Re: [Linux-Thermal-Daemon] thermald throttling my CPU too soon at 80C due to reading from coretemp / DTS which has tempX_max set to 80C
1:55 a.m.
On Mon, 2015-05-11 at 08:54 -0700, Srinivas Pandruvada wrote:
On Sun, 2015-05-10 at 12:42 +0800, Gaha Bana wrote:
> hi, i run ubuntu 15.04 with kernels 3.19.6 (tried 4.0.1 as well).
> CPU is Intel i5-2500K which is overclocked mildly to 4.1GHz.
> If I disable thermald and manually lower/control fanspeed to let CPU
> heat up to 98C (as read from DTS) CPU protection will kick in and
> frequency get lowered.
> However, with thermald active (defailt) it happens already at 80C.
> I would like to set that up to be lower then 'maximum allowed' which
> is 98C (90-92) ... so that when i am doing mass transcodings i keep
> Tjunction below 90c
> normally machine is not doing much so cpu is at less then 40C (100 F).
This you can change by sending a dbus message
Look here
https://github.com/01org/thermal_daemon/blob/master/tools/thermald_set_pr...
option 5 and 6.
>
>
> i tried changing thermal-config.xml as well as sensors3.conf to set
> different temps ... maybe someone has some experience on what to do so
> that temp1 to temp5_max would be set to e.g. 91C instead of default
> 80C.
>
>
> here are the outputs from sensors, part of sensors3.conf file .. as
> for thermal-config.xml - even if i delete it or put anything i makes
> no difference. ... lastly i include debug portion from thermald itself
> where it is clear that it does something at 80C already.
>
>
> sensors command:
> me@asus:/etc/thermald$ sensors
> coretemp-isa-0000
> Adapter: ISA adapter
> Physical id 0: +37.0°C (high = +80.0°C, crit = +98.0°C)
> Core 0: +36.0°C (high = +80.0°C, crit = +98.0°C)
> Core 1: +37.0°C (high = +80.0°C, crit = +98.0°C)
> Core 2: +36.0°C (high = +80.0°C, crit = +98.0°C)
> Core 3: +37.0°C (high = +80.0°C, crit = +98.0°C)
> nct6776-isa-0290
> Adapter: ISA adapter
> Vcore: +1.02 V (min = +0.00 V, max = +1.74 V)
> in1: +1.87 V (min = +0.00 V, max = +0.00 V)
> ALARM
> AVCC: +3.34 V (min = +2.98 V, max = +3.63 V)
> +3.3V: +3.33 V (min = +2.98 V, max = +3.63 V)
> in4: +0.86 V (min = +0.00 V, max = +0.00 V)
> ALARM
> in5: +1.69 V (min = +0.00 V, max = +0.00 V)
> ALARM
> in6: +0.82 V (min = +0.00 V, max = +0.00 V)
> ALARM
> 3VSB: +3.38 V (min = +2.98 V, max = +3.63 V)
> Vbat: +3.22 V (min = +2.70 V, max = +3.63 V)
> fan1: 0 RPM (min = 0 RPM)
> fan2: 1192 RPM (min = 0 RPM)
> fan3: 0 RPM (min = 0 RPM)
> fan4: 929 RPM (min = 0 RPM)
> fan5: 0 RPM (min = 0 RPM)
> SYSTIN: +36.0°C (high = +0.0°C, hyst = +0.0°C)
> ALARM sensor = thermistor
> CPUTIN: +35.5°C (high = +80.0°C, hyst = +75.0°C)
> sensor = thermistor
> AUXTIN: +39.0°C (high = +80.0°C, hyst = +75.0°C)
> sensor = thermistor
> PECI Agent 0: +37.0°C (high = +80.0°C, hyst = +75.0°C)
> (crit = +98.0°C)
> PCH_CHIP_TEMP: +0.0°C
> PCH_CPU_TEMP: +0.0°C
> PCH_MCH_TEMP: +0.0°C
> intrusion0: ALARM
> intrusion1: OK
> beep_enable: disabled
>
> end of sensors3.conf file (makes no difference):
>
> chip "coretemp-isa-0000"
> set temp1_max 92000
> set temp2_max 93000
> set temp3_max 87000
> set temp4_max 91000
> set temp5_max 94000
>
>
> therlmald log file (where you can see 80000 number that is reading
> from on die temperature that i can not get increased so CPU would not
> throttle at 80C already):
>
>
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/power/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/enabled/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/intel-rapl:0/name/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/intel-rapl:0/power/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed
/sys/class/powercap/intel-rapl/intel-rapl:0/constraint_0_time_window_us/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed
/sys/class/powercap/intel-rapl/intel-rapl:0/constraint_1_power_limit_uw/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/intel-rapl:0/enabled/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/intel-rapl:0/device/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed
/sys/class/powercap/intel-rapl/intel-rapl:0/constraint_0_power_limit_uw/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/intel-rapl:0/subsystem/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/intel-rapl:0/constraint_0_name/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/intel-rapl:0/constraint_1_name/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/intel-rapl:0/energy_uj/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed
/sys/class/powercap/intel-rapl/intel-rapl:0/constraint_1_max_power_uw/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/intel-rapl:0/uevent/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/intel-rapl:0/max_energy_range_uj/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed
/sys/class/powercap/intel-rapl/intel-rapl:0/constraint_0_max_power_uw/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed
/sys/class/powercap/intel-rapl/intel-rapl:0/constraint_1_time_window_us/name
> May 10 12:40:49 acus thermald[5662]: RAPL domain count 0
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/subsystem/name
> May 10 12:40:49 acus thermald[5662]: sysfs read
> failed /sys/class/powercap/intel-rapl/uevent/name
> May 10 12:40:49 acus thermald[5662]: RAPL domain count 1
> May 10 12:40:49 acus thermald[5662]: 13 CPUID levels;
> family:model:stepping 0x6:2a:7 (6:42:7)
> May 10 12:40:49 acus thermald[5662]: Running on a vanilla
> kernel
> May 10 12:40:49 acus thermald[5662]: Polling mode is enabled:
> 4
> May 10 12:40:49 acus thermald[5662]: sensor_update: type
> x86_pkg_temp
> May 10 12:40:49 acus thermald[5662]:
> thd_read_default_thermal_sensors loaded 1 sensors
> May 10 12:40:49 acus thermald[5662]:
> dts /sys/devices/platform/coretemp.0/name doesn't exist
> May 10 12:40:49 acus thermald[5662]: failed to
> open /dev/acpi_thermal_rel
> May 10 12:40:49 acus thermald[5662]: failed to
> open /dev/acpi_thermal_rel
> May 10 12:40:49 acus thermald[5662]: TRT/ART read failed
> May 10 12:40:49 acus thermald[5662]: Dumping parsed XML Data
> May 10 12:40:49 acus thermald[5662]: *** Index 0 ***
> May 10 12:40:49 acus thermald[5662]: Name: AcusServer
> May 10 12:40:49 acus thermald[5662]: UUID:
> May 10 12:40:49 acus thermald[5662]: type: 0
> May 10 12:40:49 acus thermald[5662]: Sensor 0
> May 10 12:40:49 acus thermald[5662]: Name: pkg-temp-0
> May 10 12:40:49 acus thermald[5662]:
> Path: /sys/class/thermal/thermal_zone0/
> May 10 12:40:49 acus thermald[5662]: Async Capable: 1
> May 10 12:40:49 acus thermald[5662]: Sensor 1
> May 10 12:40:49 acus thermald[5662]: Name: coretemp
> May 10 12:40:49 acus thermald[5662]:
> Path: /sys/devices/platform/coretemp.0/hwmon/hwmon0/
> May 10 12:40:49 acus thermald[5662]: Async Capable: 0
> May 10 12:40:49 acus thermald[5662]: Zone 0
> May 10 12:40:49 acus thermald[5662]: Name: cpupackage
> May 10 12:40:49 acus thermald[5662]: Trip Point 0
> May 10 12:40:49 acus thermald[5662]: temp 92000
> May 10 12:40:49 acus thermald[5662]: trip type 2
> May 10 12:40:49 acus thermald[5662]: hyst id 0
> May 10 12:40:49 acus thermald[5662]: sensor type coretemp
> May 10 12:40:49 acus thermald[5662]: cdev index 0
> May 10 12:40:49 acus thermald[5662]: type rapl_controller
> May 10 12:40:49 acus thermald[5662]: influence 50
> May 10 12:40:49 acus thermald[5662]: SamplingPeriod 10
> May 10 12:40:49 acus thermald[5662]: cdev index 1
> May 10 12:40:49 acus thermald[5662]: type intel_powerclamp
