Hi,
I thought that xfs fragmentation or leveldb(gc list growing, locking,
...) could be a problem.
Do you have any experience with this ?
---
Regards
Dominik
2016-04-24 13:40 GMT+02:00 :
> I do not see any issue with that
>
> On 24/04/2016 12:39, Dominik Mostowiec wrote:
>> Hi,
Hi,
I'm curious if using s3 like a cache - frequent put/delete in the
long term may cause some problems in radosgw or OSD(xfs)?
-
Regards
Dominik
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-c
Hi,
I'm curious if using s3 like a cache - frequent put/delete in the long
term may cause some problems in radosgw or OSD(xfs)?
-
Regards
Dominik
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-c
Hi,
Maybe this is the reason of another bug?
http://tracker.ceph.com/issues/13764
The situation is very similiar...
--
Regards
Dominik
2016-02-25 16:17 GMT+01:00 Ritter Sławomir :
> Hi,
>
>
>
> We have two CEPH clusters running on Dumpling 0.67.11 and some of our
> "multipart objects" are incompl
Hi,
In my cluster I have on one OSD with many strange logs
0 cls/rgw/cls_rgw.cc:1555: couldn't find tag in name index
tag=default.
zgrep -c 'find tag in name index tag' /var/log/ceph/ceph-osd.151.log.1.gz
7531
This osd is overloaded on CPU iostat seems to be ok.
It has many slow request.
zg
Hi,
>From few days we notice on our cluster many slow request.
Cluster:
ceph version 0.67.11
3 x mon
36 hosts -> 10 osd ( 4T ) + 2 SSD (journals)
Scrubbing and deep scrubbing is disabled but count of slow requests is
still increasing.
Disk utilisation is very small after we have disabled scrubbings
Thanks,
Is there any option to fix bucket index automaticly?
--
Regards
2015-03-14 4:49 GMT+01:00 Yehuda Sadeh-Weinraub :
>
>
> - Original Message -
>> From: "Dominik Mostowiec"
>> To: ceph-users@lists.ceph.com
>> Sent: Friday, March 13, 2015 4:
Hi,
I found a strange problem with not existing file in s3.
Object exists in list
# s3 -u list bucketimages | grep 'files/fotoobject_83884@2/55673'
files/fotoobject_83884@2/55673.JPG 2014-03-26T22:25:59Z 349K
but:
# s3 -u head 'bucketimages/files/fotoobject_83884@2/55673.JPG'
ERROR: HttpErrorN
Hi
I have stragne problem when I try to start radosgw on docker container.
When I have single container with 1 radosgw process inside everyting
is ok, I have good performance i think, for single test thread: 80
put/s for 4k objects and radosgw with debug enabled.
When I start two containers on the
Hi,
After set chooseleaf_descend_once=0, and migration 20% PGs ceph is HEALTH_OK.
"chooseleaf_descend_once" optimal value is 1 :-(
--
Regards
Dominik
2014-08-21 15:59 GMT+02:00 Dominik Mostowiec :
> Hi,
> I have 2 PG in active+remapped state.
>
> ceph health detail
>
d": 0},
"stat_cat_sum": {},
"up": [
167,
80],
"acting": [
167,
80,
145]},
"empty": 0,
"dne": 0,
"incomple
ot;up": [
143],
"acting": [
143,
261,
314]},
"empty": 0,
"dne": 0,
"incomplete": 0,
"last_epoch_started": 160261},
"recovery_state"
Hi,
After ceph osd out ( 1 osd ) cluster stopped rebalancing on
10621 active+clean, 2 active+remapped, 1 active+degraded+remapped;
My crushmap is clean, there is not 'empty' device's.
grep device /tmp/crush1.txt | grep -v osd | grep -v '^#' | wc -l
0
Can You help me with this?
"up": [
Hi,
> FWIW the tunable that fixes this was just merged today but won't
> appear in a release for another 3 weeks or so.
This is "vary_r tunable" ?
Can I use this in production?
--
Regards
Dominik
2014-02-12 3:24 GMT+01:00 Sage Weil :
> On Wed, 12 Feb 2014, Dominik Mosto
:31 GMT+01:00 Dominik Mostowiec :
> Great!
> Thanks for Your help.
