Lines Matching +full:3 +full:a

34 Consider the situation where a system’s power consumption must be
70 If the kernel can also inject idle time to the system, then a
72 level C-state. The intel_powerclamp driver is conceived as such a
73 control system, where the target set point is a user-selected idle
84 of jiffies, so accumulated errors can be prevented to avoid a jittery
92 values. This effect can be better visualized using a Perf timechart.
95 for a given "duration", then relinquishes the CPU to other tasks,
100 have a dramatic impact on the effectiveness of the powerclamp driver
121 this document. The controlling CPU is elected at runtime, with a
122 policy that favors BSP, taking into account the possibility of a CPU
126 time is considered largely as a non-causal system where its behavior
130 powerclamp monitors the actual idle for a given time window and adjust
133 When used in a causal control system, such as a temperature control,
135 past samples and outputs are included in the feedback. For example, a
137 maintain a desired target temperature, based on integral and
146 also true for the ability of a system to enter package level C-states.
149 calibration is implemented. The goals for doing such a calibration
152 a) determine the effective range of idle injection ratio
157 a) steady state error compensation
168 A debugfs file is provided for the user to examine compensation
169 progress and results, such as on a Westmere system::
178 3 3 1 0
179 4 3 1 0
180 5 3 1 0
181 6 3 1 0
182 7 3 1 0
183 8 3 1 0
185 30 3 2 0
186 31 3 2 0
187 32 3 1 0
188 33 3 2 0
189 34 3 1 0
190 35 3 2 0
191 36 3 1 0
192 37 3 2 0
193 38 3 1 0
194 39 3 2 0
195 40 3 3 0
196 41 3 1 0
197 42 3 2 0
198 43 3 1 0
199 44 3 1 0
200 45 3 2 0
201 46 3 3 0
202 47 3 0 0
203 48 3 2 0
204 49 3 3 0
208 adjacent ratios have reached satisfactory level. A confidence level
210 collected during a period without extra interrupts is considered
214 idle time is injected when such a condition is detected. Currently,
215 we have a simple algorithm to double the injection ratio. A possible
217 EOI for level triggered interrupts. But it is a challenge to be
226 to other CPUs, after a CPU offline event.
239 effectiveness. The extreme case would be doing a ping -f to generated
242 normal cases, such as scp a large file, applications can be throttled
256 Tests also show a minor, but measurable, difference between the 4P/8P
264 achieve up to 40% better performance per watt. (measured by a spin
270 The powerclamp driver is registered to the generic thermal layer as a
279 cur_state will stop idle injection. Writing a value between 1 and
303 user determine the cause of slowdown, when a powerclamp driver is in action::
314 3344 root -51 0 0 0 0 D 25 0.0 0:01.60 kidle_inject/3
318 1546 root 20 0 158m 20m 6640 S 3 0.5 0:26.97 Xorg
319 2100 jacob 20 0 1223m 88m 30m S 3 2.3 0:23.68 compiz
321 Tests have shown that by using the powerclamp driver as a cooling
322 device, a PID based userspace thermal controller can manage to
324 is added. For example, a UltraBook user can compile the kernel under
331 A bit mask of CPUs to inject idle. The format of the bitmask is same as
333 comma separated 32 bit groups. Each CPU is one bit. For example for a 256
342 this parameter allows to add a max idle percent limit. The default is 50,