All of lore.kernel.org
 help / color / mirror / Atom feed
From: Daniel Phillips <phillips@google.com>
To: ocfs2-devel@oss.oracle.com
Subject: [Ocfs2-devel] OCFS2 features RFC - separate journal?
Date: Thu, 04 May 2006 20:05:16 -0700	[thread overview]
Message-ID: <445AC0EC.2000601@google.com> (raw)
In-Reply-To: <20060504223037.GB21588@ca-server1.us.oracle.com>

Mark Fasheh wrote:
> Out of curiousity, are we talking about a single journal device (all slot 
 > journals on one disk) or one device per journal?

Hi Mark,

For me, all journals on one disk, but that is just what I want for my one
particular project.  The user should be able to specify slot by slot which
device the journal is on, if it is not on the main volume.  This is just
the logical extension of the Ext3 scheme.

I don't see that there is anything to be gained by requiring the user to
specify a different device for each journal since the user tools already
have to handle the case where all the journals are on the same device.

The configuration I am most interested at the moment has two nodes, each
of which exports one NVRAM disk and one normal disk to the other.  The
NVRAM disks form a mirror with two journals on it.  The normal disks
likewise form a mirror with the OCFS2 fs proper on it.  The latter
volume needs to be snapshotted and its mirror needs a dirty map.  The
dirty map will live on the (NVRAM) journal volume.  See how big a deal
it is to be able to factor out the journals like that?  As I mentioned
earlier, the journals don't need to be snapshotted and the mirror
doesn't need a dirty map, which is a really big help considering that
typical write latency is determined by the journal, and the latency of
a snapshoted, mirrored device with a persistent dirty map can get really
high.

A picture:

                Node0  <---- GigE cable  ---->  Node1
   NVRAM:   Slot0 Journal               Mirror of Slot0 Journal
            Slot1 Journal               Mirror of Slot1 Journal
            HDISK Dirty Map             Mirror of HDISK Dirty Map

   HDISK:   OCFS2 FS proper             Mirror of OCFS2 FS proper
            OCFS2 FS Snapshot Store     Mirror of OCFS2 FS Snapshot Store

As a side note, separate journals will allow the user to be much less
conservative about setting the number of slots.

Regards,

Daniel

  reply	other threads:[~2006-05-05  3:05 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-04-25 18:35 [Ocfs2-devel] OCFS2 features RFC Mark Fasheh
2006-04-25 21:55 ` Christoph Hellwig
2006-04-25 22:24   ` Mark Fasheh
2006-04-26 16:50   ` Daniel Phillips
2006-04-26  4:11 ` Andi Kleen
2006-04-26 18:06   ` Mark Fasheh
2006-04-26 18:08     ` Andi Kleen
2006-04-26 18:34       ` Daniel Phillips
2006-04-27 20:25 ` Paul Taysom
2006-05-03 23:04 ` [Ocfs2-devel] OCFS2 features RFC - separate journal? Daniel Phillips
2006-05-04  0:29   ` Zach Brown
2006-05-04  0:46     ` Daniel Phillips
2006-05-04 20:56       ` Zach Brown
2006-05-04 20:59         ` Wim Coekaerts
2006-05-04 22:23         ` Daniel Phillips
2006-05-04 22:30           ` Mark Fasheh
2006-05-05  3:05             ` Daniel Phillips [this message]
2006-05-05 18:25               ` Mark Fasheh
2006-05-06  3:09                 ` Daniel Phillips
2006-05-05 17:12             ` Paul Taysom
2006-05-05 18:06               ` Daniel Phillips
2006-05-05 18:57               ` Sunil Mushran
2006-05-08 14:28             ` Paul Taysom
2006-05-08 17:43               ` Daniel Phillips
2006-05-08 18:00             ` Paul Taysom
2006-05-08 18:22               ` Daniel Phillips
2006-05-11 20:04 ` [Ocfs2-devel] OCFS2 features RFC Jeff Mahoney
2006-05-11 20:40   ` Paul Taysom
2006-05-11 20:55     ` Joel Becker
2006-05-11 21:16   ` Daniel Phillips
2006-05-17  1:44   ` Mark Fasheh
     [not found]     ` <446BBCF5.7040903@google.com>
     [not found]       ` <20060518024638.GY21588@ca-server1.us.oracle.com>
2006-05-19  0:35         ` Daniel Phillips
2006-05-19 15:16           ` J. Bruce Fields
2006-05-20  6:11           ` Mark Fasheh
2006-05-22 19:18             ` Daniel Phillips
2006-05-22 17:01     ` Paul Taysom

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=445AC0EC.2000601@google.com \
    --to=phillips@google.com \
    --cc=ocfs2-devel@oss.oracle.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.