Good day!
Surprisingly we encountered ceph-mon core dumped today. It was not peak
load time and system was technically in good state.
Configuration
Debian GNU/Linux 6.0 x64
Linux h01 2.6.32-19-pve #1 SMP Wed May 15 07:32:52 CEST 2013 x86_64
GNU/Linux
ii ceph 0.61.3-
> Hi all
>
> I'm building a small ceph cluster with 3 nodes (my first ceph cluster).
> Each Node with one System Disk, one Journal SSD Disk and one SATA OSD
> Disk.
>
> My question is now should I use Desktop or Enterprise SATA Drives?
> Enterprise Drives have a higher MTBF but the Firmware is ac
Hi List,
The default journal size is 1G, which I think is too small for my Gb network. I
want to extend all the journal partitions to 2 or 4G. How can I do that? The
osds were all created by commands like "ceph-deploy osd create
ceph-node0:/dev/sdb". The journal partition is on the same disk tog
It is possible to create all of the pools manually before starting
radosgw. That allows control of the pg_num used. The pools are:
.rgw, .rgw.control, .rgw.gc, .log, .intent-log, .usage, .users,
.users.email, .users.swift, .users.uid
On Wed, Jun 19, 2013 at 6:13 PM, Derek Yarnell wrote:
> Hi,
Thanks! Rethinking same first example I think it is doable even like
shown there. Nothing prevents mapping osds to host-like entities
whatever they are called.
2013/6/20 Gregory Farnum :
> On Thursday, June 20, 2013, Edward Huyer wrote:
>>
>> > Hi,
>> >
>> > I am thinking how to make ceph with 2 p
Anyone saw the same issue as below?
We are trying to test the multi backend feature with two RBD pools on Grizzly
release. At this point, it seems that rbd.py does not take separate cephx users
for the two RBD pools for authentication as it defaults to the single ID
defined in /etc/init/cind
Is way to exclusive map rbd?
For example - I map on host A, then I try map it on host B. I want fail
map on host B while it mapped to host A.
I read about lock command, I want atomic lock and mount rbd for one host
and auto unlock it when host A fail.
--
Blog: www.rekby.ru
_
Thank you, Mike Sage and Greg.
Completely different than everything I had heard or read. Clears it all up.
:)
Gracias,
-bo
On Thu, Jun 20, 2013 at 11:15 AM, Gregory Farnum wrote:
> On Thursday, June 20, 2013, Bo wrote:
> >
> > Howdy!
> >
> > Loving working with ceph; learning a lot. :)
> >
>
On Thursday, June 20, 2013, Bo wrote:
>
> Howdy!
>
> Loving working with ceph; learning a lot. :)
>
> I am curious about the quorum process because I seem to get conflicting
> information from "experts". Those that I report to need a clear answer from
> me which I am currently unable to give.
>
>
On Thu, 20 Jun 2013, Bo wrote:
> Howdy!
> Loving working with ceph; learning a lot. :)
>
> I am curious about the quorum process because I seem to get conflicting
> information from "experts". Those that I report to need a clear answer from
> me which I am currently unable to give.
>
> Ceph needs
I'm still using Fedora 17 on some machines that use Ceph, and it seems that
the official Ceph RPM repository for Fedora 17
(http://eu.ceph.com/rpm-cuttlefish/fc17/x86_64/) hasn't seen any new releases
since 0.61.2.
Are you discontinuing RPMs for Fedora 17?
Guido
___
Quorum means you need at least %51 participating be it people following
parliamentary procedures or mons in ceph. With one dead and two up you have
%66 participating or enough to have a quorum. An even number doesn't get you
any additional safety but does give you one more thing than can fail v
Il 20/06/13 15:40, Joao Eduardo Luis ha scritto:
On 06/20/2013 01:23 PM, Fabio - NS3 srl wrote:
Hi,
there is a changlog about 0.61.4?
There will be as soon as 0.61.4 is officially released. An announcement
to ceph-devel, ceph-users and the blog at ceph.com usually accompanies
the release.
Howdy!
Loving working with ceph; learning a lot. :)
I am curious about the quorum process because I seem to get conflicting
information from "experts". Those that I report to need a clear answer from
me which I am currently unable to give.
