Adding linaro-kernel to get others involved in it.
On 17 July 2013 05:58, 이가람 wind351@gmail.com wrote:
Hello. My name is Karam Lee in Korea.
I am obviously interested in your "Queue work on power efficient wq" patch.
This is an interesting field for me, and I think the idea is good.
So I want to try to test the patch, Can you explain to me how you did it in detail?
What tool did you use to draw the results?
If you give me an answer, I will appreciate your kindness.
I copied below from my cover-letter only, where numbers are given. We used ARM Versatile express with TC2 for our tests which had a on board hwmon to get us energy numbers for A7 and A15 clusters.
Test was simple, just run some audio in background and monitor power numbers for that time.
I used to run mytrace.sh (attached), which also takes some trace for me, which I used to analyse with kernelshark then to see how wakeups are happening on my board.
-------x--------------x--------------
Setup: ----- - ARM Vexpress TC2 - big.LITTLE CPU - Core 0-1: A15, 2-4: A7 - rootfs: linaro-ubuntu-devel
This patchset has been tested on a big LITTLE system (heterogeneous) but is useful for all other homogeneous systems as well. During these tests audio was played in background using aplay.
Results: -------
Cluster A15 Energy Cluster A7 Energy Total ------------------------- ----------------------- ------
Without this patchset (Energy in Joules): ---------------------------------------------------
0.151162 2.183545 2.334707 0.223730 2.687067 2.910797 0.289687 2.732702 3.022389 0.454198 2.745908 3.200106 0.495552 2.746465 3.242017
Average: 0.322866 2.619137 2.942003
With this patchset (Energy in Joules): -----------------------------------------------
0.226421 2.283658 2.510079 0.151361 2.236656 2.388017 0.197726 2.249849 2.447575 0.221915 2.229446 2.451361 0.347098 2.257707 2.604805
Average: 0.2289042 2.2514632 2.4803674
Above tests are repeated multiple times and events are tracked using trace-cmd and analysed using kernelshark. And it was easily noticeable that idle time for many cpus has increased considerably, which eventually saved some power.