Hi, > -----Original Message----- > From: Morten Rasmussen <[email protected]> > Sent: Wednesday, July 4, 2018 7:18 PM > To: [email protected]; [email protected] > Cc: [email protected]; [email protected]; > [email protected]; Gaku Inami > <[email protected]>; [email protected]; Morten Rasmussen > <[email protected]> > Subject: [PATCHv4 00/12] sched/fair: Migrate 'misfit' tasks on asymmetric > capacity systems
[snip] > The patches have been tested on: > 1. Arm Juno (r0): 2+4 Cortex A57/A53 > 2. Hikey960: 4+4 Cortex A73/A53 > > Test case: > Big cpus are always kept busy. Pin a shorter running sysbench tasks to > big cpus, while creating a longer running set of unpinned sysbench > tasks. I have tested v4 patches on Renesas SoC again. It looks fine. You can add: Tested-by: Gaku Inami <[email protected]> The patches have been tested on: 3. Renesas R-Car H3 : 4+4 Cortex A57/A53 Results: Single runs with completion time of each task R-Car H3 (tip) total time: 0.9488s total time: 0.9766s total time: 1.3243s total time: 1.6740s R-Car H3 (misfit) total time: 0.9313s total time: 0.9214s total time: 0.9493s total time: 0.9606s 10 run summary (tracking longest running task for each run) R-Car H3 avg max tip 1.6744 1.6780 misfit 0.9616 1.0290 Also, I confirmed that these patches bring performance improvement to some benchmarks(UnixBench, LMbench). So they have very useful for Renesas SoC. [snip] Regards, Inami
