LinuxLists.cc - [REGRESSION] fan always on with 3.10-rc2

2013-05-24 11:03:24

Subject: [REGRESSION] fan always on with 3.10-rc2

Hi!

With 3.10-rc2 I see fan always or almost always on, even during extended
periods of basically idling around. I did not notice this with 3.9. This is
on an ThinkPad T520 with Intel Sandybridge i5-2520M dual core with
hyperthreading at regularily 2,5 GhZ and Intel graphics (no nvidia).

I am using full hz:

martin@merkaba:~/Linux/Kernel/Mainline/Bugs/fan always on with 3.10.2-rc2> xzgrep NO_HZ config-3.10.0-rc2-tp520.xz
CONFIG_NO_HZ_COMMON=y
# CONFIG_NO_HZ_IDLE is not set
CONFIG_NO_HZ_FULL=y
CONFIG_NO_HZ_FULL_ALL=y
CONFIG_NO_HZ=y
CONFIG_RCU_FAST_NO_HZ=y

And P-State driver (which I used in 3.9 already as well).

Kernel config attached as xz. Use xzless or xzcat to display.

What puzzles is output of powertop, especially:

PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables

Package | Core | CPU 0 CPU 1
| | C0 active 127,4% 2,3%
^^^^^^
| | POLL 98,1% 0,9 ms 0,0% 0,0 ms
^^^^^
| | C1E-SNB 0,0% 0,0 ms 0,4% 0,9 ms
C2 (pc2) 0,0% | |
C3 (pc3) 0,0% | C3 (cc3) 0,0% | C3-SNB 0,0% 0,0 ms 0,1% 0,8 ms
C6 (pc6) 0,0% | C6 (cc6) 0,0% | C6-SNB 0,0% 0,0 ms 0,0% 0,8 ms
C7 (pc7) 0,0% | C7 (cc7) 0,0% | C7-SNB 0,0% 0,0 ms 97,5% 7,4 ms

| Core | CPU 2 CPU 3
| | C0 active 1,9% 0,8%
| | POLL 0,0% 0,0 ms 0,0% 0,0 ms
| | C1E-SNB 1,1% 1,3 ms 0,0% 0,1 ms
| |
| C3 (cc3) 0,3% | C3-SNB 0,3% 1,0 ms 0,0% 0,2 ms
| C6 (cc6) 0,1% | C6-SNB 0,1% 2,5 ms 0,0% 0,3 ms
| C7 (cc7) 96,2% | C7-SNB 97,0% 7,2 ms 99,3% 17,2 ms

PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables

Package | Core | CPU 0 CPU 1
| | Actual 3,2 GHz 3,1 GHz
Idle 100,0% | Idle 100,0% | Idle 100,0% 100,0%

| Core | CPU 2 CPU 3
| | Actual 3,0 GHz 3,0 GHz
| Idle 100,0% | Idle 100,0% 100,0%

It seems the kernel is overbusying one core completely, if the output of
powertop is correct. And why is Actual frequencing of CPUs that high?
I saw that kernel tends to overtact quickly. I thought this was due to
getting work done quickly and then let it idle. But the idle stats
seem bogus to, maybe powertop is not up to date with current kernels?

I see no reason for busying one core. This happens when CPU usage is
below 20%. The fan is consistently around 2640 rpm:

PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables

Summary: 399,8 wakeups/second, 0,0 GPU ops/second, 0,0 VFS ops/sec and 3,0% CPU use

Usage Events/s Category Description
2644 rpm Device Laptop fan
100,0% Device Audio codec hwC0D1: Conexant
100,0% Device Audio codec hwC0D3: Intel
100,0% Device Audio codec hwC0D0: Conexant
30,7 ?s/s 112,3 Process [ksoftirqd/0]
4,2 ms/s 83,5 Process kwin -session 10cec7d36b000136265311700000023930000_1369322581_349094
0,8 ms/s 67,3 Process [irq/42-i915@pci]
5,5 ms/s 53,6 Process /usr/bin/X :0 vt7 -br -nolisten tcp -auth /var/run/xauth/A:0-eXsirc
698,3 ?s/s 13,3 Process [irq/16-mmc0]
85,8 ?s/s 9,1 Process [rcu_preempt]
297,1 ?s/s 8,7 Process /usr/sbin/mysqld --defaults-file=/home/martin/.local/share/akonadi/mysql.conf --datadir
78,6 ?s/s 8,1 Process [ksoftirqd/2]
6,7 ms/s 3,7 Process /usr/bin/plasma-desktop
218,9 ?s/s 5,0 Interrupt [1] timer(softirq)
2,8 ms/s 2,9 Process /usr/bin/konsole -session 10cec7d36b000135326160200000249810027_1369322580_899575
65,9 ?s/s 3,6 Process [ksoftirqd/1]
69,8 ?s/s 3,5 Process [ksoftirqd/3]
38,1 ?s/s 3,4 Process [rcuop/3]
35,3 ?s/s 2,4 Process [rcuop/2]
6,0 ms/s 0,00 Process atop
21,3 ?s/s 1,8 Process [irq/43-ahci]
33,3 ?s/s 1,7 Process [rcuop/0]
122,3 ?s/s 1,7 Process [btrfs-transacti]
66,4 ?s/s 1,5 Process /usr/bin/dirmngr --daemon --sh
61,2 ?s/s 1,0 Process [rcuop/1]
29,2 ?s/s 1,0 Process /usr/lib/gvfs/gvfs-afc-volume-monitor
40,8 ?s/s 0,9 Timer process_timeout
25,5 ?s/s 0,9 Process /usr/bin/python /usr/bin/hp-systray -x
32,2 ?s/s 0,7 Process /usr/bin/dbus-daemon --fork --print-pid 5 --print-address 7 --session
5,1 ?s/s 0,7 Process [irq/44-eth0]
612,1 ?s/s 0,4 Process ksysguardd
137,6 ?s/s 0,5 Interrupt [7] sched(softirq)
5,6 ?s/s 0,5 Timer clocksource_watchdog
71,2 ?s/s 0,4 kWork disk_events_workfn
57,5 ?s/s 0,4 Process kdeinit4: kded4 [kdeinit]
68,3 ?s/s 0,3 Process akonadiserver
34,6 ?s/s 0,3 Process /usr/bin/virtuoso-t +foreground +configfile /tmp/virtuoso_fB2599.ini +wait
14,9 ?s/s 0,3 Process /usr/bin/gpg-agent --daemon --sh --write-env-file=/home/martin/.gnupg/gpg-agent-info-me
39,4 ?s/s 0,30 Process /usr/bin/nepomukservicestub nepomukfileindexer

PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables

Usage Device name
2644 rpm Laptop fan
4,3% CPU use
100,0% Audio codec hwC0D3: Intel
100,0% Audio codec hwC0D0: Conexant
100,0% Audio codec hwC0D1: Conexant
20,9 pkts/s Network interface: eth0 (e1000e)
100,0% USB device: usb-device-8087-0024
100,0% USB device: usb-device-8087-0024
100,0% Display backlight
100,0% Display backlight
100,0% USB device: EHCI Host Controller
100,0% USB device: Biometric Coprocessor (UPEK)
100,0% USB device: Integrated Smart Card Reader (Lenovo)
100,0% USB device: EHCI Host Controller
0,0 ops/s GPU
100,0% USB device: usb-device-17ef-100a
100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 5
100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 4
100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 2
100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family High Definition Audio Controller
100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family MEI Controller #1
100,0% USB device: PS/2+USB Mouse
100,0% PCI Device: Intel Corporation QM67 Express Chipset Family LPC Controller
100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family 6 port SATA AHCI Controller
100,0% PCI Device: Ricoh Co Ltd MMC/SD Host Controller
100,0% PCI Device: Silicon Image, Inc. SiI 3531 [SATALink/SATARaid] Serial ATA Controller
100,0% PCI Device: Ricoh Co Ltd R5C832 PCIe IEEE 1394 Controller
100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family USB Enhanced Host Controller #2
100,0% PCI Device: Intel Corporation 82579LM Gigabit Network Connection
100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family SMBus Controller
100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 1
100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family USB Enhanced Host Controller #1
100,0% PCI Device: Intel Corporation 2nd Generation Core Processor Family Integrated Graphics Controller
100,0% PCI Device: Intel Corporation 2nd Generation Core Processor Family DRAM Controller
100,0% PCI Device: Intel Corporation Centrino Advanced-N 6205 [Taylor Peak]
0,0 pkts/s Network interface: wlan0 (iwlwifi)
0,0% Thinkpad light
0,0% Radio device: thinkpad_acpi
0,0% Radio device: iwlwifi

I saw nothing outstanding in dmesg or kern.log, just

merkaba:~#2> grep "Intel pstate controlling: cpu" /var/log/kern.log
May 20 10:03:31 merkaba kernel: [264852.930994] Intel pstate controlling: cpu 1
May 20 10:03:31 merkaba kernel: [264852.944479] Intel pstate controlling: cpu 2
May 20 10:03:31 merkaba kernel: [264852.957879] Intel pstate controlling: cpu 3
May 21 09:14:03 merkaba kernel: [315800.710623] Intel pstate controlling: cpu 1
May 21 09:14:03 merkaba kernel: [315800.724087] Intel pstate controlling: cpu 2
May 21 09:14:03 merkaba kernel: [315800.737493] Intel pstate controlling: cpu 3
May 21 20:01:20 merkaba kernel: [344305.122543] Intel pstate controlling: cpu 1
May 21 20:01:20 merkaba kernel: [344305.135953] Intel pstate controlling: cpu 2
May 21 20:01:20 merkaba kernel: [344305.149398] Intel pstate controlling: cpu 3
May 21 21:52:18 merkaba kernel: [ 1.441043] Intel pstate controlling: cpu 0
May 21 21:52:18 merkaba kernel: [ 1.441084] Intel pstate controlling: cpu 1
May 21 21:52:18 merkaba kernel: [ 1.441123] Intel pstate controlling: cpu 2
May 21 21:52:18 merkaba kernel: [ 1.441162] Intel pstate controlling: cpu 3
May 23 17:22:29 merkaba kernel: [ 1.860224] Intel pstate controlling: cpu 0
May 23 17:22:29 merkaba kernel: [ 1.860267] Intel pstate controlling: cpu 1
May 23 17:22:29 merkaba kernel: [ 1.860306] Intel pstate controlling: cpu 2
May 23 17:22:29 merkaba kernel: [ 1.860345] Intel pstate controlling: cpu 3

But these seem to be regular and I had them before as well.

Thanks,
--
Martin 'Helios' Steigerwald - http://www.Lichtvoll.de
GPG: 03B0 0D6C 0040 0710 4AFA B82F 991B EAAC A599 84C7

Attachments:

config-3.10.0-rc2-tp520.xz (25.25 kB)

2013-06-08 20:34:49

by Martin Steigerwald

[permalink] [raw]

Subject: Re: [REGRESSION] fan always on with 3.10-rc2

2013-06-09 18:34:17

by Martin Steigerwald

[permalink] [raw]

Subject: Re: [REGRESSION] fan always on with 3.10-rc2

Am Samstag, 8. Juni 2013, 22:34:44 schrieb Martin Steigerwald:
> Am Freitag, 24. Mai 2013, 13:03:18 schrieb Martin Steigerwald:
> > Hi!
> >
> > With 3.10-rc2 I see fan always or almost always on, even during extended
> > periods of basically idling around. I did not notice this with 3.9. This is
> > on an ThinkPad T520 with Intel Sandybridge i5-2520M dual core with
> > hyperthreading at regularily 2,5 GhZ and Intel graphics (no nvidia).
> >
> > I am using full hz:
> >
> > martin@merkaba:~/Linux/Kernel/Mainline/Bugs/fan always on with 3.10.2-rc2> xzgrep NO_HZ config-3.10.0-rc2-tp520.xz
> > CONFIG_NO_HZ_COMMON=y
> > # CONFIG_NO_HZ_IDLE is not set
> > CONFIG_NO_HZ_FULL=y
> > CONFIG_NO_HZ_FULL_ALL=y
> > CONFIG_NO_HZ=y
> > CONFIG_RCU_FAST_NO_HZ=y
> >
> > And P-State driver (which I used in 3.9 already as well).
> >
> > Kernel config attached as xz. Use xzless or xzcat to display.
> >
> >
> > What puzzles is output of powertop, especially:
>
> Still present in 3.10-rc4.
>
> I disabled P-State driver but then rpm seems to be even worse.
>
> Around 2800 rpm all the time, was about 2650 with Intel P State driver.
>
> Next I will try without CONFIG_NO_HZ_FULL and CONFIG_NO_HZ_FULL_ALL.

Okay, without these both the behavior is better. Fan still does not seem
to get into non running state, which it was able to with earlier kernels
(or userspaces?), but its down to a quiet 1950 rpm with Intel P-State driver
enabled again. CC?d to people from thread "power management regression
in linux 3.10? (related to CONFIG_NO_HZ_FULL)" which I think is related.

Powertop values make a lot more sense as well:

PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables

Package | Core | CPU 0 CPU 1
| | C0 active 1,4% 0,9%
| | POLL 0,0% 0,0 ms 0,0% 0,0 ms
| | C1E-SNB 7,7% 3,0 ms 2,9% 5,3 ms
C2 (pc2) 1,1% | |
C3 (pc3) 7,2% | C3 (cc3) 8,4% | C3-SNB 8,2% 3,1 ms 3,0% 15,2 ms
C6 (pc6) 4,9% | C6 (cc6) 9,3% | C6-SNB 7,0% 3,5 ms 6,2% 13,0 ms
C7 (pc7) 9,9% | C7 (cc7) 64,3% | C7-SNB 73,4% 6,8 ms 84,0% 21,6 ms

| Core | CPU 2 CPU 3
| | C0 active 1,1% 0,9%
| | POLL 0,0% 0,0 ms 0,0% 0,0 ms
| | C1E-SNB 11,0% 6,9 ms 1,4% 4,8 ms
| |
| C3 (cc3) 9,3% | C3-SNB 7,7% 5,8 ms 1,9% 6,0 ms
| C6 (cc6) 10,0% | C6-SNB 8,5% 7,4 ms 4,1% 4,9 ms
| C7 (cc7) 64,9% | C7-SNB 71,4% 8,2 ms 91,1% 7,1 ms

PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables

Package | Core | CPU 0 CPU 1
| | Actual 2,0 GHz 2,4 GHz
Idle 54,4% | Idle 97,4% | Idle 98,9% 98,2%
2,90 GHz 0,6% | 2,90 GHz 0,1% | 2,90 GHz 0,1% 0,1%
2,81 GHz 2,6% | 3,10 GHz 0,2% | 3,10 GHz 0,1% 0,1%
3,10 GHz 1,2% | 2,10 GHz 0,1% | 2,10 GHz 0,0% 0,0%
3,21 GHz 7,3% | 3,21 GHz 0,9% | 3,21 GHz 0,1% 0,9%
2,10 GHz 2,3% | 2,81 GHz 0,2% | 2,81 GHz 0,1% 0,1%
3,00 GHz 3,5% | 3,00 GHz 0,0% | 3,00 GHz 0,0% 0,0%
2,40 GHz 3,5% | 2,40 GHz 0,1% | 2,40 GHz 0,1% 0,1%
1,91 GHz 1,0% | 1,91 GHz 0,1% | 1,91 GHz 0,0% 0,0%
2,21 GHz 0,6% | 2,21 GHz 0,1% | 2,21 GHz 0,1% 0,1%

| Core | CPU 2 CPU 3
| | Actual 2,4 GHz 2,5 GHz
| Idle 56,3% | Idle 98,4% 57,7%
| 2,90 GHz 0,5% | 2,90 GHz 0,1% 0,9%
| 2,81 GHz 2,5% | 2,81 GHz 0,1% 6,4%
| 3,10 GHz 1,1% | 3,10 GHz 0,2% 2,2%
| 3,21 GHz 6,7% | 3,00 GHz 0,0% 2,4%
| 3,00 GHz 3,5% | 3,21 GHz 0,5% 3,4%
| 2,71 GHz 2,4% | 2,50 GHz 0,1% 3,3%
| 2,50 GHz 1,1% | 2,31 GHz 0,1% 0,4%
| 2,31 GHz 0,2% | 2,71 GHz 0,1% 1,0%
| 2,60 GHz 1,0% | 2,60 GHz 0,1% 2,7%

If I haven?t stated it. This is on a ThinkPad T520 with dual core
Sandybridge i5-2620M at 2.5 GHz (overclockable to 3.2 GhZ), now with
Kernel 3.10-rc5. I didn?t test this one with the full hz stuff enabled, only
rc2 and rc4.

> According to powertop CPU 0 is never idle
>
> PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables
>
>
> Package | Core | CPU 0 CPU 1
> | | Actual 843 MHz 1148 MHz
> Turbo Mode 2,2% | Turbo Mode 2,1% | Turbo Mode 2,1% 0,8%
> 2,50 GHz 0,9% | 2,50 GHz 0,9% | 2,50 GHz 0,9% 0,0%
> 2,00 GHz 0,0% | 2,00 GHz 0,0% | 2,00 GHz 0,0% 0,0%
> 1,80 GHz 0,1% | 1,80 GHz 0,1% | 1,80 GHz 0,1% 0,0%
> 1,60 GHz 0,0% | 1,60 GHz 0,0% | 1,60 GHz 0,0% 0,0%
> 1400 MHz 0,0% | 1400 MHz 0,0% | 1400 MHz 0,0% 0,0%
> 1200 MHz 0,0% | 1200 MHz 0,0% | 1200 MHz 0,0% 0,0%
> 1000 MHz 0,0% | 1000 MHz 0,0% | 1000 MHz 0,0% 0,0%
> 800 MHz 87,9% | 800 MHz 87,3% | 800 MHz 87,1% 3,5%
> Idle 9,0% | Idle 9,6% | Idle 9,9% 95,7%
>
> | Core | CPU 2 CPU 3
> | | Actual 953 MHz 905 MHz
> | Turbo Mode 0,8% | Turbo Mode 0,7% 0,1%
> | 2,50 GHz 0,7% | 2,50 GHz 0,7% 0,0%
> | 2,00 GHz 0,0% | 2,00 GHz 0,0% 0,0%
> | 1,80 GHz 0,1% | 1,80 GHz 0,1% 0,0%
> | 1,60 GHz 0,0% | 1,60 GHz 0,0% 0,0%
> | 1400 MHz 0,0% | 1400 MHz 0,0% 0,0%
> | 1200 MHz 0,0% | 1200 MHz 0,0% 0,0%
> | 1000 MHz 0,0% | 1000 MHz 0,0% 0,0%
> | 800 MHz 10,3% | 800 MHz 7,4% 3,7%
> | Idle 88,1% | Idle 91,0% 96,2%
>
>
>
>
> PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables
>
>
> Package | Core | CPU 0 CPU 1
> | | C0 active 32,5% 0,3%
> | | POLL 96,4% 0,9 ms 0,0% 0,0 ms
> | | C1E-SNB 0,0% 0,0 ms 0,0% 0,2 ms
> C2 (pc2) 0,0% | |
> C3 (pc3) 0,0% | C3 (cc3) 0,0% | C3-SNB 0,0% 0,0 ms 0,0% 0,1 ms
> C6 (pc6) 0,0% | C6 (cc6) 0,0% | C6-SNB 0,0% 0,0 ms 0,0% 0,0 ms
> C7 (pc7) 0,0% | C7 (cc7) 0,0% | C7-SNB 0,0% 0,0 ms 99,2% 10,9 ms
>
> | Core | CPU 2 CPU 3
> | | C0 active 1,2% 0,7%
> | | POLL 0,0% 0,0 ms 0,0% 0,0 ms
> | | C1E-SNB 0,0% 0,1 ms 0,1% 0,2 ms
> | |
> | C3 (cc3) 0,1% | C3-SNB 0,0% 0,8 ms 0,0% 0,2 ms
> | C6 (cc6) 0,0% | C6-SNB 0,0% 0,0 ms 0,0% 0,0 ms
> | C7 (cc7) 95,0% | C7-SNB 97,7% 14,5 ms 97,7% 12,2 ms
>
>
> Old outputs with rc2 and P-State driver for comparison:
>
> >
> > PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables
> >
> >
> > Package | Core | CPU 0 CPU 1
> > | | C0 active 127,4% 2,3%
> > ^^^^^^
> > | | POLL 98,1% 0,9 ms 0,0% 0,0 ms
> > ^^^^^
> > | | C1E-SNB 0,0% 0,0 ms 0,4% 0,9 ms
> > C2 (pc2) 0,0% | |
> > C3 (pc3) 0,0% | C3 (cc3) 0,0% | C3-SNB 0,0% 0,0 ms 0,1% 0,8 ms
> > C6 (pc6) 0,0% | C6 (cc6) 0,0% | C6-SNB 0,0% 0,0 ms 0,0% 0,8 ms
> > C7 (pc7) 0,0% | C7 (cc7) 0,0% | C7-SNB 0,0% 0,0 ms 97,5% 7,4 ms
> >
> > | Core | CPU 2 CPU 3
> > | | C0 active 1,9% 0,8%
> > | | POLL 0,0% 0,0 ms 0,0% 0,0 ms
> > | | C1E-SNB 1,1% 1,3 ms 0,0% 0,1 ms
> > | |
> > | C3 (cc3) 0,3% | C3-SNB 0,3% 1,0 ms 0,0% 0,2 ms
> > | C6 (cc6) 0,1% | C6-SNB 0,1% 2,5 ms 0,0% 0,3 ms
> > | C7 (cc7) 96,2% | C7-SNB 97,0% 7,2 ms 99,3% 17,2 ms
> >
> >
> > PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables
> >
> >
> > Package | Core | CPU 0 CPU 1
> > | | Actual 3,2 GHz 3,1 GHz
> > Idle 100,0% | Idle 100,0% | Idle 100,0% 100,0%
> >
> > | Core | CPU 2 CPU 3
> > | | Actual 3,0 GHz 3,0 GHz
> > | Idle 100,0% | Idle 100,0% 100,0%
> >
> >
> > It seems the kernel is overbusying one core completely, if the output of
> > powertop is correct. And why is Actual frequencing of CPUs that high?
> > I saw that kernel tends to overtact quickly. I thought this was due to
> > getting work done quickly and then let it idle. But the idle stats
> > seem bogus to, maybe powertop is not up to date with current kernels?
> >
> > I see no reason for busying one core. This happens when CPU usage is
> > below 20%. The fan is consistently around 2640 rpm:
> >
> >
> > PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables
> >
> > Summary: 399,8 wakeups/second, 0,0 GPU ops/second, 0,0 VFS ops/sec and 3,0% CPU use
> >
> > Usage Events/s Category Description
> > 2644 rpm Device Laptop fan
> > 100,0% Device Audio codec hwC0D1: Conexant
> > 100,0% Device Audio codec hwC0D3: Intel
> > 100,0% Device Audio codec hwC0D0: Conexant
> > 30,7 ?s/s 112,3 Process [ksoftirqd/0]
> > 4,2 ms/s 83,5 Process kwin -session 10cec7d36b000136265311700000023930000_1369322581_349094
> > 0,8 ms/s 67,3 Process [irq/42-i915@pci]
> > 5,5 ms/s 53,6 Process /usr/bin/X :0 vt7 -br -nolisten tcp -auth /var/run/xauth/A:0-eXsirc
> > 698,3 ?s/s 13,3 Process [irq/16-mmc0]
> > 85,8 ?s/s 9,1 Process [rcu_preempt]
> > 297,1 ?s/s 8,7 Process /usr/sbin/mysqld --defaults-file=/home/martin/.local/share/akonadi/mysql.conf --datadir
> > 78,6 ?s/s 8,1 Process [ksoftirqd/2]
> > 6,7 ms/s 3,7 Process /usr/bin/plasma-desktop
> > 218,9 ?s/s 5,0 Interrupt [1] timer(softirq)
> > 2,8 ms/s 2,9 Process /usr/bin/konsole -session 10cec7d36b000135326160200000249810027_1369322580_899575
> > 65,9 ?s/s 3,6 Process [ksoftirqd/1]
> > 69,8 ?s/s 3,5 Process [ksoftirqd/3]
> > 38,1 ?s/s 3,4 Process [rcuop/3]
> > 35,3 ?s/s 2,4 Process [rcuop/2]
> > 6,0 ms/s 0,00 Process atop
> > 21,3 ?s/s 1,8 Process [irq/43-ahci]
> > 33,3 ?s/s 1,7 Process [rcuop/0]
> > 122,3 ?s/s 1,7 Process [btrfs-transacti]
> > 66,4 ?s/s 1,5 Process /usr/bin/dirmngr --daemon --sh
> > 61,2 ?s/s 1,0 Process [rcuop/1]
> > 29,2 ?s/s 1,0 Process /usr/lib/gvfs/gvfs-afc-volume-monitor
> > 40,8 ?s/s 0,9 Timer process_timeout
> > 25,5 ?s/s 0,9 Process /usr/bin/python /usr/bin/hp-systray -x
> > 32,2 ?s/s 0,7 Process /usr/bin/dbus-daemon --fork --print-pid 5 --print-address 7 --session
> > 5,1 ?s/s 0,7 Process [irq/44-eth0]
> > 612,1 ?s/s 0,4 Process ksysguardd
> > 137,6 ?s/s 0,5 Interrupt [7] sched(softirq)
> > 5,6 ?s/s 0,5 Timer clocksource_watchdog
> > 71,2 ?s/s 0,4 kWork disk_events_workfn
> > 57,5 ?s/s 0,4 Process kdeinit4: kded4 [kdeinit]
> > 68,3 ?s/s 0,3 Process akonadiserver
> > 34,6 ?s/s 0,3 Process /usr/bin/virtuoso-t +foreground +configfile /tmp/virtuoso_fB2599.ini +wait
> > 14,9 ?s/s 0,3 Process /usr/bin/gpg-agent --daemon --sh --write-env-file=/home/martin/.gnupg/gpg-agent-info-me
> > 39,4 ?s/s 0,30 Process /usr/bin/nepomukservicestub nepomukfileindexer
> >
> >
> > PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables
> >
> >
> > Usage Device name
> > 2644 rpm Laptop fan
> > 4,3% CPU use
> > 100,0% Audio codec hwC0D3: Intel
> > 100,0% Audio codec hwC0D0: Conexant
> > 100,0% Audio codec hwC0D1: Conexant
> > 20,9 pkts/s Network interface: eth0 (e1000e)
> > 100,0% USB device: usb-device-8087-0024
> > 100,0% USB device: usb-device-8087-0024
> > 100,0% Display backlight
> > 100,0% Display backlight
> > 100,0% USB device: EHCI Host Controller
> > 100,0% USB device: Biometric Coprocessor (UPEK)
> > 100,0% USB device: Integrated Smart Card Reader (Lenovo)
> > 100,0% USB device: EHCI Host Controller
> > 0,0 ops/s GPU
> > 100,0% USB device: usb-device-17ef-100a
> > 100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 5
> > 100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 4
> > 100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 2
> > 100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family High Definition Audio Controller
> > 100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family MEI Controller #1
> > 100,0% USB device: PS/2+USB Mouse
> > 100,0% PCI Device: Intel Corporation QM67 Express Chipset Family LPC Controller
> > 100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family 6 port SATA AHCI Controller
> > 100,0% PCI Device: Ricoh Co Ltd MMC/SD Host Controller
> > 100,0% PCI Device: Silicon Image, Inc. SiI 3531 [SATALink/SATARaid] Serial ATA Controller
> > 100,0% PCI Device: Ricoh Co Ltd R5C832 PCIe IEEE 1394 Controller
> > 100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family USB Enhanced Host Controller #2
> > 100,0% PCI Device: Intel Corporation 82579LM Gigabit Network Connection
> > 100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family SMBus Controller
> > 100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 1
> > 100,0% PCI Device: Intel Corporation 6 Series/C200 Series Chipset Family USB Enhanced Host Controller #1
> > 100,0% PCI Device: Intel Corporation 2nd Generation Core Processor Family Integrated Graphics Controller
> > 100,0% PCI Device: Intel Corporation 2nd Generation Core Processor Family DRAM Controller
> > 100,0% PCI Device: Intel Corporation Centrino Advanced-N 6205 [Taylor Peak]
> > 0,0 pkts/s Network interface: wlan0 (iwlwifi)
> > 0,0% Thinkpad light
> > 0,0% Radio device: thinkpad_acpi
> > 0,0% Radio device: iwlwifi
> >
> >
> > I saw nothing outstanding in dmesg or kern.log, just
> >
> > merkaba:~#2> grep "Intel pstate controlling: cpu" /var/log/kern.log
> > May 20 10:03:31 merkaba kernel: [264852.930994] Intel pstate controlling: cpu 1
> > May 20 10:03:31 merkaba kernel: [264852.944479] Intel pstate controlling: cpu 2
> > May 20 10:03:31 merkaba kernel: [264852.957879] Intel pstate controlling: cpu 3
> > May 21 09:14:03 merkaba kernel: [315800.710623] Intel pstate controlling: cpu 1
> > May 21 09:14:03 merkaba kernel: [315800.724087] Intel pstate controlling: cpu 2
> > May 21 09:14:03 merkaba kernel: [315800.737493] Intel pstate controlling: cpu 3
> > May 21 20:01:20 merkaba kernel: [344305.122543] Intel pstate controlling: cpu 1
> > May 21 20:01:20 merkaba kernel: [344305.135953] Intel pstate controlling: cpu 2
> > May 21 20:01:20 merkaba kernel: [344305.149398] Intel pstate controlling: cpu 3
> > May 21 21:52:18 merkaba kernel: [ 1.441043] Intel pstate controlling: cpu 0
> > May 21 21:52:18 merkaba kernel: [ 1.441084] Intel pstate controlling: cpu 1
> > May 21 21:52:18 merkaba kernel: [ 1.441123] Intel pstate controlling: cpu 2
> > May 21 21:52:18 merkaba kernel: [ 1.441162] Intel pstate controlling: cpu 3
> > May 23 17:22:29 merkaba kernel: [ 1.860224] Intel pstate controlling: cpu 0
> > May 23 17:22:29 merkaba kernel: [ 1.860267] Intel pstate controlling: cpu 1
> > May 23 17:22:29 merkaba kernel: [ 1.860306] Intel pstate controlling: cpu 2
> > May 23 17:22:29 merkaba kernel: [ 1.860345] Intel pstate controlling: cpu 3
> >
> > But these seem to be regular and I had them before as well.
> >
> > Thanks,
> >
>
--
Martin 'Helios' Steigerwald - http://www.Lichtvoll.de
GPG: 03B0 0D6C 0040 0710 4AFA B82F 991B EAAC A599 84C7

2013-06-13 14:00:00

by Frederic Weisbecker

[permalink] [raw]

Subject: Re: [REGRESSION] fan always on with 3.10-rc2

On Sun, Jun 09, 2013 at 08:34:10PM +0200, Martin Steigerwald wrote:
> Am Samstag, 8. Juni 2013, 22:34:44 schrieb Martin Steigerwald:
> > Am Freitag, 24. Mai 2013, 13:03:18 schrieb Martin Steigerwald:
> > > Hi!
> > >
> > > With 3.10-rc2 I see fan always or almost always on, even during extended
> > > periods of basically idling around. I did not notice this with 3.9. This is
> > > on an ThinkPad T520 with Intel Sandybridge i5-2520M dual core with
> > > hyperthreading at regularily 2,5 GhZ and Intel graphics (no nvidia).
> > >
> > > I am using full hz:
> > >
> > > martin@merkaba:~/Linux/Kernel/Mainline/Bugs/fan always on with 3.10.2-rc2> xzgrep NO_HZ config-3.10.0-rc2-tp520.xz
> > > CONFIG_NO_HZ_COMMON=y
> > > # CONFIG_NO_HZ_IDLE is not set
> > > CONFIG_NO_HZ_FULL=y
> > > CONFIG_NO_HZ_FULL_ALL=y
> > > CONFIG_NO_HZ=y
> > > CONFIG_RCU_FAST_NO_HZ=y
> > >
> > > And P-State driver (which I used in 3.9 already as well).
> > >
> > > Kernel config attached as xz. Use xzless or xzcat to display.
> > >
> > >
> > > What puzzles is output of powertop, especially:
> >
> > Still present in 3.10-rc4.
> >
> > I disabled P-State driver but then rpm seems to be even worse.
> >
> > Around 2800 rpm all the time, was about 2650 with Intel P State driver.
> >
> > Next I will try without CONFIG_NO_HZ_FULL and CONFIG_NO_HZ_FULL_ALL.
>
> Okay, without these both the behavior is better. Fan still does not seem
> to get into non running state, which it was able to with earlier kernels
> (or userspaces?), but its down to a quiet 1950 rpm with Intel P-State driver
> enabled again. CC?d to people from thread "power management regression
> in linux 3.10? (related to CONFIG_NO_HZ_FULL)" which I think is related.
>
> Powertop values make a lot more sense as well:
>
> PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables
>
>
> Package | Core | CPU 0 CPU 1
> | | C0 active 1,4% 0,9%
> | | POLL 0,0% 0,0 ms 0,0% 0,0 ms
> | | C1E-SNB 7,7% 3,0 ms 2,9% 5,3 ms
> C2 (pc2) 1,1% | |
> C3 (pc3) 7,2% | C3 (cc3) 8,4% | C3-SNB 8,2% 3,1 ms 3,0% 15,2 ms
> C6 (pc6) 4,9% | C6 (cc6) 9,3% | C6-SNB 7,0% 3,5 ms 6,2% 13,0 ms
> C7 (pc7) 9,9% | C7 (cc7) 64,3% | C7-SNB 73,4% 6,8 ms 84,0% 21,6 ms
>
> | Core | CPU 2 CPU 3
> | | C0 active 1,1% 0,9%
> | | POLL 0,0% 0,0 ms 0,0% 0,0 ms
> | | C1E-SNB 11,0% 6,9 ms 1,4% 4,8 ms
> | |
> | C3 (cc3) 9,3% | C3-SNB 7,7% 5,8 ms 1,9% 6,0 ms
> | C6 (cc6) 10,0% | C6-SNB 8,5% 7,4 ms 4,1% 4,9 ms
> | C7 (cc7) 64,9% | C7-SNB 71,4% 8,2 ms 91,1% 7,1 ms
>
>
>
> PowerTOP v2.0 Overview Idle stats Frequency stats Device stats Tunables
>
>
> Package | Core | CPU 0 CPU 1
> | | Actual 2,0 GHz 2,4 GHz
> Idle 54,4% | Idle 97,4% | Idle 98,9% 98,2%
> 2,90 GHz 0,6% | 2,90 GHz 0,1% | 2,90 GHz 0,1% 0,1%
> 2,81 GHz 2,6% | 3,10 GHz 0,2% | 3,10 GHz 0,1% 0,1%
> 3,10 GHz 1,2% | 2,10 GHz 0,1% | 2,10 GHz 0,0% 0,0%
> 3,21 GHz 7,3% | 3,21 GHz 0,9% | 3,21 GHz 0,1% 0,9%
> 2,10 GHz 2,3% | 2,81 GHz 0,2% | 2,81 GHz 0,1% 0,1%
> 3,00 GHz 3,5% | 3,00 GHz 0,0% | 3,00 GHz 0,0% 0,0%
> 2,40 GHz 3,5% | 2,40 GHz 0,1% | 2,40 GHz 0,1% 0,1%
> 1,91 GHz 1,0% | 1,91 GHz 0,1% | 1,91 GHz 0,0% 0,0%
> 2,21 GHz 0,6% | 2,21 GHz 0,1% | 2,21 GHz 0,1% 0,1%
>
> | Core | CPU 2 CPU 3
> | | Actual 2,4 GHz 2,5 GHz
> | Idle 56,3% | Idle 98,4% 57,7%
> | 2,90 GHz 0,5% | 2,90 GHz 0,1% 0,9%
> | 2,81 GHz 2,5% | 2,81 GHz 0,1% 6,4%
> | 3,10 GHz 1,1% | 3,10 GHz 0,2% 2,2%
> | 3,21 GHz 6,7% | 3,00 GHz 0,0% 2,4%
> | 3,00 GHz 3,5% | 3,21 GHz 0,5% 3,4%
> | 2,71 GHz 2,4% | 2,50 GHz 0,1% 3,3%
> | 2,50 GHz 1,1% | 2,31 GHz 0,1% 0,4%
> | 2,31 GHz 0,2% | 2,71 GHz 0,1% 1,0%
> | 2,60 GHz 1,0% | 2,60 GHz 0,1% 2,7%
>
>
> If I haven?t stated it. This is on a ThinkPad T520 with dual core
> Sandybridge i5-2620M at 2.5 GHz (overclockable to 3.2 GhZ), now with
> Kernel 3.10-rc5. I didn?t test this one with the full hz stuff enabled, only
> rc2 and rc4.
>
> > According to powertop CPU 0 is never idle

Note that CONFIG_NO_HZ_FULL is very power unfriendly because it forces CPU 0
to keep its periodic tick to handle timekeeping, even when idle. Paul McKenney is
working on a solution to solve this.

Thanks.