On 3/27/16, 9:59 AM, "Ric Wheeler" wrote:
>On 03/16/2016 12:15 PM, Van Leeuwen, Robert wrote:
>>> My understanding of how a writeback cache should work is that it should
>>> only take a few seconds for writes to be streamed onto the network and is
>>> focussed on resolving the speed issue
Hi Dan,
Various proxmox daemons don't look happy on startup also.
Are you using a single samsung SSD for your OSD journals on this host?
Is that SSD ok?
Brian
On Tue, Mar 29, 2016 at 5:22 AM, Dan Moses wrote:
> Any suggestions to fix this issue? We are using Ceph with proxmox and vms
> won’t
unsubscribe ceph-users
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
On 03/25/2016 04:39 AM, Christian Balzer wrote:
Hello,
ID WEIGHT REWEIGHT SIZE USEAVAIL %USE VAR
0 1.0 1.0 5585G 2653G 2931G 47.51 0.85
1 1.0 1.0 5585G 2960G 2624G 53.02 0.94
2 1.0 1.0 5585G 3193G 2391G 57.18 1.02
10 1.0 1.0 3723
Thanks! I've set the parameters to the lower values and now recovery
process doesn't disrupt the rados gateway!
Regards,
J
On 03/26/2016 04:09 AM, lin zhou wrote:
Yeah,I think the main reason is the setting of pg_num and pgp_num of some key
pool.
This site will tell you the correct value:http
On 03/29/2016 10:06 AM, Van Leeuwen, Robert wrote:
On 3/27/16, 9:59 AM, "Ric Wheeler" wrote:
On 03/16/2016 12:15 PM, Van Leeuwen, Robert wrote:
My understanding of how a writeback cache should work is that it should only
take a few seconds for writes to be streamed onto the network and i
Hello,
On Tue, 29 Mar 2016 10:32:35 +0200 Jacek Jarosiewicz wrote:
> On 03/25/2016 04:39 AM, Christian Balzer wrote:
> >
> > Hello,
> >
> >>
> >> ID WEIGHT REWEIGHT SIZE USEAVAIL %USE VAR
> >>0 1.0 1.0 5585G 2653G 2931G 47.51 0.85
> >>1 1.0 1.0 5585G 2960G
Our setup matches this one exactly for Proxmox and Ceph
https://pve.proxmox.com/wiki/Ceph_Server. The brand of SSDs may not be the
same but they are the same sizes or larger and are Enterprise quality.
FilesystemSize Used Avail Use% Mounted on
udev 10M 0 1
On 03/29/2016 11:35 AM, Christian Balzer wrote:
Hello,
On Tue, 29 Mar 2016 10:32:35 +0200 Jacek Jarosiewicz wrote:
I very specifically and intentionally wrote "ceph osd crush reweight" in
my reply above.
While your current state of affairs is better, it is not permanent ("ceph
osd reweight" s
Also I see these 2 errors but not sure if they are preventing our host from
starting any VMs. Any suggestions for action to correct this?
root@pm3:~# fdisk -l
Disk /dev/ram0: 64 MiB, 67108864 bytes, 131072 sectors
Units: sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes
>>> If you try to look at the rbd device under dm-cache from another host, of
>>> course
>>> any data that was cached on the dm-cache layer will be missing since the
>>> dm-cache device itself is local to the host you wrote the data from
>>> originally.
>> And here it can (and probably will) go
Hi Dan,
the full root partition is the very first thing you have to solve.
This >can< be responsible for the missbehaviour, but it is for >sure< a
general problem you >need< to solve.
So:
1. Clean /
2. Restart the server
3. Check if its working, and if not, what are the exact error messages
If
On 03/29/2016 01:35 PM, Van Leeuwen, Robert wrote:
If you try to look at the rbd device under dm-cache from another host, of course
any data that was cached on the dm-cache layer will be missing since the
dm-cache device itself is local to the host you wrote the data from originally.
And here it
Cleaned up the old logs. All host nodes are happy now in a quorum.
However we cannot start any VMs.
trying to aquire lock...TASK ERROR: can't lock file
'/var/lock/qemu-server/lock-106.conf' - got timeout
--
Hi Dan,
the full root partition i
Hi Dan,
good.
