Hi,
On 03/07/2017 05:53 PM, Francois Blondel wrote:
Hi all,
We have (only) 2 separate "rooms" (crush bucket) and would like to
build a cluster being able to handle the complete loss of one room.
*snipsnap*
Second idea would be to use Erasure Coding, as it fits our performance
require
Hello!
To me it looks like you have one osd on host Ceph-Stress-02 and therefore only
a weight of 1 on that host and 7 on the other. If you want of three replicas on
only three hosts you need about the same storage space on all hosts.
On Wed, Mar 8, 2017 at 4:50 AM +0100, "TYLin"
mailto:woo
Hi all,
We got 4 PG active+remapped in our cluster. We set the pool’s ruleset to
ruleset 0 and got HEALTH_OK. After we set the ruleset to ruleset 1, 4 pg is
active+remapped. The testing result from crushtool also shows some bad mapping
exists. Anyone happened to know the reason?
pool 0 'rbd
Hi Cephers,
We occasionally meet an assertion failure when trying to shutdown an MDS, as
followings:
-14> 2017-01-22 14:13:46.833804 7fd210c58700 2 --
192.168.36.11:6801/2188363 >> 192.168.36.48:6800/42546 pipe(0x558ff3803400
sd=17 :52412 s=4 pgs=227 cs=1 l=1 c=0x558ff3758900).fault (0) Su
[re-adding ML, so others may benefit]
On Tue, 7 Mar 2017 13:14:14 -0700 Mike Lovell wrote:
> On Mon, Mar 6, 2017 at 8:18 PM, Christian Balzer wrote:
>
> > On Mon, 6 Mar 2017 19:57:11 -0700 Mike Lovell wrote:
> >
> > > has anyone on the list done an upgrade from hammer (something later than
>
Hello,
as Adrian pointed out, this is not really Ceph specific.
That being said, there are literally dozen of threads in this ML about
this issue and speeding up things in general, use your google-foo.
In particular Nick Fisk's articles are a good source for understanding
what is happening and h
The problem is not so much ceph, but the fact that sync workloads tend to mean
you have an effective queue depth of 1 because it serialises the IO from the
application, as it waits for the last write to complete before issuing the next
one.
From: Matteo Dacrema [mailto:mdacr...@enter.eu]
Sent
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?
Regards
Matteo
This email and any files transmitted with it are confidential and intended
solely for the use
Possibly MySQL is doing sync writes, where as your FIO could be doing buffered
writes.
Try enabling the sync option on fio and compare results.
> -Original Message-
> From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of
> Matteo Dacrema
> Sent: Wednesday, 8 March 20
I hope you did 1 minute interval of iostat. Based on your iostat & disk info.
· avgrq-sz is showing 750.49 & avgqu-sz is showing 17.39
· 375.245 KB is your average block size.
· That said, your disk is showing a Quee of 17.39 length. Typically
higher Q length will inc
On 03/07/2017 04:35 PM, Gregory Farnum wrote:
Creating a snapshot generally involves a round-trip to the monitor,
which requires a new OSDMap epoch (although it can coalesce) — ie, the
monitor paxos commit and processing the new map on all the OSDs/PGs.
Destroying a snapshot involves adding the s
On Tue, Mar 7, 2017 at 12:43 PM, Kent Borg wrote:
> On 01/04/2017 03:41 PM, Brian Andrus wrote:
>>
>> Think "many objects, few pools". The number of pools do not scale well
>> because of PG limitations. Keep a small number of pools with the proper
>> number of PGs.
>
>
> I finally got it through m
Hi,
thank you all.
I’m using Mellanox switches with connectX-3 40 gbit pro NIC.
Bond balance-xor with policy layer3+4
It’s a bit expensive but it’s very hard to saturate.
I’m using one single nic for both replica and access network.
> Il giorno 03 mar 2017, alle ore 14:52, Vy Nguyen Tan
>
Hi Deepak,
thank you.
Here an example of iostat
avg-cpu: %user %nice %system %iowait %steal %idle
5.160.002.64 15.740.00 76.45
Device: rrqm/s wrqm/s r/s w/s rkB/s
wkB/s avgrq-szavgqu-sz
My response is without any context to ceph or any SDS, purely how to check the
IO bottleneck. You can then determine if its Ceph or any other process or disk.
>> MySQL can reach only 150 iops both read or writes showing 30% of IOwait.
Lower IOPS is not issue with itself as your block size migh
Hi All,
I have a galera cluster running on openstack with data on ceph volumes capped
at 1500 iops for read and write ( 3000 total ).
I can’t understand why with fio I can reach 1500 iops without IOwait and MySQL
can reach only 150 iops both read or writes showing 30% of IOwait.
