> Op 8 maart 2017 om 0:35 schreef Matteo Dacrema :
>
>
> Thank you Adrian!
>
> I’ve forgot this option and I can reproduce the problem.
>
> Now, what could be the problem on ceph side with O_DSYNC writes?
>
As mentioned nothing, but what you can do with MySQL is provide it multiple RBD
disk
Ok, thank you guys.
I changed the innodb flush method to O_DIRECT and seems to performs quite
better.
Regards
Matteo
This email and any files transmitted with it are confidential and intended
solely for the use of the individual or entity to whom t
Dear Ceph community,
I noticed that many links on publications page[1]
are broken, including link to weil-thesis.pdf
Could you fix broken links so that the old links
are working again?
[1] http://ceph.com/publications/
--
Martin Bukatovic
USM QE team
___
Hello,
is there any risk related to cluster overload when the scrub is re enabled
after a certain amount of time being disabled?
I am thinking of the following scenario:
1. scrub/deep scrub are disabled.
2. after a while (few days) we re enable them. How will the cluster perform?
Will it run a
On Tue, Mar 7, 2017 at 3:05 PM, Xiaoxi Chen wrote:
> Thanks John.
>
> Very likely, note that mds_mem::ino + mds_cache::strays_created ~=
> mds::inodes, plus the MDS was the active-standby one, and become
> active days ago due to failover.
>
> mds": {
> "inodes": 1291393,
> }
> "mds_cache":
It will stick to the config. If you limit the amount of work scrub does
at a time, then you can let it do whatever it wants without issues
(except 10.2.x which had a bug fixed in 10.2.4, but skip to 10.2.5 to
fix a regression).
For example:
> # less scrub work at a time, with delay
> osd scrub chu
This point release fixes several important bugs in RBD mirroring, RGW
multi-site, CephFS, and RADOS.
We recommend that all v10.2.x users upgrade.
For more detailed information, see the complete changelog[1] and the release
notes[2]
Notable Changes
---
* build/ops: add hostname sani
Hi,
If using Erasure Coding, I think that should be using “choose indep” rather
than “firstn” (according to
http://lists.ceph.com/pipermail/ceph-users-ceph.com/2014-January/007306.html)
“- min_size 4
- max_size 4
- step take
- step chooseleaf firstn 2 type host
- step emit
- step take
- step
In my case we have 72 OSDs. We are experiencing some performance issues. We
believe that the reason is the scrubbing, so we want to turn scrubbing off for
a few days.
Given the default parameters of 1 day for scrub and 7 days for deep scrub. We
turn off scrub for let's say 6 days, then when we
After some investigation, we realized it looks like the bottleneck is in the
OSDs IOPS. The time it takes to resolve every IOP seems to be too high.
We'll apply the following upgrades:
* Ceph.conf modifications to allow better utilization of SSD Drives
* Some extra sysctl modifications
Hi!
Currently I have a cluster with 6 OSDs (5 hosts, 7TB RAID6 each).
We want to shut down the cluster but it holds some semi-productive VMs we
might or might not need in the future.
To keep them, we would like to shrink our cluster from 6 to 2 OSDs (we use
size 2 and min_size 1).
Should I set th
On 03/08/17 13:50, Laszlo Budai wrote:
>
> In my case we have 72 OSDs. We are experiencing some performance
> issues. We believe that the reason is the scrubbing, so we want to
> turn scrubbing off for a few days.
> Given the default parameters of 1 day for scrub and 7 days for deep
> scrub. We tur
Hi Kevin,
I don’t know about those flags, but if you want to shrink your cluster you can
simply set the weight of the OSDs to be removed to 0 like so: “ceph osd
reweight osd.X 0”
You can either do it gradually if your are concerned about client I/O (probably
not since you speak of a test / semi
On 17-03-08 15:39, Kevin Olbrich wrote:
Hi!
Currently I have a cluster with 6 OSDs (5 hosts, 7TB RAID6 each).
We want to shut down the cluster but it holds some semi-productive VMs
we might or might not need in the future.
To keep them, we would like to shrink our cluster from 6 to 2 OSDs (we
Hello,
No new information. Every two night server OSD 1 freeze with a load > 500.
It's every 2 days. Sometime during scrub, sometime during fstrim,
sometime during nothing...
But this night, this OSD server came not a life after some minutes as
before... 8 hours without this server and all i
Hello Guys .
I'm new to RGW and need some clarification ( i'm running 10.2.5 )
As much as i understand 'jewl' uses Civetweb instead of Apache and FastCGI
but in the configuration guide ( just the next step in the the install
guide ) it says "Configuring a Ceph Object Gateway requires a running
This PG/object is still doing something rather odd.
Attempted to repair the object, which it supposedly attempted, but now I appear
to have less visibility.
> $ ceph health detail
> HEALTH_ERR 3 pgs inconsistent; 4 scrub errors; mds0: Many clients (20)
> failing to respond to cache pressure; no
On 03/08/2017 04:55 PM, Yair Magnezi wrote:
> Hello Guys .
>
> I'm new to RGW and need some clarification ( i'm running 10.2.5 )
> As much as i understand 'jewl' uses Civetweb instead of Apache and
> FastCGI but in the configuration guide ( just the next step in the the
> install guide ) it
Hey Martin,
All of the links should be updated with the exception of the SK
Telecom paper that was linked to IEEE. I'm working on getting a hard
copy of that paper to host on ceph.com. Thanks for letting us know.
