On Tue, 6 Jun 2000, Stephen C. Tweedie wrote:
> Hi,
>
> On Tue, Jun 06, 2000 at 09:17:33AM -0700, Chris Mason wrote:
>
> [ shared logs through LVM ?]
>
> It really does need to be done in the journal layer, for one simple
> reason --- performance. You need to make sure that the journal
> device is streaming to disk sequentially as much as possible, and that
> means that, ideally, you want to be able to interleave blocks from
> different filesystems into the same journal disk.
>
Grin, I was hoping to be able to waive my hands at the performance issue
until later.
There are some patterns will lvm will perform as well as doing it in the
journal code, but I really doubt there will be any patterns where lvm will
beat doing it directly in the FS.
But, a shared logging device is likely to be a problem in any log
bound application, so I'm not sure how much we can really tune it for
heavy use.
Then again, if you are using an nvram card as the shared disk, the
performance might not be as big an issue as the space overhead. It will
be interesting to see how it all interacts ;-)
-chris
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Wed Jun 07 2000 - 21:00:25 EST