BFS Scheduler Updated For The Linux 4.3 Kernel

[jwh7]

I agree with this request...the last benchmarks on BFS are very old (and many changes has been made on the Kernel and on the cfs scheduler).
I would like to see through scientific tests if BFS is still useful for desktop/low latency system.

The old benchmarks from 20-Oct-2012 did list the methodology, so it could be used to replicate similar updated tests. From the pdf in here:

The collective benchmark was called from a simple Bash script that ran each individual benchmark task multiple times ? at least ten ? in order to get a decent number of observations to power a statistical comparison. Test machines were booted into either the stock kernel or into a corresponding ck1 patched kernel and then challenged with three different benchmark tasks. The time to complete each task was captured to a log file and the test repeated:

1. Compilation using gcc to `make -jx bzImage` for a preconfigured linux kernel v3.6.2. (2)
2. Compression using lrzip to compress the source tree for the linux kernel v3.6.2.
3. Video compression using ffmpeg to transcode a 720p MPEG2 clip to a 360p video suitable for playback on a smartphone.

(2) In the `make -jx bzImage` statement, x=(number of physical cores + virtual cores)+ 1. I am aware that it is recommended NOT to use the +1 for kernels running the bfs but felt that in order to fairly compare both schedulers, this needed to be held constant.