>
> --
> Regards
> Dominik
>
> 2014-02-06 21:10 GMT+01:00 Sage Weil :
>> On Thu, 6 Feb 2014, Dominik Mostowiec wrote:
>>> Hi,
>>> Thanks !!
>>> Can You suggest any workarou
ata & Storage Services || CERN IT Department --
>
>
> On Thu, Feb 6, 2014 at 2:12 PM, Dominik Mostowiec
> wrote:
>> Hi Ceph Users,
>> What do you think about virtualization of the radosgw machines?
>> Have somebody a production leve
Great!
Thanks for Your help.
--
Regards
Dominik
2014-02-06 21:10 GMT+01:00 Sage Weil :
> On Thu, 6 Feb 2014, Dominik Mostowiec wrote:
>> Hi,
>> Thanks !!
>> Can You suggest any workaround for now?
>
> You can adjust the crush weights on the overfull nodes slightly. Yo
that is pending review, but it's not a quick fix because of
> compatibility issues.
>
> sage
>
>
> On Thu, 6 Feb 2014, Dominik Mostowiec wrote:
>
>> Hi,
>> Mabye this info can help to find what is wrong.
>> For one PG (3.1e4a) which is active+remapped:
>
",
"end": "0\/\/0\/\/-1",
"objects": []},
"backfills_in_flight": [],
"pull_from_peer": [],
"pushing": []},
"scrub": { "scrubber.epoch_start": &qu
Hi Ceph Users,
What do you think about virtualization of the radosgw machines?
Have somebody a production level experience with such architecture?
--
Regards
Dominik
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cg
, though, but I'm happy to dig into that too.
>
> BTW, the osdmaptool addition I was using to play with is here:
> https://github.com/ceph/ceph/pull/1178
>
> sage
>
>
> On Mon, 3 Feb 2014, Dominik Mostowiec wrote:
>
>> In other words,
>> 1. we'
balancing is in progress.
If you need i'll send you osdmap from clean cluster. Let me know.
--
Regards
Dominik
2014-02-03 Dominik Mostowiec :
> Hi,
> Thanks,
> In attachement.
>
>
> --
> Regards
> Dominik
>
>
> 2014-02-03 Sage Weil :
>> Hi Dominik
d reweight
0 and osd rm)
Pool ".rgw.buckets": one osd has 105 PGs and other one (on the same
machine) has 144 PGs (37% more!).
Other pools also have got this problem. It's not efficient placement.
--
Regards
Dominik
2014-02-02 Dominik Mostowiec :
> Hi,
> For more info:
> cr
Hi,
After command:
"ceph osd reweight-by-utilization 105"
cluster stopped on " 249 active+remapped;" state.
I have 'crush tunables optimal'.
head -n 6 /tmp/crush.txt
# begin crush map
tunable choose_local_tries 0
tunable choose_local_fallback_tries 0
tunable choose_total_tries 50
tunable chooselea
Hi,
For more info:
crush: http://dysk.onet.pl/link/r4wGK
osd_dump: http://dysk.onet.pl/link/I3YMZ
pg_dump: http://dysk.onet.pl/link/4jkqM
--
Regards
Dominik
2014-02-02 Dominik Mostowiec :
> Hi,
> Hmm,
> You think about sumarize PGs from different pools on one OSD's i think.
pool set hashpspool true
>
> to enable the new placement logic on an existing pool, but be warned that
> this will rebalance *all* of the data in the pool, which can be a very
> heavyweight operation...
>
> sage
>
>
> On Sun, 2 Feb 2014, Dominik Mostowiec wrote:
>
>&g
51615
pool 11 '.rgw.gc' rep size 3 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 8 pgp_num 8 last_change 33487 owner
18446744073709551615
pool 12 '.rgw.root' rep size 2 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 8 pgp_num 8 last_change 44540 owner 0
pool 13 ''
Hi,
> Did you bump pgp_num as well?
Yes.
See: http://dysk.onet.pl/link/BZ968
> 25% pools is two times smaller from other.
This is changing after scrubbing.
--
Regards
Dominik
2014-02-01 Kyle Bader :
>
>> Change pg_num for .rgw.buckets to power of 2, an 'crush tunables
>> optimal' didn't help :(
f strange data distribution on OSDs.
Can I do something with it?
--
Regards
Dominik
2014-02-01 Dominik Mostowiec :
> Hi,
> Change pg_num for .rgw.buckets to power of 2, an 'crush tunables
> optimal' didn't help :(
>
> Graph: http://dysk.onet.pl/link/BZ968
>
>
0497 GB / 55110 GB avail;
--
Regards
Dominik
2014-01-30 Sage Weil :
> 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
n 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 becau
have almost all data ?
> Did you try, ceph osd crush tunables optimal
No, I'll try it after change pg_num to correct value.
--
Regards
Dominik
2014-01-30 Sage Weil :
> On Thu, 30 Jan 2014, Dominik Mostowiec wrote:
>> Hi,
>> I found something else.
>> 'ceph pg dump&
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 som
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,
>
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
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 ..
#42 @ http://inktank.com | http://ceph.com
>
>
> On Sun, Jan 26, 2014 at 12:59 PM, Dominik Mostowiec
> wrote:
>> Hi,
>> It is safe to remove this files
>>> rados -p .rgw ls | grep '.bucket.meta.my_deleted_bucket:'
>> for deleted bucket via
>> rados -p
12-10 Dominik Mostowiec :
> Is there any posibility to remove this meta files? (whithout recreate cluster)
> Files names:
> {path}.bucket.meta.test1:default.4110.{sequence number}__head_...
>
> --
> Regards
> Dominik
>
> 2013/12/8 Dominik Mostowiec :
>> Hi,
>>
Is there any posibility to remove this meta files? (whithout recreate cluster)
Files names:
{path}.bucket.meta.test1:default.4110.{sequence number}__head_...
--
Regards
Dominik
2013/12/8 Dominik Mostowiec :
> Hi,
> My api app to put files to s3/ceph checks if bucket exists by create
Hi,
My api app to put files to s3/ceph checks if bucket exists by create
this bucket.
Each bucket create command adds 2 meta files.
-
root@vm-1:/vol0/ceph/osd# find | grep meta | grep test1 | wc -l
44
root@vm-1:/vol0/ceph/osd# s3 -u create test1
Bucket successfully created.
root@vm-1:/vol0/cep
Thanks for Your help !!
---
Regards
Dominik
On Dec 7, 2013 6:34 PM, "Yehuda Sadeh" wrote:
>
> Sounds like disabling the cache triggers some bug. I'll open a relevant
> ticket.
>
> Thanks,
> Yehuda
>
> On Sat, Dec 7, 2013 at 9:29 AM, Dominik Mostowiec
ok, enabling cache helps :-)
What was wrong ?
--
Dominik
2013/12/7 Dominik Mostowiec :
> Yes, it is disabled
> grep 'cache' /etc/ceph/ceph.conf | grep rgw
> rgw_cache_enabled = false ;rgw cache enabled
> rgw_cache_lru_size = 1 ;num of entries in rgw
;rgw cache enabled = false')?
>
>
>
> On Sat, Dec 7, 2013 at 8:34 AM, Dominik Mostowiec
> wrote:
>> Hi,
>> Log:
>> -
>> 2013-12-07 17:32:42.736396 7ffbe36d3780 10 allocated request req=0xe66f40
>> 2013-12-07 17:32:4
0 ==
2013-12-07 17:32:42.794156 7ffbd1ffb700 2
RGWDataChangesLog::ChangesRenewThread: start
---
--
Regards
Dominik
2013/12/7 Yehuda Sadeh :
> Not sure what could be the reason. Can you turn set 'debug ms = 1',
> and 'debug rgw = 20'?
>
> Than
added it again to cluster.
It can be a reason?
Regards
Dominik
2013/12/6 Yehuda Sadeh :
> I'm having trouble reproducing this one. Are you running on latest
> dumpling? Does it happen with any newly created bucket, or just with
> buckets that existed before?
>
> Yehuda
&
Hi,
In version dumpling upgraded from bobtail working create the same bucket.
root@vm-1:/etc/apache2/sites-enabled# s3 -u create testcreate
Bucket successfully created.
root@vm-1:/etc/apache2/sites-enabled# s3 -u create testcreate
Bucket successfully created.
I installed new dumpling cluster and:
Thanks.
