On 25/04/15 18:38 +0200, Herve Rousseau wrote:
> From: Hervé Rousseau
>
> Running Keystone with WSGIChunkedRequest=On is not supported.
>
> We have to make sure that we set the Content-Length header when getting
> an admin token and checking revoked tokens, otherwise Keystone returns
> a HTTP 41
>>If I want to use librados API for performance testing, are there any
>>existing benchmark tools which directly accesses librados (not through
>>rbd or gateway)
you can use "rados bench" from ceph packages
http://ceph.com/docs/master/man/8/rados/
"
bench seconds mode [ -b objsize ] [ -t thre
If I want to use librados API for performance testing, are there any
existing benchmark tools which directly accesses librados (not through
rbd or gateway)
Thanks in advance,
JV
On Sun, Apr 26, 2015 at 10:46 PM, Alexandre DERUMIER
wrote:
>>>I'll retest tcmalloc, because I was prety sure to have
>>I'll retest tcmalloc, because I was prety sure to have patched it correctly.
Ok, I really think I have patched tcmalloc wrongly.
I have repatched it, reinstalled it, and now I'm getting 195k iops with a
single osd (10fio rbd jobs 4k randread).
So better than jemalloc.
- Mail original --
Hi,
also another big difference,
I can reach now 180k iops with a single jemalloc osd (data in buffer) vs 50k
iops max with tcmalloc.
I'll retest tcmalloc, because I was prety sure to have patched it correctly.
- Mail original -
De: "aderumier"
À: "Mark Nelson"
Cc: "ceph-users" , "c
On 04/26/2015 11:35 PM, Douglas Fuller wrote:
This solution just feels hacky and inefficient, so I think there is a
desire to feel like we at least tried to come up something simpler
and more efficient before proceeding.
Right. And somehow more fitting with the existing code, if
that's possibl
> On Apr 27, 2015, at 12:15 AM, Sage Weil wrote:
>
> Two basic approaches come to mind:
>
> 1) add an up-call between the front and data portions. Right now we have
> a get_reply between header and front that is used to get the buffers for
> front (and data). We could add a second that c
On Sun, 26 Apr 2015, Douglas Fuller wrote:
> >> I?d really like a solution to this, but I don?t think one is
> >> available given the constraints.
> >
> > Now that I know I understand it, I will at least provide
> > some review comments on the patches. I'll also think about
> > it a little. My i
Hi
Loic Dachary writes:
> Hi Alistair,
>
> On 29/03/2015 19:27, Alistair Israel wrote:
>> Hi, Loïc.
>>
>> Well, got some 'quality' coding time in over the weekend and managed
>> to hack this out:
>> https://gist.github.com/aisrael/b2b78d9dfdd176a232b9
I managed to hack this a little to cross ref
>> I’d really like a solution to this, but I don’t think one is
>> available given the constraints.
>
> Now that I know I understand it, I will at least provide
> some review comments on the patches. I'll also think about
> it a little. My instinct says there should be no need to
> make the cop
On 04/26/2015 09:28 AM, Douglas Fuller wrote:
Alex,
I think you are correct in both your understanding and your
impression of the approach.
OK, good to hear.
On Apr 26, 2015, at 4:44 AM, Ilya Dryomov
wrote:
On Sun, Apr 26, 2015 at 9:29 AM, Alex Elder
wrote:
On 04/24/2015 08:22 AM, Dougla
Alex,
I think you are correct in both your understanding and your impression of the
approach.
> On Apr 26, 2015, at 4:44 AM, Ilya Dryomov wrote:
>
> On Sun, Apr 26, 2015 at 9:29 AM, Alex Elder wrote:
>> On 04/24/2015 08:22 AM, Douglas Fuller wrote:
>>>
>>> Support multiple class op calls in
When we end I/O struct request with error, we need to pass
obj_request->length as @nr_bytes so that the entire obj_request worth
of bytes is completed. Otherwise block layer ends up confused and we
trip on
rbd_assert(more ^ (which == img_request->obj_request_count));
in rbd_img_obj_callback(
On Sun, Apr 26, 2015 at 9:29 AM, Alex Elder wrote:
> On 04/24/2015 08:22 AM, Douglas Fuller wrote:
>>
>> Support multiple class op calls in one ceph_msg and consolidate rbd header
>> read and refresh processes to use this feature to reduce the number of
>> ceph_msgs sent for that process. Refresh
14 matches
Mail list logo