Hello list,
i've made some further testing and have the problem that ceph doesn't
scale for me. I added a 4th osd server to my existing 3 node osd
cluster. I also reformated all to be able to start with a clean system.
While doing random 4k writes from two VMs i see about 8% idle on the osd
I see something strange with my tests:
3 nodes (8cores E5420 @ 2.50GHz) , 5 osd (xfs) by node with 15k drives,
journal on tmpfs
kvm guest, with cache=writeback or cache=none (same result):
random write test with 4k block: 5000iop/s , cpu idle 20%
sequential write test with 4k block: 2iop/
On 6/28/12 4:25 PM, Stefan Priebe wrote:
Am 28.06.2012 17:33, schrieb Sage Weil:
Have you tried adjusting 'osd op threads'? The default is 2, but bumping
that to, say, 8, might give you better concurrency and throughput.
For me this doesn't change anything. I believe the ceph-osd processes
are
On 6/29/12 5:46 AM, Stefan Priebe - Profihost AG wrote:
Hello list,
i've made some further testing and have the problem that ceph doesn't
scale for me. I added a 4th osd server to my existing 3 node osd
cluster. I also reformated all to be able to start with a clean system.
While doing random 4
Some more testing / results:
= lowering CPU cores =
1.) disabling CPUs via
echo 0 >/sys/devices/system/cpu/cpuX/online
for core 4-7 does not change anything
2.) When only 50% of the CPUs are available each ceph-osd process takes
only half of the CPU load they use when all are useable.
Am 29.06.2012 13:37, schrieb Mark Nelson:
On 6/28/12 4:25 PM, Stefan Priebe wrote:
Am 28.06.2012 17:33, schrieb Sage Weil:
Have you tried adjusting 'osd op threads'? The default is 2, but bumping
that to, say, 8, might give you better concurrency and throughput.
For me this doesn't change any
Am 29.06.2012 13:49, schrieb Mark Nelson:
I'll try to replicate your findings in house. I've got some other
things I have to do today, but hopefully I can take a look next week. If
I recall correctly, in the other thread you said that sequential writes
are using much less CPU time on your system
Another BIG hint.
While doing random 4k I/O from one VM i archieve 14k I/Os. This is
around 54MB/s. But EACH ceph-osd machine is writing between 500MB/s and
750MB/s. What do they write?!?!
Just an idea?:
Do they completely rewrite EACH 4MB block for each 4k write?
Stefan
Am 29.06.2012 15:02
Big sorry. ceph was scrubbing during my last test. Didn't recognized this.
When i redo the test i see writes between 20MB/s and 100Mb/s. That is
OK. Sorry.
Stefan
Am 29.06.2012 15:11, schrieb Stefan Priebe - Profihost AG:
Another BIG hint.
While doing random 4k I/O from one VM i archieve 14
iostat output via iostat -x -t 5 while 4k random writes
06/29/2012 03:20:55 PM
avg-cpu: %user %nice %system %iowait %steal %idle
31,630,00 52,640,780,00 14,95
Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s
avgrq-sz avgqu-sz await svctm %u
On 06/28/2012 04:53 PM, Mark Nelson wrote:
On 06/28/2012 05:37 PM, Jim Schutt wrote:
Hi,
Lots of trouble reports go by on the list - I thought
it would be useful to report a success.
Using a patch (https://lkml.org/lkml/2012/6/28/446)
on top of 2.5-rc4 for my OSD servers, the same kernel
for m
On Fri, 29 Jun 2012, Stefan Priebe - Profihost AG wrote:
> Am 29.06.2012 13:49, schrieb Mark Nelson:
> > I'll try to replicate your findings in house. I've got some other
> > things I have to do today, but hopefully I can take a look next week. If
> > I recall correctly, in the other thread you sa
Hi,
I'm cross-posting this to the ceph-devel list since there might be
people around here running CloudStack and are interested in this.
After a couple of months worth of work I'm happy to announce that the
RBD support for primary storage in CloudStack seems to be reaching a
point where it's
On Thu, May 17, 2012 at 2:27 PM, Gregory Farnum wrote:
> Sorry this got left for so long...
>
> On Thu, May 10, 2012 at 6:23 AM, Stefan Priebe - Profihost AG
> wrote:
>> Hi,
>>
>> the "Designing a cluster guide"
>> http://wiki.ceph.com/wiki/Designing_a_cluster is pretty good but it
>> still leave
On Fri, Jun 29, 2012 at 11:07 AM, Gregory Farnum wrote:
>>> the "Designing a cluster guide"
>>> http://wiki.ceph.com/wiki/Designing_a_cluster is pretty good but it
>>> still leaves some questions unanswered.
Oh, thank you. I've been poking through the Ceph docs, but somehow
had not managed to tu
On Fri, Jun 29, 2012 at 11:42 AM, Brian Edmonds wrote:
> What are the likely and worst case scenarios if the OSD journal were
> to simply be on a garden variety ramdisk, no battery backing? In the
> case of a single node losing power, and thus losing some data, surely
> Ceph can recognize this, a
On Thu, Jun 28, 2012 at 7:27 AM, Brian Edmonds wrote:
> I've installed a little, four node Ceph (0.47.2) cluster using Xen
> virtual machines for testing, and when I run bonnie against a (kernel
> driver) mount of it, it seems to be somewhat flaky (disturbing log
> messages, occasional binary deat
On Fri, Jun 29, 2012 at 11:55 AM, Gregory Farnum wrote:
> So right now you're using the Ceph filesystem, rather than RBD, right?
Right, CephFS. I'm actually not even very clear on what RBD is, and
how one might use it, but I'm sure I'll understand that in the
fullness of time. I came to Ceph fr
On Fri, Jun 29, 2012 at 11:50 AM, Gregory Farnum wrote:
> If you lose a journal, you lose the OSD.
Really? Everything? Not just recent commits? I would have hoped it
would just come back up in an old state. Replication should have
already been taking care of regaining redundancy for the stuff
On Fri, Jun 29, 2012 at 1:54 PM, Brian Edmonds wrote:
> On Fri, Jun 29, 2012 at 11:55 AM, Gregory Farnum wrote:
>> So right now you're using the Ceph filesystem, rather than RBD, right?
>
> Right, CephFS. I'm actually not even very clear on what RBD is, and
> how one might use it, but I'm sure I
On Fri, Jun 29, 2012 at 1:59 PM, Brian Edmonds wrote:
> On Fri, Jun 29, 2012 at 11:50 AM, Gregory Farnum wrote:
>> If you lose a journal, you lose the OSD.
>
> Really? Everything? Not just recent commits? I would have hoped it
> would just come back up in an old state. Replication should have
On Fri, Jun 29, 2012 at 2:06 PM, Gregory Farnum wrote:
> Okay, there's two things I'd do here. First, create a cluster that
> only has one MDS — the multi-MDS system is significantly less stable.
Ok, will do.
> Second, you've got 3 monitors doing frequent fsyncs, and 4 OSDs doing
> frequent sync
Am 29.06.2012 17:28, schrieb Sage Weil:
On Fri, 29 Jun 2012, Stefan Priebe - Profihost AG wrote:
Am 29.06.2012 13:49, schrieb Mark Nelson:
I'll try to replicate your findings in house. I've got some other
things I have to do today, but hopefully I can take a look next week. If
I recall correct
On Fri, Jun 29, 2012 at 2:11 PM, Gregory Farnum wrote:
> Well, actually this depends on the filesystem you're using. With
> btrfs, the OSD will roll back to a consistent state, but you don't
> know how out-of-date that state is.
Ok, so assuming btrfs, then a single machine failure with a ramdisk
On Fri, Jun 29, 2012 at 2:18 PM, Brian Edmonds wrote:
> On Fri, Jun 29, 2012 at 2:11 PM, Gregory Farnum wrote:
>> Well, actually this depends on the filesystem you're using. With
>> btrfs, the OSD will roll back to a consistent state, but you don't
>> know how out-of-date that state is.
>
> Ok, s
On Fri, 29 Jun 2012, Brian Edmonds wrote:
> On Fri, Jun 29, 2012 at 2:11 PM, Gregory Farnum wrote:
> > Well, actually this depends on the filesystem you're using. With
> > btrfs, the OSD will roll back to a consistent state, but you don't
> > know how out-of-date that state is.
>
> Ok, so assumin
26 matches
Mail list logo