[PATCH RFC RESEND 12/14] block, bfq: add Early Queue Merge (EQM)

paolo paolo.valente at unimore.it
Tue May 27 12:42:36 UTC 2014


From: Arianna Avanzini <avanzini.arianna at gmail.com>

A set of processes may happen to perform interleaved reads, i.e.,
read requests whose union would give rise to a sequential read pattern.
There are two typical cases: first, processes reading fixed-size chunks
of data at a fixed distance from each other; second, processes reading
variable-size chunks at variable distances. The latter case occurs for
example with QEMU, which splits the I/O generated by a guest into
multiple chunks, and lets these chunks be served by a pool of I/O
threads, iteratively assigning the next chunk of I/O to the first
available thread. CFQ denotes as 'cooperating' a set of processes that
are doing interleaved I/O, and when it detects cooperating processes,
it merges their queues to obtain a sequential I/O pattern from the union
of their I/O requests, and hence boost the throughput.

Unfortunately, in the following frequent case the mechanism
implemented in CFQ for detecting cooperating processes and merging
their queues is not responsive enough to handle also the fluctuating
I/O pattern of the second type of processes. Suppose that one process
of the second type issues a request close to the next request to serve
of another process of the same type. At that time the two processes
can be considered as cooperating. But, if the request issued by the
first process is to be merged with some other already-queued request,
then, from the moment at which this request arrives, to the moment
when CFQ controls whether the two processes are cooperating, the two
processes are likely to be already doing I/O in distant zones of the
disk surface or device memory.

CFQ uses however preemption to get a sequential read pattern out of
the read requests performed by the second type of processes too.  As a
consequence, CFQ uses two different mechanisms to achieve the same
goal: boosting the throughput with interleaved I/O.

This patch introduces Early Queue Merge (EQM), a unified mechanism to
get a sequential read pattern with both types of processes. The main
idea is to immediately check whether a newly-arrived request lets some
pair of processes become cooperating, both in the case of actual
request insertion and, to be responsive with the second type of
processes, in the case of request merge. Both types of processes are
then handled by just merging their queues.

Finally, EQM also preserves low latency, by properly restoring the
weight-raising state of a queue when it gets back to a non-merged
state.

Signed-off-by: Arianna Avanzini <avanzini.arianna at gmail.com>
Signed-off-by: Mauro Andreolini <mauro.andreolini at unimore.it>
Signed-off-by: Paolo Valente <paolo.valente at unimore.it>
---
 block/bfq-iosched.c | 658 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 block/bfq.h         |  47 +++-
 2 files changed, 688 insertions(+), 17 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 5988c70..22d4caa 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -203,6 +203,72 @@ static inline void bfq_schedule_dispatch(struct bfq_data *bfqd)
 	}
 }
 
+static struct bfq_queue *
+bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
+		     sector_t sector, struct rb_node **ret_parent,
+		     struct rb_node ***rb_link)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *bfqq = NULL;
+
+	parent = NULL;
+	p = &root->rb_node;
+	while (*p) {
+		struct rb_node **n;
+
+		parent = *p;
+		bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+
+		/*
+		 * Sort strictly based on sector. Smallest to the left,
+		 * largest to the right.
+		 */
+		if (sector > blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_right;
+		else if (sector < blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_left;
+		else
+			break;
+		p = n;
+		bfqq = NULL;
+	}
+
+	*ret_parent = parent;
+	if (rb_link)
+		*rb_link = p;
+
+	bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
+		(long long unsigned)sector,
+		bfqq != NULL ? bfqq->pid : 0);
+
+	return bfqq;
+}
+
+static void bfq_rq_pos_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *__bfqq;
+
+	if (bfqq->pos_root != NULL) {
+		rb_erase(&bfqq->pos_node, bfqq->pos_root);
+		bfqq->pos_root = NULL;
+	}
+
+	if (bfq_class_idle(bfqq))
+		return;
+	if (!bfqq->next_rq)
+		return;
+
+	bfqq->pos_root = &bfqd->rq_pos_tree;
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
+			blk_rq_pos(bfqq->next_rq), &parent, &p);
+	if (__bfqq == NULL) {
+		rb_link_node(&bfqq->pos_node, parent, p);
+		rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
+	} else
+		bfqq->pos_root = NULL;
+}
+
 /*
  * Lifted from AS - choose which of rq1 and rq2 that is best served now.
  * We choose the request that is closesr to the head right now.  Distance
@@ -380,6 +446,45 @@ static inline unsigned int bfq_wr_duration(struct bfq_data *bfqd)
 	return dur;
 }
 
+static inline void
+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+{
+	if (bic->saved_idle_window)
+		bfq_mark_bfqq_idle_window(bfqq);
+	else
+		bfq_clear_bfqq_idle_window(bfqq);
+	if (bic->wr_time_left && bfqq->bfqd->low_latency) {
+		/*
+		 * Start a weight raising period with the duration given by
+		 * the raising_time_left snapshot.
+		 */
+		if (bfq_bfqq_busy(bfqq))
+			bfqq->bfqd->wr_busy_queues++;
+		bfqq->wr_coeff = bfqq->bfqd->bfq_wr_coeff;
+		bfqq->wr_cur_max_time = bic->wr_time_left;
+		bfqq->last_wr_start_finish = jiffies;
+		bfqq->entity.ioprio_changed = 1;
+	}
+	/*
+	 * Clear wr_time_left to prevent bfq_bfqq_save_state() from
+	 * getting confused about the queue's need of a weight-raising
+	 * period.
+	 */
+	bic->wr_time_left = 0;
+}
+
+/*
+ * Must be called with the queue_lock held.
+ */
+static int bfqq_process_refs(struct bfq_queue *bfqq)
+{
+	int process_refs, io_refs;
+
+	io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
+	process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st;
+	return process_refs;
+}
+
 static void bfq_add_request(struct request *rq)
 {
 	struct bfq_queue *bfqq = RQ_BFQQ(rq);
@@ -402,6 +507,12 @@ static void bfq_add_request(struct request *rq)
 	next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
 	bfqq->next_rq = next_rq;
 
+	/*
+	 * Adjust priority tree position, if next_rq changes.
+	 */
+	if (prev != bfqq->next_rq)
+		bfq_rq_pos_tree_add(bfqd, bfqq);
+
 	if (!bfq_bfqq_busy(bfqq)) {
 		int soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
 			time_is_before_jiffies(bfqq->soft_rt_next_start);
@@ -414,11 +525,20 @@ static void bfq_add_request(struct request *rq)
 		if (!bfqd->low_latency)
 			goto add_bfqq_busy;
 
+		if (bfq_bfqq_just_split(bfqq))
+			goto set_ioprio_changed;
+
 		/*
-		 * If the queue is not being boosted and has been idle for
-		 * enough time, start a weight-raising period.
+		 * If the queue:
+		 * - is not being boosted,
+		 * - has been idle for enough time,
+		 * - is not a sync queue or is linked to a bfq_io_cq (it is
+		 *   shared "for its nature" or it is not shared and its
+		 *   requests have not been redirected to a shared queue)
+		 * start a weight-raising period.
 		 */
-		if (old_wr_coeff == 1 && (idle_for_long_time || soft_rt)) {
+		if (old_wr_coeff == 1 && (idle_for_long_time || soft_rt) &&
+		    (!bfq_bfqq_sync(bfqq) || bfqq->bic != NULL)) {
 			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
 			if (idle_for_long_time)
 				bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
@@ -496,6 +616,7 @@ static void bfq_add_request(struct request *rq)
 					bfqd->bfq_wr_rt_max_time;
 			}
 		}
+set_ioprio_changed:
 		if (old_wr_coeff != bfqq->wr_coeff)
 			entity->ioprio_changed = 1;
 add_bfqq_busy:
@@ -583,6 +704,13 @@ static void bfq_remove_request(struct request *rq)
 	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
 		if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue)
 			bfq_del_bfqq_busy(bfqd, bfqq, 1);
+		/*
+		 * Remove queue from request-position tree as it is empty.
+		 */
+		if (bfqq->pos_root != NULL) {
+			rb_erase(&bfqq->pos_node, bfqq->pos_root);
+			bfqq->pos_root = NULL;
+		}
 	}
 
 	if (rq->cmd_flags & REQ_META)
@@ -625,11 +753,14 @@ static void bfq_merged_request(struct request_queue *q, struct request *req,
 					 bfqd->last_position);
 		bfqq->next_rq = next_rq;
 		/*
-		 * If next_rq changes, update the queue's budget to fit
-		 * the new request.
+		 * If next_rq changes, update both the queue's budget to
+		 * fit the new request and the queue's position in its
+		 * rq_pos_tree.
 		 */
-		if (prev != bfqq->next_rq)
+		if (prev != bfqq->next_rq) {
 			bfq_updated_next_req(bfqd, bfqq);
+			bfq_rq_pos_tree_add(bfqd, bfqq);
+		}
 	}
 }
 
