Date: Thu, 2 Sep 1999 19:47:31 -0500 (CDT) From: Jonathan Lemon <jlemon@americantv.com> To: jkh@zippy.cdrom.com, hackers@freebsd.org Subject: Re: CFD: "bogomips" CPU performance metric Message-ID: <199909030047.TAA16433@free.pcs> In-Reply-To: <local.mail.freebsd-hackers/19990902233418$550a@fish.pcs> References: <local.mail.freebsd-hackers/199909022105.PAA43424@bootp.sls.usu.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
In article <local.mail.freebsd-hackers/19990902233418$550a@fish.pcs> you write: >> CPU: Pentium/P54C (132.73-MHz 586-class CPU) >> Origin = "GenuineIntel" Id = 0x52c Stepping=12 >> Features=0x1bf<FPU,VME,DE,PSE,TSC,MSR,MCE,CX8> >> >> Seems more precise and informative. For 386/486 based hardware >> someone could adapt one of the numerous CPU speed detection routines >> out there. > >Indeed. In fact, if someone is truly motivated to go and find >something to do, rather than adding a BogoMIPS counter why not instead >figure out some way to add CPU speed detection to SMP machines? As >anyone with an SMP box knows, that speed information is disabled for >various reasons. What I want is a simple new readable sysctl, something like: hw.clockrate: 132 I think that this would be useful both for development (how fast is that stupid machine down in the bunker?), and system admininstration (who needs a cpu upgrade this year?). Doing this for Pentium and better systems should be trivial. Doing it for 486 and lower would just add a timing loop. Doing it for SMP would be harder. hw.cpu0.clockrate: 233 hw.cpu1.clockrate: 233 Possibly? The implementer gets to pick a better name than these. -- Jonathan 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?199909030047.TAA16433>