Commit 87760e5e authored by Jens Axboe's avatar Jens Axboe
Browse files

block: hook up writeback throttling 



Enable throttling of buffered writeback to make it a lot
more smooth, and has way less impact on other system activity.
Background writeback should be, by definition, background
activity. The fact that we flush huge bundles of it at the time
means that it potentially has heavy impacts on foreground workloads,
which isn't ideal. We can't easily limit the sizes of writes that
we do, since that would impact file system layout in the presence
of delayed allocation. So just throttle back buffered writeback,
unless someone is waiting for it.

The algorithm for when to throttle takes its inspiration in the
CoDel networking scheduling algorithm. Like CoDel, blk-wb monitors
the minimum latencies of requests over a window of time. In that
window of time, if the minimum latency of any request exceeds a
given target, then a scale count is incremented and the queue depth
is shrunk. The next monitoring window is shrunk accordingly. Unlike
CoDel, if we hit a window that exhibits good behavior, then we
simply increment the scale count and re-calculate the limits for that
scale value. This prevents us from oscillating between a
close-to-ideal value and max all the time, instead remaining in the
windows where we get good behavior.

Unlike CoDel, blk-wb allows the scale count to to negative. This
happens if we primarily have writes going on. Unlike positive
scale counts, this doesn't change the size of the monitoring window.
When the heavy writers finish, blk-bw quickly snaps back to it's
stable state of a zero scale count.

The patch registers a sysfs entry, 'wb_lat_usec'. This sets the latency
target to me met. It defaults to 2 msec for non-rotational storage, and
75 msec for rotational storage. Setting this value to '0' disables
blk-wb. Generally, a user would not have to touch this setting.

We don't enable WBT on devices that are managed with CFQ, and have
a non-root block cgroup attached. If we have a proportional share setup
on this particular disk, then the wbt throttling will interfere with
that. We don't have a strong need for wbt for that case, since we will
rely on CFQ doing that for us.

Signed-off-by: default avatarJens Axboe <axboe@fb.com>
parent e34cbd30

Documentation/block/queue-sysfs.txt

+7 −0
Original line number Diff line number Diff line
@@ -169,5 +169,12 @@ This is the number of bytes the device can write in a single write-same 
command.  A value of '0' means write-same is not supported by this

device.



wb_lat_usec (RW)

----------------

If the device is registered for writeback throttling, then this file shows

the target minimum read latency. If this latency is exceeded in a given

window of time (see wb_window_usec), then the writeback throttling will start

scaling back writes.





Jens Axboe <jens.axboe@oracle.com>, February 2009

block/Kconfig

+26 −0
Original line number Diff line number Diff line
@@ -121,6 +121,32 @@ config BLK_CMDLINE_PARSER 


	See Documentation/block/cmdline-partition.txt for more information.



config BLK_WBT

	bool "Enable support for block device writeback throttling"

	default n

	---help---

	Enabling this option enables the block layer to throttle buffered

	background writeback from the VM, making it more smooth and having

	less impact on foreground operations. The throttling is done

	dynamically on an algorithm loosely based on CoDel, factoring in

	the realtime performance of the disk.



config BLK_WBT_SQ

	bool "Single queue writeback throttling"

	default n

	depends on BLK_WBT

	---help---

	Enable writeback throttling by default on legacy single queue devices



config BLK_WBT_MQ

	bool "Multiqueue writeback throttling"

	default y

	depends on BLK_WBT

	---help---

	Enable writeback throttling by default on multiqueue devices.

	Multiqueue currently doesn't have support for IO scheduling,

	enabling this option is recommended.



menu "Partition Types"



source "block/partitions/Kconfig"

block/blk-core.c

+15 −2
Original line number Diff line number Diff line
@@ -39,6 +39,7 @@ 


#include "blk.h"

#include "blk-mq.h"

#include "blk-wbt.h"



EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);

EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
@@ -882,6 +883,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, 


fail:

	blk_free_flush_queue(q->fq);

	wbt_exit(q);

	return NULL;

}

EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -1344,6 +1346,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq) 
	blk_delete_timer(rq);

	blk_clear_rq_complete(rq);

	trace_block_rq_requeue(q, rq);

	wbt_requeue(q->rq_wb, &rq->issue_stat);



	if (rq->rq_flags & RQF_QUEUED)

		blk_queue_end_tag(q, rq);
@@ -1436,6 +1439,8 @@ void __blk_put_request(struct request_queue *q, struct request *req) 
	/* this is a bio leak */

	WARN_ON(req->bio != NULL);



	wbt_done(q->rq_wb, &req->issue_stat);



	/*

	 * Request may not have originated from ll_rw_blk. if not,

	 * it didn't come out of our reserved rq pools
@@ -1663,6 +1668,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) 
	int el_ret, where = ELEVATOR_INSERT_SORT;

	struct request *req;

	unsigned int request_count = 0;

	unsigned int wb_acct;



	/*

	 * low level driver can indicate that it wants pages above a
@@ -1715,17 +1721,22 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) 
	}



get_rq:

	wb_acct = wbt_wait(q->rq_wb, bio, q->queue_lock);



	/*

	 * Grab a free request. This is might sleep but can not fail.

	 * Returns with the queue unlocked.

