Date: Mon, 21 Sep 1998 09:50:40 -0400 (EDT) From: "Ron G. Minnich" <rminnich@Sarnoff.COM> To: hackers@FreeBSD.ORG Subject: Re: malloc()ing 64K physically contiguous buffer in kernel Message-ID: <Pine.SUN.3.91.980921094533.25671B-100000@terra> In-Reply-To: <199809201745.NAA21711@skynet.ctr.columbia.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
FWIW, the whole issue of mallocing physically contiguous memory also came up as a sore point at the Extreme Linux workshop. People need to be able to allocate physically contiguous memory long after boot time, not just in that small window of time where lots of contig memory is available. Nobody, nobody, nobody has a decent answer. NT has the least indecent answer at the moment, so people seem to think it's good :-( At the same time, hardware keeps coming out that needs large blocks of physically contiguous memory. I think a reasonable approach would be a /dev/physcontig, which you open and make requests to, and which operates via requests to the VM system. I think the ugly answer is to do terrible things to the VM to make physcontig requests work. But you all know better than I do. Lest you say too many bad things about hardware designers, speaking as someone who was recently in that boat I can say that having physically contiguous memory makes many things easier not only in hardware but also in the driver ... ron Ron Minnich |"Using Windows NT, which is known to have some rminnich@sarnoff.com | failure modes, on a warship is similar to hoping (609)-734-3120 | that luck will be in our favor"- A. Digiorgio ftp://ftp.sarnoff.com/pub/mnfs/www/docs/cluster.html To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.SUN.3.91.980921094533.25671B-100000>