On Sun, 18 Jun 2006 18:26:38 +1000 Peter Williams <[EMAIL PROTECTED]> wrote:
> These patches implement CPU usage rate limits for tasks. Via /proc/pid/cpu_rate_cap. Important detail, that. People are going to want to extend this to capping a *group* of tasks, with some yet-to-be-determined means of tying those tasks together. How well suited is this code to that extension? If the task can exceed its cap without impacting any other tasks (ie: there is spare idle capacity), what happens? I trust that spare capacity gets used? (Is this termed "work conserving"?) > 5. Code size measurements: > > Vanilla kernel: > > text data bss dec hex filename > 33800 4689 296 38785 9781 sched.o > 2554 79 0 2633 a49 mutex.o > 12076 2632 0 14708 3974 base.o > > Patches applied: > > text data bss dec hex filename > 36870 4721 296 41887 a39f sched.o > 2630 79 0 2709 a95 mutex.o > 13011 2920 0 15931 3e3b base.o > > Indicating that the size cost of the patch proper is about > 3 kilobytes and the procfs costs about another 1.2 kilobytes. > hm. That seems rather a lot. I guess it's not a simple thing to do. _______________________________________________ ckrm-tech mailing list https://lists.sourceforge.net/lists/listinfo/ckrm-tech