---
Please run the command manually.
For now this is a proxmox specific problem, that something is the way,
proxmox does not like.
But why, we dont know.
You need to provide more info.
So run the command manually or search in the logs for some more info
around this task error.
The error I pasted is what we got when we ran the qm start command. Here is
something that could be the cause. I can tell from the error that we need some
tweaking but is there anything I can do to just allow us to start vms for now?
root@pm3:~# ceph health
HEALTH_WARN 380 pgs backfill; 32 pg
On Tue, 29 Mar 2016, Ric Wheeler wrote:
> > However, if the write cache would would be "flushed in-order" to Ceph
> > you would just lose x seconds of data and, hopefully, not have a
> > corrupted disk. That could be acceptable for some people. I was just
> > stressing that that isn’t the case.
Hi Dan,
please try to access the rbd volume via rados tools.
If its working ( you can list images ) then the problem is not ceph.
If its not working, then you should take care of the ceph cluster first
and make it healthy(er).
At first you should correct the mistake with the pg numbers.
--
Mi
On 03/29/2016 03:42 PM, Sage Weil wrote:
On Tue, 29 Mar 2016, Ric Wheeler wrote:
However, if the write cache would would be "flushed in-order" to Ceph
you would just lose x seconds of data and, hopefully, not have a
corrupted disk. That could be acceptable for some people. I was just
stressing t
> -Original Message-
> From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of
> Ric Wheeler
> Sent: 29 March 2016 14:07
> To: Sage Weil
> Cc: ceph-users@lists.ceph.com
> Subject: Re: [ceph-users] Local SSD cache for ceph on each compute node.
>
> On 03/29/2016 03:42 PM,
On 03/29/2016 04:35 PM, Nick Fisk wrote:
One thing I picked up on when looking at dm-cache for doing caching with
RBD's is that it wasn't really designed to be used as a writeback cache for
new writes, as in how you would expect a traditional writeback cache to
work. It seems all the policies are
> -Original Message-
> From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of
> Ric Wheeler
> Sent: 29 March 2016 14:40
> To: Nick Fisk ; 'Sage Weil'
> Cc: ceph-users@lists.ceph.com; device-mapper development de...@redhat.com>
> Subject: Re: [ceph-users] Local SSD cache
resend any one can help ?
On Thu, Mar 17, 2016 at 5:44 PM, ceph new wrote:
> HI
> i setup 2 clusters and in using radosgw_agent to sync them last week the
> sync stop working if on runinig the agent from command line i see its stuck
> on 2 files in the console im geting :
> 2016-03-17 21:11:57,3
On 03/29/2016 04:53 PM, Nick Fisk wrote:
-Original Message-
From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of
Ric Wheeler
Sent: 29 March 2016 14:40
To: Nick Fisk ; 'Sage Weil'
Cc: ceph-users@lists.ceph.com; device-mapper development
Subject: Re: [ceph-users] Local
Hi All,
I've maybe a simple question, I've setup a new cluster with Infernalis
release, there's no IO going on at the cluster level and I'm receiving a
lot of these messages:
2016-03-29 12:22:07.462818 mon.0 [INF] pgmap v158062: 8192 pgs: 8192
active+clean; 20617 MB data, 46164 MB used, 52484 GB
That seems to be scrubbing pretty often. Can you attach a config diff
from osd.4 (ceph daemon osd.4 config diff)?
-Sam
On Tue, Mar 29, 2016 at 9:30 AM, German Anders wrote:
> Hi All,
>
> I've maybe a simple question, I've setup a new cluster with Infernalis
> release, there's no IO going on at t
Sure, also the scrubbing is happening on all the osds :S
# ceph --cluster cephIB daemon osd.4 config diff
{
"diff": {
"current": {
"admin_socket": "\/var\/run\/ceph\/cephIB-osd.4.asok",
"auth_client_required": "cephx",
"filestore_fd_cache_size": "102
Hello all,
We are currently running ceph version 0.80.11 on Ubuntu 12.04.5 LTS.
I would like to upgrade the cluster so that we can stay a little more
current on the releases and hopefully take advantage of some of the
exciting new features coming out soon.