> May 10 12:40:49 acus thermald[5662]: influence 30
> May 10 12:40:49 acus thermald[5662]: SamplingPeriod 10
> May 10 12:40:49 acus thermald[5662]: cdev index 2
> May 10 12:40:49 acus thermald[5662]: type cpufreq
> May 10 12:40:49 acus thermald[5662]: influence 100
> May 10 12:40:49 acus thermald[5662]: SamplingPeriod 8
> May 10 12:40:49 acus thermald[5662]: Product Name matched
> [wildcard]
> May 10 12:40:49 acus thermald[5662]: sensor index:0
> x86_pkg_temp Async:1
> May 10 12:40:49 acus thermald[5662]: sensor index:1 hwmon
> Async:0
> May 10 12:40:49 acus thermald[5662]: sensor index:2 hwmon
> Async:0
> May 10 12:40:49 acus thermald[5662]: sensor index:3 hwmon
> Async:0
> May 10 12:40:49 acus thermald[5662]: sensor index:4 pkg-temp-0
> Async:0
> May 10 12:40:49 acus thermald[5662]: sensor index:5 coretemp
> Async:0
> May 10 12:40:49 acus thermald[5662]: thd_read_default_cooling
> devices loaded 6 cdevs
> May 10 12:40:49 acus thermald[5662]: Default constraint power
> limit is more than max power 200000000:95000000
> May 10 12:40:49 acus thermald[5662]: powercap RAPL max power
> limit range 200000000
> May 10 12:40:49 acus thermald[5662]: set_pid_param 6
> [1000.100,10]
> May 10 12:40:49 acus thermald[5662]: Use Default pstate drv
> settings
> May 10 12:40:49 acus thermald[5662]: Product Name matched
> [wildcard]
> May 10 12:40:49 acus thermald[5662]: name = package-0
> May 10 12:40:49 acus thermald[5662]: name = core
> May 10 12:40:49 acus thermald[5662]: name = uncore
> May 10 12:40:49 acus thermald[5662]: 0: Processor, C:0 MN: 0
> MX:3 ST:1 pt:/sys/class/thermal/ rd_bk 0
> May 10 12:40:49 acus thermald[5662]: 1: Processor, C:0 MN: 0
> MX:3 ST:1 pt:/sys/class/thermal/ rd_bk 0
> May 10 12:40:49 acus thermald[5662]: 2: Processor, C:0 MN: 0
> MX:3 ST:1 pt:/sys/class/thermal/ rd_bk 0
> May 10 12:40:49 acus thermald[5662]: 3: Processor, C:0 MN: 0
> MX:3 ST:1 pt:/sys/class/thermal/ rd_bk 0
> May 10 12:40:49 acus thermald[5662]: 4: LCD, C:0 MN: 0 MX:20
> ST:5 pt:/sys/class/thermal/ rd_bk 0
> May 10 12:40:49 acus thermald[5662]: 5: intel_powerclamp, C:-1
> MN: 0 MX:50 ST:5 pt:/sys/class/thermal/ rd_bk 0
> May 10 12:40:49 acus thermald[5662]: 6: rapl_controller, C:0
> MN: 0 MX:150000000 ST:10000000
> pt:/sys/devices/virtual/powercap/intel-rapl/intel-rapl:0/
> rd_bk 1
> May 10 12:40:49 acus thermald[5662]: 7: intel_pstate, C:0 MN:
> 0 MX:10 ST:1 pt:/sys/devices/system/cpu/intel_pstate/ rd_bk 1
> May 10 12:40:49 acus thermald[5662]:
> thd_read_default_thermal_zones loaded 0 zones
> May 10 12:40:49 acus thermald[5662]: zone cpu will be created
> May 10 12:40:49 acus thermald[5662]: dts
> zone /sys/devices/platform/coretemp.0/name doesn't exist
> May 10 12:40:49 acus
> thermald[5662]: /sys/class/hwmon/hwmon0/name->coretemp
> May 10 12:40:49 acus thermald[5662]: Core temp DTS :critical
> 98000, max 80000
> May 10 12:40:49 acus thermald[5662]: Read set point 0
> May 10 12:40:49 acus thermald[5662]: node type: Element, name:
> CoolingDevice value: rapl_controller
> May 10 12:40:49 acus thermald[5662]: node type: Element, name:
> CoolingDevice value: intel_pstate
> May 10 12:40:49 acus thermald[5662]: node type: Element, name:
> CoolingDevice value: intel_powerclamp
> May 10 12:40:49 acus thermald[5662]: node type: Element, name:
> CoolingDevice value: cpufreq
> May 10 12:40:49 acus thermald[5662]: node type: Element, name:
> CoolingDevice value: Processor
> May 10 12:40:49 acus thermald[5662]: CDEVS order specified in
> thermal-cpu-cdev-order.xml
> May 10 12:40:49 acus thermald[5662]: Sorted trip dump :
> May 10 12:40:49 acus thermald[5662]: index 1: type:passive
> temp:80000 hyst:0 zone id:0 sensor id:65535 cdev size:4
> May 10 12:40:49 acus thermald[5662]: cdev[0] rapl_controller
> May 10 12:40:49 acus thermald[5662]: cdev[1] intel_pstate
> May 10 12:40:49 acus thermald[5662]: cdev[2] intel_powerclamp
> May 10 12:40:49 acus thermald[5662]: cdev[3] Processor
> May 10 12:40:49 acus thermald[5662]: index 0: type:max
> temp:88000 hyst:0 zone id:0 sensor id:65535 cdev size:4
> May 10 12:40:49 acus thermald[5662]: cdev[0] rapl_controller
> May 10 12:40:49 acus thermald[5662]: cdev[1] intel_pstate
> May 10 12:40:49 acus thermald[5662]: cdev[2] intel_powerclamp
> May 10 12:40:49 acus thermald[5662]: cdev[3] Processor
> May 10 12:40:49 acus thermald[5662]: trip type: 2 temp: 80000
> May 10 12:40:49 acus thermald[5662]: trip type: 1 temp: 88000
> May 10 12:40:49 acus thermald[5662]: Read set point 0
> May 10 12:40:49 acus thermald[5662]: Read set point 0
> May 10 12:40:49 acus
> thermald[5662]: /sys/class/hwmon/hwmon1/name->nct6776
> May 10 12:40:49 acus thermald[5662]: Product Name matched
> [wildcard]
> May 10 12:40:49 acus thermald[5662]: zone cpupackage bounded
> May 10 12:40:49 acus thermald[5662]: zone cpupackage bounded
> May 10 12:40:49 acus thermald[5662]: Sorted trip dump :
> May 10 12:40:49 acus thermald[5662]: index 0: type:passive
> temp:92000 hyst:0 zone id:1 sensor id:5 cdev size:2
> May 10 12:40:49 acus thermald[5662]: cdev[0] rapl_controller
> May 10 12:40:49 acus thermald[5662]: cdev[1] intel_powerclamp
> May 10 12:40:49 acus thermald[5662]: trip type: 2 temp: 92000
> May 10 12:40:49 acus thermald[5662]: Zone 0: cpu, Active:1
> Bind:0 Sensor_cnt:2
> May 10 12:40:49 acus thermald[5662]: ..sensors..
> May 10 12:40:49 acus thermald[5662]: sensor index:4 pkg-temp-0
> Async:0
> May 10 12:40:49 acus thermald[5662]: sensor index:0
> x86_pkg_temp Async:1
> May 10 12:40:49 acus thermald[5662]: ..trips..
> May 10 12:40:49 acus thermald[5662]: index 1: type:passive
> temp:80000 hyst:0 zone id:0 sensor id:65535 cdev size:4
> May 10 12:40:49 acus thermald[5662]: cdev[0] rapl_controller
> May 10 12:40:49 acus thermald[5662]: cdev[1] intel_pstate
> May 10 12:40:49 acus thermald[5662]: cdev[2] intel_powerclamp
> May 10 12:40:49 acus thermald[5662]: cdev[3] Processor
> May 10 12:40:49 acus thermald[5662]: index 0: type:max
> temp:88000 hyst:0 zone id:0 sensor id:65535 cdev size:4
> May 10 12:40:49 acus thermald[5662]: cdev[0] rapl_controller
> May 10 12:40:49 acus thermald[5662]: cdev[1] intel_pstate
> May 10 12:40:49 acus thermald[5662]: cdev[2] intel_powerclamp
> May 10 12:40:49 acus thermald[5662]: cdev[3] Processor
> May 10 12:40:49 acus thermald[5662]: index 2: type:polling
> temp:69600 hyst:0 zone id:0 sensor id:0 cdev size:0
> May 10 12:40:49 acus thermald[5662]: Zone 1: cpupackage,
> Active:1 Bind:1 Sensor_cnt:1
> May 10 12:40:49 acus thermald[5662]: ..sensors..
> May 10 12:40:49 acus thermald[5662]: sensor index:5 coretemp
> Async:0
> May 10 12:40:49 acus thermald[5662]: ..trips..
> May 10 12:40:49 acus thermald[5662]: index 0: type:passive
> temp:92000 hyst:0 zone id:1 sensor id:5 cdev size:2
> May 10 12:40:49 acus thermald[5662]: cdev[0] rapl_controller
> May 10 12:40:49 acus thermald[5662]: cdev[1] intel_powerclamp
> May 10 12:40:49 acus thermald[5662]: FD = 8
> May 10 12:40:49 acus thermald[5662]: Current user preference
> is 0
> May 10 12:40:49 acus thermald[5662]: thd_engine_thread begin
>
> Thanks in advance for help and/or advice !
>
>
> Gaha
>
> _______________________________________________
> Linux-Thermal-Daemon mailing list
> Linux-Thermal-Daemon(a)lists.01.org
> https://lists.01.org/mailman/listinfo/linux-thermal-daemon
2687
days inactive
2687
days old
linux-thermal-daemon@lists.01.org
0 comments
1 participants
participants (1)
-
Srinivas Pandruvada