Date: Fri, 19 Sep 1997 18:06:09 -0700 From: Joe Eykholt <jre@ipsilon.com> To: Nate Williams <nate@mt.sri.com> Cc: Terry Lambert <tlambert@primenet.com>, toor@dyson.iquest.net, dyson@FreeBSD.ORG, karpen@ocean.campus.luth.se, current@FreeBSD.ORG Subject: Re: FYI: regarding our rfork(2) Message-ID: <34232181.718FFBF0@ipsilon.com> References: <199709192104.PAA20740@rocky.mt.sri.com> <199709192130.OAA05946@usr06.primenet.com> <199709192145.PAA20992@rocky.mt.sri.com>
next in thread | previous in thread | raw e-mail | index | archive | help
An aspect of sharing stacks that I didn't see mentioned is that it's more efficient from an implementation viewpoint for all threads to use the same virtual address space. I don't think we should impose unnecessary requirements without considering what would be lost in efficiency. If threads are to be truly light-weight, and you want the ability to run threads from the same process on different processors, then you'll want the two processors to use the identical virtual space for that process. Otherwise the kernel will need to duplicate most of the page directory in order to have some pages mapped differently in different threads. ... that'll be almost as expensive as separate processes. On a single processor, it'll mean doing a VM context switch when switching between threads on the same processor. Joe
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?34232181.718FFBF0>