Date: Thu, 18 Nov 1999 22:13:43 -0700 (MST) From: David G Andersen <danderse@cs.utah.edu> To: dillon@apollo.backplane.com (Matthew Dillon) Cc: danderse@cs.utah.edu, barrett@phoenix.aye.net, wes@softweyr.com, kris@hub.freebsd.org, trouble@netquick.net, freebsd-security@FreeBSD.ORG Subject: Re: secure filesystem wiping Message-ID: <199911190513.WAA26469@faith.cs.utah.edu> In-Reply-To: <199911190454.UAA90603@apollo.backplane.com> from "Matthew Dillon" at Nov 18, 99 08:54:43 pm
next in thread | previous in thread | raw e-mail | index | archive | help
So, one side point to Wes: Under 3.3-STABLE (Early October), obliterate on a 141 MB file on my machine with 148M ram managed to deadlock my system. I recall something about a problem like this with /dev/random, so I'm sure it's cleaned up in -current. Lo and behold, Matthew Dillon once said: > > > Both the VFS interface (read and write) and the mmap interface will > properly handle write-behind and reuse pages without loading the system > too badly. Current does a somewhat better job at it due to tuning work > and a change in the way the file position is cached in regards to > determining the file mode. Cool. MADV_SEQUENTIAL resulted in some huge "playing well with others" benefits under an earlier 3.0, but I'll confess that I haven't revisted the project of mine that was using it since. -Dave To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-security" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199911190513.WAA26469>