From: Andreas Dilger <adilger@sun.com>
To: Sage Weil <sage@newdream.net>
Cc: linux-fsdevel@vger.kernel.org
Subject: Re: common layout xattr
Date: Fri, 17 Jul 2009 00:45:18 -0400 [thread overview]
Message-ID: <20090717044518.GB4207@webber.adilger.int> (raw)
In-Reply-To: <Pine.LNX.4.64.0907161513210.8026@cobra.newdream.net>
On Jul 16, 2009 15:29 -0700, Sage Weil wrote:
> The fs would need to add in any unspecified local settings with defaults,
> so that in general reading the xattr will still always fully describe the
> layout.
The filesystem pretty much has to do that already, because currently no
layout information is passed to the filesystem with the majority of
file creates.
> So in your example, on fsX (Lustre) you might see
>
> chunk_bytes=65536
> stripe_count=32
> mirror_count=3
> raid_type=1+0
>
> On fsY (ceph) you might see
>
> chunk_bytes=65536
> stripe_count=32
> mirror_count=3 (ceph ignores)
> raid_type=1+0 (ceph ignores)
> max_object_size=64MB (ceph adds)
Hmm, I thought Ceph had replication for files? "mirror_count" was intended
to indicate the number of copies of that file that are maintained. Maybe it
needs a better name?
> and back on fsX (Lustre) you'd get
>
> chunk_bytes=65536
> stripe_count=32
> mirror_count=3
> raid_type=1+0
> max_object_size=64MB (lustre ignores)
Exactly what I was thinking.
> How would you indicate which parameters are being ignored? Something
> easily parsed (and ignored) when setting the xattr.
I was just thinking something like a prefix or postfix character:
chunk_bytes=65536
stripe_count=32
mirror_count=3
raid_type=1+0
*max_object_size=64MB
or
max_object_size=64MB*
It might also make sense to use "*" (or some other character) to
indicate values that are the filesystem-wide default values, and
not store them either, but that isn't a well-formed opinion yet.
Even dynamically-added "comments" might be OK, like:
chunk_bytes=65536 # default
stripe_count=32 # default
mirror_count=3
raid_type=1+0 # default
max_object_size=64MB # unknown
> As long as the common parameter names are somewhat standardized, this
> seems straightforward enough.
Good, I don't want anything too complex.
Cheers, Andreas
--
Andreas Dilger
Sr. Staff Engineer, Lustre Group
Sun Microsystems of Canada, Inc.
next prev parent reply other threads:[~2009-07-17 4:45 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-07-15 21:24 [PATCH 00/20] ceph: Ceph distributed file system client v0.10 Sage Weil
2009-07-15 21:24 ` [PATCH 01/20] ceph: documentation Sage Weil
2009-07-15 21:24 ` [PATCH 02/20] ceph: on-wire types Sage Weil
2009-07-15 21:24 ` [PATCH 03/20] ceph: client types Sage Weil
2009-07-15 21:24 ` [PATCH 04/20] ceph: super.c Sage Weil
2009-07-15 21:24 ` [PATCH 05/20] ceph: inode operations Sage Weil
2009-07-15 21:24 ` [PATCH 06/20] ceph: directory operations Sage Weil
2009-07-15 21:24 ` [PATCH 07/20] ceph: file operations Sage Weil
2009-07-15 21:24 ` [PATCH 08/20] ceph: address space operations Sage Weil
2009-07-15 21:24 ` [PATCH 09/20] ceph: MDS client Sage Weil
2009-07-15 21:24 ` [PATCH 10/20] ceph: OSD client Sage Weil
2009-07-15 21:24 ` [PATCH 11/20] ceph: CRUSH mapping algorithm Sage Weil
2009-07-15 21:24 ` [PATCH 12/20] ceph: monitor client Sage Weil
2009-07-15 21:24 ` [PATCH 13/20] ceph: capability management Sage Weil
2009-07-15 21:24 ` [PATCH 14/20] ceph: snapshot management Sage Weil
2009-07-15 21:24 ` [PATCH 15/20] ceph: messenger library Sage Weil
2009-07-15 21:24 ` [PATCH 16/20] ceph: nfs re-export support Sage Weil
2009-07-15 21:24 ` [PATCH 17/20] ceph: ioctls Sage Weil
2009-07-15 21:24 ` [PATCH 18/20] ceph: debugging Sage Weil
2009-07-15 21:24 ` [PATCH 19/20] ceph: debugfs Sage Weil
2009-07-15 21:24 ` [PATCH 20/20] ceph: Kconfig, Makefile Sage Weil
2009-07-16 12:27 ` [PATCH 18/20] ceph: debugging Andi Kleen
2009-07-16 17:17 ` Sage Weil
2009-07-17 18:07 ` Sage Weil
2009-07-17 18:56 ` Andi Kleen
2009-07-17 19:52 ` Sage Weil
2009-07-17 20:01 ` Andi Kleen
2009-07-17 21:35 ` Sage Weil
2009-07-17 21:51 ` Andi Kleen
2009-07-15 22:05 ` common layout xattr Andreas Dilger
2009-07-15 22:19 ` Sage Weil
2009-07-16 5:13 ` Andreas Dilger
2009-07-16 22:29 ` Sage Weil
2009-07-17 4:45 ` Andreas Dilger [this message]
2009-07-18 4:51 ` Sage Weil
2009-07-16 19:27 ` [PATCH 16/20] ceph: nfs re-export support J. Bruce Fields
2009-07-16 19:50 ` Sage Weil
2009-07-16 21:21 ` Trond Myklebust
2009-07-16 22:07 ` Sage Weil
2009-07-17 14:05 ` J. Bruce Fields
2009-07-17 16:49 ` Sage Weil
2009-07-17 16:57 ` J. Bruce Fields
2009-07-16 12:31 ` [PATCH 02/20] ceph: on-wire types Andi Kleen
2009-07-16 16:58 ` Sage Weil
2009-07-16 3:59 ` [PATCH 00/20] ceph: Ceph distributed file system client v0.10 Noah Watkins
2009-07-16 17:03 ` Sage Weil
2009-07-16 12:26 ` Andi Kleen
2009-07-16 17:11 ` Sage Weil
2009-07-18 1:28 ` Chris Wright
2009-07-18 4:39 ` Sage Weil
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=20090717044518.GB4207@webber.adilger.int \
--to=adilger@sun.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=sage@newdream.net \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).