My questions are:
1)Which version
On Mon, Mar 28, 2016 at 9:55 PM, Sumit Gaur wrote:
> Hello ,
> Can anybody let me know if ceph team is working on porting of librbd on
> openSolaris like it did for librados ?
Nope, this isn't on anybody's roadmap.
-Greg
___
ceph-users mailing list
ceph
On Sat, Mar 26, 2016 at 3:13 PM, Nick Fisk wrote:
>
> Evening All,
>
> I’ve been testing the RBD snapshot functionality and one thing that I have
> seen is that once you take a snapshot of a RBD and perform small random IO on
> the original RBD, performance is really bad due to the amount of wri
Dear all,
We try to leverage RDMA as the underlying data transfer protocol to run
ceph. A quick survey leads us to XioMessenger.
When cloning code from https://github.com/linuxbox2/linuxbox-ceph
, we observe multiple branches associated with it. Can we know which one is
working and we can use for
Ceph cluster with 60 OSDs, Giant 0.87.2. One of the OSDs failed due to a
hardware error, however after normal recovery it seems stuck with
one active+undersized+degraded+inconsistent pg.
I haven't been able to get repair to happen using "ceph pg repair 12.28a";
I can see the activity logged in t
So an update for anyone else having this issue. It looks like radosgw
either has a memory leak or it spools the whole object into ram or
something.
root@kh11-9:/etc/apt/sources.list.d# free -m
total used free sharedbuffers cached
Mem: 64397 63775
Been a while, but...
On Thu, Feb 25, 2016 at 9:50 AM, Nick Fisk wrote:
> I'm just trying to understand the steps each IO goes through and have been
> looking at the output dump historic ops command from the admin socket.
> There's a couple of steps I'm not quite sure what they mean and also
> sli
> -Original Message-
> From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of
> Gregory Farnum
> Sent: 29 March 2016 18:52
> To: Nick Fisk
> Cc: Ceph Users
> Subject: Re: [ceph-users] Redirect snapshot COW to alternative pool
>
> On Sat, Mar 26, 2016 at 3:13 PM, Nick Fi
> Been a while, but...
Brilliant, just what I needed to know. Thanks for the confirmation/answers.
>
> On Thu, Feb 25, 2016 at 9:50 AM, Nick Fisk wrote:
> > I'm just trying to understand the steps each IO goes through and have
> > been looking at the output dump historic ops command from the ad
> I think this is where I see slow performance. If you are doing large IO, then
> copying 4MB objects (assuming defaults) is maybe only 2x times the original
> IO to the disk. However if you are doing smaller IO from what I can see a
> single 4kb write would lead to a 4MB object being copied to the
I've just upgrade to *jewel*, and the scrubbing seems to been corrected...
but now I'm not able to map an rbd on a host (before I was able to),
basically I'm getting this error msg:
*rbd: sysfs write failedrbd: map failed: (5) Input/output error*
# rbd --cluster cephIB create host01 --size 10240
Sounds like a version/compatibility thing. Are your rbd clients really old?
-Sam
On Tue, Mar 29, 2016 at 1:19 PM, German Anders wrote:
> I've just upgrade to jewel, and the scrubbing seems to been corrected... but
> now I'm not able to map an rbd on a host (before I was able to), basically
> I'm
Or you needed to run it as root?
-Sam
On Tue, Mar 29, 2016 at 1:24 PM, Samuel Just wrote:
> Sounds like a version/compatibility thing. Are your rbd clients really old?
> -Sam
>
> On Tue, Mar 29, 2016 at 1:19 PM, German Anders wrote:
>> I've just upgrade to jewel, and the scrubbing seems to been
On the host:
# ceph --cluster cephIB --version
*ceph version 10.1.0* (96ae8bd25f31862dbd5302f304ebf8bf1166aba6)
# rbd --version
*ceph version 10.1.0* (96ae8bd25f31862dbd5302f304ebf8bf1166aba6)
If I run the command without root or sudo the command failed with a
Permission denied
*German*
2016-0
What's the kernel version?
