is running on RHEL 6.4 (kernel 2.6.32). As such I cannot use
the RDB kernel module and so map block device images to t
The ceph kernel module is only for mounting rbd block devices on bare metal
(technically you could do it in a vm but there is no good reason to do so).
QEMU/KVM has its own rbd implementation that tends to lead the kernel
implementation and should be used with vm's.
The rbd module is always us
Hi Chris,
Does this then mean that I cannot access these block devices from
another server using libvirt/KVM ?
No, qemu-kvm implement user-space access to rados block devices via
librbd. So that will work fine even without the kernel module. Both
locally on Ceph osd/mon servers as well as on
Hi,
Something in the back of my mind keeps saying that there were plans to
implement read caching in librbd, but I haven't been able to find any
reference about that.
In the tracker however I wasn't able to find anything, so it has to be me.
Any plans or ideas on this? A simple idea was that
Hi,
I haven't been able to do this. I was asked to wipe the Ceph cluster, so
I wiped all the OSDs and the Mons and restored the system from backups.
Would have been something interesting to investigate, but this was a
system ready to go production and had to be online before a deadline.
On
On 06/28/2013 05:02 PM, Gregory Farnum wrote:
It's the tool. We definitely want a way to find out if a config option
is set or not, but I think patches here would be welcome. :)
I'll see what I can do.
You can also look at ceph-disk's get_conf and get_conf_with_default
methods for how I hand
Hi Wido!
On Tue, 2 Jul 2013, Wido den Hollander wrote:
> Something in the back of my mind keeps saying that there were plans to
> implement read caching in librbd, but I haven't been able to find any
> reference about that.
>
> In the tracker however I wasn't able to find anything, so it has to b
Hello Again,
I purged Ceph on the Kitt node, rebooted, then used ceph-deploy to
reinstall and redeploy the monitors and osds.
Everything seemed to work like a charm and the node is now able to reboot
and the monitor and osds come back up fast now.
Not sure why, but everything is back up and runn
Hi Wido and Sage,
I am also interested in adding persistent caching in RBD.
Is there any plan scheduled on this topic? I'd like to involve in and help.
Best regards,
Chendi
-Original Message-
From: ceph-users-boun...@lists.ceph.com
[mailto:ceph-users-boun...@lists.ceph.com] On Behalf O
25 matches
Mail list logo
