Benchmarks found: 797
-short = sched_burst_smoothness_short=1 -scale = sched_burst_penalty_scale=1024
By .dnaimThis is captured on sched-ext from main (https://github.com/sched-ext/scx/tree/d4a5a629ffc5d01768f6052b1156c9b0479d0f70) with https://github.com/sched-ext/scx/pull/456 and https://github.com/sched-ext/scx/pull/457 backported. This is while in a static scenario while not GPU limited, the system is otherwise idle.
By summedkibbles36This is captured on sched-ext from main (https://github.com/sched-ext/scx/tree/d4a5a629ffc5d01768f6052b1156c9b0479d0f70) with https://github.com/sched-ext/scx/pull/456 and https://github.com/sched-ext/scx/pull/457 backported. This is Elden Ring while in a static scenario while not GPU limited with very low GPU load (~30%)
By summedkibbles36This is captured on sched-ext from main (https://github.com/sched-ext/scx/tree/d4a5a629ffc5d01768f6052b1156c9b0479d0f70) with https://github.com/sched-ext/scx/pull/456 and https://github.com/sched-ext/scx/pull/457 backported. This is Elden Ring while in a static scenario while not GPU limited but still at a realistic load (~80%)
By summedkibbles36scx-scheds-git 1.0.1.r67.gd4a5a62-1
By .dnaimI am uploading this benchmark to understand FPS stability of different schedulers. I state that bpfland gives SUPERIOR fps stability to the point that there are no stutters at all. Remember when you set FPS limit to 40 or 30fps, so it would be stable? That's right, except bpfland gives such stable fps without any need for FPS cap. Let's see if numbers would prove me right. :D
By erikas2Background load = Kernel compilation + Discord call Same mouse motions were made in all instances
By aarrayy