Date: Wed, 6 Dec 2000 20:26:17 -0500 (EST) From: Andrew Gallatin <gallatin@cs.duke.edu> To: Wilko Bulte <wkb@freebie.demon.nl> Cc: Terry Lambert <tlambert@primenet.com>, Mike Smith <msmith@FreeBSD.ORG>, freebsd-alpha@FreeBSD.ORG Subject: Re: Lynx test / 2nd attempt Message-ID: <14894.58877.158848.243199@grasshopper.cs.duke.edu> In-Reply-To: <20001206234557.A3309@freebie.demon.nl> References: <200012062053.eB6KrNF52293@mass.osd.bsdi.com> <200012062235.PAA25544@usr08.primenet.com> <20001206234557.A3309@freebie.demon.nl>
next in thread | previous in thread | raw e-mail | index | archive | help
Wilko Bulte writes: > I *think* SRM zeros the RAM for you. And in most cases you have to The SRM does not zero memory across warm reboots, at least. This gives us opportunities to screw things up royally, like the problem that jb was seeing with newly installed bootblocks working until a cold boot. Not zeroing also allows all sorts of opportunities for cool hacks. Like leaving the buffer cache warm in ram, rebooting a box, and not needing to read the data from back from disk. Have a look at http://www.eecs.umich.edu/Rio/papers/rioFileCacheTech.ps Drew To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?14894.58877.158848.243199>