Hi Dietmar,
On Thu, Dec 17, 2015 at 07:18:52PM +0000, Dietmar Eggemann wrote:
sorry for the huge delay but I was on a 4 weeks sabbatical.
On 10/11/15 09:58, Leo Yan wrote:
This patch series is a following up for EASv5 power profiling on Hikey. From profiling result, rt-app-31/38/44 are inconsistent; Finally found this issue can be fixed by these 4 patches. After applied these patch, we can get good improvement for these cases (mW):
Energy BestComb Mainline(ndm) noEAS(ndm) EAS(ndm) EAS(sched) EAS(Applied Patches) mp3 412 604.41 551.79 528.99 530.20 491.10 rt-app-6 676 864.18 846.72 792.88 840.33 759.96 rt-app-13 968 1222.47 1210.35 1673.04 1332.13 1253.99 rt-app-19 1348 1412.08 1474.86 1612.12 1421.28 1355.49 rt-app-25 1619 1718.67 1710.73 2104.41 2028.25 1584.25 rt-app-31 1878 1968.08 1965.87 2318.11 2976.59 1903.69 rt-app-38 2283 2580.23 2540.45 2576.46 2724.32 2241.29 rt-app-44 2578 3092.66 3056.92 2913.91 2669.91 2406.45 rt-app-50 2848 3492.36 3423.26 3489.14 3429.41 3290.25
Would you be able to switch to Patrick's schedtest to run the EAS test there? This would enable us to compare the results much more easy.
Sure, will do this.
I know that there is a little bit of work remaining to integrate the Hikey board into schedtest (the actual board integration and the integration of the ARM Energy Probe).
board integration has finished, but AEP integration need time to do. I will finish this in next week and share with you.
If you don't have time to do this right now, would you be able to share an instrumented Hikey board with us so we could do the integration?
I usually need finish other more prioritized tasks, and use rest time for EAS profiling on Hikey; So strongly suggest you build up Hikey environment at your side, and I will fully support for this.
For sharing board, let us use one offline email to track this.
The main point is that to be able to evaluate patches for possible EAS integration which might add SMP (and/or exotic PM configurations, like the Frequency Domain spawning two clusters) we need a common understanding what these test results actually mean in detail. I don't see another way than using the same tool for the test.
Could you please switch to EAS RFC 5.2 ? It will have the PELT rewrite so some of your fixes should be no longer necessary or already addressed.
linux-arm.org/linux-power.git energy_model_rfc_v5.2
Totally agree, before I continue more profiling EAS I will firstly switch to EAS RFC 5.2 and new profiling tool (schedtest).
Thanks, Leo Yan
This patch series is ONLY for EXPERIMENTAL purpose.
Leo Yan (4): sched/fair: EASv5: Fix CPU shared capacity issue sched/fair: EASv5: snapshot CPU's utilization sched/fair: EASv5: Add CPU's total utilization sched/fair: EASv5: update new capacity index
kernel/sched/fair.c | 88 +++++++++++++++++++++++++++++++++++++++++++--------- kernel/sched/sched.h | 1 + 2 files changed, 74 insertions(+), 15 deletions(-)
IMPORTANT NOTICE: The contents of this email and any attachments are confidential and may also be privileged. If you are not the intended recipient, please notify the sender immediately and do not disclose the contents to any other person, use it for any purpose, or store or copy the information in any medium. Thank you.