Date: Mon, 13 Jul 1998 17:20:29 -0700 From: "Ronald F. Guilmette" <rfg@monkeys.com> To: Doug White <dwhite@resnet.uoregon.edu> Cc: questions@FreeBSD.ORG Subject: Re: What to do about limited caching on 430FX chipset (?) Message-ID: <11762.900375629@monkeys.com> In-Reply-To: Your message of Mon, 13 Jul 1998 14:27:31 -0700. <Pine.BSF.3.96.980713142626.25570z-100000@resnet.uoregon.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
In message <Pine.BSF.3.96.980713142626.25570z-100000@resnet.uoregon.edu>, you w rote: >On Mon, 13 Jul 1998, Ronald F. Guilmette wrote: > >> Is there any way, short of removing 64MB of memory from this system, that >> I can convince the FreeBSD kernel to avoid allocating space for programs >> and data in the upper 64MB on this system if it can be avoided? I mean >> ideally, that upper 64MB would be used only for stuff like the disk buffer >> cache and perhaps other not-too-time-sensitive stuff... unless of course >> the kernel really has no other choice but to use that for programs and >> associated data (because it has run out of run for such stuff in the lower >> 64MB). > >You can try using the MAXMEM option to your kernel to define the maximum >amount of memory the system is to use as 64MB, but then your other 64MB of >RAM sits rotting. Thanks for the tip. I may perhaps just try setting MAXMEM and then rerunning the application just to see if my suspicions about the non-caching of the upper 64MB are in fact what is making the performance of this program suck. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?11762.900375629>