From: Boaz Harrosh <bharrosh@panasas.com>
To: open-osd <osd-dev@open-osd.org>,
NFS list <linux-nfs@vger.kernel.org>,
Daniel Gryniewicz <dang@linuxbox.com>,
Elizabeth Ellenbogen Ziph <elizabeth@linuxbox.com>,
"Pathak, Santosh" <santoshp@panasas.com>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>
Cc: Benny Halevy <bhalevy@primarydata.com>,
Sachin bhamare <sachin.bhamare@gmail.com>,
Tigran Mkrtchyan <tigran.mkrtchyan@desy.de>
Subject: [PACHSET 0/3] ore: raid6
Date: Thu, 22 May 2014 16:03:48 +0300 [thread overview]
Message-ID: <537DF5B4.4070001@panasas.com> (raw)
Hi all
proud to present support for raid6 in ORE.
changes since RFC:
Nothing changed. one checkpatch fix. And this time all patches actually
compile (thanks to Tigran)
I have by now tested better. RAID6 code was not actually tested heavily
but RAID5 was, and there are no known regressions to RAID5 so I'm pushing
this for next merge.
.I.E: Yes I did run all tests on RAID6 but user-mode utils do not support
scrubbing and checking of RAID6 yet. So I'm not confident that it is
100% cosher. But I do have a XOR checker and RAID5 is just as good as
current code. So I'm pushing this now and any RAID6 specific problems
can be fixed when they are found.
These simple patches will enable raid6 using the Kernel's raid6_pq engine
for support under exofs and pnfs-objects. There is nothing needed to do
at exofs and pnfs-obj. Just fire your mkfs.exofs with --raid=6 (that was
already supported before) and off you go as usual. The ORE will pick up
the new map and will start writing two devices of redundancy bits.
Including the pNFS server code and pnfs-export bits at exofs, they all
work supporting raid6 without any code modifications.
I want to deeply thank Daniel Gryniewicz who found first all the
bugs in the old raid code, and inspired these patches.
list of patches:
[PATCH 1/4] ore: (trivial) reformat some code
[PATCH 2/4] ore: Remove redundant dev_order(), more cleanups
[PATCH 3/4] ore: Support for raid 6
Cheers
Boaz
WARNING: multiple messages have this Message-ID (diff)
From: Boaz Harrosh <bharrosh-C4P08NqkoRlBDgjK7y7TUQ@public.gmane.org>
To: open-osd <osd-dev-yNzVSZO3znNg9hUCZPvPmw@public.gmane.org>,
NFS list <linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
Daniel Gryniewicz <dang-Jp3n8lUXroRWk0Htik3J/w@public.gmane.org>,
Elizabeth Ellenbogen Ziph
<elizabeth-Jp3n8lUXroRWk0Htik3J/w@public.gmane.org>,
"Pathak,
Santosh" <santoshp-C4P08NqkoRlBDgjK7y7TUQ@public.gmane.org>,
linux-fsdevel
<linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Cc: Benny Halevy <bhalevy-7I+n7zu2hftEKMMhf/gKZA@public.gmane.org>,
Sachin bhamare
<sachin.bhamare-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>,
Tigran Mkrtchyan <tigran.mkrtchyan-T5F83Mi6MZE@public.gmane.org>
Subject: [PACHSET 0/3] ore: raid6
Date: Thu, 22 May 2014 16:03:48 +0300 [thread overview]
Message-ID: <537DF5B4.4070001@panasas.com> (raw)
Hi all
proud to present support for raid6 in ORE.
changes since RFC:
Nothing changed. one checkpatch fix. And this time all patches actually
compile (thanks to Tigran)
I have by now tested better. RAID6 code was not actually tested heavily
but RAID5 was, and there are no known regressions to RAID5 so I'm pushing
this for next merge.
.I.E: Yes I did run all tests on RAID6 but user-mode utils do not support
scrubbing and checking of RAID6 yet. So I'm not confident that it is
100% cosher. But I do have a XOR checker and RAID5 is just as good as
current code. So I'm pushing this now and any RAID6 specific problems
can be fixed when they are found.
These simple patches will enable raid6 using the Kernel's raid6_pq engine
for support under exofs and pnfs-objects. There is nothing needed to do
at exofs and pnfs-obj. Just fire your mkfs.exofs with --raid=6 (that was
already supported before) and off you go as usual. The ORE will pick up
the new map and will start writing two devices of redundancy bits.
Including the pNFS server code and pnfs-export bits at exofs, they all
work supporting raid6 without any code modifications.
I want to deeply thank Daniel Gryniewicz who found first all the
bugs in the old raid code, and inspired these patches.
list of patches:
[PATCH 1/4] ore: (trivial) reformat some code
[PATCH 2/4] ore: Remove redundant dev_order(), more cleanups
[PATCH 3/4] ore: Support for raid 6
Cheers
Boaz
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next reply other threads:[~2014-05-22 13:05 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-05-22 13:03 Boaz Harrosh [this message]
2014-05-22 13:03 ` [PACHSET 0/3] ore: raid6 Boaz Harrosh
2014-05-22 13:07 ` [PATCH 1/3] ore: (trivial) reformat some code Boaz Harrosh
2014-05-22 13:07 ` Boaz Harrosh
2014-05-22 13:08 ` [PATCH 2/3] ore: Remove redundant dev_order(), more cleanups Boaz Harrosh
2014-05-22 13:11 ` [PATCH 3/3] ore: Support for raid 6 Boaz Harrosh
2014-05-22 13:11 ` Boaz Harrosh
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=537DF5B4.4070001@panasas.com \
--to=bharrosh@panasas.com \
--cc=bhalevy@primarydata.com \
--cc=dang@linuxbox.com \
--cc=elizabeth@linuxbox.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=osd-dev@open-osd.org \
--cc=sachin.bhamare@gmail.com \
--cc=santoshp@panasas.com \
--cc=tigran.mkrtchyan@desy.de \
/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.