Date: Fri, 10 Aug 2007 13:15:19 +0200 From: =?utf-8?Q?Dag-Erling_Sm=C3=B8rgrav?= <des@des.no> To: Pietro Cerutti <gahr@gahr.ch> Cc: freebsd-hackers@freebsd.org Subject: Re: Core temperature Message-ID: <86r6mb7i9k.fsf@ds4.des.no> In-Reply-To: <46BC4309.8000802@gahr.ch> (Pietro Cerutti's message of "Fri\, 10 Aug 2007 12\:50\:49 %2B0200") References: <86myx0pa9i.fsf@ds4.des.no> <46BC4309.8000802@gahr.ch>
next in thread | previous in thread | raw e-mail | index | archive | help
Pietro Cerutti <gahr@gahr.ch> writes: > Could you please try to explain these results? > > % sysctl hw.coretemp.tjmax hw.coretemp.delta hw.acpi.thermal.tz0.temperat= ure > hw.coretemp.tjmax: 100 > hw.coretemp.delta: -38 > hw.acpi.thermal.tz0.temperature: 66.8C > > Shouldn't hw.coretemp.delta be (hw.coretemp.tjmax - > hw.acpi.thermal.tz0.temperature)? The value reported by hw.acpi.thermal.tz0.temperature most likely comes from a temperature sensor mounted somewhere on the motherboard, while hw.coretemp.delta reports the temperature inside the CPU itself. In my experience, Core-based CPUs run very cool under light load, so the result does not surprise me. here's what coretemp reports on my file server: hw.coretemp.tjmax: 100 hw.coretemp.delta: -46 although I believe this is actually one of the CPUs that have an 85=C2=B0C Tj(max), giving a core temperature of 39=C2=B0C and not 54=C2=B0C (the box = has a 2.4 GHz C2D but spends most of its time barely ticking over at 200 MHz) DES --=20 Dag-Erling Sm=C3=B8rgrav - des@des.no
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?86r6mb7i9k.fsf>