DL380 G6 - unstable tsc clocksource running CentOs 6

[leifhetlesaethe]

Hi,

Got 4 Proliant DL 380 G6 with Intel quadcore E5420 processors. The all have trouble withe the tsc clocksourse.

When i run #dmesg|egrep 'hpet|tsc' 

hpet clockevent registered
hpet0: at MMIO 0xfed00000, IRQs 2, 8, 0, 0
hpet0: 4 comparators, 64-bit 14.318180 MHz counter
Switching to clocksource hpet
rtc0: alarms up to one year, y3k, 114 bytes nvram, hpet irqs
Switching to clocksource tsc
CE: hpet increasing min_delta_ns to 40226 nsec
CE: hpet increasing min_delta_ns to 60338 nsec
CE: hpet increasing min_delta_ns to 90506 nsec
CE: hpet increasing min_delta_ns to 135758 nsec
CE: hpet increasing min_delta_ns to 203636 nsec

I have other Proliant servers running centos 6, DL380 G5, DL380 G7, DL160G6, but none of them have these have these problems. (E5405, E5606, E5649)

All machines are running Centos 6.3 with the latesk kernel.

#uname -a
Linux wsprod02.backbone.gurusoft.no 2.6.32-279.2.1.el6.x86_64 #1 SMP Fri Jul 20 01:55:29 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux

Anyone else experienced this on D380 G6?