Re: [PATCH] sched/fair: util_est: fix cpu_util_wake for execl

2018-11-02 Thread Patrick Bellasi
On 31-Oct 19:45, Peter Zijlstra wrote: > On Tue, Oct 30, 2018 at 04:09:47PM +, Patrick Bellasi wrote: > > > Let's fix this by ensuring to always discount the task estimated > > utilization from the CPU's estimated utilization when the task is also > > the current one. The same benchmark of the

Re: [PATCH] sched/fair: util_est: fix cpu_util_wake for execl

2018-10-31 Thread Peter Zijlstra
On Tue, Oct 30, 2018 at 04:09:47PM +, Patrick Bellasi wrote: > Let's fix this by ensuring to always discount the task estimated > utilization from the CPU's estimated utilization when the task is also > the current one. The same benchmark of the bug report, executed on a > dual socket 40 CPUs

[PATCH] sched/fair: util_est: fix cpu_util_wake for execl

2018-10-30 Thread Patrick Bellasi
A ~10% regression has been reported for UnixBench's execl throughput test: Message-ID: <20180402032000.GD3101@yexl-desktop> Message-ID: <20181024064100.ga27...@intel.com> That test is pretty simple, it does a "recursive" execve syscall on the same binary. Starting from the syscall, this seq