-Sam
On Tue, Mar 29, 2016 at 1:33 PM, German Anders wrote:
> On the host:
>
> # ceph --cluster cephIB --version
> ceph version 10.1.0 (96ae8bd25f31862dbd5302f304ebf8bf1166aba6)
>
> # rbd --version
> ceph version 10.1.0 (96ae8bd25f31862dbd5302f304ebf8bf1166aba6)
>
> If I
Under Jewel, newly created images default to features that are not currently
compatible with krbd. If you run 'rbd --cluster cephIB info host01 --pool
cinder-volumes', what features do you see? If you see more than layering, you
need to disable them via the 'rbd feature disable' command.
[1]
# rbd --cluster cephIB info e60host02 --pool cinder-volumes
rbd image 'e60host02':
size 102400 MB in 25600 objects
order 22 (4096 kB objects)
block_name_prefix: rbd_data.5ef1238e1f29
format: 2
features: layering, exclusive-lock, object-map, fast-diff, deep-flatten
flags:
I agrree. I ran in to the same issue and the error massage is not that clear.
Mapping with the kernel rbd client (rbd map) needs a quite new kernel to handle
the new image format. The work-around is to use - - image-format 1 when
creating the image.
Originalmeddelande
Från:
Running the following should fix your image up for krbd usage:
# rbd --cluster cephIB feature disable e60host02
exclusive-lock,object-map,fast-diff,deep-flatten --pool cinder-volumes
In the future, you can create krbd-compatible images by adding "--image-feature
layering" to the "rbd create" co
> > I think this is where I see slow performance. If you are doing large
> > IO, then copying 4MB objects (assuming defaults) is maybe only 2x
> > times the original IO to the disk. However if you are doing smaller IO
> > from what I can see a single 4kb write would lead to a 4MB object
> > being
it seems that the image-format option is deprecated:
# rbd --id cinder --cluster cephIB create e60host01v2 --size 100G
--image-format 1 --pool cinder-volumes -k
/etc/ceph/cephIB.client.cinder.keyring
rbd: image format 1 is deprecated
# rbd --cluster cephIB info e60host01v2 --pool cinder-volu
Jason, I try that but the mapping is not working anyway:
# rbd --cluster cephIB map e60host02 --pool cinder-volumes -k
/etc/ceph/cephIB.client.cinder.keyring
rbd: sysfs write failed
rbd: map failed: (5) Input/output error
*German*
2016-03-29 17:46 GMT-03:00 Jason Dillaman :
> Running the follo
Ok, i also got the warning but was able to use it anyway. Could be blocked in
the new release of Jewel. Probably the more correct answer is to use the other
answer (to use - - image-features layering) but haven't tried that myself.
Skickat från min Samsung-enhet
Originalmeddelande
Any Ceph krbd logs in dmesg? Given that this is a Jewel cluster on an older
kernel, my blind guess is that your CRUSH map is using newer features not
supported by your kernel. If that is the case, there should be a log message.
--
Jason Dillaman
- Original Message -
> From: "Ger
Image format 1 is still supported -- just trying to slowly move users off of it
and onto image format 2 through lots of log message nagging.
--
Jason Dillaman
- Original Message -
> From: "Stefan Lissmats"
> To: "German Anders"
> Cc: "ceph-users"
> Sent: Tuesday, March 29, 2016
On Tue, Mar 29, 2016 at 1:07 PM, Jason Dillaman wrote:
>> I think this is where I see slow performance. If you are doing large IO, then
>> copying 4MB objects (assuming defaults) is maybe only 2x times the original
>> IO to the disk. However if you are doing smaller IO from what I can see a
>> sin
Hello,
On Tue, 29 Mar 2016 18:15:00 -0400 (EDT) Jason Dillaman wrote:
> Image format 1 is still supported -- just trying to slowly move users
> off of it and onto image format 2 through lots of log message nagging.
>
Until there is a "live" migration or something as close to it as possible,
do
We faced this issue too and figured out it in Jewel the default image creation
was with format 2.
Not sure if this is a good idea to change the default though as almost all the
LTS releases are with older kernel and will face incompatibility issue.
