From: Xunlei Pang <pang.xunlei(a)linaro.org>
DVFS adds a latency in the execution of task because of the time to
decide to move at max freq. We need to measure this latency and check
that the governor stays in an acceptable range.
When workgen runs a json file, a log file is created for each thread.
This log file records the number of loop that has been executed and
the duration for executing these loops (per phase). We can use these
figures to evaluate to latency that is added by a cpufreq governor
and its "performance efficiency".
We use the run+sleep patten to do the measurement, for the run time per
loop, the performance governor should run the expected duration as the
CPU stays a max freq. At the opposite, the powersave governor will give
use the longest duration (as it stays at lowest OPP). Other governor will
be somewhere between the 2 previous duration as they will use several OPP
and will go back to max frequency after a defined duration which depends
on its monitoring period.
The formula:
duration of powersave gov - duration of the gov
-------------------------------------------------------- x 100%
duration of powersave gov - duration of performance gov
will give the efficiency of the governor. 100% means as efficient as
the perf governor and 0% means as efficient as the powersave governor.
This patch offers json files and shell scripts to do the measurement,
Usage: ./test.sh <cpus> <runtime> <sleeptime>
cpus: number of cpus in the CPU0's frequency domain
runtime: running time in ms per loop of the workload pattern
sleeptime: sleeping time in ms per loop of the workload patten
Example:
"./test.sh 4 100 1000" means
CPU0~CPU3 sharing frequency, "100ms run + 1000ms sleep" workload pattern.
test result on my machine:
~#./test.sh 4 100 1000
Frequency domain CPU0~CPU3, run 100ms, sleep 1000ms:
conservative efficiency: 28%
ondemand efficiency: 95%
NOTE: Make sure there are "sed", "cut", "grep", "rt-app" tools on your test
machine, and run the script under root privilege.
Signed-off-by: Xunlei Pang <pang.xunlei(a)linaro.org>
---
.../cpufreq_governor_efficiency/calibration.json | 27 ++++++++
.../cpufreq_governor_efficiency/calibration.sh | 9 +++
doc/examples/cpufreq_governor_efficiency/dvfs.json | 27 ++++++++
doc/examples/cpufreq_governor_efficiency/dvfs.sh | 38 ++++++++++++
doc/examples/cpufreq_governor_efficiency/test.sh | 71 ++++++++++++++++++++++
5 files changed, 172 insertions(+)
create mode 100644 doc/examples/cpufreq_governor_efficiency/calibration.json
create mode 100755 doc/examples/cpufreq_governor_efficiency/calibration.sh
create mode 100644 doc/examples/cpufreq_governor_efficiency/dvfs.json
create mode 100755 doc/examples/cpufreq_governor_efficiency/dvfs.sh
create mode 100755 doc/examples/cpufreq_governor_efficiency/test.sh
diff --git a/doc/examples/cpufreq_governor_efficiency/calibration.json b/doc/examples/cpufreq_governor_efficiency/calibration.json
new file mode 100644
index 0000000..4377990
--- /dev/null
+++ b/doc/examples/cpufreq_governor_efficiency/calibration.json
@@ -0,0 +1,27 @@
+{
+ "tasks" : {
+ "thread" : {
+ "instance" : 1,
+ "cpus" : [0],
+ "loop" : 1,
+ "phases" : {
+ "run" : {
+ "loop" : 1,
+ "run" : 200000,
+ },
+ "sleep" : {
+ "loop" : 1,
+ "sleep" : 200000,
+ }
+ }
+ }
+ },
+ "global" : {
+ "default_policy" : "SCHED_FIFO",
+ "calibration" : "CPU0",
+ "lock_pages" : true,
+ "ftrace" : true,
+ "logdir" : "./",
+ }
+}
+
diff --git a/doc/examples/cpufreq_governor_efficiency/calibration.sh b/doc/examples/cpufreq_governor_efficiency/calibration.sh
new file mode 100755
index 0000000..89fe5de
--- /dev/null
+++ b/doc/examples/cpufreq_governor_efficiency/calibration.sh
@@ -0,0 +1,9 @@
+# !/bin/bash
+
+echo performance > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
