From owner-freebsd-hackers Thu Mar 7 8:57:31 2002 Delivered-To: freebsd-hackers@freebsd.org Received: from dire.bris.ac.uk (dire.bris.ac.uk [137.222.10.60]) by hub.freebsd.org (Postfix) with ESMTP id 896BB37B400 for ; Thu, 7 Mar 2002 08:57:16 -0800 (PST) Received: from mail.ilrt.bris.ac.uk by dire.bris.ac.uk with SMTP-PRIV with ESMTP; Thu, 7 Mar 2002 16:57:08 +0000 Received: from cmjg (helo=localhost) by mail.ilrt.bris.ac.uk with local-esmtp (Exim 3.16 #1) id 16j1AI-0001i2-00; Thu, 07 Mar 2002 16:54:50 +0000 Date: Thu, 7 Mar 2002 16:54:50 +0000 (GMT) From: Jan Grant X-X-Sender: cmjg@mail.ilrt.bris.ac.uk To: Alfred Perlstein Cc: freebsd-hackers@freebsd.org Subject: Re: Bug? still looking, yet to knock up small test case. Suggestions solicited. In-Reply-To: <20020307164259.GE26621@elvis.mu.org> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG On Thu, 7 Mar 2002, Alfred Perlstein wrote: > * Jan Grant [020307 08:12] wrote: > > Something odd seems to be happening; I'd appreciate "look here" > > suggestions. I suspect mmapped pages aren't being flushed but gawd alone > > knows why. > > > > Situation: vmware2, with a "fake disk", files in the /external FS > > (/external/vmware1/nt1.*). > > > > FBSD-stable. Behaviour's been like this for quite some time (since > > around 4.3-release, I think) > [snip] > > Note: this doesn't result in ultimately broken behaviour, because those > > pages are eventually flushed on orderly shutdown. I'm just curious as to > > why sync(2) isn't forcing this. > > Afaik this is a "feature" of Linux that the emulator tries to emulate. > > From what I've _heard_ (not witnessed), Linux doesn't have the syncer > flush mmap(2)'d data on a regular basis, so in FreeBSD we emulate this > behaviour and you get the behaviour you've been seeing. > > Since, sync(2) schedules the syncer to sync out the buffers which > are marked for ignore by the syncer you don't see anything being > done. :) Heh, cheers, I'll check that now I know what I'm after. That would explain why I couldn't replicate this using "plain" FBSD though :-) -- jan grant, ILRT, University of Bristol. http://www.ilrt.bris.ac.uk/ Tel +44(0)117 9287088 Fax +44 (0)117 9287112 RFC822 jan.grant@bris.ac.uk Generalisation is never appropriate. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message