Hi all,
my monitor3 is not able to rejoin the cluster (containing mon1, mon2 and mon3 -
running stable emperor).
I try to recreate/inject a new monmap to all 3 mon's - but only mon1 and mon2
are up and joined.
Now, enabling debugging on mon3, I got the following:
2014-01-30 08:51:03.823669 7f3
Hello Ilya,
thank you for your help.
I first tried 'ceph osd crush tunables legacy' on each server with
rebooting.
That didn't help anything. I though, that running this command the
feature should be disabled, but the error remains.
In the past i only did rolling ceph-upgrades with 'apt-get up
OK - found the problem:
> mon_status
> { "name": "ceph-mon3",
..
> "mons": [
> { "rank": 2,
> "name": "mon.ceph-mon3",
NAME is wrong
> "addr": "192.168.135.33:6789\/0"}]}}
>
In the docu http://ceph.com/docs/master/man/8/monmaptool/
the creation of t
Hi,
I have problem with data distribution.
Smallest disk usage 40% vs highest 82%.
All PGS: 6504.
Almost all data is in '.rgw.buckets' pool with pg_num 4800.
The best way to better data distribution is increese pg_num in this pool?
Is thre another way? ( eg crush tunables, or something like that ..
Hi,
The inaugural meeting of the Ceph Berlin community took place on Monday,
January 27th. A total of 14 "Cephalopods" found their way to the
Heinlein Offices. That was a great response to a group that was formed
just under three weeks ago. And we even have around 30 members right now.
In the org
Hello everybody,
in case you haven't noticed already, this weekend at FOSDEM'14,
we will be presenting the Synnefo stack and it's integration with
Google Ganeti, Archipelago and RADOS to provide advanced,
unified cloud storage with unique features.
You can find the official announcement here:
ht
Hi.
I'm using ntpd on each ceph server and is syncing properly but every
time that I reboot, ceph starts in degraded mode with "clock skew"
warning.
The only way that I have to solve this is manually restart ceph on
each node (without resyncing clock)
Any suggestion ?
Hi,
yesterday i tried to fix my "pgs stuck unclean" problem by using
tunables and edited my crushmap.
today i can't start my osds anymore.
/etc/init.d/ceph restart osd.0
=== osd.0 ===
=== osd.0 ===
Stopping Ceph osd.0 on rokix...done
=== osd.0 ===
Error EINVAL: (22) Invalid argument
failed: 'tim
Hi,
just a small question: Createing a new OSD i use e.g.
ceph-deploy osd create ceph-node1:sdg:/dev/sdb5
Question: What happens if the mapping of my disks changes (e.g. because adding
new disks to the server)
sdg becomes sgh
sdb becomes sdc
Is this handled (how?) by ce
Hello list,
Is it correct behavior during copy to thicking rbd image?
igor@hv03:~$ rbd create rbd/test -s 1024
igor@hv03:~$ rbd diff rbd/test | awk '{ SUM += $2 } END { print
SUM/1024/1024 " MB" }'
0 MB
igor@hv03:~$ rbd copy rbd/test rbd/cloneoftest
Image copy: 100% complete...done.
igor@hv03:~$
Hi,
I'm looking for solution how to verify file downloaded from s3 where
ETag is multiparted ( with '-' ) and don't know how is part size.
When part size is known, it is possible eg do it with scrip:
https://github.com/Teachnova/s3md5/blob/master/s3md5
In aws doc i found that there is only lower
Am 30.01.2014 13:03, schrieb Ingo Ebel:
> /etc/init.d/ceph restart osd.0
> [...]
> Error EINVAL: (22) Invalid argument
> failed: 'timeout 10 /usr/bin/ceph --name=osd.0
> --keyring=/var/lib/ceph/osd/ceph-0/keyringosd crush
> create-or-move
Hi,
I found something else.
'ceph pg dump' shows PGs:
- with zero or near zero objects count
- with ~6,5k objects, size ~1,4G
- with ~13k objects, size ~2,8G
This can be a reason of wrong data distribution on OSD's?
