Hi Patrick,
Sorry for the slow response you caught me taking a few days off :-)
On 03/07/2014 07:49 AM, Patrik Lundquist wrote:
Hi,
booting 3.13.5 on a dual socket Ivy Bridge-EP resulted in this error:
[ 0.194139] smpboot: CPU0: Intel(R) Xeon(R) CPU E5-2687W v2 @
3.40GHz (fam: 06, model: 3e, stepping: 04)
...
[ 0.246755] x86: Booting SMP configuration:
[ 0.250935] .... node #0, CPUs: #1 #2 #3 #4 #5 #6 #7
[ 0.357648] .... node #1, CPUs: #8 #9 #10 #11 #12 #13 #14 #15
[ 0.553293] x86: Booted up 2 nodes, 16 CPUs
[ 0.557666] smpboot: Total of 16 processors activated (108850.19 BogoMIPS)
...
[ 5.210204] Intel P-state driver initializing.
[ 5.232407] Intel pstate controlling: cpu 0
[ 5.253628] Intel pstate controlling: cpu 1
[ 5.274899] cpufreq: __cpufreq_add_dev: ->get() failed
[ 5.294856] Intel pstate controlling: cpu 2
[ 5.313553] Intel pstate controlling: cpu 3
[ 5.332526] Intel pstate controlling: cpu 4
[ 5.352347] Intel pstate controlling: cpu 5
[ 5.372112] Intel pstate controlling: cpu 6
[ 5.391097] Intel pstate controlling: cpu 7
[ 5.410272] Intel pstate controlling: cpu 8
[ 5.429092] Intel pstate controlling: cpu 9
[ 5.447714] Intel pstate controlling: cpu 10
[ 5.465872] Intel pstate controlling: cpu 11
[ 5.482942] Intel pstate controlling: cpu 12
[ 5.498414] Intel pstate controlling: cpu 13
[ 5.513586] Intel pstate controlling: cpu 14
[ 5.529200] Intel pstate controlling: cpu 15
CPU 1 is alive and well but missing the cpufreq driver. The system is
running fine otherwise.
This is a regression introduced by commit
da60ce9f2fa cpufreq: call cpufreq_driver->get() after calling ->init()
A return of zero from cpufreq_driver->get() is a warning at best for
intel_pstate at init time. In fact zero is a valid return value AFAICT.
I should be doing something rational in any case.
Looking closer at the problem gives that intel_pstate_init_cpu() is
successful but intel_pstate_get(), which is called right after by
cpufreq, fails.
Since all_cpu_data[1] is initialized it gives that sample->freq must
be zero. So the bug should be in intel_pstate_calc_busy() which
incorrectly sets sample->freq to zero.
I guess cpu->pstate.max_pstate == 4000000 since that's what
cpuinfo_max_freq and scaling_max_freq is on the other cores.
So the error is likely that core_pct is calculated to 0 in
intel_pstate.c:intel_pstate_calc_busy():
core_pct = div64_u64(int_tofp(sample->aperf * 100),
sample->mperf);
The truncation from the integer math is the likely culprit.
Might be fixed by this commit but should be backported in that case:
commit fcb6a15c2e7e76d493e6f91ea889ab40e1c643a4
Author: Dirk Brandewie <dirk.j.brandewie@xxxxxxxxx>
Date: Mon Feb 3 08:55:31 2014 -0800
intel_pstate: Take core C0 time into account for core busy calculation
This commit and the follow-on to fix a performance regression it introduced
are on my list to get into stable.
If you could file a bugzilla and add me to the CC list it would help me out
when I update stable.
My options to explore the problem further by backporting patches and
continuous reboots are a bit limited at the moment.
Regards,
Patrik
--
To unsubscribe from this list: send the line "unsubscribe cpufreq" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe cpufreq" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
