From owner-freebsd-hackers Sun Sep 23 3:47:10 2001 Delivered-To: freebsd-hackers@freebsd.org Received: from smtp8.xs4all.nl (smtp8.xs4all.nl [194.109.127.134]) by hub.freebsd.org (Postfix) with ESMTP id 5735E37B42A for ; Sun, 23 Sep 2001 03:47:04 -0700 (PDT) Received: from freebie.xs4all.nl (freebie.xs4all.nl [213.84.32.253]) by smtp8.xs4all.nl (8.9.3/8.9.3) with ESMTP id MAA13453; Sun, 23 Sep 2001 12:47:02 +0200 (CEST) Received: (from wkb@localhost) by freebie.xs4all.nl (8.11.6/8.11.4) id f8NAl2M09958; Sun, 23 Sep 2001 12:47:02 +0200 (CEST) (envelope-from wkb) Date: Sun, 23 Sep 2001 12:47:02 +0200 From: Wilko Bulte To: Matt Dillon Cc: Poul-Henning Kamp , David Greenman , Seigo Tanimura , bright@wintelcom.net, hackers@FreeBSD.ORG Subject: Re: Conclusions on... was Re: More on the cache_purgeleafdirs() routine Message-ID: <20010923124702.B9914@freebie.xs4all.nl> References: <96469.1001237641@critter> <200109231040.f8NAeXw86352@earth.backplane.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i In-Reply-To: <200109231040.f8NAeXw86352@earth.backplane.com>; from dillon@earth.backplane.com on Sun, Sep 23, 2001 at 03:40:33AM -0700 X-OS: FreeBSD 4.4-STABLE X-PGP: finger wilko@freebsd.org 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 Sun, Sep 23, 2001 at 03:40:33AM -0700, Matt Dillon wrote: > > :> VM Page Cache, and thus not be candidates for reuse anyway. So my patch > :> has a very similar effect but without the overhead. > : > :Back when I rewrote the VFS namecache back in 1997 I added that > :clause because I saw directories getting nuked in no time because > :there were no pages holding on to them (device nodes were even worse!) > : > :So refresh my memory here, does directories get pages cached in VM if > :you have vfs.vmiodirenable=0 ? > : > :What about !UFS filesystems ? Do they show a performance difference ? > : > :Also, don't forget that if the VM system gave preferential caching to > :directory pages, we wouldn't need the VFS-cache very much in the first > :place... > : > :-- > :Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 > > Ah yes, vmiodirenable. We should just turn it on by default now. I've Has the problem of small-memory machines (< 64M IIRC) solved now? As I understand it vmiodirenable is counter-productive for these boxes. Maybe one could decide on-boot whether the amount of mem is enough to make it useful? Just a thought of course. > been waffling too long on that. With it off the buffer cache will > remember at most vfs.maxmallocspace worth of directory data (read: not > very much), and without VMIO backing, which means vnodes could be > reclaimed immediately. Ah! Now I see why that clause was put > in... but it's obsolete now if vmiodirenable is turned on, and it > doesn't scale well to large-memory machines if it is left in. -- | / o / /_ _ email: wilko@FreeBSD.org |/|/ / / /( (_) Bulte Arnhem, The Netherlands To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message