---
Regards
Dominik
2014-01-30 Dominik Mostowiec :
> Hi,
> I have problem with
On Thu, Jan 30, 2014 at 12:53:22PM +0100, Gandalf Corvotempesta wrote:
> Hi.
> I'm using ntpd on each ceph server and is syncing properly but every
> time that I reboot, ceph starts in degraded mode with "clock skew"
> warning.
>
> The only way that I have to solve this is manually restart ceph on
Hi,
I found something else what I think can help.
PG distribution it seems isn't ok.
Graph: http://dysk.onet.pl/link/AVzTe
All PGS is from 70 to 140 per OSD.
Primary 15 to 58 per OSD.
Is there some way to fix it?
--
Regards
Dominik
2014-01-30 Dominik Mostowiec :
> Hi,
> I found something else.
you can run 'ntpdate -b '
read ntpdate-manual for the parameters.
Markus
Am 30.01.2014 16:05, schrieb Emmanuel Lacour:
On Thu, Jan 30, 2014 at 12:53:22PM +0100, Gandalf Corvotempesta wrote:
Hi.
I'm using ntpd on each ceph server and is syncing properly but every
time that I reboot, ceph starts
On Thu, Jan 30, 2014 at 5:58 AM, Dominik Mostowiec
wrote:
> Hi,
> I'm looking for solution how to verify file downloaded from s3 where
> ETag is multiparted ( with '-' ) and don't know how is part size.
>
> When part size is known, it is possible eg do it with scrip:
> https://github.com/Teachnova
Am 30.01.14 15:09, schrieb Christian Kauhaus:
> Am 30.01.2014 13:03, schrieb Ingo Ebel:
>> /etc/init.d/ceph restart osd.0
>> [...]
>> Error EINVAL: (22) Invalid argument
>> failed: 'timeout 10 /usr/bin/ceph--name=osd.0
>> --keyring=/var/lib/ceph/osd/ceph-0/keyring
2014-01-30 Emmanuel Lacour :
> here, I just wait until the skew is finished, without touching ceph. It
> doesn't seems to do anything bad ...
I've waited more than 1 hour with no success.
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists
Hello,
I'm just started using ceph and I'm trying to understand how works
connections between monitors, client and OSDs. I have test
infrastructure with two monitors and 3 OSDs. I create pool which is
mapped to host (client). Now I'm not quite sure how exactly connections
works when for examp
During on of tests, my test client painfully crashed with a couple of
mapped images. When it came back online I have not been able to rm
formerly mapped images as watchers were still registered.
Host A > rbd create test-image --size 10240
Host A > rbd map test-image
#
# after some time > 3
Hi Markus,
You need to remove the erasure rule from the CRUSH map that was
erroneously put in the default map for this version. The command you need
is
ceph osd crush rule rm
you can list rules with
ceph osd crush rule ls
and the one you want to remove is named 'erasure-default' or some
On Thu, 30 Jan 2014, Dominik Mostowiec wrote:
> Hi,
> I found something else.
> 'ceph pg dump' shows PGs:
> - with zero or near zero objects count
These are probably for a different pool than the big ones, right? The
PG id is basically $pool.$shard.
> - with ~6,5k objects, size ~1,4G
> - with
Hi,
I have successfully upgraded production cluster to:
ceph version 0.67.5 (a60ac9194718083a4b6a225fc17cad6096c69bd1)
1. after this upgrade i see in radosgw.log:
WARNING: couldn't find acl header for bucket, generating default
i found this http://tracker.ceph.com/issues/5691
and checked the revi
Hi,
Thaks for Your response.
> - with ~6,5k objects, size ~1,4G
> - with ~13k objects, size ~2,8G
is on one the biggest pool 5 '.rgw.buckets'
> This is because pg_num is not a power of 2
This is for all PGs (sum of all pools) or for pool 5 '.rgw.buckets'
where i have almost all data ?
> Did you
On Thu, 30 Jan 2014, Dominik Mostowiec wrote:
> Hi,
> Thaks for Your response.