+
+sleep 1
+
+pLoad=`rt-app calibration.json 2>&1 |grep pLoad |sed 's/.*= \(.*\)ns.*/\1/'`
+sed 's/"calibration" : .*,/"calibration" : '$pLoad',/' -i dvfs.json
+
diff --git a/doc/examples/cpufreq_governor_efficiency/dvfs.json b/doc/examples/cpufreq_governor_efficiency/dvfs.json
new file mode 100644
index 0000000..b413156
--- /dev/null
+++ b/doc/examples/cpufreq_governor_efficiency/dvfs.json
@@ -0,0 +1,27 @@
+{
+ "tasks" : {
+ "thread" : {
+ "instance" : 1,
+ "cpus" : [0],
+ "loop" : 5,
+ "phases" : {
+ "running" : {
+ "loop" : 1,
+ "run" : 100000,
+ },
+ "sleeping" : {
+ "loop" : 1,
+ "sleep" : 1000000,
+ }
+ }
+ }
+ },
+ "global" : {
+ "default_policy" : "SCHED_OTHER",
+ "calibration" : 90,
+ "lock_pages" : true,
+ "ftrace" : true,
+ "logdir" : "./",
+ }
+}
+
diff --git a/doc/examples/cpufreq_governor_efficiency/dvfs.sh b/doc/examples/cpufreq_governor_efficiency/dvfs.sh
new file mode 100755
index 0000000..1772041
--- /dev/null
+++ b/doc/examples/cpufreq_governor_efficiency/dvfs.sh
@@ -0,0 +1,38 @@
+# !/bin/bash
+
+#echo $1 $2 $3
+
+if [ $1 ] && [ $2 ] ; then
+ for i in `seq 0 1 $[$2-1]`
+ do
+ echo $1 > /sys/devices/system/cpu/cpu$i/cpufreq/scaling_governor
+ #cat /sys/devices/system/cpu/cpu$i/cpufreq/scaling_governor
+ done
+
+ sleep 3
+fi
+
+if [ $3 ] ; then
+ sed 's/"run" : .*,/"run" : '$3',/' -i dvfs.json
+fi
+
+if [ $4 ] ; then
+ sed 's/"sleep" : .*,/"sleep" : '$4',/' -i dvfs.json
+fi
+
+#cat dvfs.json
+
+rt-app dvfs.json 2> /dev/null
+
+if [ $1 ] ; then
+ mv rt-app-thread-0.log rt-app_$1_run$3us_sleep$4us.log
+
+ declare -i sum
+ sum=0
+ for i in `cat rt-app_$1_run$3us_sleep$4us.log | sed '1~2!d' | sed '1d' |cut -d " " -f 3`;
+ do sum=sum+$i
+ done
+ sum=sum/5
+ echo $sum
+fi
+
diff --git a/doc/examples/cpufreq_governor_efficiency/test.sh b/doc/examples/cpufreq_governor_efficiency/test.sh
new file mode 100755
index 0000000..6f41a1b
--- /dev/null
+++ b/doc/examples/cpufreq_governor_efficiency/test.sh
@@ -0,0 +1,71 @@
+# !/bin/bash
+
+function set_calibration
+{
+ calibration.sh
+}
+
+function test_efficiency
+{
+ declare -i performance
+ declare -i powersave
+ declare -i conservative
+ declare -i ondemand
+ declare -i denominator
+ declare -i numerator
+
+ FILENAME="results_$RANDOM$$.txt"
+
+ dvfs.sh performance $1 $2 $3> $FILENAME
+ dvfs.sh powersave $1 $2 $3 >> $FILENAME
+ dvfs.sh conservative $1 $2 $3 >> $FILENAME
+ dvfs.sh ondemand $1 $2 $3 >> $FILENAME
+
+ performance=`cat $FILENAME |sed -n '1p'`
+ powersave=`cat $FILENAME |sed -n '2p'`
+ conservative=`cat $FILENAME |sed -n '3p'`
+ ondemand=`cat $FILENAME |sed -n '4p'`
+
+ rm -f $FILENAME
+
+ denominator=$powersave-$performance
+ numerator=($powersave-$conservative)*100
+
+ if [ $denominator -le 0 ] ; then
+ echo "Probably not input all the cpus in the same frequncy domain"
+ exit
+ fi
+
+ if [ $numerator -lt 0 ] ; then
+ numerator=0
+ fi
+
+ conservative=$numerator/$denominator
+ echo "conservative efficiency: $conservative%"
+
+ numerator=($powersave-$ondemand)*100
+ if [ $numerator -lt 0 ] ; then
+ numerator=0
+ fi
+
+ ondemand=$numerator/$denominator
+ echo -e "ondemand efficiency: $ondemand%\n"
+}
+
+if [ $# -lt 3 ]; then
+ echo "Usage: ./test.sh <cpus> <runtime> <sleeptime>"
+ echo "cpus: number of cpus in the CPU0's frequency domain"
+ echo "runtime: running time in ms per loop of the workload pattern"
+ echo "sleeptime: sleeping time in ms per loop of the workload patten"
+ echo -e "\nExample: \n\"./test.sh 4 100 1000\" means\nCPU0~CPU3 sharing frequency, \"100ms run + 1000ms sleep\" workload pattern.\n"
+ exit
+fi
+
+echo "Frequency domain CPU0~CPU$[$1-1], run $2ms, sleep $3ms:"
+
+PATH=$PATH:.
+set_calibration
+test_efficiency $1 $[$2*1000] $[$3*1000]
+
+sleep 5
+
--
1.9.1
