From: Mark Nelson <mark.nelson@inktank.com>
To: Sage Weil <sage@inktank.com>
Cc: Loic Dachary <loic@dachary.org>, James Plank <plank@cs.utk.edu>,
Ceph Development <ceph-devel@vger.kernel.org>
Subject: Re: Jerasure 1.2A plugin for Ceph
Date: Wed, 11 Sep 2013 11:32:40 -0500 [thread overview]
Message-ID: <52309B28.3010607@inktank.com> (raw)
In-Reply-To: <alpine.DEB.2.00.1309110927280.23522@cobra.newdream.net>
On 09/11/2013 11:29 AM, Sage Weil wrote:
> On Wed, 11 Sep 2013, Loic Dachary wrote:
>> [cc'ing the devel mailing list]
>>
>> Hi James,
>>
>> Thanks for the positive feedback :-) I found the API fairly
>> straightforward and I don't see what could be improved. However, I've
>> learnt about erasure code and designed the Ceph plugin abstract API
>> mostly by studying jerasure. I'm probably biased : let hear what others
>> have to suggest.
>>
>> Cheers
>>
>> On 11/09/2013 17:04, James Plank wrote:
>>> Hi Loic -- I took a scan, and it looks like a nice usage of the
>>> library. Here's a question -- for the next revision of jerasure, are
>>> there any functionalities that you would like to see, that would make
>>> your life as a developer easier? Thanks! Jim ----------
>
> Hi James-
>
> Late to this discussion, and this may have already been covered, but:
> there is a bunch of Intel-optimized code floating around for various
> erasure codes. I would love to see this incorporated into jerasure (with
> automatic arch and CPU feature detection) so that users can transparently
> take advantage of it.
>
> sage
>
+1. Same for ARM down the road. :D
Mark
>
>>>
>>> On Aug 30, 2013, at 4:20 AM, Loic Dachary wrote:
>>>
>>>> Hi James,
>>>>
>>>> The first version of the jerasure 1.2A plugin for Ceph is complete at
>>>>
>>>> https://github.com/ceph/ceph/pull/538#commits-pushed-763275e
>>>>
>>>> This commit introduces the main part:
>>>> ErasureCodeJerasure: base class for jerasure ErasureCodeInterface
>>>> https://github.com/dachary/ceph/commit/76d2842358465e560a4929d60131762f8c93804f
>>>>
>>>> and each technique is derived from it in six successive commits, starting from here
>>>> ErasureCodeJerasure: define technique ReedSolomonVandermonde
>>>>
>>>> It would be great if you could take a look and let us know if you see anything odd.
>>>>
>>>> Cheers
>>>>
>>>> --
>>>> Lo?c Dachary, Artisan Logiciel Libre
>>>> All that is necessary for the triumph of evil is that good people do nothing.
>>>>
>>>
>>
>> --
>> Lo?c Dachary, Artisan Logiciel Libre
>> All that is necessary for the triumph of evil is that good people do nothing.
>>
>>
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
next prev parent reply other threads:[~2013-09-11 16:32 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-30 8:20 Jerasure 1.2A plugin for Ceph Loic Dachary
[not found] ` <CFA250A5-F536-4C28-AC69-10C7F2B6DD39@cs.utk.edu>
2013-09-11 15:40 ` Loic Dachary
2013-09-11 16:29 ` Sage Weil
2013-09-11 16:32 ` Mark Nelson [this message]
2013-09-11 17:44 ` James Plank
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=52309B28.3010607@inktank.com \
--to=mark.nelson@inktank.com \
--cc=ceph-devel@vger.kernel.org \
--cc=loic@dachary.org \
--cc=plank@cs.utk.edu \
--cc=sage@inktank.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.