--
Regards
Dominik
2013/12/3 Yehuda Sadeh :
> For bobtail at this point yes. You can try the unofficial version with
> that fix off the gitbuilder. Another option is to upgrade everything
> to dumpling.
>
> Yehuda
>
> On Mon, Dec 2, 2013 at 10:24 PM, Dominik Mostowie
io that you did. Was probably hitting it as part of
> the development work that was done then.
> In any case I created a branch with the relevant fixes in it (wip-6919).
>
> Thanks,
> Yehuda
>
> On Mon, Dec 2, 2013 at 8:39 PM, Dominik Mostowiec
> wrote:
> > for another obj
for another object.
http://pastebin.com/VkVAYgwn
2013/12/3 Yehuda Sadeh :
> I see. Do you have backtrace for the crash?
>
> On Mon, Dec 2, 2013 at 6:19 PM, Dominik Mostowiec
> wrote:
>> 0.56.7
>>
>> W dniu poniedziałek, 2 grudnia 2013 użytkownik Yehuda Sadeh napi
that differently. It only says that if there's more
> > than 1 part, all parts except for the last one need to be > 5M. Which
> > means that for uploads that are smaller than 5M there should be zero
> > or one parts.
> >
> > On Mon, Dec 2, 2013 at 12:54 PM, Do
ys that if there's more
> > than 1 part, all parts except for the last one need to be > 5M. Which
> > means that for uploads that are smaller than 5M there should be zero
> > or one parts.
> >
> > On Mon, Dec 2, 2013 at 12:54 PM, Dominik Mostowiec
> > wr
triggered from radosgw also.
--
Regards
Dominik
2013/12/2 Yehuda Sadeh :
> Looks like it. There should be a guard against it (mulitpart upload
> minimum is 5M).
>
> On Mon, Dec 2, 2013 at 12:32 PM, Dominik Mostowiec
> wrote:
>> Yes, this is probably upload empty file.
>>
Yes, this is probably upload empty file.
This is the problem?
--
Regards
Dominik
2013/12/2 Yehuda Sadeh :
> By any chance are you uploading empty objects through the multipart upload
> api?
>
> On Mon, Dec 2, 2013 at 12:08 PM, Dominik Mostowiec
> wrote:
>> Hi,
>>
ginal object, but only copy fails?
>
> On Dec 2, 2013 4:53 AM, "Dominik Mostowiec"
> wrote:
>>
>> Hi,
>> I found that issue is related with "ETag: -0" (ends -0)
>> This is known bug ?
>>
>> --
>> Regards
>> Dominik
Yes I can read it. Oryginal object is 0 size.
Regards
Dominik
On Dec 2, 2013 6:14 PM, "Yehuda Sadeh" wrote:
> That's unknown bug. I have a guess as to how the original object was
> created. Can you read the original object, but only copy fails?
> On Dec 2, 2013 4:5
Hi,
I found that issue is related with "ETag: -0" (ends -0)
This is known bug ?
--
Regards
Dominik
2013/12/2 Dominik Mostowiec :
> Hi,
> I have strange problem.
> Obj copy (0 size) killing radosgw.
>
> Head for this file:
> Content-Type: application/octet-st
Hi,
I have strange problem.
Obj copy (0 size) killing radosgw.
Head for this file:
Content-Type: application/octet-stream
Server: Apache/2.2.22 (Ubuntu)
ETag: "d41d8cd98f00b204e9800998ecf8427e-0"
Last-Modified: 2013-12-01T10:37:15Z
rgw log.
2013-12-02 08:18:59.196651 7f5308ff1700 1 == starti
Hi,
I I have replication = 3, obj A -> PG -> [1,2,3].
Osd.1 -master, 2,3 replica.
osd.1 -> host1,
osd.2 -> host2,
osd.3 -> host3.
Radosgw on host2 requests(GET) for obj A to osd.1 or to local osd.2 ?
--
Regards
Dominik
___
ceph-users mailing list
ceph-
Thanks.
--
Regards
Dominik
2013/11/26 Sage Weil :
> On Tue, 26 Nov 2013, Christoph Hellwig wrote:
>> On Tue, Nov 26, 2013 at 11:43:07AM +0100, Dominik Mostowiec wrote:
>> > Hi,
>> > I found in doc: http://ceph.com/docs/master/start/os-recommendations/
>> >
Hi,
We have 2 clusters with copy of objects.
