Commit a46c2702 authored by Ming Lei's avatar Ming Lei Committed by Jens Axboe
Browse files

blk-mq: don't schedule block kworker on isolated CPUs 



Kernel parameter of `isolcpus=` or 'nohz_full=' are used to isolate CPUs
for specific task, and it isn't expected to let block IO disturb these CPUs.
blk-mq kworker shouldn't be scheduled on isolated CPUs. Also if isolated
CPUs is run for blk-mq kworker, long block IO latency can be caused.

Kernel workqueue only respects CPU isolation for WQ_UNBOUND, for bound
WQ, the responsibility is on user because CPU is specified as WQ API
parameter, such as mod_delayed_work_on(cpu), queue_delayed_work_on(cpu)
and queue_work_on(cpu).

So not run blk-mq kworker on isolated CPUs by removing isolated CPUs
from hctx->cpumask. Meantime use queue map to check if all CPUs in this
hw queue are offline instead of hctx->cpumask, this way can avoid any
cost in fast IO code path, and is safe since hctx->cpumask are only
used in the two cases.

Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Andrew Theurer <atheurer@redhat.com>
Cc: Joe Mario <jmario@redhat.com>
Cc: Sebastian Jug <sejug@redhat.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Tejun Heo <tj@kernel.org>
Tesed-by: default avatarJoe Mario <jmario@redhat.com>
Signed-off-by: default avatarMing Lei <ming.lei@redhat.com>
Reviewed-by: default avatarEwan D. Milne <emilne@redhat.com>
Link: https://lore.kernel.org/r/20240322021244.1056223-1-ming.lei@redhat.com


Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent 7d8d3579

block/blk-mq.c

+47 −10
Original line number Diff line number Diff line
@@ -28,6 +28,7 @@ 
#include <linux/prefetch.h>

#include <linux/blk-crypto.h>

#include <linux/part_stat.h>

#include <linux/sched/isolation.h>



#include <trace/events/block.h>
@@ -2163,6 +2164,15 @@ static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx) 
	return cpu;

}



/*

 * ->next_cpu is always calculated from hctx->cpumask, so simply use

 * it for speeding up the check

 */

static bool blk_mq_hctx_empty_cpumask(struct blk_mq_hw_ctx *hctx)

{

        return hctx->next_cpu >= nr_cpu_ids;

}



/*

 * It'd be great if the workqueue API had a way to pass

 * in a mask and had some smarts for more clever placement.
@@ -2174,7 +2184,8 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) 
	bool tried = false;

	int next_cpu = hctx->next_cpu;



	if (hctx->queue->nr_hw_queues == 1)

	/* Switch to unbound if no allowable CPUs in this hctx */

	if (hctx->queue->nr_hw_queues == 1 || blk_mq_hctx_empty_cpumask(hctx))

		return WORK_CPU_UNBOUND;



	if (--hctx->next_cpu_batch <= 0) {
@@ -3483,23 +3494,38 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx) 
	return data.has_rq;

}



static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu,

		struct blk_mq_hw_ctx *hctx)

static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,

		unsigned int this_cpu)

{

	if (cpumask_first_and(hctx->cpumask, cpu_online_mask) != cpu)

		return false;

	if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids)

		return false;

	enum hctx_type type = hctx->type;

	int cpu;



	/*

	 * hctx->cpumask has to rule out isolated CPUs, but userspace still

	 * might submit IOs on these isolated CPUs, so use the queue map to

	 * check if all CPUs mapped to this hctx are offline

	 */

	for_each_online_cpu(cpu) {

		struct blk_mq_hw_ctx *h = blk_mq_map_queue_type(hctx->queue,

				type, cpu);



		if (h != hctx)

			continue;



		/* this hctx has at least one online CPU */

		if (this_cpu != cpu)

			return true;

	}



	return false;

}



static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)

{

	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,

			struct blk_mq_hw_ctx, cpuhp_online);



	if (!cpumask_test_cpu(cpu, hctx->cpumask) ||

	    !blk_mq_last_cpu_in_hctx(cpu, hctx))

	if (blk_mq_hctx_has_online_cpu(hctx, cpu))

		return 0;



	/*
@@ -3907,6 +3933,8 @@ static void blk_mq_map_swqueue(struct request_queue *q) 
	}



	queue_for_each_hw_ctx(q, hctx, i) {

		int cpu;



		/*

		 * If no software queues are mapped to this hardware queue,

		 * disable it and free the request entries.
@@ -3933,6 +3961,15 @@ static void blk_mq_map_swqueue(struct request_queue *q) 
		 */

		sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx);



		/*

		 * Rule out isolated CPUs from hctx->cpumask to avoid

		 * running block kworker on isolated CPUs

		 */

		for_each_cpu(cpu, hctx->cpumask) {

			if (cpu_is_isolated(cpu))

				cpumask_clear_cpu(cpu, hctx->cpumask);

		}



		/*

		 * Initialize batch roundrobin counts

		 */