Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
sched/fair: Fix frequency selection for non-invariant case
Linus reported a ~50% performance regression on single-threaded workloads on his AMD Ryzen system, and bisected it to: 9c0b4bb ("sched/cpufreq: Rework schedutil governor performance estimation") When frequency invariance is not enabled, get_capacity_ref_freq(policy) is supposed to return the current frequency and the performance margin applied by map_util_perf(), enabling the utilization to go above the maximum compute capacity and to select a higher frequency than the current one. After the changes in 9c0b4bb, the performance margin was applied earlier in the path to take into account utilization clampings and we couldn't get a utilization higher than the maximum compute capacity, and the CPU remained 'stuck' at lower frequencies. To fix this, we must use a frequency above the current frequency to get a chance to select a higher OPP when the current one becomes fully used. Apply the same margin and return a frequency 25% higher than the current one in order to switch to the next OPP before we fully use the CPU at the current one. [ mingo: Clarified the changelog. ] Fixes: 9c0b4bb ("sched/cpufreq: Rework schedutil governor performance estimation") Reported-by: Linus Torvalds <[email protected]> Bisected-by: Linus Torvalds <[email protected]> Reported-by: Wyes Karny <[email protected]> Signed-off-by: Vincent Guittot <[email protected]> Signed-off-by: Ingo Molnar <[email protected]> Tested-by: Wyes Karny <[email protected]> Link: https://lore.kernel.org/r/[email protected]
- Loading branch information