	 */

	req = get_request(q, bio->bi_opf, bio, GFP_NOIO);

	if (IS_ERR(req)) {

		__wbt_done(q->rq_wb, wb_acct);

		bio->bi_error = PTR_ERR(req);

		bio_endio(bio);

		goto out_unlock;

	}



	wbt_track(&req->issue_stat, wb_acct);



	/*

	 * After dropping the lock and possibly sleeping here, our request

	 * may now be mergeable after it had proven unmergeable (above).
@@ -2467,6 +2478,7 @@ void blk_start_request(struct request *req) 
	if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {

		blk_stat_set_issue_time(&req->issue_stat);

		req->rq_flags |= RQF_STATS;

		wbt_issue(req->q->rq_wb, &req->issue_stat);

	}



	/*
@@ -2708,9 +2720,10 @@ void blk_finish_request(struct request *req, int error) 


	blk_account_io_done(req);



	if (req->end_io)

	if (req->end_io) {

		wbt_done(req->q->rq_wb, &req->issue_stat);

		req->end_io(req, error);

	else {

	} else {

		if (blk_bidi_rq(req))

			__blk_put_request(req->next_rq->q, req->next_rq);

block/blk-mq.c

+24 −2
Original line number Diff line number Diff line
@@ -31,6 +31,7 @@ 
#include "blk-mq.h"

#include "blk-mq-tag.h"

#include "blk-stat.h"

#include "blk-wbt.h"



static DEFINE_MUTEX(all_q_mutex);

static LIST_HEAD(all_q_list);
@@ -326,6 +327,8 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, 


	if (rq->rq_flags & RQF_MQ_INFLIGHT)

		atomic_dec(&hctx->nr_active);



	wbt_done(q->rq_wb, &rq->issue_stat);

	rq->rq_flags = 0;



	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
@@ -354,6 +357,7 @@ inline void __blk_mq_end_request(struct request *rq, int error) 
	blk_account_io_done(rq);



	if (rq->end_io) {

		wbt_done(rq->q->rq_wb, &rq->issue_stat);

		rq->end_io(rq, error);

	} else {

		if (unlikely(blk_bidi_rq(rq)))
@@ -471,6 +475,7 @@ void blk_mq_start_request(struct request *rq) 
	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {

		blk_stat_set_issue_time(&rq->issue_stat);

		rq->rq_flags |= RQF_STATS;

		wbt_issue(q->rq_wb, &rq->issue_stat);

	}



	blk_add_timer(rq);
@@ -508,6 +513,7 @@ static void __blk_mq_requeue_request(struct request *rq) 
	struct request_queue *q = rq->q;



	trace_block_rq_requeue(q, rq);

	wbt_requeue(q->rq_wb, &rq->issue_stat);



	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {

		if (q->dma_drain_size && blk_rq_bytes(rq))
@@ -1339,6 +1345,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) 
	struct blk_plug *plug;

	struct request *same_queue_rq = NULL;

	blk_qc_t cookie;

	unsigned int wb_acct;



	blk_queue_bounce(q, &bio);
@@ -1353,9 +1360,15 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) 
	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))

		return BLK_QC_T_NONE;



	wb_acct = wbt_wait(q->rq_wb, bio, NULL);



	rq = blk_mq_map_request(q, bio, &data);

	if (unlikely(!rq))

	if (unlikely(!rq)) {

		__wbt_done(q->rq_wb, wb_acct);

		return BLK_QC_T_NONE;

	}



	wbt_track(&rq->issue_stat, wb_acct);



	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
@@ -1439,6 +1452,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) 
	struct blk_mq_alloc_data data;

	struct request *rq;

	blk_qc_t cookie;

	unsigned int wb_acct;



	blk_queue_bounce(q, &bio);
@@ -1455,9 +1469,15 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) 
	} else

		request_count = blk_plug_queued_count(q);



	wb_acct = wbt_wait(q->rq_wb, bio, NULL);



	rq = blk_mq_map_request(q, bio, &data);

	if (unlikely(!rq))

	if (unlikely(!rq)) {

		__wbt_done(q->rq_wb, wb_acct);

		return BLK_QC_T_NONE;

	}



	wbt_track(&rq->issue_stat, wb_acct);



	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
@@ -2139,6 +2159,8 @@ void blk_mq_free_queue(struct request_queue *q) 
	list_del_init(&q->all_q_node);

	mutex_unlock(&all_q_mutex);



	wbt_exit(q);



	blk_mq_del_queue_tag_set(q);



	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);

block/blk-settings.c

+4 −0
Original line number Diff line number Diff line
@@ -13,6 +13,7 @@ 
#include <linux/gfp.h>



#include "blk.h"

#include "blk-wbt.h"



unsigned long blk_max_low_pfn;

EXPORT_SYMBOL(blk_max_low_pfn);
@@ -845,6 +846,7 @@ EXPORT_SYMBOL_GPL(blk_queue_flush_queueable); 
void blk_set_queue_depth(struct request_queue *q, unsigned int depth)

{

	q->queue_depth = depth;

	wbt_set_queue_depth(q->rq_wb, depth);

}

EXPORT_SYMBOL(blk_set_queue_depth);
@@ -868,6 +870,8 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua) 
	else

		queue_flag_clear(QUEUE_FLAG_FUA, q);

	spin_unlock_irq(q->queue_lock);



	wbt_set_write_cache(q->rq_wb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));

}

EXPORT_SYMBOL_GPL(blk_queue_write_cache);

CRA Git | Maintained and supported by SUSTech CRA and CCSE