>
> Anyone got any comments on this with respect to XFS?
Well, XFS transactions do not have 'invalidation blocks' they work
differently than the scheme this seems to describe. The XFS journal
is also very compact since it only logs the changes to blocks rather
than the whole block. Right now we do not have any plans for changing
the journalling in XFS - except for getting rid of the synchronous
transactions in the delete path.
Steve
>
> DSL
>
> -------- Original Message --------
> Subject: [reiserfs-list] Pingpong-Journaling in reiser4?
> Date: Thu, 30 Aug 2001 23:30:16 +0200
> From: Xuan Baldauf <xuan--reiserfs@xxxxxxxxxxx>
> Organization: Medium.net
> To: Hans Reiser <reiser@xxxxxxxxxxx>
> CC: reiserfs-list@xxxxxxxxxxx
>
> Hello Hans,
>
> are you considering pingpong-journaling for reiser4?
>
> Ping-Pong journaling is that, in the case you are able to
> know that the blocks you are writing to will be overwritten
> due to outstanding requests|future transactions, you do not
> write the invalidation block of the old transaction until
> the affected blocks are overwritten by the new transaction.
> Doing journaling in that way, you are bringing the count of
> required writes for journaling to the count of required
> writes for non-journaling (1 changed block, 1 write instead
> of 1 changed block, 1 write to the journal and 1 write to
> the real location), and thus saving half the
> journal-related writes in the ideal case. The superblock is
> a good candidate for this feature.
>
> I think that heavily loaded servers with parallel disk
> writes will be able to see a considerable speedup.
>
> Xubn.
|