@@ -692,12 +823,339 @@ static void bfq_end_wr(struct bfq_data *bfqd)
 	spin_unlock_irq(bfqd->queue->queue_lock);
 }
 
+static inline sector_t bfq_io_struct_pos(void *io_struct, bool request)
+{
+	if (request)
+		return blk_rq_pos(io_struct);
+	else
+		return ((struct bio *)io_struct)->bi_iter.bi_sector;
+}
+
+static inline sector_t bfq_dist_from(sector_t pos1,
+				     sector_t pos2)
+{
+	if (pos1 >= pos2)
+		return pos1 - pos2;
+	else
+		return pos2 - pos1;
+}
+
+static inline int bfq_rq_close_to_sector(void *io_struct, bool request,
+					 sector_t sector)
+{
+	return bfq_dist_from(bfq_io_struct_pos(io_struct, request), sector) <=
+	       BFQQ_SEEK_THR;
+}
+
+static struct bfq_queue *bfqq_close(struct bfq_data *bfqd, sector_t sector)
+{
+	struct rb_root *root = &bfqd->rq_pos_tree;
+	struct rb_node *parent, *node;
+	struct bfq_queue *__bfqq;
+
+	if (RB_EMPTY_ROOT(root))
+		return NULL;
+
+	/*
+	 * First, if we find a request starting at the end of the last
+	 * request, choose it.
+	 */
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
+	if (__bfqq != NULL)
+		return __bfqq;
+
+	/*
+	 * If the exact sector wasn't found, the parent of the NULL leaf
+	 * will contain the closest sector (rq_pos_tree sorted by
+	 * next_request position).
+	 */
+	__bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+		return __bfqq;
+
+	if (blk_rq_pos(__bfqq->next_rq) < sector)
+		node = rb_next(&__bfqq->pos_node);
+	else
+		node = rb_prev(&__bfqq->pos_node);
+	if (node == NULL)
+		return NULL;
+
+	__bfqq = rb_entry(node, struct bfq_queue, pos_node);
+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+		return __bfqq;
+
+	return NULL;
+}
+
+/*
+ * bfqd - obvious
+ * cur_bfqq - passed in so that we don't decide that the current queue
+ *            is closely cooperating with itself
+ * sector - used as a reference point to search for a close queue
+ */
+static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd,
+					      struct bfq_queue *cur_bfqq,
+					      sector_t sector)
+{
+	struct bfq_queue *bfqq;
+
+	if (bfq_class_idle(cur_bfqq))
+		return NULL;
+	if (!bfq_bfqq_sync(cur_bfqq))
+		return NULL;
+	if (BFQQ_SEEKY(cur_bfqq))
+		return NULL;
+
+	/* If device has only one backlogged bfq_queue, don't search. */
+	if (bfqd->busy_queues == 1)
+		return NULL;
+
+	/*
+	 * We should notice if some of the queues are cooperating, e.g.
+	 * working closely on the same area of the disk. In that case,
+	 * we can group them together and don't waste time idling.
+	 */
+	bfqq = bfqq_close(bfqd, sector);
+	if (bfqq == NULL || bfqq == cur_bfqq)
+		return NULL;
+
+	/*
+	 * Do not merge queues from different bfq_groups.
+	*/
+	if (bfqq->entity.parent != cur_bfqq->entity.parent)
+		return NULL;
+
+	/*
+	 * It only makes sense to merge sync queues.
+	 */
+	if (!bfq_bfqq_sync(bfqq))
+		return NULL;
+	if (BFQQ_SEEKY(bfqq))
+		return NULL;
+
+	/*
+	 * Do not merge queues of different priority classes.
+	 */
+	if (bfq_class_rt(bfqq) != bfq_class_rt(cur_bfqq))
+		return NULL;
+
+	return bfqq;
+}
+
+static struct bfq_queue *
+bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	int process_refs, new_process_refs;
+	struct bfq_queue *__bfqq;
+
+	/*
+	 * If there are no process references on the new_bfqq, then it is
+	 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
+	 * may have dropped their last reference (not just their last process
+	 * reference).
+	 */
+	if (!bfqq_process_refs(new_bfqq))
+		return NULL;
+
+	/* Avoid a circular list and skip interim queue merges. */
+	while ((__bfqq = new_bfqq->new_bfqq)) {
+		if (__bfqq == bfqq)
+			return NULL;
+		new_bfqq = __bfqq;
+	}
+
+	process_refs = bfqq_process_refs(bfqq);
+	new_process_refs = bfqq_process_refs(new_bfqq);
+	/*
+	 * If the process for the bfqq has gone away, there is no
+	 * sense in merging the queues.
+	 */
+	if (process_refs == 0 || new_process_refs == 0)
+		return NULL;
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
+		new_bfqq->pid);
+
+	/*
+	 * Merging is just a redirection: the requests of the process
+	 * owning one of the two queues are redirected to the other queue.
+	 * The latter queue, in its turn, is set as shared if this is the
+	 * first time that the requests of some process are redirected to
+	 * it.
+	 *
+	 * We redirect bfqq to new_bfqq and not the opposite, because we
+	 * are in the context of the process owning bfqq, hence we have
+	 * the io_cq of this process. So we can immediately configure this
+	 * io_cq to redirect the requests of the process to new_bfqq.
+	 *
+	 * NOTE, even if new_bfqq coincides with the in-service queue, the
+	 * io_cq of new_bfqq is not available, because, if the in-service
+	 * queue is shared, bfqd->in_service_bic may not point to the
+	 * io_cq of the in-service queue.
+	 * Redirecting the requests of the process owning bfqq to the
+	 * currently in-service queue is in any case the best option, as
+	 * we feed the in-service queue with new requests close to the
+	 * last request served and, by doing so, hopefully increase the
+	 * throughput.
+	 */
+	bfqq->new_bfqq = new_bfqq;
+	atomic_add(process_refs, &new_bfqq->ref);
+	return new_bfqq;
+}
+
+/*
+ * Attempt to schedule a merge of bfqq with the currently in-service queue
+ * or with a close queue among the scheduled queues.
+ * Return NULL if no merge was scheduled, a pointer to the shared bfq_queue
+ * structure otherwise.
+ */
+static struct bfq_queue *
+bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		     void *io_struct, bool request)
+{
+	struct bfq_queue *in_service_bfqq, *new_bfqq;
+
+	if (bfqq->new_bfqq)
+		return bfqq->new_bfqq;
+
+	if (!io_struct)
+		return NULL;
+
+	in_service_bfqq = bfqd->in_service_queue;
+
+	if (in_service_bfqq == NULL || in_service_bfqq == bfqq ||
+	    !bfqd->in_service_bic)
+		goto check_scheduled;
+
+	if (bfq_class_idle(in_service_bfqq) || bfq_class_idle(bfqq))
+		goto check_scheduled;
+
+	if (bfq_class_rt(in_service_bfqq) != bfq_class_rt(bfqq))
+		goto check_scheduled;
+
+	if (in_service_bfqq->entity.parent != bfqq->entity.parent)
+		goto check_scheduled;
+
+	if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
+	    bfq_bfqq_sync(in_service_bfqq) && bfq_bfqq_sync(bfqq)) {
+		new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
+		if (new_bfqq != NULL)
+			return new_bfqq; /* Merge with in-service queue */
+	}
+
+	/*
+	 * Check whether there is a cooperator among currently scheduled
+	 * queues. The only thing we need is that the bio/request is not
+	 * NULL, as we need it to establish whether a cooperator exists.
+	 */
+check_scheduled:
+	new_bfqq = bfq_close_cooperator(bfqd, bfqq,
+					bfq_io_struct_pos(io_struct, request));
+	if (new_bfqq)
+		return bfq_setup_merge(bfqq, new_bfqq);
