Messages in this thread Patch in this message | | | Date | Tue, 28 Feb 2006 16:05:32 +0100 | From | Martin Andersson <> | Subject | Re: [Patch] task interactivity calculation (was Strange interactivity behaviour) |
| |
>On Tue, 2006-02-28 at 11:33 +0100, Martin Andersson wrote: >>The appended patch fixes the problem mentioned in >>http://lkml.org/lkml/2006/2/27/104 >>regarding wrong truncations in the calculation of task interactivity >>when the nice value is negative. The problem causes the interactivity to >>scale nonlinearly and differ from examples in the code.
Hi Mike,
Point taken. Is it correct now?
/Martin
Signed-off-by: Martin Andersson <martin.andersson@control.lth.se>
diff -uprN linux-2.6.15.4.orig/kernel/sched.c linux-2.6.15.4/kernel/sched.c --- linux-2.6.15.4.orig/kernel/sched.c 2006-02-10 08:22:48.000000000 +0100 +++ linux-2.6.15.4/kernel/sched.c 2006-02-28 15:49:12.000000000 +0100 @@ -142,7 +142,8 @@ (v1) * (v2_max) / (v1_max)
#define DELTA(p) \ - (SCALE(TASK_NICE(p), 40, MAX_BONUS) + INTERACTIVE_DELTA) + (SCALE(TASK_NICE(p) + 20, 40, MAX_BONUS) - 20 * MAX_BONUS / 40 + \ + INTERACTIVE_DELTA)
#define TASK_INTERACTIVE(p) \ ((p)->prio <= (p)->static_prio - DELTA(p)) - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |