Lines Matching defs:pools

20  * automatically managed.  There are two worker pools for each CPU (one for
22  * pools for workqueues which are not bound to any specific CPU - the
23  * number of these backing pools is dynamic.
107 	NR_STD_WORKER_POOLS	= 2,		/* # standard pools per cpu */
235 	int			refcnt;		/* PL: refcnt for unbound pools */
458 static DEFINE_MUTEX(wq_pool_mutex);	/* protects pools and workqueues list */
497 /* to raise softirq for the BH worker pools on other CPUs */
500 /* the BH worker pools */
503 /* the per-cpu worker pools */
506 static DEFINE_IDR(worker_pool_idr);	/* PR: idr of all pools */
508 /* PL: hash of all unbound pools keyed by pool->attrs */
511 /* I: attributes used when instantiating standard unbound pools on demand */
514 /* I: attributes used when instantiating ordered pools on demand */
938  * pools are managed.  Unless noted otherwise, these functions assume that
947  * function will always return %true for unbound pools as long as the
1693 		 * As both pwqs and pools are RCU protected, the
1997 	 * multiple pwqs and pools may be sharing the nr_active count. When a
2345 	 * pwq is determined and locked. For unbound pools, we could have raced
3255 	 * Kick @pool if necessary. It's always noop for per-cpu worker pools
3967 	 * For unbound workqueue, pwqs will map to only a few pools.
5035  * and this function should be able to release pools which went through,
5604 		struct worker_pool __percpu *pools;
5607 			pools = bh_worker_pools;
5609 			pools = cpu_worker_pools;
5615 			pool = &(per_cpu_ptr(pools, cpu)[highpri]);
6575  * Called from a sysrq handler and prints out all busy workqueues and pools.
6585 	pr_info("Showing busy workqueues and worker pools:\n");
6665  * worker pools serve mix of short, long and very long running works making
6668  * This is solved by allowing the pools to be disassociated from the CPU
6829 		/* BH pools aren't affected by hotplug */
7639  * Workqueue watchdog monitors all worker pools periodically and dumps
7640  * state if some pools failed to make forward progress for a while where
7698 	pr_info("Showing backtraces of busy workers in stalled worker pools:\n");
7991 	/* initialize BH and CPU pools */
8095  * executing the work items yet. Populate the worker pools with the initial
8109 	 * Per-cpu pools created earlier could be missing node hint. Fix them