Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 19 Sep 1998 19:54:57 +0000 (GMT)
From:      Terry Lambert <tlambert@primenet.com>
To:        eivind@yes.no (Eivind Eklund)
Cc:        tlambert@primenet.com, Don.Lewis@tsc.tdk.com, current@FreeBSD.ORG
Subject:   Re: softupdates & fsck
Message-ID:  <199809191954.MAA11587@usr02.primenet.com>
In-Reply-To: <19980919202409.40703@follo.net> from "Eivind Eklund" at Sep 19, 98 08:24:09 pm

next in thread | previous in thread | raw e-mail | index | archive | help
> > They do if you set their options correctly and insure a holdup
> > time after power failure, during which you will not engage in
> > scheduling new writes.
> 
> Eh?  Without an UPS, I can't do that.

You only need a little notification.  Like the time between AC fail
and DC fail.

> The problem is drives that don't honour the immediate-write flag,
> returning before data is committed to disk anyway (done to get better
> benchmarks).  I think there also is some problems with drives that
> will re-order requests no matter what constraints you give it :-(

I don't think this is the case.  The problem was only recently reported,
and it's only misconfigured or crappy (IDE) drives that do this (if a
SCSI drive does this, it should be fixable in mode page 2, I think).


> BTW: I didn't mean that this applied in this particular case, just
> that this may become a problem when soft updates become fsck-less.

It's a serious problem, as serious as running your FS's mounted async.

Oh... here's a thought -- is someone trying to combine "async" with
"soft updates"?

Soft updates had this problem originally because the sync(2) call didn't
do the right thing (tick the sync soft clock wheel until it was empty)
in the first pass at the soft updates code.

Fixing this took a long time, and it *was* fixed.  Unordered writes
of async queued events are equivalent to async writes, and you know
how I hate those.  8-(.


					Terry Lambert
					terry@lambert.org
---
Any opinions in this posting are my own and not those of my present
or previous employers.

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199809191954.MAA11587>