I tried with fi
Hi,
We have a pure SSD based Ceph cluster (+100 OSDs with Enterprise SSDs and IT
mode cards) Hammer 0.94.9 over 10G. It's really stable and we are really happy
with the performance we are getting. But after a customer ran some tests, we
realized about something quite strange. Our user did some
On 01/04/2017 03:41 PM, Brian Andrus wrote:
Think "many objects, few pools". The number of pools do not scale well
because of PG limitations. Keep a small number of pools with the
proper number of PGs.
I finally got it through my head, seems the larger answer is: Not only
it is okay to have a
Gregory, thanks for the response, what you've said is by far, the most
enlightneen thing i know about ceph in a long time.
What brings even greater doubt, which is, this "non-functional" pool, was
only 1.5GB large, vs 50-150GB on the other effected pools, the tiny pool
was still being used, and ju
Hi Dan,
On Tue, Mar 7, 2017 at 11:10 AM, Daniel Davidson
wrote:
> When I try this command, I still get errors:
>
> ceph daemon mds.0 config show
> admin_socket: exception getting command descriptions: [Errno 2] No such file
> or directory
> admin_socket: exception getting command descriptions: [E
Some facts:
The OSDs use a lot of gossip protocols to distribute information.
The OSDs limit how many client messages they let in to the system at a time.
The OSDs do not distinguish between client ops for different pools (the
blocking happens before they have any idea what the target is).
So, yes
Hi all,
We have (only) 2 separate "rooms" (crush bucket) and would like to build a
cluster being able to handle the complete loss of one room.
First idea would be to use replication:
-> As we read the mail thread "2x replication: A BIG warning", we would chose a
replication size of 3.
-> We
When I try this command, I still get errors:
ceph daemon mds.0 config show
admin_socket: exception getting command descriptions: [Errno 2] No such
file or directory
admin_socket: exception getting command descriptions: [Errno 2] No such
file or directory
I am guessing there is a path set up i
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": {
"num_strays": 3559,
"strays_created": 706120,
On Tue, Mar 7, 2017 at 9:17 AM, Xiaoxi Chen wrote:
> Hi,
>
> From the admin socket of mds, I got following data on our
> production cephfs env, roughly we have 585K inodes and almost same
> amount of caps, but we have>2x dentries than inodes.
>
> I am pretty sure we dont use hard link
On Tue, Mar 7, 2017 at 3:30 PM, kefu chai wrote:
> On Fri, Mar 3, 2017 at 11:40 PM, Sage Weil wrote:
>> On Fri, 3 Mar 2017, Mike Lovell wrote:
>>> i started an upgrade process to go from 0.94.7 to 10.2.5 on a production
>>> cluster that is using cache tiering. this cluster has 3 monitors, 28 stor
Am Dienstag, den 07.03.2017, 11:14 +0100 schrieb Ilya Dryomov:
On Tue, Mar 7, 2017 at 10:27 AM, Francois Blondel
mailto:fblon...@intelliad.de>> wrote:
Hi all,
I have been triyng to use RBD devices on a Erasure Coded data-pool on Ubuntu
Xenial.
I created my block device "blockec2" with :
rbd c
On Tue, Mar 7, 2017 at 10:27 AM, Francois Blondel wrote:
> Hi all,
>
> I have been triyng to use RBD devices on a Erasure Coded data-pool on Ubuntu
> Xenial.
>
> I created my block device "blockec2" with :
> rbd create blockec2 --size 300G --data-pool ecpool --image-feature
> layering,data-pool
>
they are there, as workaround, download it manually from:
http://download.ceph.com/debian-hammer/pool/main/c/ceph/
*0.94.9-1~bpo70+1
http://download.ceph.com/debian-hammer/pool/main/c/curl/
*7.29.0-1~bpo70+1
and install with dpkg -i *.deb what u need
best regards rainer
On 06/03/17 22:50,
> -Original Message-
> From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of John
> Spray
> Sent: 07 March 2017 01:45
> To: Christian Balzer
> Cc: ceph-users@lists.ceph.com
> Subject: Re: [ceph-users] A Jewel in the rough? (cache tier bugs and
> documentation omissions
Hi all,
I have been triyng to use RBD devices on a Erasure Coded data-pool on Ubuntu
Xenial.
I created my block device "blockec2" with :
rbd create blockec2 --size 300G --data-pool ecpool --image-feature
layering,data-pool
(same issue with "rbd create blockec2 --size 300G --data-pool ecpool" )
Hi,
From the admin socket of mds, I got following data on our
production cephfs env, roughly we have 585K inodes and almost same
amount of caps, but we have>2x dentries than inodes.
I am pretty sure we dont use hard link intensively (if any).
And the #ino match with "rados ls --pool $
32 matches
Mail list logo
