Messages in this thread | | | From | Heinz Mauelshagen <> | Subject | Re: Buffer Memory | Date | Thu, 11 Jun 1998 13:48:25 METDST |
| |
On Thu, 11 Jun 1998, Rik van Riel wrote
<SNIP>
> > o Patch is reverse :) > o This can give some nasty deadlocks, better would be to > allocate one 'last' page to the buffer memory, call > bdflush, schedule and return. This might give us enough > delay to clear things up. > o Something like this, written by me, got rejected by > Linus once for the very same reason I just outlined :) >
Astonished by this, because i've had the effect of VERY bad performance and even locking up WITHOUT my patch.
But with it i never recognized a lockup and allways had sufficient performance, while doing REALLY i/o intesive tests??? For example fsck'ing large filesystem (20GB++) while doing i/o on other filesystems.
I'm not sure, why this patch can cause a deadlock, because a "return 0;" is the "normal" case, if "__get_free_page" in "grow_buffers()" fails.
Heinz
--
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Systemmanagement Entwicklungsbereich 2 Deutsche Telekom AG Entwicklungszentrum Darmstadt Heinz Mauelshagen Otto-Roehm-Strasse 71c Postfach 10 05 41 mge@ez-darmstadt.telekom.de 64205 Darmstadt Germany +49 6151 886-425 FAX-386 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu
| |