On one of them we splited all large buckets (largest 17mln objects) to
256 buckets each (shards) and we have added 3 extra servers (6->9).
Old bucket was created in ceph argonaut.
Now we have dumpling.
After this operation get avg time increased almost t
Ok, Thanks :-)
--
Regards
Dominik
2013/11/26 Jens Kristian Søgaard :
> Hi,
>
>
>> "Putting multiple ceph-osd daemons using XFS or ext4 on the same host
>> will not perform as well as they could."
>
>
>> This means that for the best performance setup should be 1 OSD per host?
>
>
> The note only a
Hi,
I found in doc: http://ceph.com/docs/master/start/os-recommendations/
"Putting multiple ceph-osd daemons using XFS or ext4 on the same host
will not perform as well as they could."
For now recommended filesystem is XFS.
This means that for the best performance setup should be 1 OSD per host?
Hi,
I plan to delete 2 buckets, 5M and 15M files.
This can be dangerous if I do it via:
radosgw-admin --bucket=largebucket1 --purge-objects bucket rm
?
--
Pozdrawiam
Dominik
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/lis
I hope it will help.
crush: https://www.dropbox.com/s/inrmq3t40om26vf/crush.txt
ceph osd dump: https://www.dropbox.com/s/jsbt7iypyfnnbqm/ceph_osd_dump.txt
--
Regards
Dominik
2013/11/6 yy-nm :
> On 2013/11/5 22:02, Dominik Mostowiec wrote:
>>
>> Hi,
>> After remove ( ceph os
Hi,
This is s3/ceph cluster, .rgw.buckets has 3 copies of data.
Many PG's are only on 2 OSD's and are marked as 'degraded'.
Scrubbing can fix this on degraded object's?
I don't have set tunables in cruch, mabye this can help (this is safe?)?
--
Regards
Dominik
Hi,
After remove ( ceph osd out X) osd from one server ( 11 osd ) ceph
starts data migration process.
It stopped on:
32424 pgs: 30635 active+clean, 191 active+remapped, 1596
active+degraded, 2 active+clean+scrubbing;
degraded (1.718%)
All osd with reweight==1 are UP.
ceph -v
ceph version 0.56.7 (
Hi,
I have strange radosgw error:
==
2013-10-26 21:18:29.844676 7f637beaf700 0 setting object
tag=_ZPeVs7d6W8GjU8qKr4dsilbGeo6NOgw
2013-10-26 21:18:30.049588 7f637beaf700 0 WARNING: set_req_state_err
err_no=125 resorting to 500
2013-10-26 21:18:30.049738 7f637beaf700 2 req 61655:0.224186:s3
Hi,
"radosgw-admin object unlink" can do stomething like 'blind bucket'
(object in bucket without rgw index)?
--
Regards
Dominik
2013/10/13 Dominik Mostowiec :
> hmm, 'tail' - do you mean file/object content?
> I thought that this command might be workaro
Hi,
I also looking for something like that.
It is possible to set FULL_CONTROL permissions for "Group All Users", and:
- it is possible to put object to bucket (whitout authentication -> anonymous)
- setacl,getacl,get,delete not working for this object.
--
Regards
Dominik
2013/9/26 david zhang
Hi
I have found somthing.
After restart time was wrong on server (+2hours) before ntp has fixed it.
I restarted this 3 osd - it not helps.
It is possible that ceph banned this osd? Or after start with wrong
time osd has broken hi's filestore?
--
Regards
Dominik
2013/10/14 Dominik Most
Hi,
I had server failure that starts from one disk failure:
Oct 14 03:25:04 s3-10-177-64-6 kernel: [1027237.023986] sd 4:2:26:0:
[sdaa] Unhandled error code
Oct 14 03:25:04 s3-10-177-64-6 kernel: [1027237.023990] sd 4:2:26:0:
[sdaa] Result: hostbyte=DID_ERROR driverbyte=DRIVER_OK
Oct 14 03:25:04 s
en it's going to be removed later by the garbage
> collector.
>
> On Sat, Oct 12, 2013 at 11:02 PM, Dominik Mostowiec
> wrote:
>> Thanks :-)
>>
>> This command removes object from rgw index (not mark it as removed)?
>>
>> --
>> Regards
>>
Thanks :-)
This command removes object from rgw index (not mark it as removed)?
--
Regards
Domink
2013/10/13 Yehuda Sadeh :
> On Sat, Oct 12, 2013 at 4:00 PM, Dominik Mostowiec
> wrote:
>> Hi,
>> How works radosgw-admin object unlink?
>>
>> After:
>>
monitor timing configurables appropriately for that skew.
> I don't remember all the constraints you'll need to satisfy when doing that
> so I really recommend the first option.
> -Greg
>
> On Friday, September 13, 2013, Dominik Mostowiec wrote:
>>
>> Hi,
>> I
Hi,
How works radosgw-admin object unlink?
After:
radosgw-admin object unlink --bucket=testbucket 'test_file_1001.txt'
File still exists in bucket list:
s3 -u list testbucket | grep 'test_file_1001.txt'
test_file_1001.txt 2013-10-11T11:46:54Z 5
ceph -v
ceph
Ok, I found where i have seen info about upgrade bobtail->dumpling:
http://www.spinics.net/lists/ceph-users/msg03408.html
--
Regards
Dominik
2013/10/8 Dominik Mostowiec :
> ok, if I do not know for sure it is safe i will do this step by step.
> But i'm almost sure that i have see
ok, if I do not know for sure it is safe i will do this step by step.
But i'm almost sure that i have seen instructions to upgrade bobtail
to dumpling
--
Regards
Dominik
2013/10/8 Maciej Gałkiewicz :
> On 8 October 2013 09:23, Dominik Mostowiec wrote:
>> Yes,
>> i
umpling (or I can't
find this).
In this doc http://ceph.com/docs/next/install/upgrading-ceph/
For example I found argonaut->cuttlelfish.
--
Regards
Dominik
2013/10/8 Corin Langosch :
> http://ceph.com/docs/master/release-notes/
>
> Am 08.10.2013 07:37, schrieb Dominik Mostowie
hi,
It is possible to (safe) upgrade directly from bobtail (0.56.6) to
dumpling (latest)?
Is there any instruction?
--
Regards
Dominik
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
:6789 s=0 pgs=0 cs=0
l=0).accept connect_seq 122 vs existing 122 state connecting
2013-09-13 00:11:21.553559 7fd63ac3e700 0 log [INF] : mon.4 calling
new monitor election
--
Dominik
2013/9/13 Joao Eduardo Luis :
> On 09/13/2013 03:38 AM, Sage Weil wrote:
>>
>> On Thu, 12 Sep 20
Hi,
Today i have some issues with ceph cluster.
After new mon election many osd has been marked failed.
Some time later osd boot and i think recover because meny slow request appear.
Cluster come back after about 20minutes.
cluster:
ceph version 0.56.6
6 servers x 26 osd
2013-09-12 07:11:40.92038
Thanks for your answer.
Regards
Dominik
On Aug 30, 2013 4:59 PM, "Yehuda Sadeh" wrote:
> On Fri, Aug 30, 2013 at 7:44 AM, Dominik Mostowiec
> wrote:
> > (echo -n 'GET /dysk/files/test.test%
> 40op.pl/DOMIWENT%202013/Damian%20DW/dw/Specyfikacja%20istotnych%2
ska_Dolne_PB-0_went_15_11_06%20Layout1%20%284%29.pdf::http
status=400
2013-08-30 14:32:52.166653 7f42e77d6700 1 == req done
req=0x12cff20 http_status=400 ==
--
Dominik
2013/8/30 Alfredo Deza :
>
>
>
> On Fri, Aug 30, 2013 at 9:52 AM, Dominik Mostowiec
> wrote:
>>
>&
Hi,
I got err (400) from radosgw on request:
2013-08-30 08:09:19.396812 7f3b307c0700 2 req 3070:0.000150::POST
/dysk/files/test.test%40op.pl/DOMIWENT%202013/DW%202013_03_27/PROJEKTY%202012/ZB%20KROL/Szko%C5%82a%20%C5%81aziska%20ZB%20KROL/sala-%A3aziska_Dolne_PB-0_went_15_11_06%20Layout1%20%283%29.
Thank's for your answer.
