Date: 04 Jan 2001 16:30:04 -0500 From: Lowell Gilbert <lowell@world.std.com> To: freebsd-questions@freebsd.org Subject: Re: SMP kernel overheats Message-ID: <44snmzf1k3.fsf@lowellg.ne.mediaone.net> In-Reply-To: bright@wintelcom.net's message of "4 Jan 2001 20:19:33 %2B0100" References: <20010104191237.A580@wells.org.uk> <20010104111913.B292@fw.wintelcom.net>
next in thread | previous in thread | raw e-mail | index | archive | help
bright@wintelcom.net (Alfred Perlstein) writes: > * Michael Wells <michael@wells.org.uk> [010104 11:16] wrote: > > > > With that in mind, is it fair to ask for support of SMP systems to > > change at some point to include the instructions to run the chips > > cooler? I note the comment on temperature stability, but I think my > > mileage is varying. > > While it would be a nice feature, anyone depending on it is not being > very bright about it. Basically, you don't want a machine that's > vulnerable to a "while bomb": Or to look at it a different way, there *is* a good reason for halting idle processors: avoiding the waste of electricity on executing no-ops. Temperature, however, is *not* a good reason, because as several people have pointed out, that "solution" *depends* on your leaving the machine idle for a substantial fraction of its cycles. If your machine can't run safely without being idle a lot of the time, the operating system isn't the place to fix the "problem". 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?44snmzf1k3.fsf>