Re: [patch] Trivial diff: M_ZERO

#1 (**permalink**) 02-18-2008, 09:32 AM

> Date: Fri, 07 Sep 2007 11:33:55 +0200
> From: Miod Vallat <miod@online.fr>
> Cc: Artur Grabowski <art@blahonga.org>,
> Owain Ainsworth <zerooa@googlemail.com>, tech@openbsd.org
> X-Loop: tech@openbsd.org
> Sender: owner-tech@openbsd.org
> X-XS4ALL-DNSBL-Checked: mxdrop28.xs4all.nl checked 192.43.244.163 against DNS blacklists
> X-Virus-Scanned: by XS4ALL Virus Scanner
> X-XS4ALL-Spam-Score: 0.0 () DK_POLICY_SIGNSOME
> X-XS4ALL-Spam: NO
> X-CNFS-Analysis: v=1.0 c=1 a=DaTGkZDUyzMA:15 a=A3duGc4wJ8K8BtNzzvyz4A==:17 a=yvmfCgYe8HwM_ULmt1sA:9 a=69BfWku5YhJBH8tph_J4_SANKUQA:4 a=WcGY3-TIXCwA:10
> Envelope-To: mark.kettenis@xs4all.nl
> X-UIDL: 1189158313._smtp.mxdrop28.30809,S=2720
>
> >> There's not much we can do in malloc to actually do something smart about
> >> this flag, so, my question is: is it really that much harder to just do
> >> that zeroing yourself?
> >
> > the point is that back-end allocator can then pull tha pags
> > from the zero pool that is replenished in the idle loop.
>
> But page zeroing in the idle loop is disabled on all platforms so far.

Except on landisk if I read the code correctly.

Thread Tools
Show Printable Version Email this Page
Display Modes
Linear Mode Switch to Hybrid Mode Switch to Threaded Mode