Message-ID: <1473259610-3295-9-git-send-email-axboe@fb.com>
Date:   Wed, 7 Sep 2016 08:46:50 -0600
From:   Jens Axboe <axboe@...com>
To:     <axboe@...nel.dk>, <linux-kernel@...r.kernel.org>,
        <linux-fsdevel@...r.kernel.org>, <linux-block@...r.kernel.org>
CC:     Jens Axboe <axboe@...com>
Subject: [PATCH 8/8] writeback: throttle buffered writeback

Test patch that throttles 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 two sysfs entries. The first one, 'wb_window_usec',
defines the window of monitoring. The second one, 'wb_lat_usec',
sets the latency target for the window. 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 these settings.

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: Jens Axboe <axboe@...com>
---
 Documentation/block/queue-sysfs.txt |  13 ++++
 block/Kconfig                       |   1 +
 block/blk-core.c                    |  20 +++++-
 block/blk-mq.c                      |  30 ++++++++-
 block/blk-settings.c                |   3 +
 block/blk-stat.c                    |   5 +-
 block/blk-sysfs.c                   | 125 ++++++++++++++++++++++++++++++++++++
 block/cfq-iosched.c                 |  12 ++++
 include/linux/blkdev.h              |   6 +-
 9 files changed, 206 insertions(+), 9 deletions(-)

diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index 2a3904030dea..2847219ebd8c 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -169,5 +169,18 @@ 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.
+
+wb_window_usec (RW)
+-------------------
+If the device is registered for writeback throttling, then this file shows
+the value of the monitoring window in which we'll look at the target
+latency. See wb_lat_usec.
+
 
 Jens Axboe <jens.axboe@...cle.com>, February 2009
diff --git a/block/Kconfig b/block/Kconfig
index 161491d0a879..6da79e670709 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -4,6 +4,7 @@
 menuconfig BLOCK
        bool "Enable the block layer" if EXPERT
        default y
+       select WBT
        help
 	 Provide block layer support for the kernel.
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 4075cbeb720e..4f4ce050290c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -33,6 +33,7 @@
 #include <linux/ratelimit.h>
 #include <linux/pm_runtime.h>
 #include <linux/blk-cgroup.h>
+#include <linux/wbt.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
@@ -882,6 +883,8 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 
 fail:
 	blk_free_flush_queue(q->fq);
+	wbt_exit(q->rq_wb);
+	q->rq_wb = NULL;
 	return NULL;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -1346,6 +1349,7 @@ 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->wb_stat);
 
 	if (rq->cmd_flags & REQ_QUEUED)
 		blk_queue_end_tag(q, rq);
@@ -1436,6 +1440,8 @@ 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->wb_stat);
+
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
 	 * it didn't come out of our reserved rq pools
@@ -1667,6 +1673,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	int el_ret, rw_flags = 0, 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
@@ -1719,6 +1726,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	}
 
 get_rq:
+	wb_acct = wbt_wait(q->rq_wb, bio->bi_opf, q->queue_lock);
+
 	/*
 	 * This sync check and mask will be re-done in init_request_from_bio(),
 	 * but we need to set it earlier to expose the sync flag to the
@@ -1738,11 +1747,15 @@ get_rq:
 	 */
 	req = get_request(q, bio_data_dir(bio), rw_flags, bio, GFP_NOIO);
 	if (IS_ERR(req)) {
+		if (wb_acct & WBT_TRACKED)
+			__wbt_done(q->rq_wb);
 		bio->bi_error = PTR_ERR(req);
 		bio_endio(bio);
 		goto out_unlock;
 	}
 
+	wbt_track(&req->wb_stat, wb_acct);
+
 	/*
 	 * After dropping the lock and possibly sleeping here, our request
 	 * may now be mergeable after it had proven unmergeable (above).
@@ -2475,7 +2488,7 @@ void blk_start_request(struct request *req)
 {
 	blk_dequeue_request(req);
 
-	req->issue_time = ktime_to_ns(ktime_get());
+	wbt_issue(req->q->rq_wb, &req->wb_stat);
 
 	/*
 	 * We are now handing the request to the hardware, initialize
@@ -2713,9 +2726,10 @@ 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->wb_stat);
 		req->end_io(req, error);
-	else {
+	} else {
 		if (blk_bidi_rq(req))
 			__blk_put_request(req->next_rq->q, req->next_rq);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 712f141a6f1a..511289a4626a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -22,6 +22,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/delay.h>
 #include <linux/crash_dump.h>
+#include <linux/wbt.h>
 
 #include <trace/events/block.h>
 
@@ -319,6 +320,8 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 
 	if (rq->cmd_flags & REQ_MQ_INFLIGHT)
 		atomic_dec(&hctx->nr_active);
+
+	wbt_done(q->rq_wb, &rq->wb_stat);
 	rq->cmd_flags = 0;
 
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
@@ -351,6 +354,7 @@ 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->wb_stat);
 		rq->end_io(rq, error);
 	} else {
 		if (unlikely(blk_bidi_rq(rq)))
@@ -457,7 +461,7 @@ void blk_mq_start_request(struct request *rq)
 	if (unlikely(blk_bidi_rq(rq)))
 		rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);
 
-	rq->issue_time = ktime_to_ns(ktime_get());
+	wbt_issue(q->rq_wb, &rq->wb_stat);
 
 	blk_add_timer(rq);
 
@@ -494,6 +498,7 @@ 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->wb_stat);
 
 	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
 		if (q->dma_drain_size && blk_rq_bytes(rq))
@@ -1312,6 +1317,7 @@ 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);
 
@@ -1326,9 +1332,16 @@ 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->bi_opf, NULL);
+
 	rq = blk_mq_map_request(q, bio, &data);
-	if (unlikely(!rq))
+	if (unlikely(!rq)) {
+		if (wb_acct & WBT_TRACKED)
+			__wbt_done(q->rq_wb);
 		return BLK_QC_T_NONE;
+	}
+
+	wbt_track(&rq->wb_stat, wb_acct);
 
 	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
 
@@ -1405,6 +1418,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	struct blk_map_ctx data;
 	struct request *rq;
 	blk_qc_t cookie;
+	unsigned int wb_acct;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1421,9 +1435,16 @@ 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->bi_opf, NULL);
+
 	rq = blk_mq_map_request(q, bio, &data);
-	if (unlikely(!rq))
+	if (unlikely(!rq)) {
+		if (wb_acct & WBT_TRACKED)
+			__wbt_done(q->rq_wb);
 		return BLK_QC_T_NONE;
+	}
+
+	wbt_track(&rq->wb_stat, wb_acct);
 
 	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
 
@@ -2147,6 +2168,9 @@ void blk_mq_free_queue(struct request_queue *q)
 	list_del_init(&q->all_q_node);
 	mutex_unlock(&all_q_mutex);
 
+	wbt_exit(q->rq_wb);
+	q->rq_wb = NULL;
+
 	blk_mq_del_queue_tag_set(q);
 
 	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index f7e122e717e8..746dc9fee1ac 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -840,6 +840,7 @@ 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);
 
@@ -863,6 +864,8 @@ 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);
 
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 3965e8a258c8..bdb16d84b914 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -178,15 +178,16 @@ bool blk_stat_is_current(struct blk_rq_stat *stat)
 void blk_stat_add(struct blk_rq_stat *stat, struct request *rq)
 {
 	s64 now, value;
+	u64 rq_time = wbt_issue_stat_get_time(&rq->wb_stat);
 
 	now = ktime_to_ns(ktime_get());
-	if (now < rq->issue_time)
+	if (now < rq_time)
 		return;
 
 	if (!__blk_stat_is_current(stat, now))
 		__blk_stat_init(stat, now);
 
-	value = now - rq->issue_time;
+	value = now - rq_time;
 	if (value > stat->max)
 		stat->max = value;
 	if (value < stat->min)
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 0b9e435fec97..85c3dc22307b 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -10,6 +10,7 @@
 #include <linux/blktrace_api.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-cgroup.h>
+#include <linux/wbt.h>
 
 #include "blk.h"
 #include "blk-mq.h"
@@ -41,6 +42,19 @@ queue_var_store(unsigned long *var, const char *page, size_t count)
 	return count;
 }
 
+static ssize_t queue_var_store64(u64 *var, const char *page)
+{
+	int err;
+	u64 v;
+
+	err = kstrtou64(page, 10, &v);
+	if (err < 0)
+		return err;
+
+	*var = v;
+	return 0;
+}
+
 static ssize_t queue_requests_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(q->nr_requests, (page));
@@ -347,6 +361,58 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 	return ret;
 }
 
+static ssize_t queue_wb_win_show(struct request_queue *q, char *page)
+{
+	if (!q->rq_wb)
+		return -EINVAL;
+
+	return sprintf(page, "%llu\n", div_u64(q->rq_wb->win_nsec, 1000));
+}
+
+static ssize_t queue_wb_win_store(struct request_queue *q, const char *page,
+				  size_t count)
+{
+	ssize_t ret;
+	u64 val;
+
+	if (!q->rq_wb)
+		return -EINVAL;
+
+	ret = queue_var_store64(&val, page);
+	if (ret < 0)
+		return ret;
+
+	q->rq_wb->win_nsec = val * 1000ULL;
+	wbt_update_limits(q->rq_wb);
+	return count;
+}
+
+static ssize_t queue_wb_lat_show(struct request_queue *q, char *page)
+{
+	if (!q->rq_wb)
+		return -EINVAL;
+
+	return sprintf(page, "%llu\n", div_u64(q->rq_wb->min_lat_nsec, 1000));
+}
+
+static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
+				  size_t count)
+{
+	ssize_t ret;
+	u64 val;
+
+	if (!q->rq_wb)
+		return -EINVAL;
+
+	ret = queue_var_store64(&val, page);
+	if (ret < 0)
+		return ret;
+
+	q->rq_wb->min_lat_nsec = val * 1000ULL;
+	wbt_update_limits(q->rq_wb);
+	return count;
+}
+
 static ssize_t queue_wc_show(struct request_queue *q, char *page)
 {
 	if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
@@ -551,6 +617,18 @@ static struct queue_sysfs_entry queue_stats_entry = {
 	.show = queue_stats_show,
 };
 
+static struct queue_sysfs_entry queue_wb_lat_entry = {
+	.attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_wb_lat_show,
+	.store = queue_wb_lat_store,
+};
+
+static struct queue_sysfs_entry queue_wb_win_entry = {
+	.attr = {.name = "wbt_window_usec", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_wb_win_show,
+	.store = queue_wb_win_store,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -579,6 +657,8 @@ static struct attribute *default_attrs[] = {
 	&queue_wc_entry.attr,
 	&queue_dax_entry.attr,
 	&queue_stats_entry.attr,
+	&queue_wb_lat_entry.attr,
+	&queue_wb_win_entry.attr,
 	NULL,
 };
 
@@ -693,6 +773,49 @@ struct kobj_type blk_queue_ktype = {
 	.release	= blk_release_queue,
 };
 
+static void blk_wb_stat_get(void *data, struct blk_rq_stat *stat)
+{
+	blk_queue_stat_get(data, stat);
+}
+
+static void blk_wb_stat_clear(void *data)
+{
+	blk_stat_clear(data);
+}
+
+static bool blk_wb_stat_is_current(struct blk_rq_stat *stat)
+{
+	return blk_stat_is_current(stat);
+}
+
+static struct wb_stat_ops wb_stat_ops = {
+	.get		= blk_wb_stat_get,
+	.is_current	= blk_wb_stat_is_current,
+	.clear		= blk_wb_stat_clear,
+};
+
+static void blk_wb_init(struct request_queue *q)
+{
+	struct rq_wb *rwb;
+
+	rwb = wbt_init(&q->backing_dev_info, &wb_stat_ops, q);
+
+	/*
+	 * If this fails, we don't get throttling
+	 */
+	if (IS_ERR(rwb))
+		return;
+
+	if (blk_queue_nonrot(q))
+		rwb->min_lat_nsec = 2000000ULL;
+	else
+		rwb->min_lat_nsec = 75000000ULL;
+
+	wbt_set_queue_depth(rwb, blk_queue_depth(q));
+	wbt_set_write_cache(rwb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
+	q->rq_wb = rwb;
+}
+
 int blk_register_queue(struct gendisk *disk)
 {
 	int ret;
@@ -732,6 +855,8 @@ int blk_register_queue(struct gendisk *disk)
 	if (q->mq_ops)
 		blk_mq_register_disk(disk);
 
+	blk_wb_init(q);
+
 	if (!q->request_fn)
 		return 0;
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index cc2f6dbd4303..ef61bda76317 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3777,6 +3777,18 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 		return;
 
 	/*
+	 * If we have a non-root cgroup, we can depend on that to
+	 * do proper throttling of writes. Turn off wbt for that
+	 * case.
+	 */
+	if (bio_blkcg(bio) != &blkcg_root) {
+		struct request_queue *q = cfqd->queue;
+
+		if (q->rq_wb)
+			wbt_disable(q->rq_wb);
+	}
+
+	/*
 	 * Drop reference to queues.  New queues will be assigned in new
 	 * group upon arrival of fresh requests.
 	 */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 259eba88f991..45256d75c4b7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,7 @@
 #include <linux/rcupdate.h>
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
+#include <linux/wbt.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -37,6 +38,7 @@ struct bsg_job;
 struct blkcg_gq;
 struct blk_flush_queue;
 struct pr_ops;
+struct rq_wb;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
@@ -151,7 +153,7 @@ struct request {
 	struct gendisk *rq_disk;
 	struct hd_struct *part;
 	unsigned long start_time;
-	s64 issue_time;
+	struct wb_issue_stat wb_stat;
 #ifdef CONFIG_BLK_CGROUP
 	struct request_list *rl;		/* rl this rq is alloced from */
 	unsigned long long start_time_ns;
@@ -303,6 +305,8 @@ struct request_queue {
 	int			nr_rqs[2];	/* # allocated [a]sync rqs */
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
+	struct rq_wb		*rq_wb;
+
 	/*
 	 * If blkcg is not used, @q->root_rl serves all requests.  If blkcg
 	 * is used, root blkg allocates from @q->root_rl and all other
-- 
2.7.4

Powered by blists - more mailing lists