[REGRESSION] sudden cpu hogging in kernel 3.2 rc-series

[Nicolas Kalkhof]

Hello,

since the merges for kernel 3.2 came in late october, my mobile i7 2620M sandybridge cpu/gpu seems to run hotter (approx 10 ÂC) when idling and after some minutes according to top the cpu load goes up on all cores but the cpu frequency stays low (800 MHz) as well as the gpu (650MHz) and the system is responding well. Yet still additional 5-8 watts are continously drained from the power supply. Something is throttling up :(. Oprofile shows that the kernel hogs the cpu (see dump below). This happens with every kernel since the 3.2 merge window closed up to latest linux-next. I wasn't able to track the bad commit down yet.

Could someone please confirm the issue?

Kernel Boot Params: intel_iommu=off i915.i915_enable_rc6=1
Attached: dmesg and kernel .config.

CPU: Intel Sandy Bridge microarchitecture, speed 2.701e+06 MHz (estimated)
Counted CPU_CLK_UNHALTED events (Clock cycles when not halted) with a unit mask of 0x00 (No unit mask) count 100000
CPU_CLK_UNHALT...|
 samples| %|
------------------
 1515048 99.8101 vmlinux
ÂÂÂÂ 1950Â 0.1285 oprofiled
ÂÂÂÂÂ 356Â 0.0235 cfbimgblt
ÂÂÂÂÂ 275Â 0.0181 libc-2.13.so
ÂÂÂÂÂÂ 73Â 0.0048 cfbcopyarea
ÂÂÂÂÂÂ 62Â 0.0041 libncursesw.so.5.9
ÂÂÂÂÂÂ 45Â 0.0030 iwlwifi
ÂÂÂÂÂÂ 26Â 0.0017 bash
ÂÂÂÂÂÂ 25Â 0.0016 cfbfillrect
ÂÂÂÂÂÂ 22Â 0.0014 ld-2.13.so
ÂÂÂÂÂÂ 16Â 0.0011 htop
ÂÂÂÂÂÂ 13 8.6e-04 e1000e
ÂÂÂÂÂÂÂ 9 5.9e-04 opreport
ÂÂÂÂÂÂÂ 5 3.3e-04 libstdc++.so.6.0.14
ÂÂÂÂÂÂÂ 3 2.0e-04 acpid
ÂÂÂÂÂÂÂ 1 6.6e-05 ls
ÂÂÂÂÂÂÂ 1 6.6e-05 libncurses.so.5.9
ÂÂÂÂÂÂÂ 1 6.6e-05 libbfd-2.21.1.so


Regards
Nic

___________________________________________________________
SMS schreiben mit WEB.DE FreeMail - einfach, schnell und
kostenguenstig. Jetzt gleich testen! http://f.web.de/?mc=021192

Attachment: dmesg.next
Description: Binary data

Attachment: .config
Description: Binary data