[BUG] Speedstep / intel_pstate not working?

[Atomic234]

I just installed CentOS 7 on an ASRock Z87 Pro 3 with Intel G3258. I have Speedstep and all related power savings options enabled in the firmware, but the CPU's run at full speed, even when idle:

Code: Select all

[jweage@sailfish ~]$ sudo cpupower frequency-info
analyzing CPU 0:
  driver: intel_pstate
  CPUs which run at the same hardware frequency: 0
  CPUs which need to have their frequency coordinated by software: 0
  maximum transition latency: 0.97 ms.
  hardware limits: 800 MHz - 3.20 GHz
  available cpufreq governors: performance, powersave
  current policy: frequency should be within 800 MHz and 3.20 GHz.
                  The governor "powersave" may decide which speed to use
                  within this range.
  current CPU frequency is 3.20 GHz (asserted by call to hardware).
  boost state support:
    Supported: yes
    Active: yes
[jweage@sailfish ~]$ sudo cpupower monitor -i 10
    |Nehalem                    || SandyBridge        || Mperf              || Idle_Stats                       
CPU | C3   | C6   | PC3  | PC6  || C7   | PC2  | PC7  || C0   | Cx   | Freq || POLL | C1-H | C1E- | C3-H | C6-H 
   0|  0.02| 96.95|  0.00|  0.00||  0.00| 96.65|  0.00||  2.93| 97.07|  3199||  2.75|  0.06|  0.00|  0.03| 96.97
   1|  0.00| 99.61|  0.00|  0.00||  0.00| 96.65|  0.00||  0.24| 99.76|  3199||  0.00|  0.00|  0.00|  0.00| 99.72

[jweage@sailfish ~]$ cat /proc/cpuinfo
processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 60
model name	: Intel(R) Pentium(R) CPU G3258 @ 3.20GHz
stepping	: 3
microcode	: 0x1a
cpu MHz		: 3200.375
cache size	: 3072 KB
physical id	: 0
siblings	: 2
core id		: 0
cpu cores	: 2
apicid		: 0
initial apicid	: 0
fpu		: yes
fpu_exception	: yes
cpuid level	: 13
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm pcid sse4_1 sse4_2 movbe popcnt tsc_deadline_timer xsave rdrand lahf_lm abm ida arat xsaveopt pln pts dtherm tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust erms invpcid
bogomips	: 6397.62
clflush size	: 64
cache_alignment	: 64
address sizes	: 39 bits physical, 48 bits virtual
power management:

processor	: 1
vendor_id	: GenuineIntel
cpu family	: 6
model		: 60
model name	: Intel(R) Pentium(R) CPU G3258 @ 3.20GHz
stepping	: 3
microcode	: 0x1a
cpu MHz		: 3200.000
cache size	: 3072 KB
physical id	: 0
siblings	: 2
core id		: 1
cpu cores	: 2
apicid		: 2
initial apicid	: 2
fpu		: yes
fpu_exception	: yes
cpuid level	: 13
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm pcid sse4_1 sse4_2 movbe popcnt tsc_deadline_timer xsave rdrand lahf_lm abm ida arat xsaveopt pln pts dtherm tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust erms invpcid
bogomips	: 6397.62
clflush size	: 64
cache_alignment	: 64
address sizes	: 39 bits physical, 48 bits virtual
power management:

[jweage@sailfish ~]$ uname -a
Linux sailfish.localdomain 3.10.0-123.20.1.el7.x86_64 #1 SMP Thu Jan 29 18:05:33 UTC 2015 x86_64 x86_64 x86_64 GNU/Linux

I have the latest firmware on the motherboard and CentOS is fully updated.

I didn't see any interesting messages in the logs. Any ideas?

[Atomic234]

I tried the latest mainline kernel (3.18.5-1) from elrepo and frequency scaling now works as expected. This is another bug in the RHEL 7/CentOS 7 kernel.

[AlanBartlett]

CentOS is a clone build of RHEL; they are both built from the same source code. Hence a bug present in RHEL will also be present in CentOS.

In cases like this, which you have recently noted, the correct process is to open a report in the Red Hat bug tracker against the current RHEL 7 kernel. Then once the issue is resolved by Red Hat for RHEL 7, the fix will (automatically) appear in CentOS 7.

[Atomic234]

I posted here because there are several identical bugs logged against Fedora, which have been closed and marked as NOTABUG.

I filed a bug report with RedHat since this clearly is a bug: https://bugzilla.redhat.com/show_bug.cgi?id=1188448

[AlanBartlett]

Thank you for opening that report. We can now only wait to see the response.