Check out my first novel, midnight's simulacra!
Power Management: Difference between revisions
From dankwiki
No edit summary |
|||
(6 intermediate revisions by the same user not shown) | |||
Line 1: | Line 1: | ||
Matthew Garrett's "[http://www.codon.org.uk/~mjg59/power/good_practices.html Observations on Power Management]" is a great intro. | |||
==Implementations== | ==Implementations== | ||
* APM (Advanced Power Management): All PM policy/mechanism resides within the BIOS | * APM (Advanced Power Management): All PM policy/mechanism resides within the BIOS | ||
Line 8: | Line 9: | ||
* P4 Thermal Throttling: Slows down or shuts off the processor based on CPU temperature | * P4 Thermal Throttling: Slows down or shuts off the processor based on CPU temperature | ||
** Adjustment is either via idle cycle insertion or lowering the clock multiplier | ** Adjustment is either via idle cycle insertion or lowering the clock multiplier | ||
==Batteries== | |||
* upower can be used to get battery details, if its daemon is running: | |||
<pre>upower -i /org/freedesktop/UPower/devices/battery_BAT1 | |||
native-path: BAT1 | |||
vendor: SMP | |||
model: 01AV452 | |||
serial: 5642 | |||
power supply: yes | |||
updated: Sun 15 Jul 2018 12:33:08 PM EDT (104 seconds ago) | |||
has history: yes | |||
has statistics: yes | |||
battery | |||
present: yes | |||
rechargeable: yes | |||
state: discharging | |||
warning-level: none | |||
energy: 15.94 Wh | |||
energy-empty: 0 Wh | |||
energy-full: 24.54 Wh | |||
energy-full-design: 24 Wh | |||
energy-rate: 7.994 W | |||
voltage: 11.405 V | |||
time to empty: 2.0 hours | |||
percentage: 66% | |||
capacity: 100% | |||
technology: lithium-polymer | |||
icon-name: 'battery-full-symbolic' | |||
History (charge): | |||
1531672388 66.000 discharging | |||
History (rate): | |||
1531672388 7.994 discharging</pre> | |||
==CPU Frequency== | ==CPU Frequency== | ||
Line 37: | Line 70: | ||
cpufreq stats: 2.39 GHz:4.32%, 1.60 GHz:95.68% (19387) | cpufreq stats: 2.39 GHz:4.32%, 1.60 GHz:95.68% (19387) | ||
[recombinator](0) $ </pre> | [recombinator](0) $ </pre> | ||
* You can get C-state latency information from <tt>/proc/acpi/processor/*/power</tt>: | |||
<pre>[wopr](0) $ cat /proc/acpi/processor/CP10/power | |||
active state: C0 | |||
max_cstate: C8 | |||
maximum allowed latency: 2000000000 usec | |||
states: | |||
C1: type[C1] promotion[--] demotion[--] latency[032] usage[02035391] duration[00000000000000000000] | |||
C2: type[C2] promotion[--] demotion[--] latency[064] usage[01050475] duration[00000000000624232458] | |||
C3: type[C2] promotion[--] demotion[--] latency[096] usage[150501625] duration[00000020175094863449] | |||
[wopr](0) $ </pre> | |||
* On [[FreeBSD]], sysctls from the dev.cpu and debug.cpufreq MIB hierarchies are your window into frequency control. See [http://www.freebsd.org/cgi/man.cgi?query=cpufreq&apropos=0&sektion=0&format=html cpufreq(4)]. | * On [[FreeBSD]], sysctls from the dev.cpu and debug.cpufreq MIB hierarchies are your window into frequency control. See [http://www.freebsd.org/cgi/man.cgi?query=cpufreq&apropos=0&sektion=0&format=html cpufreq(4)]. | ||
==Disks/Filesystems== | ==Disks/Filesystems== | ||
* noatime -- critical for all kinds of things! don't believe me; trust [http://article.gmane.org/gmane.linux.kernel/565148 ingo | * noatime -- critical for all kinds of things! don't believe me; trust [http://article.gmane.org/gmane.linux.kernel/565148 ingo molnár]: | ||
<pre>i cannot over-emphasise how much of a deal it is in practice. Atime | <pre>i cannot over-emphasise how much of a deal it is in practice. Atime | ||
updates are by far the biggest IO performance deficiency that Linux has | updates are by far the biggest IO performance deficiency that Linux has | ||
Line 66: | Line 109: | ||
==Workload Distribution== | ==Workload Distribution== | ||
* The <tt>/sys/devices/system/cpu/sched_smt_power_savings</tt> tunable causes tasks (under light load) to be preferentially distributed across processing elements (ie including [[SMT | * The <tt>/sys/devices/system/cpu/sched_smt_power_savings</tt> tunable causes tasks (under light load) to be preferentially distributed across processing elements (ie including [[SMP on x86|SMT]] units) and cores of physical packages (as opposed to packages themselves). | ||
* The <tt>/sys/devices/system/cpu/sched_mc_power_savings</tt> tunable does the same, but doesn't apply to SMT. | * The <tt>/sys/devices/system/cpu/sched_mc_power_savings</tt> tunable does the same, but doesn't apply to SMT. | ||
* Task migration has overhead and associated [[architecture]] warmup (ie, caches, branch prediction and hardware prefetching). How is this affected? '''FIXME''' | * Task migration has overhead and associated [[architecture]] warmup (ie, caches, branch prediction and hardware prefetching). How is this affected? '''FIXME''' | ||
==Networking== | |||
===Wired=== | |||
* Disable Wake-on-LAN if it's not being used: <tt>ethtool -s DEVICE wol d</tt> | |||
===Wireless=== | |||
* PS-Poll (PowerSave Poll) turns the radio off longer in exchange for higher latencies (only when it's disabled, though) | |||
** Requires support from access point | |||
* Auto-association / aggressive scanning, especially when wireless is not being used | |||
* MAC80211_DEFAULT_PS, introduced in the 2.6.32 development cycle, sets wireless powersaving by default | |||
** Use latency requirement registration (Documentation/power/pm_qos_interface.txt) for applications which need it | |||
==See Also== | ==See Also== | ||
Line 75: | Line 129: | ||
* [http://www.linux.com/articles/54610 linux.com article on hibernate and suspend] | * [http://www.linux.com/articles/54610 linux.com article on hibernate and suspend] | ||
* lesswatts.org article on [http://www.lesswatts.org/tips/cpu.php power-aware scheduling] for multicores | * lesswatts.org article on [http://www.lesswatts.org/tips/cpu.php power-aware scheduling] for multicores | ||
* lesswatts.org article on [http://www.lesswatts.org/tips/wireless.php wireless] power-saving |
Latest revision as of 16:36, 15 July 2018
Matthew Garrett's "Observations on Power Management" is a great intro.
Implementations
- APM (Advanced Power Management): All PM policy/mechanism resides within the BIOS
- Motivated by, largely relevant only to laptops
- apmd debian package
- No longer supported in Vista. Off by default in recent Debian kernels.
- ACPI: Current, often buggy (but also often easily repairable via BIOS flash or by hand)
- C-States, which are decomposable into P-States and T-States
- P4 Thermal Throttling: Slows down or shuts off the processor based on CPU temperature
- Adjustment is either via idle cycle insertion or lowering the clock multiplier
Batteries
- upower can be used to get battery details, if its daemon is running:
upower -i /org/freedesktop/UPower/devices/battery_BAT1 native-path: BAT1 vendor: SMP model: 01AV452 serial: 5642 power supply: yes updated: Sun 15 Jul 2018 12:33:08 PM EDT (104 seconds ago) has history: yes has statistics: yes battery present: yes rechargeable: yes state: discharging warning-level: none energy: 15.94 Wh energy-empty: 0 Wh energy-full: 24.54 Wh energy-full-design: 24 Wh energy-rate: 7.994 W voltage: 11.405 V time to empty: 2.0 hours percentage: 66% capacity: 100% technology: lithium-polymer icon-name: 'battery-full-symbolic' History (charge): 1531672388 66.000 discharging History (rate): 1531672388 7.994 discharging
CPU Frequency
- On Linux, cpufreq-info provides lots of good information:
[recombinator](0) $ cpufreq-info cpufrequtils 004: cpufreq-info (C) Dominik Brodowski 2004-2006 Report errors and bugs to cpufreq@lists.linux.org.uk, please. analyzing CPU 0: driver: acpi-cpufreq CPUs which need to switch frequency at the same time: 0 hardware limits: 1.60 GHz - 2.39 GHz available frequency steps: 2.39 GHz, 1.60 GHz available cpufreq governors: ondemand, performance current policy: frequency should be within 1.60 GHz and 2.39 GHz. The governor "ondemand" may decide which speed to use within this range. current CPU frequency is 1.60 GHz. cpufreq stats: 2.39 GHz:27.25%, 1.60 GHz:72.75% (78631) analyzing CPU 1: driver: acpi-cpufreq CPUs which need to switch frequency at the same time: 1 hardware limits: 1.60 GHz - 2.39 GHz available frequency steps: 2.39 GHz, 1.60 GHz available cpufreq governors: ondemand, performance current policy: frequency should be within 1.60 GHz and 2.39 GHz. The governor "ondemand" may decide which speed to use within this range. current CPU frequency is 1.60 GHz. cpufreq stats: 2.39 GHz:4.32%, 1.60 GHz:95.68% (19387) [recombinator](0) $
- You can get C-state latency information from /proc/acpi/processor/*/power:
[wopr](0) $ cat /proc/acpi/processor/CP10/power active state: C0 max_cstate: C8 maximum allowed latency: 2000000000 usec states: C1: type[C1] promotion[--] demotion[--] latency[032] usage[02035391] duration[00000000000000000000] C2: type[C2] promotion[--] demotion[--] latency[064] usage[01050475] duration[00000000000624232458] C3: type[C2] promotion[--] demotion[--] latency[096] usage[150501625] duration[00000020175094863449] [wopr](0) $
- On FreeBSD, sysctls from the dev.cpu and debug.cpufreq MIB hierarchies are your window into frequency control. See cpufreq(4).
Disks/Filesystems
- noatime -- critical for all kinds of things! don't believe me; trust ingo molnár:
i cannot over-emphasise how much of a deal it is in practice. Atime updates are by far the biggest IO performance deficiency that Linux has today. Getting rid of atime updates would give us more everyday Linux performance than all the pagecache speedups of the past 10 years, _combined_. it's also perhaps the most stupid Unix design idea of all times. Unix is really nice and well done, but think about this a bit: ' For every file that is read from the disk, lets do a ... write to the disk! And, for every file that is already cached and which we read from the cache ... do a write to the disk! ' tell that concept to any rookie programmer who knows nothing about kernels and the answer will be: 'huh, what? That's gross!'. And Linux does this unconditionally for everything, and no, it's not only done on some high-security servers that need all sorts of auditing enabled that logs every file read - no, it's done by 99% of the Linux desktops and servers. For the sake of some lazy mailers that could now be using inotify, and for the sake of ... nothing much, really - forensics software perhaps.
- SATA link state management? what is this? seen in powertop output
- turning up the writeback time / disk head parking / other debatable techniques
Workload Distribution
- The /sys/devices/system/cpu/sched_smt_power_savings tunable causes tasks (under light load) to be preferentially distributed across processing elements (ie including SMT units) and cores of physical packages (as opposed to packages themselves).
- The /sys/devices/system/cpu/sched_mc_power_savings tunable does the same, but doesn't apply to SMT.
- Task migration has overhead and associated architecture warmup (ie, caches, branch prediction and hardware prefetching). How is this affected? FIXME
Networking
Wired
- Disable Wake-on-LAN if it's not being used: ethtool -s DEVICE wol d
Wireless
- PS-Poll (PowerSave Poll) turns the radio off longer in exchange for higher latencies (only when it's disabled, though)
- Requires support from access point
- Auto-association / aggressive scanning, especially when wireless is not being used
- MAC80211_DEFAULT_PS, introduced in the 2.6.32 development cycle, sets wireless powersaving by default
- Use latency requirement registration (Documentation/power/pm_qos_interface.txt) for applications which need it
See Also
- P4 Thermal Throttling at Van's Hardware Journal
- P4 Thermal Throttling at Hardware Secrets
- linux.com article on hibernate and suspend
- lesswatts.org article on power-aware scheduling for multicores
- lesswatts.org article on wireless power-saving