Date: Fri, 25 Sep 1998 22:58:52 +0000 (GMT) From: Terry Lambert <tlambert@primenet.com> To: kkennawa@physics.adelaide.edu.au (Kris Kennaway) Cc: current@FreeBSD.ORG Subject: Re: VM out-of-swap problems Message-ID: <199809252258.PAA22094@usr04.primenet.com> In-Reply-To: <Pine.OSF.4.03.9809251119030.290-100000@mercury.physics.adelaide.edu.au> from "Kris Kennaway" at Sep 25, 98 11:26:34 am
next in thread | previous in thread | raw e-mail | index | archive | help
> Is anyone actively working on the problems related to daemons dying after the > system has used a large amount of swap (the old "inetd() in realloc: junk > pointer" thing)? It seems to me that with the release just around the corner > this is something which should be killed now, as it seems to be an easily > repeatable problem for many people and would adversely impact many servers in > the real world (e.g. potential DoS risk). This is known to be related to the mmap/normal-file buffer problems; specifically, a page of the executing image gets corrupted. So long as there are instances of the page cached, then you are screwed. There are at least three know bugs in this code, with one of them fixed by applying strained bits of the last Dyson mega-patch (the one that implemented CPU affinit for kernel threads, and other experimental things, at the same time). I am currently tracking one of them down, slowly (the "random processes SIG-11 during normal operation, but only on 486DX clock multiplied processors" bug). Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199809252258.PAA22094>