--
Regards
Dominik
2013/8/22 Yehuda Sadeh :
> On Thu, Aug 22, 2013 at 7:11 AM, Dominik Mostowiec
> wrote:
>> Hi,
>> I think about sharding s3 buckets in CEPH cluster, create
>> bucket-per-XX (256 buckets) or even bucket-per-XXX (4096 bucke
I'm sorry for the spam :-(
--
Dominik
2013/8/22 Dominik Mostowiec :
> Hi,
> I think about sharding s3 buckets in CEPH cluster, create
> bucket-per-XX (256 buckets) or even bucket-per-XXX (4096 buckets)
> where XXX is sign from object md5 url.
> Could this be the problem? (
Hi,
I think about sharding s3 buckets in CEPH cluster, create
bucket-per-XX (256 buckets) or even bucket-per-XXX (4096 buckets)
where XXX is sign from object md5 url.
Could this be the problem? (performance, or some limits)
--
Regards
Dominik
___
ceph-us
Hi,
Rgw bucket index is in one file (one osd performance issues).
Is there on roudmap sharding or other change to increase performance?
--
Pozdrawiam
Dominik
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-u
Hi,
Something interesting, osd whith problems eats much more memory.
Standard is about 300m,
This osd eats even 30G.
Can i do any tests to help find where the problem is?
--
Regards
Dominik
2013/7/16 Dominik Mostowiec :
> Hi,
> I noticed that problem is more frequent at nigth where traf
hreads = 4
osd recovery threads = 1
osd recovery max active = 1
osd recovery op priority = 1
osd client op priority = 100
osd max backfills = 1
--
Regards
Dominik
2013/7/4 Dominik Mostowiec :
> I reported bug: http://tracker.ceph.com/issues/5504
>
> --
I reported bug: http://tracker.ceph.com/issues/5504
--
Regards
Dominik
2013/7/2 Dominik Mostowiec :
> 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 t
ated to the epochs too - restarting one mon
> resulting to slight dataplacement change at the moment when _first rebooted_
> monitor came up, not shown up with one hour delays between quorum restart.
>
>
>
>
> On Tue, Jul 2, 2013 at 1:37 PM, Dominik Mostowiec
> wrote:
>&g
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
I have only 'ceph healht details' from previous crash.
ceph health details
HEALTH_WARN 6 pgs peering; 9 pgs stuck unclean
pg 3.c62 is stuck unclean for 583.220063, current state active, last
acting [57,23,51]
pg 4.269 is stuck unclean for 4842.519837, current state peering, last
acting [23,57,106]
Ver. 0.56.6
Hmm, osd not died, 1 or more pg stack on peereng on it.
Regards
Dominik
On Jun 28, 2013 11:28 PM, "Sage Weil" wrote:
> On Sat, 29 Jun 2013, Andrey Korolyov wrote:
> > There is almost same problem with the 0.61 cluster, at least with same
> > symptoms. Could be reproduced quite easily
Today I have peereng problem not when I put osd.71 out, but in normal CEPH work.
Regards
Dominik
2013/6/28 Andrey Korolyov :
> There is almost same problem with the 0.61 cluster, at least with same
> symptoms. Could be reproduced quite easily - remove an osd and then
> mark it as out and with qui
Hi,
We took osd.71 out and now problem is on osd.57.
Something curious, op_rw on osd.57 is much higher than other.
See here: https://www.dropbox.com/s/o5q0xi9wbvpwyiz/op_rw_osd57.PNG
On data on this osd I found:
> data/osd.57/current# du -sh omap/
> 2.3Gomap/
That much higher op_rw on one osd
s
2013-06-04 21:22:59.836444 osd.91 [WRN] slow request 4515.530167
seconds old, received at 2013-06-04 20:07:44.306200:
osd_op(client.12947699.0:7466 rb.0.c5895a.238e1f29.1d24
[delete] 3.695f3c2a e12006) v4 currently reached pg
Regards
Dominik
2013/6/3 Gregory Farnum :
> On Sunday, June 2, 201
Hi,
I try to start postgres cluster on VMs with second disk mounted from
ceph (rbd - kvm).
I started some writes (pgbench initialisation) on 8 VMs and VMs freez.
Ceph reports slow request on 1 osd. I restarted this osd to remove
slows and VMs hangs permanently.
Is this a normal situation afer clust
99 matches
Mail list logo