Gentoo Forums
Gentoo Forums
Gentoo Forums
Quick Search: in
Intel P state always at max freq when idle
View unanswered posts
View posts from last 24 hours

 
Reply to topic    Gentoo Forums Forum Index Kernel & Hardware
View previous topic :: View next topic  
Author Message
Bloot
Tux's lil' helper
Tux's lil' helper


Joined: 10 Mar 2006
Posts: 99
Location: Barcelona

PostPosted: Fri Mar 27, 2015 12:00 am    Post subject: Intel P state always at max freq when idle Reply with quote

Hello,

I recently upgraded to a i5-4590 Haswell refresh installed on a Gigabyte Z97P-D3 motherboard, so I activated Intel P state in the kernel. But it always stays at maximum frequency when the system is idle, it only scales down when it's busy which is disconcerting, it behaves the opposite way :?:

My kernel setup
Code:
$ cat /usr/src/linux/.config | grep CPU_FREQ
CONFIG_CPU_FREQ=y
# CONFIG_CPU_FREQ_STAT is not set
CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
CONFIG_CPU_FREQ_GOV_POWERSAVE=y
# CONFIG_CPU_FREQ_GOV_USERSPACE is not set
# CONFIG_CPU_FREQ_GOV_ONDEMAND is not set
# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set


Code:
$ cat /usr/src/linux/.config | grep PSTATE
CONFIG_X86_INTEL_PSTATE=y


Code:
$ cat /usr/src/linux/.config | grep NO_HZ
CONFIG_NO_HZ_COMMON=y
CONFIG_NO_HZ_IDLE=y
# CONFIG_NO_HZ_FULL is not set
# CONFIG_NO_HZ is not set
# CONFIG_RCU_FAST_NO_HZ is not set


Is there something I am missing, or is this driver really buggy? I am turning mad, I've compiled the kernel lots of times with no luck, it always stays at maximum frequency (3700MHz) on idle and only scales down when compiling, surfing the net etc...

Some cpupower info:

Code:
# 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 - 3.70 GHz
  available cpufreq governors: performance, powersave
  current policy: frequency should be within 800 MHz and 3.70 GHz.
                  The governor "powersave" may decide which speed to use
                  within this range.
  current CPU frequency is 3.69 GHz (asserted by call to hardware).
  boost state support:
    Supported: yes
    Active: yes


Code:
# cpupower idle-info
CPUidle driver: intel_idle
CPUidle governor: menu

Analyzing CPU 0:
Number of idle states: 6
Available idle states: POLL C1-HSW C1E-HSW C3-HSW C6-HSW C7s-HSW
POLL:
Flags/Description: CPUIDLE CORE POLL IDLE
Latency: 0
Usage: 155
Duration: 148047
C1-HSW:
Flags/Description: MWAIT 0x00
Latency: 2
Usage: 29439
Duration: 3517980
C1E-HSW:
Flags/Description: MWAIT 0x01
Latency: 10
Usage: 13720
Duration: 8908518
C3-HSW:
Flags/Description: MWAIT 0x10
Latency: 33
Usage: 23891
Duration: 23960449
C6-HSW:
Flags/Description: MWAIT 0x20
Latency: 133
Usage: 3355
Duration: 4377164
C7s-HSW:
Flags/Description: MWAIT 0x32
Latency: 166
Usage: 33282
Duration: 88202668


Code:
# cpupower monitor
    |Nehalem                    || SandyBridge        || Mperf              || Idle_Stats                             
CPU | C3   | C6   | PC3  | PC6  || C7   | PC2  | PC7  || C0   | Cx   | Freq || POLL | C1-H | C1E- | C3-H | C6-H | C7s-
   0|******|******|******|******||******|******|******||******|******|******||  0,00|  0,32|  0,12|  0,36|  0,33| 98,49
   1|******|******|******|******||******|******|******||******|******|******||  0,00|  0,00|  0,00|  0,20|  0,00| 103,6
   2|******|******|******|******||******|******|******||******|******|******||  0,00|  0,35|  0,09|  0,21|  0,25| 92,30
   3|******|******|******|******||******|******|******||******|******|******||  0,00|  0,47|  0,01|  0,35|  0,20| 101,9


Temperatures are ok though

Code:
$ sensors
coretemp-isa-0000
Adapter: ISA adapter
Physical id 0:  +36.0°C  (high = +80.0°C, crit = +100.0°C)
Core 0:         +32.0°C  (high = +80.0°C, crit = +100.0°C)
Core 1:         +30.0°C  (high = +80.0°C, crit = +100.0°C)
Core 2:         +31.0°C  (high = +80.0°C, crit = +100.0°C)
Core 3:         +33.0°C  (high = +80.0°C, crit = +100.0°C)


I'd really appreciate if someone can shed some ligh, thanks.


