Arch Linux User Repository

Again, a major benefit of using the BFS is increased responsiveness. The benefits however, are not limited to desktop feel. I put together some non-responsiveness based benchmarks to compare it to the CFS contained in the "stock" linux kernel. Recognize however, that it was not implicitly designed to provide superior performance. The purpose of the benchmarks was to evaluate the CPU scheduler in the stock Linux kernel against the BFS in the corresponding kernel patched with the ck1 patchset on different machines to see if differences exist and to what degree they scale using performance based metrics even though these end points were never within the scope of primary design goals of the BFS. http://repo-ck.com/bench/benchmark.pdf For those not wanting to see the data and just wanting the highlights: *7 different machines ranging from 1 to 16 cores were benchmark using both a make and a x264-based video benchmark. *Each machine ran both the "standard" linux kernel (linux-3.0.1-2 from [core]) and the ck1-patched version of this kernel (linux-ck-3.0.6-2 from the unofficial repo). *All 7 machines preformed better using the linux-ck package on the make benchmark. *x264 encoding results were mixed. 4 machines performed better on the BFS scheduler; 1 gave same results; and 3 performed worse. It should be noted that an experimental version (svn) of handbrake was used for these tests.

Well, it looks like the pf-kernel has incorporated the patch Andrea and I proposed without hearing back from ck. I will go ahead and release 3.0.7-1 in a few minutes with the very same patch to kernel/posix-cpu-timers.c for those who wanna build now. I'm hoping ck will reply to the blog post I made asking about this patch soon as well.

Thanks for your work and your time graysky ;)

OK. -3 includes bfs v0.413 but just sit tight because 3.0.7 was released yesterday. Problem is that the ck1 patchset doesn't apply to it. I emailed ck.

Update - CK needs to port bfs v0.413 to work with the ck1 patchset. When this happens, I can update the PKGBUILD with it. Unflagging out-of-date.

THanks... error in my build script. Fixed the pkg now: pacman -Syy && pacman -Syu - you will probably get an error about not matching checksums so answer "y" to deleting the invalid package and run again. I will bump to -2 and rebuild later today. NOTE TO ALL -- the above error only affects certain nvidia-ck-xxx packages in the repo.

Hey! Just wanna let you know, the new nvidia-ck-core2 in the repo depends upon linux-ck and not linux-ck-core2. Please fix?

@Det - two lines actually here - http://mailman.archlinux.org/pipermail/arch-dev-public/2011-October/021716.html

No, there's no redundancy or regressions. That's not the point here at all. The governor _should_ be "performance" with the [core] kernel because the iso needs it. Also what the update log says is this: "fix archiso support and change back governor to performance as default". Just one line.