Mike,

Could you try this patch to see if it solves the latency problem?

  tong

Changes:

1. Modified vruntime adjustment logic in set_task_cpu(). See comments in code. This fixed the negative vruntime problem.

2. This code in update_curr() seems to be wrong:

if (unlikely(!curr))
        return sync_vruntime(cfs_rq);

cfs_rq->curr can be NULL even if cfs_rq->nr_running is non-zero (e.g., when an RT task is running). We only want to call sync_vruntime when cfs_rq->nr_running is 0. This fixed the large latency problem (at least in my tests).

Signed-off-by: Tong Li <[EMAIL PROTECTED]>
---
diff -uprN linux-2.6-sched-devel-orig/kernel/sched.c 
linux-2.6-sched-devel/kernel/sched.c
--- linux-2.6-sched-devel-orig/kernel/sched.c   2007-09-20 12:15:41.000000000 
-0700
+++ linux-2.6-sched-devel/kernel/sched.c        2007-09-21 19:40:08.000000000 
-0700
@@ -1033,9 +1033,20 @@ void set_task_cpu(struct task_struct *p,
        if (p->se.block_start)
                p->se.block_start -= clock_offset;
 #endif
-       if (likely(new_rq->cfs.min_vruntime))
-               p->se.vruntime -= old_rq->cfs.min_vruntime -
-                                               new_rq->cfs.min_vruntime;
+ /* + * Reset p's vruntime if it moves to new_cpu whose min_vruntime is + * 100,000,000 (equivalent to 100ms for nice-0 tasks) larger or
+        * smaller than p's vruntime. This improves interactivity when
+        * pinned and unpinned tasks co-exist. For example, pinning a few
+        * tasks to a CPU can cause its min_vruntime much smaller than the
+        * other CPUs. If a task moves to this CPU, its vruntime can be so
+        * large it won't be scheduled until the locally pinned tasks'
+        * vruntimes catch up, causing large delays.
+        */
+ if (unlikely(old_cpu != new_cpu && p->se.vruntime && + (p->se.vruntime > new_rq->cfs.min_vruntime + 100000000 || + p->se.vruntime + 100000000 < new_rq->cfs.min_vruntime)))
+               p->se.vruntime = new_rq->cfs.min_vruntime;

        __set_task_cpu(p, new_cpu);
 }
@@ -1599,6 +1610,7 @@ static void __sched_fork(struct task_str
        p->se.exec_start             = 0;
        p->se.sum_exec_runtime               = 0;
        p->se.prev_sum_exec_runtime  = 0;
+       p->se.vruntime                       = 0;

 #ifdef CONFIG_SCHEDSTATS
        p->se.wait_start             = 0;
diff -uprN linux-2.6-sched-devel-orig/kernel/sched_fair.c 
linux-2.6-sched-devel/kernel/sched_fair.c
--- linux-2.6-sched-devel-orig/kernel/sched_fair.c      2007-09-20 
12:15:41.000000000 -0700
+++ linux-2.6-sched-devel/kernel/sched_fair.c   2007-09-21 17:23:09.000000000 
-0700
@@ -306,8 +306,10 @@ static void update_curr(struct cfs_rq *c
        u64 now = rq_of(cfs_rq)->clock;
        unsigned long delta_exec;

-       if (unlikely(!curr))
+       if (unlikely(!cfs_rq->nr_running))
                return sync_vruntime(cfs_rq);
+       if (unlikely(!curr))
+               return;

        /*
         * Get the amount of time the current task was running
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to