Last edited by Bloot on Fri Mar 27, 2015 6:00 pm; edited 2 times in total
Back to top
View user's profile Send private message
abduct
Apprentice
Apprentice


Joined: 19 Mar 2015
Posts: 215

PostPosted: Fri Mar 27, 2015 1:20 am    Post subject: Reply with quote

In the kernel try setting the "default CPUFreq governor" to "ondemand" so that the system adjusts the processor for you. The option can be found under "Power management and ACPI options -> CPU Frequency Scaling". Also try using the ACPI P-States option as I've read that the Intel P option has a similar bug in which it maxes out the CPU.

Source: I had a similar problem with a laptop and the processor not enabling turbo-boost or scaling automatically.
Back to top
View user's profile Send private message
Bloot
Tux's lil' helper
Tux's lil' helper


Joined: 10 Mar 2006
Posts: 99
Location: Barcelona

PostPosted: Fri Mar 27, 2015 9:23 am    Post subject: Reply with quote

abduct wrote:
In the kernel try setting the "default CPUFreq governor" to "ondemand" so that the system adjusts the processor for you. The option can be found under "Power management and ACPI options -> CPU Frequency Scaling". Also try using the ACPI P-States option as I've read that the Intel P option has a similar bug in which it maxes out the CPU.

Source: I had a similar problem with a laptop and the processor not enabling turbo-boost or scaling automatically.


Thanks for you reply. I already tried ondemand, in fact I tried so many combinations I could spend the hole thread numering them :o

Intel themselves don't recommend using any other driver than their own's for the newer chips, so that's why I selected Intel P-State over ACPI P-States.

I think I've made some progress and maybe solved the erratic Intel P-State behaviour, I've disabled acpi processor:

Code:
$ cat /usr/src/linux/.config | grep PROCESSOR
# CONFIG_ACPI_PROCESSOR is not set


And now intel p state is working as it should, though it never stays permanently at 800MHz (as it did with ondemand and acpi p-states), it's always oscilating and frankly, I don't know if this is the correct behaviour. At least it's not always at full power frequency like before.

Code:
# 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 - 3.70 GHz
  available cpufreq governors: performance, powersave
  current policy: frequency should be within 800 MHz and 3.70 GHz.
                  The governor "powersave" may decide which speed to use
                  within this range.
  current CPU frequency is 1.19 GHz (asserted by call to hardware).
  boost state support:
    Supported: yes
    Active: yes


Code:
$ cat /usr/src/linux/.config | grep IDLE
CONFIG_NO_HZ_IDLE=y
CONFIG_GENERIC_SMP_IDLE_THREAD=y
CONFIG_CPU_IDLE=y
CONFIG_CPU_IDLE_GOV_LADDER=y
CONFIG_CPU_IDLE_GOV_MENU=y
# CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED is not set
# CONFIG_INTEL_IDLE is not set
# CONFIG_I7300_IDLE is not set
# CONFIG_NETFILTER_XT_TARGET_IDLETIMER is not set


The drawback is that INTEL_IDLE cannot be used, or it will force max cpu frequency again, and thus cpupower is unable to show idle information without intel idle driver. But as long as it works, I don't mind not having access to idle information.

Code:
# cpupower idle-info
CPUidle driver: none
CPUidle governor: menu

Analyzing CPU 0:
CPU 0: No idle states


Code:
# cpupower monitor
    |Nehalem                    || SandyBridge        || Mperf             
CPU | C3   | C6   | PC3  | PC6  || C7   | PC2  | PC7  || C0   | Cx   | Freq
   0|******|******|******|******||******|******|******||******|******|******
   1|******|******|******|******||******|******|******||******|******|******
   2|******|******|******|******||******|******|******||******|******|******
   3|******|******|******|******||******|******|******||******|******|******


So I'll mark it as solved, thank you very much and hope it helps someone.
Back to top
View user's profile Send private message
albright
Advocate
Advocate


Joined: 16 Nov 2003
Posts: 2588
Location: Near Toronto

PostPosted: Fri Mar 27, 2015 11:40 am    Post subject: Reply with quote

Quote:
And now intel p state is working as it should, though it never stays permanently at 800MHz (as it did with ondemand and acpi p-states), it's always oscilating and frankly, I don't know if this is the correct behaviour


I think that's right; at least my two machines with p-state are like that
_________________
.... there is nothing - absolutely nothing - half so much worth
doing as simply messing about with Linux ...
(apologies to Kenneth Graeme)
Back to top
View user's profile Send private message
Bloot
Tux's lil' helper
Tux's lil' helper


Joined: 10 Mar 2006
Posts: 99
Location: Barcelona

PostPosted: Fri Mar 27, 2015 12:11 pm    Post subject: Reply with quote

albright wrote:
Quote:
And now intel p state is working as it should, though it never stays permanently at 800MHz (as it did with ondemand and acpi p-states), it's always oscilating and frankly, I don't know if this is the correct behaviour


I think that's right; at least my two machines with p-state are like that


Thank you very much

Would you mind sharing your kernel config with me? Now powersave works without acpi processor, but can't get past 3500Mhz and this chip should get up to 3700Mhz, at least it did when Intel P-State forced the max frequency on idle.
Back to top
View user's profile Send private message
Yamakuzure
Advocate
Advocate


Joined: 21 Jun 2006
Posts: 2284
Location: Adendorf, Germany

PostPosted: Fri Mar 27, 2015 1:48 pm    Post subject: Reply with quote

  1. You can only use performance and powersave governors, because the p-state driver does not support any other.
    If you want other governors, you have to use ACPI and replace it using phc-intel (which is a p-state driver, too).
    *but* : phc-intel can not fully power up the cpu. My 2.8 GHz i7 (With turbo up to 3.4 GHz) can not go over 2.6 GHz with phc-intel.
  2. Therefore I use the intel pstate driver from the kernel.

    With performance governor:
    Code:
     ~ # LC_ALL=C 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 - 3.40 GHz
      available cpufreq governors: performance, powersave
      current policy: frequency should be within 800 MHz and 3.40 GHz.
                      The governor "performance" may decide which speed to use
                      within this range.
      current CPU frequency is 3.29 GHz (asserted by call to hardware).
      boost state support:
        Supported: yes
        Active: yes
    and with powersave governor, AC unplugged:
    Code:
     ~ # LC_ALL=C 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 - 3.40 GHz
      available cpufreq governors: performance, powersave
      current policy: frequency should be within 800 MHz and 3.40 GHz.
                      The governor "powersave" may decide which speed to use
                      within this range.
      current CPU frequency is 605 MHz (asserted by call to hardware).
      boost state support:
        Supported: yes
        Active: yes

    (Interestingly the tool says that minimum frequency is 800MHz, but it was scaled down to 600MHz. ... conky reports the same, by the way...)
  3. There seems to be something else wrong with your config if you can not use INTEL_IDLE. Or maybe it's the cpu?
    Here is my config for reference:
    Code:
     /usr/src/linux # grep -P "^[^#].*(FREQ|IDLE|PSTATE)" .config
    CONFIG_NO_HZ_IDLE=y
    CONFIG_GENERIC_SMP_IDLE_THREAD=y
    CONFIG_CPU_FREQ=y
    CONFIG_CPU_FREQ_GOV_COMMON=y
    CONFIG_CPU_FREQ_STAT=m
    CONFIG_CPU_FREQ_STAT_DETAILS=y
    CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
    CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
    CONFIG_CPU_FREQ_GOV_POWERSAVE=y
    CONFIG_CPU_FREQ_GOV_USERSPACE=y
    CONFIG_CPU_FREQ_GOV_ONDEMAND=y
    CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
    CONFIG_X86_INTEL_PSTATE=y
    CONFIG_X86_ACPI_CPUFREQ=m
    CONFIG_CPU_IDLE=y
    CONFIG_CPU_IDLE_GOV_LADDER=y
    CONFIG_CPU_IDLE_GOV_MENU=y
    CONFIG_INTEL_IDLE=y
    and this is what idle-info comes up with:
    Code:
     ~ # LC_ALL=C cpupower idle-info
    CPUidle driver: intel_idle
    CPUidle governor: menu

    Analyzing CPU 0:
    Number of idle states: 6
    Available idle states: POLL C1-HSW C1E-HSW C3-HSW C6-HSW C7s-HSW
    POLL:
    Flags/Description: CPUIDLE CORE POLL IDLE
    Latency: 0
    Usage: 20346
    Duration: 20113894
    C1-HSW:
    Flags/Description: MWAIT 0x00
    Latency: 2
    Usage: 7175620
    Duration: 2884307784
    C1E-HSW:
    Flags/Description: MWAIT 0x01
    Latency: 10
    Usage: 2076175
    Duration: 1951980913
    C3-HSW:
    Flags/Description: MWAIT 0x10
    Latency: 33
    Usage: 3480621
    Duration: 2181767439
    C6-HSW:
    Flags/Description: MWAIT 0x20
    Latency: 133
    Usage: 1282988
    Duration: 980550922
    C7s-HSW:
    Flags/Description: MWAIT 0x32
    Latency: 166
    Usage: 23154988
    Duration: 73947612700
I hope it helps.
_________________
Important German:
  1. "Aha" - German reaction to pretend that you are really interested while giving no f*ck.
  2. "Tja" - German reaction to the apocalypse, nuclear war, an alien invasion or no bread in the house.
Back to top
View user's profile Send private message
Bloot
Tux's lil' helper
Tux's lil' helper


Joined: 10 Mar 2006
Posts: 99
Location: Barcelona

PostPosted: Fri Mar 27, 2015 5:58 pm    Post subject: Reply with quote

Thanks Yamakuzure, unfortunately when using you config my cpu never goes down 3.7GHz when idle hence the powersave doesn't work at all even if I adjust it manually.

Code:
# cpupower frequency-set --governor powersave && cpupower frequency-info && cat /proc/cpuinfo | grep MHz
Setting cpu: 0
Setting cpu: 1
Setting cpu: 2
Setting cpu: 3
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 - 3.70 GHz
  available cpufreq governors: performance, powersave
  current policy: frequency should be within 800 MHz and 3.70 GHz.
                  The governor "powersave" may decide which speed to use
                  within this range.
  current CPU frequency is 3.63 GHz (asserted by call to hardware).
  boost state support:
    Supported: yes
    Active: yes
cpu MHz      : 3628.066
cpu MHz      : 3680.789
cpu MHz      : 3588.105
cpu MHz      : 3665.835


So that's how I found out that disabling acpi_cpu and intel_idle did the trick, trial and error for hours! But then the chip can't get to the maximum frequency of 3.7GHz, just up to 3,5GHz. Maybe the problem is present only in the newer haswell refresh and it's a known bug.

Thanks for your time, I will remove the "solved" mark because it clearly it's not solved yet.
Back to top
View user's profile Send private message
albright
Advocate
Advocate


Joined: 16 Nov 2003
Posts: 2588
Location: Near Toronto

PostPosted: Fri Mar 27, 2015 6:31 pm    Post subject: Reply with quote

Here is my config

Code:
/usr/src/linux $ grep -P "^[^#].*(FREQ|IDLE|PSTATE)" .config
CONFIG_NO_HZ_IDLE=y
CONFIG_GENERIC_SMP_IDLE_THREAD=y
CONFIG_CPU_FREQ=y
CONFIG_CPU_FREQ_GOV_COMMON=y
CONFIG_CPU_FREQ_STAT=y
CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
CONFIG_CPU_FREQ_GOV_ONDEMAND=y
CONFIG_X86_INTEL_PSTATE=y
CONFIG_CPU_IDLE=y
CONFIG_CPU_IDLE_GOV_MENU=y
CONFIG_INTEL_IDLE=y

_________________
.... there is nothing - absolutely nothing - half so much worth
doing as simply messing about with Linux ...
(apologies to Kenneth Graeme)
Back to top
View user's profile Send private message
Ant P.
Watchman
Watchman


Joined: 18 Apr 2009
Posts: 6920

PostPosted: Sat Mar 28, 2015 11:32 pm    Post subject: Reply with quote

Intel cheats, basically. The newer chips use C-states alone for power saving - C2 and higher is effectively 0MHz, though you can't tell that from cpufreq numbers alone.
Back to top
View user's profile Send private message
Bloot
Tux's lil' helper
Tux's lil' helper


Joined: 10 Mar 2006
Posts: 99
Location: Barcelona

PostPosted: Mon Mar 30, 2015 4:12 pm    Post subject: Reply with quote

It seems Intel P-States is broken for haswell refresh chips https://bugzilla.kernel.org/show_bug.cgi?id=93521

So must wait for next kernel sources and see if it has been adressed.
Back to top
View user's profile Send private message
Bloot
Tux's lil' helper
Tux's lil' helper


Joined: 10 Mar 2006
Posts: 99
Location: Barcelona

PostPosted: Thu Jun 18, 2015 11:43 pm    Post subject: Reply with quote

4.0.5 kernel finally solved it. :D

Edit

False alarm... once ati-drivers got compiled against the new kernel, the problem is there again, so I guess it's ati-drivers who prevents the cpu being idle.
Back to top
View user's profile Send private message
Yamakuzure
Advocate
Advocate


Joined: 21 Jun 2006
Posts: 2284
Location: Adendorf, Germany

PostPosted: Fri Jun 19, 2015 7:27 am    Post subject: Reply with quote

Bloot wrote:
4.0.5 kernel finally solved it. :D

Edit

False alarm... once ati-drivers got compiled against the new kernel, the problem is there again, so I guess it's ati-drivers who prevents the cpu being idle.
There could be another issue.

Even in powersave mode, the CPUs can go up to maximum MHz including Turbo Boost if something wakes them up too often.

Could you try out powertop? Maybe it is something ompletely different?

(P.S : However: Powersave mode does *not* necessarily extend battery life, but may actually shorten it.
The reason is, that a CPU in a lower frequency needs longer to switch to C1, do its work, and switch back. So reducing the frequency actually lengthens the periods the CPUs are in a non-idle state, consuming more power. Theoretically.
Hence, unless undervolting the CPU, doing regular work while using the powersave governor, is a bad idea. ;-) )
_________________
Important German:
  1. "Aha" - German reaction to pretend that you are really interested while giving no f*ck.
  2. "Tja" - German reaction to the apocalypse, nuclear war, an alien invasion or no bread in the house.
Back to top
View user's profile Send private message
s4e8
Guru
Guru


Joined: 29 Jul 2006
Posts: 311

PostPosted: Fri Jun 19, 2015 9:10 am    Post subject: Reply with quote

There's NO freq at idle (C-state), all C3/C6/C7 states stop core-clock, C1 will running at low-speed if C1E enable, or high speed if C1E disable. The reported idle freq is useless.
Back to top
View user's profile Send private message
Bloot
Tux's lil' helper
Tux's lil' helper


Joined: 10 Mar 2006
Posts: 99
Location: Barcelona

PostPosted: Fri Jun 19, 2015 11:40 pm    Post subject: Reply with quote

Yamakuzure wrote:
Bloot wrote:
4.0.5 kernel finally solved it. :D

Edit

False alarm... once ati-drivers got compiled against the new kernel, the problem is there again, so I guess it's ati-drivers who prevents the cpu being idle.
There could be another issue.

Even in powersave mode, the CPUs can go up to maximum MHz including Turbo Boost if something wakes them up too often.

Could you try out powertop? Maybe it is something ompletely different?

(P.S : However: Powersave mode does *not* necessarily extend battery life, but may actually shorten it.
The reason is, that a CPU in a lower frequency needs longer to switch to C1, do its work, and switch back. So reducing the frequency actually lengthens the periods the CPUs are in a non-idle state, consuming more power. Theoretically.
Hence, unless undervolting the CPU, doing regular work while using the powersave governor, is a bad idea. ;-) )


Hi, mine's a desktop computer, so no problem with batteries. It's funny, because before I compiled the proprietary ATi drivers, the frequency stayed at 800-900MHz with no cpu load (as it should), and after compiled the video drivers the cpu stays again at 3.7GHz with no cpu load, I can only guess it's a video drivers fault, or maybe the KDE desktop effects has also something to do with it (I tried disabling them, but no luck).

Code:
top - 01:36:20 up 10 min,  1 user,  load average: 0,92, 1,72, 1,08
Tasks: 213 total,   1 running, 212 sleeping,   0 stopped,   0 zombie
%Cpu(s):  1,6 us,  0,4 sy,  0,0 ni, 97,4 id,  0,6 wa,  0,0 hi,  0,0 si,  0,0 st

  PID USER      PR  NI    VIRT    RES    SHR S  %CPU %MEM     TIME+ COMMAND                                                           
 5917 debaser   20   0  884192 129712  73484 S   3,0  1,6   0:08.83 chrome                                                             
 3017 debaser   20   0 3047140 133848 100236 S   1,7  1,7   0:14.88 kwin                                                               
 3812 debaser   20   0 1070612 268824 109188 S   1,3  3,3   0:13.78 chrome                                                             
 2604 root      20   0  436124 208408 163136 S   0,7  2,6   0:11.67 X                                                                 
 3734 debaser   20   0  331220  48672  33620 S   0,7  0,6   0:03.68 urxvt                                                             
 3865 debaser   20   0  437792  65600  51712 S   0,7  0,8   0:03.52 chrome                                                             
 7225 debaser   20   0  328648  45756  33136 S   0,7  0,6   0:02.87 urxvt                                                             
 5665 debaser   20   0  920888 154780  54300 S   0,3  1,9   0:01.56 chrome                                                             
 6068 debaser   20   0  954012 161688  59372 S   0,3  2,0   0:02.05 chrome                                                             
 7450 debaser   20   0  826720  86344  51108 S   0,3  1,1   0:00.24 chrome                                                             
 7761 debaser   20   0  328648  46256  33636 S   0,3  0,6   0:02.00 urxvt                                                             
    1 root      20   0    4168   1456   1352 S   0,0  0,0   0:00.41 init                                                               
    2 root      20   0       0      0      0 S   0,0  0,0   0:00.00 kthreadd                                                           
    3 root      20   0       0      0      0 S   0,0  0,0   0:00.06 ksoftirqd/0                                                       
    4 root      20   0       0      0      0 S   0,0  0,0   0:00.04 kworker/0:0                                                       
    5 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 kworker/0:0H                                                       
    6 root      20   0       0      0      0 S   0,0  0,0   0:02.20 kworker/u8:0                                                       
    7 root      20   0       0      0      0 S   0,0  0,0   0:00.48 rcu_sched                                                         
    8 root      20   0       0      0      0 S   0,0  0,0   0:00.00 rcu_bh                                                             
    9 root      rt   0       0      0      0 S   0,0  0,0   0:00.00 migration/0                                                       
   10 root      rt   0       0      0      0 S   0,0  0,0   0:00.00 migration/1                                                       
   11 root      20   0       0      0      0 S   0,0  0,0   0:00.02 ksoftirqd/1                                                       
   13 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 kworker/1:0H                                                       
   14 root      rt   0       0      0      0 S   0,0  0,0   0:00.00 migration/2                                                       
   15 root      20   0       0      0      0 S   0,0  0,0   0:00.01 ksoftirqd/2                                                       
   17 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 kworker/2:0H                                                       
   18 root      rt   0       0      0      0 S   0,0  0,0   0:00.00 migration/3                                                       
   19 root      20   0       0      0      0 S   0,0  0,0   0:00.02 ksoftirqd/3                                                       
   21 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 kworker/3:0H                                                       
   22 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 khelper                                                           
   23 root      20   0       0      0      0 S   0,0  0,0   0:00.00 kdevtmpfs                                                         
   24 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 netns                                                             
   27 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 perf                                                               
  286 root      20   0       0      0      0 S   0,0  0,0   0:00.00 khungtaskd                                                         
  287 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 writeback                                                         
  289 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 crypto                                                             
  290 root      20   0       0      0      0 S   0,0  0,0   0:00.01 kworker/1:1                                                       
  291 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 bioset                                                             
  293 root       0 -20       0      0      0 S   0,0  0,0   0:00.00 kblockd


I think I'll give up, funniest thing is the chip frequencies works fine on Windows, it's just Linux related.
Back to top
View user's profile Send private message
s4e8
Guru
Guru


Joined: 29 Jul 2006
Posts: 311

PostPosted: Sat Jun 20, 2015 12:54 am    Post subject: Reply with quote

new intel_idle, export both C1 and C1E states, let the cpuidle gorvenor choose which one to use. ACPI idle driver always combine C1 and C1E, and auto-promotion to C1E if BIOS enable it. Unless cpu wont enter deeper C3 or C6 states, there's NO problem if idle governor prefer to C1 instead C1E.
Back to top
View user's profile Send private message
Bloot
Tux's lil' helper
Tux's lil' helper


Joined: 10 Mar 2006
Posts: 99
Location: Barcelona

PostPosted: Sat Jun 20, 2015 11:05 pm    Post subject: Reply with quote

s4e8 wrote:
new intel_idle, export both C1 and C1E states, let the cpuidle gorvenor choose which one to use. ACPI idle driver always combine C1 and C1E, and auto-promotion to C1E if BIOS enable it. Unless cpu wont enter deeper C3 or C6 states, there's NO problem if idle governor prefer to C1 instead C1E.


Yes I'm giving up, I guess it's the normal Haswell refresh chips behaviour under Linux, most important temps are OK, thank you all.
Back to top
View user's profile Send private message
Yamakuzure
Advocate
Advocate


Joined: 21 Jun 2006
Posts: 2284
Location: Adendorf, Germany

PostPosted: Mon Jun 22, 2015 6:43 am    Post subject: Reply with quote

@Bloot: I meant "sys-power/powertop", not "top".

But as you are on a desktop computer without battery, it wouldn't help that much anyway. I guess you are right, and your desktop hardware simply isn't able to do it like you want. I always assumed you were on a laptop.

However, my laptop came shipped with an ATI card, but both the open source and proprietary drivers gave me too much trouble. I had it replaced by an nvidia card and am happy now. So if you are right, and it is a driver issue with the proprietary ATI-Drivers, I can at least be sure that my decision was a good one. ;-)

For completenes' sake:

Output with AC connected on my laptop:
Code:
 ~ # LC_ALL=C powertop --time=5
PowerTOP 2.6      Overview   Idle stats   Frequency stats   Device stats   Tunables                                     

Summary: 4506.7 wakeups/second,  109.7 GPU ops/seconds, 0.0 VFS ops/sec and 23.5% CPU use

                Usage       Events/s    Category       Description
            137.0 ms/s     2169.6       Process        /usr/sbin/mysqld --defaults-file=/etc/mysql/my.cnf
              7.7 ms/s     1109.8       Process        akonadiserver
             43.3 ms/s     429.8        Process        /usr/bin/lancelot
              1.3 ms/s     255.1        Process        /usr/games/bin/wesnoth
              2.6 ms/s     204.2        Timer          tick_sched_timer
              6.8 ms/s     147.8        Process        kdeinit4: plasma-desktop [kdeinit]
              2.1 ms/s     125.9        Timer          hrtimer_wakeup
              9.0 ms/s      34.3        Process        /usr/bin/firefox
              6.9 ms/s      37.6        Process        /usr/bin/X :0 -auth /var/run/sddm/:0 -nolisten tcp -background none -noreset vt7
              2.0 ms/s      27.7        Interrupt      [25] i915
              1.0 ms/s      11.2        Process        kwin -session 10143143147fd000143149784900000084790000_1434736059_314150
              1.5 ms/s       8.4        Process        /usr/bin/yakuake -session 10143143147fd000140059895900000131970026_1434736059_305163
              4.1 ms/s       7.0        Process        /usr/bin/kontact
              8.5 us/s       6.6        kWork          blk_delay_work
            104.6 us/s       6.0        Process        /usr/lib/jvm/oracle-jdk-bin-1.8//bin/java -classpath /usr/share/davmail-bin/lib/activation-1.1.1.jar:/usr/share/davmail-bin/lib
             16.7 us/s       5.8        Process        [rcu_sched]
             58.6 us/s       3.4        Process        [z_null_iss/0]
            529.7 us/s       2.2        Process        /usr/bin/conky
            154.0 us/s       2.0        Process        [z_wr_iss/1]
             23.0 us/s       2.0        Process        [txg_sync]
            651.9 us/s       1.4        Interrupt      [30] snd_hda_intel
            155.8 us/s       1.4        Process        [z_wr_iss/0]
              1.9 ms/s       0.6        Process        [uksmd]
             65.0 us/s       1.0        Process        /usr/sbin/syslog-ng --persist-file /var/lib/syslog-ng/syslog-ng.persist --cfgfile /etc/syslog-ng/syslog-ng.conf --pidfile /run/
Output while on batteries on my laptop with powersave governor (600-800MHz on all 8 CPUs):
Code:
 ~ # LC_ALL=C powertop --time=5
PowerTOP 2.6      Overview   Idle stats   Frequency stats   Device stats   Tunables                                     

The battery reports a discharge rate of 20.0 W
The estimated remaining time is 3 hours, 21 minutes

Summary: 2671.8 wakeups/second,  148.2 GPU ops/seconds, 0.0 VFS ops/sec and 19.9% CPU use

                Usage       Events/s    Category       Description
             18.9 ms/s     1041.9       Process        /usr/games/bin/wesnoth
             60.7 ms/s     433.6        Process        /usr/bin/firefox
              2.5 ms/s     324.9        Timer          tick_sched_timer
             11.8 ms/s     182.6        Process        kdeinit4: plasma-desktop [kdeinit]
              6.9 ms/s     162.8        Process        /usr/bin/conky
              9.7 ms/s     148.8        Process        kwin -session 10143143147fd000143149784900000084790000_1434736059_314150
              4.8 ms/s      83.9        Process        /usr/bin/yakuake -session 10143143147fd000140059895900000131970026_1434736059_305163
              1.9 ms/s      73.7        Interrupt      [25] i915
              1.0 ms/s      62.2        Process        [txg_sync]
            334.0 us/s      56.0        Process        [rcu_sched]
              1.2 ms/s      43.7        Process        /usr/lib/jvm/oracle-jdk-bin-1.8//bin/java -classpath /usr/share/davmail-bin/lib/activation-1.1.1.jar:/usr/share/davmail-bin/lib
             27.4 ms/s      21.7        Process        /usr/bin/X :0 -auth /var/run/sddm/:0 -nolisten tcp -background none -noreset vt7
            311.6 us/s      25.6        Process        /usr/sbin/mysqld --defaults-file=/etc/mysql/my.cnf
              1.3 ms/s      22.7        Process        /usr/sbin/syslog-ng --persist-file /var/lib/syslog-ng/syslog-ng.persist --cfgfile /etc/syslog-ng/syslog-ng.conf --pidfile /run/
            280.3 us/s      21.3        Process        [z_null_iss/0]
              5.5 ms/s      18.9        Process        default.sh
              6.8 ms/s       7.4        Process        acpid
              0.7 ms/s       7.6        Process        /usr/sbin/acpid --netlink
              7.0 ms/s       3.8        Process        sh
            130.1 us/s       4.6        kWork          acpi_os_execute_deferred
              5.1 ms/s       2.4        Process        [uksmd]
Idle stats:
Code:
          Package   |             Core    |            CPU 0       CPU 4
                    |                     | C0 active   2.6%        0.9%
                    |                     | POLL        0.0%    0.0 ms  0.0%    0.0 ms
                    |                     | C1E-HSW     0.1%    0.1 ms 19.6%   49.5 ms
C2 (pc2)   22.0%    |                     |
C3 (pc3)    0.0%    | C3 (cc3)    0.4%    | C3-HSW      1.6%    0.4 ms  0.0%    0.0 ms
C6 (pc6)    0.0%    | C6 (cc6)    0.2%    | C6-HSW      1.5%    1.0 ms  0.0%    0.0 ms
C7 (pc7)    0.0%    | C7 (cc7)   33.4%    | C7s-HSW    93.6%    2.5 ms 35.8%   15.0 ms

