From 50ddd96917e4548b3813bfb5dd6f97f052b652bd Mon Sep 17 00:00:00 2001 From: Peter Williams Date: Tue, 27 Jun 2006 02:54:36 -0700 Subject: [PATCH] [PATCH] sched: modify move_tasks() to improve load balancing outcomes Problem: The move_tasks() function is designed to move UP TO the amount of load it is asked to move and in doing this it skips over tasks looking for ones whose load weights are less than or equal to the remaining load to be moved. This is (in general) a good thing but it has the unfortunate result of breaking one of the original load balancer's good points: namely, that (within the limits imposed by the active/expired array model and the fact the expired is processed first) it moves high priority tasks before low priority ones and this means there's a good chance (see active/expired problem for why it's only a chance) that the highest priority task on the queue but not actually on the CPU will be moved to the other CPU where (as a high priority task) it may preempt the current task. Solution: Modify move_tasks() so that high priority tasks are not skipped when moving them will make them the highest priority task on their new run queue. Signed-off-by: Peter Williams Cc: Ingo Molnar Cc: "Siddha, Suresh B" Cc: "Chen, Kenneth W" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 1847a4456a..b4dab63c6d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1955,7 +1955,7 @@ static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest, { prio_array_t *array, *dst_array; struct list_head *head, *curr; - int idx, pulled = 0, pinned = 0; + int idx, pulled = 0, pinned = 0, this_min_prio; long rem_load_move; task_t *tmp; @@ -1964,6 +1964,7 @@ static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest, rem_load_move = max_load_move; pinned = 1; + this_min_prio = this_rq->curr->prio; /* * We first consider expired tasks. Those will likely not be @@ -2003,7 +2004,12 @@ skip_queue: curr = curr->prev; - if (tmp->load_weight > rem_load_move || + /* + * To help distribute high priority tasks accross CPUs we don't + * skip a task if it will be the highest priority task (i.e. smallest + * prio value) on its new queue regardless of its load weight + */ + if ((idx >= this_min_prio && tmp->load_weight > rem_load_move) || !can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) { if (curr != head) goto skip_queue; @@ -2025,6 +2031,8 @@ skip_queue: * and the prescribed amount of weighted load. */ if (pulled < max_nr_move && rem_load_move > 0) { + if (idx < this_min_prio) + this_min_prio = idx; if (curr != head) goto skip_queue; idx++; -- 2.39.5