ia64/linux-2.6.18-xen.hg

view Documentation/cpu-freq/governors.txt @ 897:329ea0ccb344

balloon: try harder to balloon up under memory pressure.

Currently if the balloon driver is unable to increase the guest's
reservation it assumes the failure was due to reaching its full
allocation, gives up on the ballooning operation and records the limit
it reached as the "hard limit". The driver will not try again until
the target is set again (even to the same value).

However it is possible that ballooning has in fact failed due to
memory pressure in the host and therefore it is desirable to keep
attempting to reach the target in case memory becomes available. The
most likely scenario is that some guests are ballooning down while
others are ballooning up and therefore there is temporary memory
pressure while things stabilise. You would not expect a well behaved
toolstack to ask a domain to balloon to more than its allocation nor
would you expect it to deliberately over-commit memory by setting
balloon targets which exceed the total host memory.

This patch drops the concept of a hard limit and causes the balloon
driver to retry increasing the reservation on a timer in the same
manner as when decreasing the reservation.

Also if we partially succeed in increasing the reservation
(i.e. receive less pages than we asked for) then we may as well keep
those pages rather than returning them to Xen.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
author Keir Fraser <keir.fraser@citrix.com>
date Fri Jun 05 14:01:20 2009 +0100 (2009-06-05)
parents 831230e53067
children
line source
1 CPU frequency and voltage scaling code in the Linux(TM) kernel
4 L i n u x C P U F r e q
6 C P U F r e q G o v e r n o r s
8 - information for users and developers -
11 Dominik Brodowski <linux@brodo.de>
12 some additions and corrections by Nico Golde <nico@ngolde.de>
16 Clock scaling allows you to change the clock speed of the CPUs on the
17 fly. This is a nice method to save battery power, because the lower
18 the clock speed, the less power the CPU consumes.
21 Contents:
22 ---------
23 1. What is a CPUFreq Governor?
25 2. Governors In the Linux Kernel
26 2.1 Performance
27 2.2 Powersave
28 2.3 Userspace
29 2.4 Ondemand
30 2.5 Conservative
32 3. The Governor Interface in the CPUfreq Core
36 1. What Is A CPUFreq Governor?
37 ==============================
39 Most cpufreq drivers (in fact, all except one, longrun) or even most
40 cpu frequency scaling algorithms only offer the CPU to be set to one
41 frequency. In order to offer dynamic frequency scaling, the cpufreq
42 core must be able to tell these drivers of a "target frequency". So
43 these specific drivers will be transformed to offer a "->target"
44 call instead of the existing "->setpolicy" call. For "longrun", all
45 stays the same, though.
47 How to decide what frequency within the CPUfreq policy should be used?
48 That's done using "cpufreq governors". Two are already in this patch
49 -- they're the already existing "powersave" and "performance" which
50 set the frequency statically to the lowest or highest frequency,
51 respectively. At least two more such governors will be ready for
52 addition in the near future, but likely many more as there are various
53 different theories and models about dynamic frequency scaling
54 around. Using such a generic interface as cpufreq offers to scaling
55 governors, these can be tested extensively, and the best one can be
56 selected for each specific use.
58 Basically, it's the following flow graph:
60 CPU can be set to switch independetly | CPU can only be set
61 within specific "limits" | to specific frequencies
63 "CPUfreq policy"
64 consists of frequency limits (policy->{min,max})
65 and CPUfreq governor to be used
66 / \
67 / \
68 / the cpufreq governor decides
69 / (dynamically or statically)
70 / what target_freq to set within
71 / the limits of policy->{min,max}
72 / \
73 / \
74 Using the ->setpolicy call, Using the ->target call,
75 the limits and the the frequency closest
76 "policy" is set. to target_freq is set.
77 It is assured that it
78 is within policy->{min,max}
81 2. Governors In the Linux Kernel
82 ================================
84 2.1 Performance
85 ---------------
87 The CPUfreq governor "performance" sets the CPU statically to the
88 highest frequency within the borders of scaling_min_freq and
89 scaling_max_freq.
92 2.2 Powersave
93 -------------
95 The CPUfreq governor "powersave" sets the CPU statically to the
96 lowest frequency within the borders of scaling_min_freq and
97 scaling_max_freq.
100 2.3 Userspace
101 -------------
103 The CPUfreq governor "userspace" allows the user, or any userspace
104 program running with UID "root", to set the CPU to a specific frequency
105 by making a sysfs file "scaling_setspeed" available in the CPU-device
106 directory.
109 2.4 Ondemand
110 ------------
112 The CPUfreq govenor "ondemand" sets the CPU depending on the
113 current usage. To do this the CPU must have the capability to
114 switch the frequency very quickly. There are a number of sysfs file
115 accessible parameters:
117 sampling_rate: measured in uS (10^-6 seconds), this is how often you
118 want the kernel to look at the CPU usage and to make decisions on
119 what to do about the frequency. Typically this is set to values of
120 around '10000' or more.
122 show_sampling_rate_(min|max): the minimum and maximum sampling rates
123 available that you may set 'sampling_rate' to.
125 up_threshold: defines what the average CPU usaged between the samplings
126 of 'sampling_rate' needs to be for the kernel to make a decision on
127 whether it should increase the frequency. For example when it is set
128 to its default value of '80' it means that between the checking
129 intervals the CPU needs to be on average more than 80% in use to then
130 decide that the CPU frequency needs to be increased.
132 sampling_down_factor: this parameter controls the rate that the CPU
133 makes a decision on when to decrease the frequency. When set to its
134 default value of '5' it means that at 1/5 the sampling_rate the kernel
135 makes a decision to lower the frequency. Five "lower rate" decisions
136 have to be made in a row before the CPU frequency is actually lower.
137 If set to '1' then the frequency decreases as quickly as it increases,
138 if set to '2' it decreases at half the rate of the increase.
140 ignore_nice_load: this parameter takes a value of '0' or '1', when set
141 to '0' (its default) then all processes are counted towards towards the
142 'cpu utilisation' value. When set to '1' then processes that are
143 run with a 'nice' value will not count (and thus be ignored) in the
144 overal usage calculation. This is useful if you are running a CPU
145 intensive calculation on your laptop that you do not care how long it
146 takes to complete as you can 'nice' it and prevent it from taking part
147 in the deciding process of whether to increase your CPU frequency.
150 2.5 Conservative
151 ----------------
153 The CPUfreq governor "conservative", much like the "ondemand"
154 governor, sets the CPU depending on the current usage. It differs in
155 behaviour in that it gracefully increases and decreases the CPU speed
156 rather than jumping to max speed the moment there is any load on the
157 CPU. This behaviour more suitable in a battery powered environment.
158 The governor is tweaked in the same manner as the "ondemand" governor
159 through sysfs with the addition of:
161 freq_step: this describes what percentage steps the cpu freq should be
162 increased and decreased smoothly by. By default the cpu frequency will
163 increase in 5% chunks of your maximum cpu frequency. You can change this
164 value to anywhere between 0 and 100 where '0' will effectively lock your
165 CPU at a speed regardless of its load whilst '100' will, in theory, make
166 it behave identically to the "ondemand" governor.
168 down_threshold: same as the 'up_threshold' found for the "ondemand"
169 governor but for the opposite direction. For example when set to its
170 default value of '20' it means that if the CPU usage needs to be below
171 20% between samples to have the frequency decreased.
173 3. The Governor Interface in the CPUfreq Core
174 =============================================
176 A new governor must register itself with the CPUfreq core using
177 "cpufreq_register_governor". The struct cpufreq_governor, which has to
178 be passed to that function, must contain the following values:
180 governor->name - A unique name for this governor
181 governor->governor - The governor callback function
182 governor->owner - .THIS_MODULE for the governor module (if
183 appropriate)
185 The governor->governor callback is called with the current (or to-be-set)
186 cpufreq_policy struct for that CPU, and an unsigned int event. The
187 following events are currently defined:
189 CPUFREQ_GOV_START: This governor shall start its duty for the CPU
190 policy->cpu
191 CPUFREQ_GOV_STOP: This governor shall end its duty for the CPU
192 policy->cpu
193 CPUFREQ_GOV_LIMITS: The limits for CPU policy->cpu have changed to
194 policy->min and policy->max.
196 If you need other "events" externally of your driver, _only_ use the
197 cpufreq_governor_l(unsigned int cpu, unsigned int event) call to the
198 CPUfreq core to ensure proper locking.
201 The CPUfreq governor may call the CPU processor driver using one of
202 these two functions:
204 int cpufreq_driver_target(struct cpufreq_policy *policy,
205 unsigned int target_freq,
206 unsigned int relation);
208 int __cpufreq_driver_target(struct cpufreq_policy *policy,
209 unsigned int target_freq,
210 unsigned int relation);
212 target_freq must be within policy->min and policy->max, of course.
213 What's the difference between these two functions? When your governor
214 still is in a direct code path of a call to governor->governor, the
215 per-CPU cpufreq lock is still held in the cpufreq core, and there's
216 no need to lock it again (in fact, this would cause a deadlock). So
217 use __cpufreq_driver_target only in these cases. In all other cases
218 (for example, when there's a "daemonized" function that wakes up
219 every second), use cpufreq_driver_target to lock the cpufreq per-CPU
220 lock before the command is passed to the cpufreq processor driver.