On Wed, Mar 8, 2017 at 4:22 AM, Martin Bukatovic wrote:
> Dear Ceph community,
>
>
On this subject, I have noticed there are no downloads available for
the documentation at http://docs.ceph.com/docs/master/. Would there be
any concern if this were pulled via wget scripts and made into a PDF for
offline reading or printing ? Possibly even being made available to
share.
---
-
You'd might have an easier time grabbing the source out of ceph.git/doc and
converting the raw rst files to whatever you want. :)
On Wed, Mar 8, 2017 at 10:33 AM Daniel W Corley
wrote:
> On this subject, I have noticed there are no downloads available for the
> documentation at http://docs.ceph
Two questions on Cephfs and erasure coding that Google couldn't answer.
1) How well does cephfs work with erasure coding?
2) How would you move an existing cephfs pool that uses replication to erasure
coding?
Rhian Resnick
Assistant Director Middleware and HPC
Office of Information Techno
On Wed, Mar 8, 2017 at 7:54 PM, Rhian Resnick wrote:
> Two questions on Cephfs and erasure coding that Google couldn't answer.
>
>
>
> 1) How well does cephfs work with erasure coding?
>
In the current released versions, you cannot use erasure coded pools with
CephFS, unless there is a replicate
Hi Guys,
After a disaster recovery process, making a Secondary zone the Master,
and the old Master as a Secondary zone. We could see the metadata stop
syncing between the clusters, and any new bucket or users is replicated to
Secondary Zone.
*Version Running: 10.2.6*
Running "radosgw-admin s
I use CephFS on erasure coding at home using a cache tier. It works fine for
my use case, but we know nothing about your use case to know if it will work
well for you.
The answer as to how to move an existing cephfs pool from replication to
erasure coding (and vice versa) is to create the new
Python is such a great way to learn things. Such a shame the librados
Python library is missing so much. It makes RADOS look so much more
limited than it is.
-kb
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/
I'm slowly working my way through Ceph's features...
I recently happened upon object maps. (I had heard of LevelDB being in
there but never saw how to use it: That's because I have been using
Python! And the Python library is missing lots of features! Grrr.)
How fast are those omap calls?
Wh
On Wed, Mar 8, 2017 at 2:01 PM, Kent Borg wrote:
> I'm slowly working my way through Ceph's features...
>
> I recently happened upon object maps. (I had heard of LevelDB being in there
> but never saw how to use it: That's because I have been using Python! And
> the Python library is missing lots
On Wed, Mar 8, 2017 at 9:28 PM, Kent Borg wrote:
> Python is such a great way to learn things. Such a shame the librados Python
> library is missing so much. It makes RADOS look so much more limited than it
> is.
Specifically?
I'm not saying you're wrong, but I am curious which bits in particula
On 03/08/2017 05:08 PM, John Spray wrote:
Specifically?
I'm not saying you're wrong, but I am curious which bits in particular
you missed.
Object maps. Those transaction-y things. Object classes. Maybe more I
don't know about because I have been learning via Python.
-kb, the Kent who has be
On 03/08/2017 02:15 PM, Kent Borg wrote:
On 03/08/2017 05:08 PM, John Spray wrote:
Specifically?
I'm not saying you're wrong, but I am curious which bits in particular
you missed.
Object maps. Those transaction-y things. Object classes. Maybe more I
don't know about because I have been learni
Hello,
during OSD restarts with Jewel (10.2.5 and .6 at least) I've seen
"stuck inactive for more than 300 seconds" errors like this when observing
things with "watch ceph -s" :
---
health HEALTH_ERR
59 pgs are stuck inactive for more than 300 seconds
223 pgs degrad
Hi,
We have made sure that the key,ceph user ,ceph admin keys are correct.
could you let us know if there is any other possibility that would mess
up the integration.
Regards,
Frank
On 03/06/2017 01:22 PM, Wido den Hollander wrote:
Op 6 maart 2017 om 6:26 schreef frank :
Hi,
We have se
Hello,
Yes, this is Debian Jessie with sysv-init, not systemd.
I prefer my servers to be deterministic.
Firstly an issue with /var/run/ceph.
The init.d/ceph script has these lines:
---
if [ ! -d $run_dir ]; then
# assume /var/run exists
install -d -m0
Hi, everyone.
Recently, in our test, we found a strange phenomenon: a READ req from client A
that arrived later than a WRITE req from client B is finished ealier than that
WRITE req.
The logs are as follows(we did a little modification to the level of some logs
to 1 in order to get some insigh
Hi,
I'm trying to debut why there is a big difference using POSIX AIO and libaio
when performing read tests from inside a VM using librbd.
The results I'm getting using FIO are:
POSIX AIO Read:
Type: Random Read - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block
Size: 4KB - Disk Targ
Hi,
>“The answer as to how to move an existing cephfs pool from replication to
>erasure coding (and vice versa) is to create the new pool and rsync your data
>between them.”
Shouldn’t it be possible to just do the “ceph osd tier add ecpool cachepool &&
ceph osd tier cache-mode cachepool writeb
37 matches
Mail list logo
