On Tue, Jun 05, 2012 at 11:12:30PM +0900, MORITA Kazutaka wrote:
> The old sheepdog driver didn't do asynchronous I/Os; it did a busy
> loop when send/recv returns with EAGAIN. I moved to coroutine
> implementation because it could make the sheepdog driver asynchronous
> with a very little change.
At Mon, 28 May 2012 17:36:06 +0800,
HaiTing Yao wrote:
>
> These days I created a test framework for sheepdog. In the framework, you
> just need write case definition file, then run the test and get report
> through email.
>
> I have written the basic test cases, such as create/delete, read/write
On Sat, Jun 09, 2012 at 01:18:52AM +0900, MORITA Kazutaka wrote:
> Okay, let's leave it untouched for now. I think the real advantage
> would be the optimization with splice system call mentioned by
> Christoph. I'm looking forward to it.
Yes, I'll keep the patch in my queue until I get to start
At Thu, 07 Jun 2012 10:20:49 +0800,
Liu Yuan wrote:
>
> On 06/07/2012 09:28 AM, MORITA Kazutaka wrote:
>
> > At Wed, 06 Jun 2012 18:52:16 +0800,
> > Liu Yuan wrote:
> >>
> >> On 06/06/2012 06:44 PM, Christoph Hellwig wrote:
> >>
> >>> On Wed, Jun 06, 2012 at 11:56:53AM +0800, Liu Yuan wrote:
> >>
At Fri, 8 Jun 2012 13:54:19 +0800,
Liu Yuan wrote:
>
> From: Liu Yuan
>
> The timeout of 5s really cause trouble from our observation, we see a lot of
> timeout failure when cluster is doing IO heavily.
>
> Use keepalive means we don't fail-timeout until the other end of node is
> really down.
Am 2012-06-08 14:46, schrieb David Douard:
Hi, just asking: shouldn't this question (and the "Dead sheeps" one)
better be sent on sheepdog-users mailing-list? (I mean, we **should**
begin to use it).
I think, you are right, if nobody disagree, please
send answers to my questions to sheepdog-use
On 07/06/2012 11:19, Bastian Scholz wrote:
> I have a question about migration a Qemu Virtual Machines from
> one node to another...
[...]
>
> Bastian
Hi, just asking: shouldn't this question (and the "Dead sheeps" one)
better be sent on sheepdog-users mailing-list? (I mean, we **should**
begin t
On 06/08/2012 03:44 PM, Bastian Scholz wrote:
> root@sv-it-cloud3:~# sheep /mnt/soeren-1/
>
> root@sv-it-cloud2:~# sheep /mnt/soeren-1/
> root@sv-it-cloud2:~# collie cluster format --copies=2
> root@sv-it-cloud2:~# qemu-img convert sv-bss-visu.qcow2
> sheepdog:sv-bss-visu
Would you please add '
Am 2012-06-07 12:07, schrieb Yibin Shen:
On Thu, Jun 7, 2012 at 5:38 PM, Liu Yuan
wrote:
Maybe you refer to object cache?
Yes, sorry, mixed that two...
Without object cache, the answer is NO, the data will be known to
the
cluster as soon as the request is completely.
With object cache ena
I am using sheepdog 0.2.4 since its out without any Problems, yesterday
I start upgrading to current git version, but one of my virtual
machines
crashed the hole cluster... Other Machines seems to work without
Problems..
Steps for repoducing it in a very stripped down environment.
Using the im
10 matches
Mail list logo