Ceph needs an odd number of monitors in any given cluste
On Thursday, June 20, 2013, Edward Huyer wrote:
> > Hi,
> >
> > I am thinking how to make ceph with 2 pools - fast and slow.
> > Plan is to use SSDs and SATAs(or SAS) in the same hosts and define pools
> that
> > use fast and slow disks accordingly. Later it would be easy to grow
> either pool
> >
On Thursday, June 20, 2013, Kurt Bauer wrote:
> Hi,
>
> we run a 3 node cluster, every node runs a mon and 4 osds. 2 defined
> pools, one with replication level 2, the second with replication level 3.
> We now want to relocate one node from one datacenter to another, which
> means a downtime of a
On Thu, 20 Jun 2013, Da Chun wrote:
> Hi List,
> According to the doc, the journal partition is not recommended to be on the
> same disk as the osd. Should I put it in a separate one? But the total
> journal size is not big, 2 or 4g is enough for gigabyte network. It's
> a tremendous waste to put i
We have resolved a number of issues that v0.61.x Cuttlefish users have
been hitting and have prepared another point release, v0.61.4. This
release fixes a rare data corruption during power cycle when using the XFS
file system, a few monitor sync problems, several issues with ceph-disk
and ceph-
Hi all
I'm building a small ceph cluster with 3 nodes (my first ceph cluster).Each
Node with one System Disk, one Journal SSD Disk and one SATA OSD Disk.
My question is now should I use Desktop or Enterprise SATA Drives? Enterprise
Drives have a higher MTBF but the Firmware is actually build for
Hi,
is there any way to create snapshots of individual buckets, that can
be restored from piecemeal?
i.e. if someone deletes objects by mistake?
Cheers
Mike
--
Mike Bryant | Systems Administrator | Ocado Technology
mike.bry...@ocado.com | 01707 382148 | www.ocadotechnology.com
--
Notice: This
Hi,
we run a 3 node cluster, every node runs a mon and 4 osds. 2 defined
pools, one with replication level 2, the second with replication level 3.
We now want to relocate one node from one datacenter to another, which
means a downtime of about 4 hours for that specific node, which
shouldn't hurt
> Hi,
>
> I am thinking how to make ceph with 2 pools - fast and slow.
> Plan is to use SSDs and SATAs(or SAS) in the same hosts and define pools that
> use fast and slow disks accordingly. Later it would be easy to grow either
> pool
> by need.
>
> I found example for CRUSH map that does simila
Hi,
I am thinking how to make ceph with 2 pools - fast and slow.
Plan is to use SSDs and SATAs(or SAS) in the same hosts and define
pools that use fast and slow disks accordingly. Later it would be easy
to grow either pool by need.
I found example for CRUSH map that does similar thing by defining
On 06/20/2013 01:23 PM, Fabio - NS3 srl wrote:
Hi,
there is a changlog about 0.61.4?
There will be as soon as 0.61.4 is officially released. An announcement
to ceph-devel, ceph-users and the blog at ceph.com usually accompanies
the release.
-Joao
--
Joao Eduardo Luis
Software Engineer |
Hi,
there is a changlog about 0.61.4?
Thanks
FabioFVZ
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Hi,No this must always be the same UUID. You can only specify one in cinder.conf.Btw nova does the attachment this is why it needs the uuid and secret.The first secret import generates an UUID, then always re-use the same one for all your compute node, do something like: 9e4c7795-0681-cd4f-cf36-8
On 06/20/2013 10:09 AM, Matthew Anderson wrote:
Hi All,
I've had a few conversations on IRC about getting RDMA support into Ceph
and thought I would give it a quick attempt to hopefully spur some
interest. What I would like to accomplish is an RSockets only
implementation so I'm able to use Ceph
Hello list!
I am trying deploy Ceph RBD + OpenStack Cinder.
Basically, my question related to this section in documentation:
cat > secret.xml <
client.volumes secret
EOF
sudo virsh secret-define --file secret.xml
sudo virsh secret-set-value --secret {uuid of secret} --base64 $(cat
cli
Hi All,
I've had a few conversations on IRC about getting RDMA support into Ceph
and thought I would give it a quick attempt to hopefully spur some
interest. What I would like to accomplish is an RSockets only
implementation so I'm able to use Ceph, RBD and QEMU at full speed over an
Infiniband fa
29 matches
Mail list logo
