(tsc) clock too slow on Core-i7/ASRock X58
in [Kernel]
|
Prev: posix_timer: move copy_to_user(created_timer_id) down in timer_create
Next: [PATCH] cris: check kmalloc return value before use data
From: 宾西蒙 on 18 May 2010 03:00 I have a problem with the system clock being off roughly 10 minutes a 2 hours on a Xeon W3250 (like Core-i7 920) using the 2.6.34 Linux and tsc clocksource. Switching to hpet seems to improve the situation momentarily, however, are there any other thoughts on this matter? What I find odd is that the processor speed in dmesg (after TSC calibration message) is 2.8 GHz, whereas BIOS says @2.67GHz, might that be related? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: john stultz on 25 May 2010 16:10
On Mon, May 17, 2010 at 11:56 PM, 宾西蒙 <binximeng(a)gmail.com> wrote: > I have a problem with the system clock being off roughly 10 minutes a 2 > hours on a Xeon W3250 (like Core-i7 920) using the 2.6.34 Linux and tsc > clocksource. Switching to hpet seems to improve the situation > momentarily, however, are there any other thoughts on this matter? > > What I find odd is that the processor speed in dmesg (after TSC > calibration message) is 2.8 GHz, whereas BIOS says @2.67GHz, might that > be related? So just to be clear, I assume the clock is ahead (fast) 10 minutes every 2 hours, right? Could you include or link to the full dmesg? Did earlier kernels (prior to 2.6.34) work properly on this machine? thanks -john -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |