Power Management - revision history

Dank at 16:36, 15 July 2018

2018-07-15T16:36:35Z

@@ Line 9: / Line 9: @@
 * 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
 ==CPU Frequency==

Dank at 19:12, 5 November 2009

2009-11-05T19:12:59Z

← Older revision		Revision as of 19:12, 5 November 2009
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

Dank: /* Disks/Filesystems */

2009-09-19T10:57:45Z

Disks/Filesystems

← Older revision		Revision as of 10:57, 19 September 2009
Line 50:		Line 50:

	==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 ~~molnar~~]:		* 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

Dank: /* Wireless */

2009-07-14T04:46:34Z

Wireless

← Older revision		Revision as of 04:46, 14 July 2009
Line 88:		Line 88:
	** Requires support from access point		** Requires support from access point
	* Auto-association / aggressive scanning, especially when wireless is not being used		* 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==

Dank: /* CPU Frequency */

2009-06-27T06:08:04Z

CPU Frequency

@@ Line 37: / Line 37: @@
    cpufreq stats: 2.39 GHz:4.32%, 1.60 GHz:95.68%  (19387)
 [recombinator](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)].

Dank at 11:07, 11 June 2009

2009-06-11T11:07:11Z

@@ Line 69: / Line 69: @@
 * 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'''
 ==See Also==
@@ Line 75: / Line 84: @@
 * [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

Dank at 16:46, 21 April 2009

2009-04-21T16:46:00Z

← Older revision		Revision as of 16:46, 21 April 2009
Line 66:		Line 66:

	==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~~\|SMP~~]] units) and cores of physical packages (as opposed to packages themselves).		* 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'''

Dank: /* Disks/Filesystems */

2009-04-21T16:44:32Z

Disks/Filesystems

@@ Line 40: / Line 40: @@
 ==Disks/Filesystems==
-* noatime -- critical for all kinds of things! ''FIXME: find and add great Ingo Molnar quote''
+* noatime -- critical for all kinds of things! don't believe me; trust [http://article.gmane.org/gmane.linux.kernel/565148 ingo molnar]:
 * [[SATA]] link state management? what is this? seen in <tt>powertop</tt> output
 * turning up the writeback time / disk head parking / other debatable techniques

Dank: /* See Also */

2009-04-21T16:40:54Z

Dank at 16:40, 21 April 2009

2009-04-21T16:40:07Z

← Older revision		Revision as of 16:40, 21 April 2009
Line 1:		Line 1:
	~~==References==~~
	~~[http://www.linux.com/articles/54610 linux.com article on hibernate and suspend]~~

	==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 46:		Line 43:
	* [[SATA]] link state management? what is this? seen in <tt>powertop</tt> output		* [[SATA]] link state management? what is this? seen in <tt>powertop</tt> output
	* turning up the writeback time / disk head parking / other debatable techniques		* turning up the writeback time / disk head parking / other debatable techniques

			==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\|SMP]] 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.
			* Task migration has overhead and associated [[architecture]] warmup (ie, caches, branch prediction and hardware prefetching). How is this affected? '''FIXME'''

	==See Also==		==See Also==
	* [http://www.vanshardware.com/articles/2001/july/010723_P4_Throttling/010723_P4_Throttling.htm P4 Thermal Throttling] at Van's Hardware Journal		* [http://www.vanshardware.com/articles/2001/july/010723_P4_Throttling/010723_P4_Throttling.htm P4 Thermal Throttling] at Van's Hardware Journal
	* [http://www.hardwaresecrets.com/article/104 P4 Thermal Throttling] at Hardware Secrets		* [http://www.hardwaresecrets.com/article/104 P4 Thermal Throttling] at Hardware Secrets
			* [http://www.linux.com/articles/54610 linux.com article on hibernate and suspend]
			* [http://www.lesswatts.org/tips/cpu.php] lesswatts.org article on power-aware scheduling for multicores

← Older revision		Revision as of 16:40, 21 April 2009
Line 53:		Line 53:
	* [http://www.hardwaresecrets.com/article/104 P4 Thermal Throttling] at Hardware Secrets		* [http://www.hardwaresecrets.com/article/104 P4 Thermal Throttling] at Hardware Secrets
	* [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]
	* [http://www.lesswatts.org/tips/cpu.php~~] lesswatts.org article on~~ power-aware scheduling for multicores		* lesswatts.org article on [http://www.lesswatts.org/tips/cpu.php power-aware scheduling] for multicores