>
> > - with ~6,5k objects, size ~1,4G
> > - with ~13k objects, size ~2,8G
> is on one the biggest pool 5 '.rgw.buckets'
>
> > This is because pg_num is not a power of 2
> This is for all PGs (sum of all pools) or for
Hi,
I am busy configuring the object gateway and have reached the point where I
need to start the radosgw. The documentation calls for the following command:
/etc/init.d/radosgw start
On my deployment, radosgw seems to be located in /usr/bin and trying to start
it from there results in the f
Am 30.01.14 16:52, schrieb Ingo Ebel:
> Am 30.01.14 15:09, schrieb Christian Kauhaus:
>> Am 30.01.2014 13:03, schrieb Ingo Ebel:
>>> /etc/init.d/ceph restart osd.0
>>> [...]
>>> Error EINVAL: (22) Invalid argument
>>> failed: 'timeout 10 /usr/bin/ceph --name=osd.0
>>>
I have this problem on some of my Ceph clusters, and I think it is due
to the older hardware the I am using does not have the best clocks. To
fix the problem, I setup one server in my lab to be my local NTP time
server, and then on each of my Ceph monitors, in the /etc/ntp.conf
file, I put in
Hi Constantinos,
Count me in https://fosdem.org/2014/schedule/event/virtiaas02/ :-)
If you're in Brussels tomorrow (friday), you're welcome to join the Ceph meetup
http://www.meetup.com/Ceph-Brussels/ !
Cheers
On 30/01/2014 12:51, Constantinos Venetsanopoulos wrote:
> Hello everybody,
>
> in
fix: it was not python boto, it was https://github.com/dyarnell/rgwadmin
but it doesn`t matter
--
Regards,
Mikhail
On Thu, 30 Jan 2014 19:54:16 +0300
Mikhail Krotyuk wrote:
> Hi,
> I have successfully upgraded production cluster to:
> ceph version 0.67.5 (a60ac9194718083a4b6a225fc17cad6096c69
Hi Mikhail,
Sorry did you find an issue with the library I wrote? Let me test the
bucket linking as I didn't have a good unit test for it yet.
Thanks,
derek
On 1/30/14, 12:45 PM, myk...@gmail.com wrote:
> fix: it was not python boto, it was https://github.com/dyarnell/rgwadmin
> but it doesn`t
no its not in the library, the problem is with radosgw
--
Regards,
Mikhail
On Thu, 30 Jan 2014 13:17:41 -0500
Derek Yarnell wrote:
> Hi Mikhail,
>
> Sorry did you find an issue with the library I wrote? Let me test the
> bucket linking as I didn't have a good unit test for it yet.
>
> Th
Hi,
So I am trying to remove OSDs from one of our 6 ceph OSDs, this is a
brand new cluster and no data is yet on it. I was following the manual
procedure[1] with the following script. I removed OSDs 0-3 but I am
seeing ceph not fully recovering.
#!/bin/bash
ceph osd out ${1}
/etc/init.d/ceph st
On 1/30/14, 12:16 PM, alistair.whit...@barclays.com wrote:
> radosgw: must specify 'rgw socket path' or 'rgw port' to run as a daemon
>
This is defined in your /etc/ceph/ceph.conf. For example if the host
you are running the radosgw is named 'myhostname' then your ceph.conf
should have a secti
Philipp,
I have had issues with clock sync on machines before that I could usually
alleviate by tweaking the kernel config. Changing CONFIG_HZ to 300 instead
of 1000 can help. If you ever reboot the machines, making sure your init
system writes the current software clock to the hardware clock on s
Hi,
For this cluster 198x100/3 = 6600
If i bump up pool .rgw.buckets to 8192 (now it is 4800 ), it'll be 9896.
It is not to much?
Mabye better way is to destroy eg '.log' pool and create it with lower
pool count (it is safe?)?
--
Regards
Dominik
2014-01-30 Sage Weil :
> On Thu, 30 Jan 2014, Domi
37 matches
Mail list logo