                    |             Core    |            CPU 1       CPU 5
                    |                     | C0 active   2.3%        0.6%
                    |                     | POLL        0.0%    0.0 ms  0.0%    0.0 ms
                    |                     | C1E-HSW     5.4%    0.9 ms  1.6%    1.8 ms
                    |                     |
                    | C3 (cc3)    1.6%    | C3-HSW      2.1%    0.5 ms  0.0%    0.0 ms
                    | C6 (cc6)    0.9%    | C6-HSW      0.8%    0.6 ms  0.2%    0.7 ms
                    | C7 (cc7)   84.6%    | C7s-HSW    88.3%    3.2 ms 96.3%   60.7 ms

                    |             Core    |            CPU 2       CPU 6
                    |                     | C0 active   4.7%        1.5%
                    |                     | POLL        0.0%    0.0 ms  0.0%    0.0 ms
                    |                     | C1E-HSW    19.4%    5.7 ms  0.0%    0.0 ms
                    |                     |
                    | C3 (cc3)    1.2%    | C3-HSW      0.4%    0.5 ms  1.7%    2.1 ms
                    | C6 (cc6)    0.5%    | C6-HSW      0.5%    0.6 ms  0.3%    1.6 ms
                    | C7 (cc7)   70.7%    | C7s-HSW    73.6%    3.2 ms 96.6%   11.3 ms

                    |             Core    |            CPU 3       CPU 7
                    |                     | C0 active   2.0%        0.2%
                    |                     | POLL        0.0%    0.0 ms  0.0%    0.0 ms
                    |                     | C1E-HSW     0.5%    0.2 ms  0.0%    0.2 ms
                    |                     |
                    | C3 (cc3)    1.6%    | C3-HSW      1.7%    0.4 ms  0.0%    0.1 ms
                    | C6 (cc6)    0.8%    | C6-HSW      0.8%    0.6 ms  0.1%    0.3 ms
                    | C7 (cc7)   91.0%    | C7s-HSW    93.1%    1.6 ms 99.7%   83.8 ms

                    |             GPU     |
                    |                     |
                    | Powered On  1.5%    |
                    | RC6        98.5%    |
                    | RC6p        0.0%    |
                    | RC6pp       0.0%    |
                    |                     |
                    |                     |
So you can at least see what wakes up your CPUs and what time they spend in which state.
_________________
Important German:
  1. "Aha" - German reaction to pretend that you are really interested while giving no f*ck.
  2. "Tja" - German reaction to the apocalypse, nuclear war, an alien invasion or no bread in the house.
Back to top
View user's profile Send private message
yaclo
n00b
n00b


Joined: 11 Sep 2015
Posts: 20

PostPosted: Mon Feb 01, 2016 10:08 pm    Post subject: Reply with quote

same problem here and it's a desktop :D it's first generation haswell cpu i7 4770 / r9 290

with radeonsi cpu frequency scaling works fine
but with fglrx cpu freq goes to max no matter what

fglrx prevents the cpu being idle
Back to top
View user's profile Send private message
Display posts from previous:   
Reply to topic    Gentoo Forums Forum Index Kernel & Hardware All times are GMT
Page 1 of 1

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum