[Top] [All Lists]

Re: More on write caching

To: Steve Lord <lord@xxxxxxx>
Subject: Re: More on write caching
From: Simon Matter <simon.matter@xxxxxxxxxxxxxxxx>
Date: Mon, 09 Jul 2001 08:30:07 +0200
>received: from mobile.sauter-bc.com (unknown []) by basel1.sauter-bc.com (Postfix) with ESMTP id 2E90357306; Mon, 9 Jul 2001 08:39:09 +0200 (CEST)
Cc: Andrew Morton <andrewm@xxxxxxxxxx>, Jens Axboe <axboe@xxxxxxx>, Andrew Klaassen <ak@xxxxxxx>, linux-xfs@xxxxxxxxxxx
Organization: Sauter AG, Basel
References: <200107071411.f67EB9323526@xxxxxxxxxxxxxxxxxxxx>
Sender: owner-linux-xfs@xxxxxxxxxxx
Steve Lord schrieb:
> > Jens Axboe wrote:
> > >
> > > > Question is: does IDE need it at all?  If we can assume
> > > > that the data is safe once the drive has acked it, then that's
> > > > all a journalling fs cares about, yes?
> > >
> > > It would enable safe use of write caching, so yes. For a barrier write,
> > > do a sync flush following a write/write_dma/write_dma_queued command
> > > (yes dma_queued has no ordered/sync option, yay ide).
> >
> > There was some discussion a while back, (triggered by someone's
> > benchmark where IDE was thrashing SCSI) where it turned out that
> > some IDE disks were simply ignoring the flush command.
> I think the issue was that write caching was on on ide disks by default
> where on scsi it is usually off by default. The discussion was about O_SYNC,
> and they got the expected performance by disabling the caching.
> I think the only real answer is to write some tests which can be run
> on a raw disk. Work out the cache size of a device and push about that
> much data out to a raw disk, then drop the power. The tricky part is
> dropping the power quickly enough, is it possible to hook into apm
> or something and drop the power automatically? Then check that the
> data made it to disk after power up. You would need to run lots of
> cases to trust a device with write caching on.
> This would at least give us a testbed for drives and is somewhat similar
> to part of the process SGI uses to qualify scsi drives for hardware.
> Steve
> >
> > Which is a quite sane thing to do if the write cache integrity
> > is guaranteed in this manner.
> >
> > What's the story with other storage interfaces apart from SCSI?
> > Seems that most of them implement SCSI in some way anyway - are
> > there other technologies that need thinking about?

I would never trust an IDE disk will flush the cache somewhere when
power goes off. Some disks may do it, some will just use the
capasitors energy to safely park the heads and some will not even
do that. How can you know and how can one be sure? I remember a
problem people were having with windows(don't know) on fast
machines with soft power down. The machine was shutdown too fast
and poweroff without giving enough time to flush the cache and
data was lost. So how could this happen if the disk did write the
cache out to disks somewhere when power went off?


<Prev in Thread] Current Thread [Next in Thread>