Date: Wed, 27 Sep 2000 15:51:07 +0200 From: Andreas Persson <pap@garen.net> To: "O. Hartmann" <ohartman@ipamzlx.physik.uni-mainz.de> Cc: freebsd-stable@freebsd.org, freebsd-hardware@freebsd.org Subject: Re: max. amount of physical memory in FBSD 4.1? Message-ID: <20000927155106.C72327@sophocles> In-Reply-To: <Pine.BSF.4.21.0009271326460.2125-100000@ipamzlx.physik.uni-mainz.de>; from ohartman@ipamzlx.physik.uni-mainz.de on Wed, Sep 27, 2000 at 01:34:02PM %2B0200 References: <Pine.BSF.4.21.0009271326460.2125-100000@ipamzlx.physik.uni-mainz.de>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, Sep 27, 2000 at 01:34:02PM +0200, "O. Hartmann" <ohartman@ipamzlx.physik.uni-mainz.de> wrote: >Dear Sirs. > >Every step done under Linux is well documented by the press, especially here >in Germany! When Microsoft found a bug in AMD's Athlon CPUs which causes >Win2k to crash, the 4GB physical memory limit came into play again. Some >discussions were made about PAE addressing modell and so on and although the >discussion started on a M$ <-> AMD problem, the migration towards Linux's >memory modell was done smoothly. Well, we now know, Linux has recently a >4GB physical memory limitation due its PAE address space model. And what is >about FreeBSD 4.1? We use now TYAN's Thunder 2500 maonboard which is capable >to hold two CPUs and get equipted with max. 8GB main memory. This is a nice >option because we plan to solve some memory intensive environtmental >research calculations. So, my question seems to be stupid for those who >understand reading kernel code, but for me, a kind of "normalo", please >tell me: how much memory and how many CPUs is FreeBSD 4.1.1-STABLE capable to >work with in a stable fashion? There are some fairly complex issues that need to be resolved before FreeBSD can support more than 4GB of physical memory (splitting vm_offset/vm_size into virtual and physical parts like netbsd, cleanups, drivers that do dma..). But 4GB works just fine. As for processors, IIRC, it supports any amount that the hardware can handle, but it won't scale very well with many due to the big lock. >Many thanks, > >Gruss O. Hartmann >------------------------------------------------------------------- >ohartman@ipamzlx.physik.uni-mainz.de > >Klimadatenserver des IPA, Universitaet Mainz >Netzwerk- und Systembetreuung -- Andreas Persson pap@garen.net To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20000927155106.C72327>