Date: Mon, 12 Mar 2001 01:25:28 -0800 From: Jordan Hubbard <jkh@osd.bsdi.com> To: clash@tasam.com Cc: bright@wintelcom.net, ianc@ednet.co.uk, freebsd-hackers@FreeBSD.ORG Subject: Re: Greater than 2GB per process Message-ID: <20010312012528D.jkh@osd.bsdi.com> In-Reply-To: <003701c0aaaf$a4566ce0$dc02010a@fireduck.com> References: <Pine.LNX.4.31L2.0103120005460.9179-100000@pachabel.ednet.co.uk> <20010311204130.N18351@fw.wintelcom.net> <003701c0aaaf$a4566ce0$dc02010a@fireduck.com>
next in thread | previous in thread | raw e-mail | index | archive | help
> I know very little about how kernel or low level processor stuff works, but > shouldn't we be able to do a 4GB process on a 32-bit system? > The limitation of 2GB per process should only be an issue if there is some > need to use signed numbers, right? Well, that single 4GB of address space is divided up into kernel data structures, which are in the address space of the process but subject to various levels of MMU-provided memory protection, and the process' own "user data." I believe the break is currently set in the middle at 2GB, and various attempts to adjust it more aggressively (in user data's favor) have been interesting but ultimately also proved to break things like BSD/OS binaries, which have their own assumptions about the setting of the break. - Jordan 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?20010312012528D.jkh>