Thanks & Regards
Somnath
-Original Message
> > > I think this is where I see slow performance. If you are doing large
> > > IO, then copying 4MB objects (assuming defaults) is maybe only 2x
> > > times the original IO to the disk. However if you are doing smaller IO
> > > from what I can see a single 4kb write would lead to a 4MB object
> >
Very good points w.r.t. easing migration. There is no plan to remove support
for image format 1 -- it's more about being able to concentrate our attention
to format 2 and to nudge users towards creating new images in format 2.
--
Jason Dillaman
- Original Message -
> From: "Christia
Understood -- format 2 was promoted to the default image format starting with
Infernalis (which not all users would have played with since it isn't LTS).
The defaults can be overridden via the command-line when creating new images or
via the Ceph configuration file.
I'll let Ilya provide input
> >> From reading the RBD layering docs it looked like you could also specify a
> >> different object size for the target. If there was some way that the
> >> snapshot could have a different object size or some sort of dirty bitmap,
> >> then this would reduce the amount of data that would have to
On Tue, 29 Mar 2016 20:45:38 -0400 (EDT) Jason Dillaman wrote:
> Very good points w.r.t. easing migration. There is no plan to remove
> support for image format 1 -- it's more about being able to concentrate
> our attention to format 2 and to nudge users towards creating new images
> in format 2.
Hello,
On Tue, 29 Mar 2016 13:47:04 -0400 Shain Miley wrote:
> Hello all,
>
> We are currently running ceph version 0.80.11 on Ubuntu 12.04.5 LTS.
>
Used to be 0.80.10/11 on Debian Jessie here.
> I would like to upgrade the cluster so that we can stay a little more
> current on the releases
Hi,cephers
some osd has high latency in theoutput of ceph osd perf,but I have
setting the reweight of these osd in crushmap tp 0.0
and I use iostat to check these disk,no load.
so how does command `ceph osd perf` work?
root@node-67:~# ceph osd perf
osdid fs_commit_latency(ms) fs_apply_latency(ms
2016-03-29 14:50 GMT+08:00 Christian Balzer :
>
> Hello,
>
> On Tue, 29 Mar 2016 14:00:44 +0800 lin zhou wrote:
>
>> Hi,Christian.
>> When I re-add these OSD(0,3,9,12,15),the high latency occur again.the
>> default reweight of these OSD is 0.0
>>
> That makes no sense, at a crush weight (not reweig
some info update:
disk are 3TB SATA,Model Number: WDC WD3000FYYZ-01UL1B1
and today,I try to set osd.0 reweight to 0.1;and then check.some
useful data found.
avg-cpu: %user %nice %system %iowait %steal %idle
1.630.000.48 16.150.00 81.75
Device: rrqm/
maybe I found the problerm:
smartctl -a /dev/sda | grep Media_Wearout_Indicator
233 Media_Wearout_Indicator 0x0032 001 001 000Old_age Always
root@node-65:~# fio -direct=1 -bs=4k -ramp_time=40 -runtime=100
-size=20g -filename=./testfio.file -ioengine=libaio -iodepth=8
-norandommap -ran
Hello,
On Wed, 30 Mar 2016 12:19:57 +0800 lin zhou wrote:
> 2016-03-29 14:50 GMT+08:00 Christian Balzer :
> >
> > Hello,
> >
> > On Tue, 29 Mar 2016 14:00:44 +0800 lin zhou wrote:
> >
> >> Hi,Christian.
> >> When I re-add these OSD(0,3,9,12,15),the high latency occur again.the
> >> default rewei
Hello,
On Wed, 30 Mar 2016 13:50:17 +0800 lin zhou wrote:
> maybe I found the problerm:
>
> smartctl -a /dev/sda | grep Media_Wearout_Indicator
> 233 Media_Wearout_Indicator 0x0032 001 001 000Old_age Always
>
Exactly what I thought it would be.
See my previous mail.
Christian
>
Any suggestions how to clean up ceph errors that don't autocorrect? All these
counters haven't moved in 2 hours now.
HEALTH_WARN 93 pgs degraded; 93 pgs stuck degraded; 113 pgs stuck unclean; 93
pgs stuck undersized; 93 pgs undersized; too many PGs per OSD (472 > max 300);
mon.0 low disk space
68 matches
Mail list logo