Hello Orit,
Yes, this bug looks to correlate. Was this included in 10.2.3?
I guess not as I have since updated to 10.2.3 but getting the same errors
This bug talks about not retrying after a failure, however do you know
why the sync fails in the first place? It seems that basically any
object ov
Thanks for your suggestions, but I managed it without removing OSDs.
Coming back to the office today I found ceph still in error state, but
the number of inconsistent PGs seemed to be stable at 22. So I started
all over with the manual repair (grepped log files for PG, searched
the respecti
see comment below
On Mon, Sep 26, 2016 at 10:00 PM, John Rowe wrote:
> Hi Orit,
>
> Sure thing, please see below.
>
> Thanks!
>
>
> DFW (Primary)
> radosgw-admin zonegroupmap get
> {
> "zonegroups": [
> {
> "key": "235b010c-22e2-4b43-8fcc-8ae01939273e",
> "val"
Hi, everyone.
After the file system synchronization, does OSD delete those journals that
corresponds to operations before the synchronization point?___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph
Hi, everyone.
I've got a problem, here. Due to some miss operations, I deleted all three
replicas of my data, is there any way to recover it?
This is a very urgent problem.
Please help me, Thanks.___
ceph-users mailing list
ceph-users@lists.ceph.com
Hi Ceph user,
I am learning bugs in ceph and am trying to reproduce
http://tracker.ceph.com/issues/15113 on my local machine.
On the description, I may see the scenario:
1. ___*_*__ SafeTimer::timer_thread(), with mon_lock:
2. ___*_*__ elector: in win_electi
Hi Orit,
That was my failed attempt at sanitizing :)
They are actually all identical:
Periods:
MD5 (cephrgw1-1-dfw-period.json) = 12ed481381c1f2937a27b57db0473d6d
MD5 (cephrgw1-1-phx-period.json) = 12ed481381c1f2937a27b57db0473d6d
MD5 (cephrgw1-2-dfw-period.json) = 12ed481381c1f2937a27b57db0473d
How to mount a cephfs using subtree ?? mount.ceph mon0:/web/data
/data/ -o name=admin,secretfile=/etc/ceph/admin.secret Receive mount
error 2 = No such file or directory.
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/lis
(I tried to start this discussion on irc, but I wound up with the wrong
paste buffer and wound up getting kicked off for a paste flood, sorry,
that was on me :( )
We were having some weirdness with our Ceph and did an upgrade up to
10.2.3, which fixed some, but not all of our problems.
It looke
Hi Orit,
It appears it must have been one of the known bugs in 10.2.2. I just
upgraded to 10.2.3 and bi-directional syncing now works.
I am still seeing some errors when I run synch-related commands but they
don't seem to be affecting operations as of yet:
radosgw-admin sync status
2016-09-27 1
Hi Cephers,
We need to add two new monitors to a production cluster (0.94.9) which has
3 existing monitors. It looks like it's as easy as ceph-deploy mon add .
What's the best practice in terms of when to update the existing monitor
and osd ceph.conf file to include the new monitors in mon_initia
Hi...
Here are a couple of examples based on what we do.
We have not tried all of them so some are just extrapolations based on
the underlying logic. Maybe someone else can correct me if I am wrong. I
the following examples, the root of the filesystem is /cephfs
- Mounting your cephfs filesy
Hi Daleep,
Thank you for reply.
I have read the document for a moment. Let me try to clarify this.
In my case, I only assgin “mon ‘allow r” permission to account appuser. But, I
still can mount cephfs and see the directory created before(the folder name is
“test”).
And, I can create a fo
13 matches
Mail list logo
