This seems like a case of accumulating lots of new osd maps.
What might help is also setting the noup and nodown flags and wait for
the OSDs to start up. Use the "status" daemon command to check the
current OSD state even if it can't come up in the cluster map due to
noup (it also somewhere shows
Question about OSD sizes: I have two cluster nodes, each with 4x 800GiB SLC SSD
using BlueStore. They boot from SATADOM so the OSDs are data-only, but the MLC
SATADOM have terrible reliability and the SLC are way overpriced for this
application.
Can I carve off 64GiB of from one of the four dri
Hi all,
I have a simple two-node Ceph cluster that I’m comfortable with the care and
feeding of. Both nodes are in a single rack and captured in the attached dump,
it has two nodes, only one mon, all pools size 2. Due to physical limitations,
the primary location can’t move past two nodes at th
Hi,
We have a cluster with 9 hosts and 540 HDDs using Bluestore and
containerized OSDs running luminous 12.2.4. While trying to add new nodes,
the cluster collapsed as it could not keep up with establishing
enough tcp connections. We fixed sysctl to be able to handle more
connections and also
On Fri, Jan 11, 2019 at 8:58 PM Rom Freiman wrote:
>
> Same kernel :)
Not exactly the point I had in mind, but sure ;)
>
>
> On Fri, Jan 11, 2019, 12:49 Brad Hubbard wrote:
>>
>> Haha, in the email thread he says CentOS but the bug is opened against RHEL
>> :P
>>
>> Is it worth recommending a
Hi All,
We wanted to let everyone know about a couple of meetups that are happening in
the near future relating to Ceph and it was suggested we send it out to the
list.
First of all, in Dallas on January 15th with details here:
https://www.meetup.com/Object-Storage-Craft-Beer-Dallas/events/257
Hello all (and maybe this would be better suited for the ceph devel mailing
list):
I’d like to use RBD mirroring between two sites (to each other), but I have the
following limitations:
- The clusters use the same name (“ceph”)
- The clusters share IP address space on a private, non-routed storag
I was going through the permissions on the various keys in the cluster and
I think the admin capabilities look a little weird. (below) Could this be
causing the ceph-mgr problems when it starts?
[client.admin]
key = [redacted]
auid = 0
caps mds = "allow"
caps mgr =
I think I found myself the problem (for the time being I am debugging the
issue on a testbed):
[root@c-mon-01 ceph]# ceph osd crush weight-set create-compat
Error EPERM: crush map contains one or more bucket(s) that are not straw2
So I issued:
[root@c-mon-01 ceph]# ceph osd crush set-all-straw-b
I've created the following bug report to address this issue:
http://tracker.ceph.com/issues/37875
Bryan
From: ceph-users on behalf of Bryan
Stillwell
Date: Friday, January 11, 2019 at 8:59 AM
To: Dan van der Ster
Cc: ceph-users
Subject: Re: [ceph-users] osdmaps not being cleaned up in 12.2.
That thread looks like the right one.
So far I haven't needed to restart the osd's for the churn trick to work. I
bet you're right that something thinks it still needs one of the old osdmaps on
your cluster. Last night our cluster finished another round of expansions and
we're seeing up to 49
I am trying to enable the automatic balancer in my Luminous ceph cluster,
following the documentation at:
http://docs.ceph.com/docs/luminous/mgr/balancer/
[root@ceph-mon-01 ~]# ceph balancer status
{
"active": true,
"plans": [],
"mode": "crush-compat"
}
After having issued the comma
Done.
On Fri, Jan 11, 2019 at 3:36 PM Ilya Dryomov wrote:
> On Fri, Jan 11, 2019 at 11:58 AM Rom Freiman wrote:
> >
> > Same kernel :)
>
> Rom, can you update your CentOS ticket with the link to the Ceph BZ?
>
> Thanks,
>
> Ilya
>
___
Hi Igor,
On 11/01/2019 20:16, Igor Fedotov wrote:
In short - we're planning to support main device expansion for Nautilus+
and to introduce better error handling for the case in Mimic and
Luminous. Nautilus PR has been merged, M & L PRs are pending review at
the moment:
Got it. No problem then
krbd doesn't yet support several RBD features, including journaling
[1]. The only current way to use object-map, fast-diff, deep-flatten,
and/or journaling features against a block device is to use "rbd
device map --device-type nbd " (or use a TCMU loopback
device to create an librbd-backed SCSI bl
On Fri, Jan 11, 2019 at 11:58 AM Rom Freiman wrote:
>
> Same kernel :)
Rom, can you update your CentOS ticket with the link to the Ceph BZ?
Thanks,
Ilya
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listin
Hallo again, re-reading my message I realized I need to point out an
important detail about my use-case.
The pool I need to migrate is an object-storage one: it is the
destination of an OpenStack-Swift.
Do you think that, in this case, the procedure below would be the
correct one to use?
Hi Hector,
just realized that you're trying to expand main (and exclusive) device
which isn't supported in mimic.
Here is bluestore_tool complaint (pretty confusing and not preventing
from the partial expansion though) while expanding:
expanding dev 1 from 0x1df2eb0 to 0x3a38120
Ca
Same kernel :)
On Fri, Jan 11, 2019, 12:49 Brad Hubbard wrote:
> Haha, in the email thread he says CentOS but the bug is opened against
> RHEL :P
>
> Is it worth recommending a fix in skb_can_coalesce() upstream so other
> modules don't hit this?
>
> On Fri, Jan 11, 2019 at 7:39 PM Ilya Dryomov
Haha, in the email thread he says CentOS but the bug is opened against RHEL :P
Is it worth recommending a fix in skb_can_coalesce() upstream so other
modules don't hit this?
On Fri, Jan 11, 2019 at 7:39 PM Ilya Dryomov wrote:
>
> On Fri, Jan 11, 2019 at 1:38 AM Brad Hubbard wrote:
> >
> > On Fr
Thanks for the answers, guys!
Am I right to assume msgr2 (http://docs.ceph.com/docs/mimic/dev/msgr2/)
will provide encryption between Ceph daemons as well as between clients and
daemons?
Does anybody know if it will be available in Nautilus?
On Fri, Jan 11, 2019 at 8:10 AM Tobias Florek wrote:
Sorry for the late reply,
Here's what I did this time around. osd.0 and osd.1 should be identical,
except osd.0 was recreated (that's the first one that failed) and I'm
trying to expand osd.1 from its original size.
# ceph-bluestore-tool show-label --path /var/lib/ceph/osd/ceph-0 | grep size
On Fri, Jan 11, 2019 at 1:38 AM Brad Hubbard wrote:
>
> On Fri, Jan 11, 2019 at 9:57 AM Jason Dillaman wrote:
> >
> > I think Ilya recently looked into a bug that can occur when
> > CONFIG_HARDENED_USERCOPY is enabled and the IO's TCP message goes
> > through the loopback interface (i.e. co-locat
23 matches
Mail list logo
