Date: Mon, 18 Dec 2000 21:22:45 +0100 From: Poul-Henning Kamp <phk@critter.freebsd.dk> To: dg@root.com Cc: cvs-committers@FreeBSD.org, cvs-all@FreeBSD.org Subject: Re: cvs commit: src/sys/vm vm_page.c Message-ID: <32456.977170965@critter> In-Reply-To: Your message of "Mon, 18 Dec 2000 12:14:24 PST." <200012182014.MAA09279@implode.root.com>
next in thread | previous in thread | raw e-mail | index | archive | help
In message <200012182014.MAA09279@implode.root.com>, David Greenman writes: >> The fix works by reverting the ordering of free memory so that the >> chances of contig_malloc() succeeding increases. >> >> PR: 23291 >> Submitted by: Andrew Atrens <atrens@nortel.ca> >> >> Revision Changes Path >> 1.155 +2 -2 src/sys/vm/vm_page.c > > You've just significantly reduced the performance of FreeBSD in the >process. FreeBSD does HEAD insertions in order to minimize cache thrashing. >This is not an appropriate fix for the problem that you're trying to fix >and I want to see this change backed out. As soon as floppies work with whatever appropriate patch the VM Gods deem suitable this can be backed out. Until this commit floppies did not work on systems with more than 256M (128M ?) of RAM because the bounce-buffer setup failed. Please look in the PR for an analysis which I think indicates that the optimization you mention were invalid since it broke floppy disks and other bounce-buffer users (like aha ?) -- Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 phk@FreeBSD.ORG | TCP/IP since RFC 956 FreeBSD committer | BSD since 4.3-tahoe Never attribute to malice what can adequately be explained by incompetence. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?32456.977170965>