[PATCH] sched: relax pinned balancing (77391d71) · Commits · 戴 / test

The maximum rebalance interval allowed by the multiprocessor balancing backoff is often not large enough to handle corner cases where there are lots of tasks pinned on a CPU. Suresh reported: I see system livelock's if for example I have 7000 processes pinned onto one cpu (this is on the fastest 8-way system I have access to). After this patch, the machine is reported to go well above this number. Signed-off-by:

Nick Piggin <nickpiggin@yahoo.com.au> Acked-by:

Ingo Molnar <mingo@elte.hu> Signed-off-by:

Andrew Morton <akpm@osdl.org> Signed-off-by:

Linus Torvalds <torvalds@osdl.org>

kernel/sched.c

+9 −2

Original line number	Diff line number	Diff line
		@@ -2030,6 +2030,12 @@ static runqueue_t find_busiest_queue(struct sched_group group)
		return busiest;
		}

		/*
		* Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
		* so long as it is large enough.
		*/
		#define MAX_PINNED_INTERVAL 512

		/*
		* Check this_cpu to ensure it is balanced within domain. Attempt to move
		* tasks if there is an imbalance.
		@@ -2042,7 +2048,7 @@ static int load_balance(int this_cpu, runqueue_t *this_rq,
		struct sched_group *group;
		runqueue_t *busiest;
		unsigned long imbalance;
		int nr_moved, all_pinned;
		int nr_moved, all_pinned = 0;
		int active_balance = 0;

		spin_lock(&this_rq->lock);
		@@ -2133,7 +2139,8 @@ out_balanced:

		sd->nr_balance_failed = 0;
		/* tune up the balancing interval */
		if (sd->balance_interval < sd->max_interval)
		if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) \|\|
		(sd->balance_interval < sd->max_interval))
		sd->balance_interval *= 2;

		return 0;

Admin message