On Sun, Nov 28, 2010 at 7:39 PM, walt <w41...@gmail.com> wrote: > I'm confused about which of all these various mechanisms apply to single-cpu > machines. AFAICT Con's BFS (e.g.) is really a CPU scheduler and doesn't > affect > single-cpu machines very much. What about CFQ and group scheduling? > Others? > > Thanks for any clues.
Don't mix them, CFS --> upstream official CPU scheduler (also supports cgroups, that got used in the 200line patch, which is useless imo) CFQ --> upstream official I/O (disk) scheduler (afaik the only one that supports "ionice") BFS --> ck's CPU scheduler (I don't know what i/o scheduler ck's patchset uses) Anyway, the problem with the long pauses under disk usage is not related to any scheduler at all, and it is a "page cache management" problem that the linux kernel has (in all new versions). CK's patchset includes optimizations to page cache management. (Not related to any scheduler) so it is worth a try. That's it.