+
+	return NULL;
+}
+
+static inline void
+bfq_bfqq_save_state(struct bfq_queue *bfqq)
+{
+	/*
+	 * If bfqq->bic == NULL, the queue is already shared or its requests
+	 * have already been redirected to a shared queue; both idle window
+	 * and weight raising state have already been saved. Do nothing.
+	 */
+	if (bfqq->bic == NULL)
+		return;
+	if (bfqq->bic->wr_time_left)
+		/*
+		 * This is the queue of a just-started process, and would
+		 * deserve weight raising: we set wr_time_left to the full
+		 * weight-raising duration to trigger weight-raising when
+		 * and if the queue is split and the first request of the
+		 * queue is enqueued.
+		 */
+		bfqq->bic->wr_time_left = bfq_wr_duration(bfqq->bfqd);
+	else if (bfqq->wr_coeff > 1) {
+		unsigned long wr_duration =
+			jiffies - bfqq->last_wr_start_finish;
+		/*
+		 * It may happen that a queue's weight raising period lasts
+		 * longer than its wr_cur_max_time, as weight raising is
+		 * handled only when a request is enqueued or dispatched (it
+		 * does not use any timer). If the weight raising period is
+		 * about to end, don't save it.
+		 */
+		if (bfqq->wr_cur_max_time <= wr_duration)
+			bfqq->bic->wr_time_left = 0;
+		else
+			bfqq->bic->wr_time_left =
+				bfqq->wr_cur_max_time - wr_duration;
+		/*
+		 * The bfq_queue is becoming shared or the requests of the
+		 * process owning the queue are being redirected to a shared
+		 * queue. Stop the weight raising period of the queue, as in
+		 * both cases it should not be owned by an interactive or
+		 * soft real-time application.
+		 */
+		bfq_bfqq_end_wr(bfqq);
+	} else
+		bfqq->bic->wr_time_left = 0;
+	bfqq->bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
+}
+
+static inline void
+bfq_get_bic_reference(struct bfq_queue *bfqq)
+{
+	/*
+	 * If bfqq->bic has a non-NULL value, the bic to which it belongs
+	 * is about to begin using a shared bfq_queue.
+	 */
+	if (bfqq->bic)
+		atomic_long_inc(&bfqq->bic->icq.ioc->refcount);
+}
+
+static void
+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
+		(long unsigned)new_bfqq->pid);
+	/* Save weight raising and idle window of the merged queues */
+	bfq_bfqq_save_state(bfqq);
+	bfq_bfqq_save_state(new_bfqq);
+	/*
+	 * Grab a reference to the bic, to prevent it from being destroyed
+	 * before being possibly touched by a bfq_split_bfqq().
+	 */
+	bfq_get_bic_reference(bfqq);
+	bfq_get_bic_reference(new_bfqq);
+	/*
+	 * Merge queues (that is, let bic redirect its requests to new_bfqq)
+	 */
+	bic_set_bfqq(bic, new_bfqq, 1);
+	bfq_mark_bfqq_coop(new_bfqq);
+	/*
+	 * new_bfqq now belongs to at least two bics (it is a shared queue):
+	 * set new_bfqq->bic to NULL. bfqq either:
+	 * - does not belong to any bic any more, and hence bfqq->bic must
+	 *   be set to NULL, or
+	 * - is a queue whose owning bics have already been redirected to a
+	 *   different queue, hence the queue is destined to not belong to
+	 *   any bic soon and bfqq->bic is already NULL (therefore the next
+	 *   assignment causes no harm).
+	 */
+	new_bfqq->bic = NULL;
+	bfqq->bic = NULL;
+	bfq_put_queue(bfqq);
+}
+
 static int bfq_allow_merge(struct request_queue *q, struct request *rq,
 			   struct bio *bio)
 {
 	struct bfq_data *bfqd = q->elevator->elevator_data;
 	struct bfq_io_cq *bic;
-	struct bfq_queue *bfqq;
+	struct bfq_queue *bfqq, *new_bfqq;
 
 	/*
 	 * Disallow merge of a sync bio into an async request.
@@ -715,6 +1173,23 @@ static int bfq_allow_merge(struct request_queue *q, struct request *rq,
 		return 0;
 
 	bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
+	/*
+	 * We take advantage of this function to perform an early merge
+	 * of the queues of possible cooperating processes.
+	 */
+	if (bfqq != NULL) {
+		new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
+		if (new_bfqq != NULL) {
+			bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq);
+			/*
+			 * If we get here, the bio will be queued in the
+			 * shared queue, i.e., new_bfqq, so use new_bfqq
+			 * to decide whether bio and rq can be merged.
+			 */
+			bfqq = new_bfqq;
+		}
+	}
+
 	return bfqq == RQ_BFQQ(rq);
 }
 
@@ -898,6 +1373,15 @@ static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	__bfq_bfqd_reset_in_service(bfqd);
 
+	/*
+	 * If this bfqq is shared between multiple processes, check
+	 * to make sure that those processes are still issuing I/Os
+	 * within the mean seek distance. If not, it may be time to
+	 * break the queues apart again.
+	 */
+	if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
+		bfq_mark_bfqq_split_coop(bfqq);
+
 	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
 		/*
 		 * Overloading budget_timeout field to store the time
@@ -906,8 +1390,13 @@ static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 		 */
 		bfqq->budget_timeout = jiffies;
 		bfq_del_bfqq_busy(bfqd, bfqq, 1);
-	} else
+	} else {
 		bfq_activate_bfqq(bfqd, bfqq);
+		/*
+		 * Resort priority tree of potential close cooperators.
+		 */
+		bfq_rq_pos_tree_add(bfqd, bfqq);
+	}
 }
 
 /**
@@ -1773,6 +2262,25 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 	kmem_cache_free(bfq_pool, bfqq);
 }
 
+static void bfq_put_cooperator(struct bfq_queue *bfqq)
+{
+	struct bfq_queue *__bfqq, *next;
+
+	/*
+	 * If this queue was scheduled to merge with another queue, be
+	 * sure to drop the reference taken on that queue (and others in
+	 * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
+	 */
+	__bfqq = bfqq->new_bfqq;
+	while (__bfqq) {
+		if (__bfqq == bfqq)
+			break;
+		next = __bfqq->new_bfqq;
+		bfq_put_queue(__bfqq);
+		__bfqq = next;
+	}
+}
+
 static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	if (bfqq == bfqd->in_service_queue) {
@@ -1783,12 +2291,35 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq,
 		     atomic_read(&bfqq->ref));
 
+	bfq_put_cooperator(bfqq);
+
 	bfq_put_queue(bfqq);
 }
 
 static inline void bfq_init_icq(struct io_cq *icq)
 {
-	icq_to_bic(icq)->ttime.last_end_request = jiffies;
+	struct bfq_io_cq *bic = icq_to_bic(icq);
+
+	bic->ttime.last_end_request = jiffies;
+	/*
+	 * A newly created bic indicates that the process has just
+	 * started doing I/O, and is probably mapping into memory its
+	 * executable and libraries: it definitely needs weight raising.
+	 * There is however the possibility that the process performs,
+	 * for a while, I/O close to some other process. EQM intercepts
+	 * this behavior and may merge the queue corresponding to the
+	 * process  with some other queue, BEFORE the weight of the queue
+	 * is raised. Merged queues are not weight-raised (they are assumed
+	 * to belong to processes that benefit only from high throughput).
+	 * If the merge is basically the consequence of an accident, then
+	 * the queue will be split soon and will get back its old weight.
+	 * It is then important to write down somewhere that this queue
+	 * does need weight raising, even if it did not make it to get its
+	 * weight raised before being merged. To this purpose, we overload
+	 * the field raising_time_left and assign 1 to it, to mark the queue
+	 * as needing weight raising.
+	 */
+	bic->wr_time_left = 1;
 }
 
 static void bfq_exit_icq(struct io_cq *icq)
@@ -1802,6 +2333,13 @@ static void bfq_exit_icq(struct io_cq *icq)
 	}
 
 	if (bic->bfqq[BLK_RW_SYNC]) {
+		/*
+		 * If the bic is using a shared queue, put the reference
+		 * taken on the io_context when the bic started using a
+		 * shared bfq_queue.
+		 */
+		if (bfq_bfqq_coop(bic->bfqq[BLK_RW_SYNC]))
+			put_io_context(icq->ioc);
 		bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_SYNC]);
 		bic->bfqq[BLK_RW_SYNC] = NULL;
 	}
@@ -2089,6 +2627,10 @@ static void bfq_update_idle_window(struct bfq_data *bfqd,
 	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
 		return;
 
+	/* Idle window just restored, statistics are meaningless. */
+	if (bfq_bfqq_just_split(bfqq))
+		return;
+
 	enable_idle = bfq_bfqq_idle_window(bfqq);
 
 	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
@@ -2131,6 +2673,7 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
 	    !BFQQ_SEEKY(bfqq))
 		bfq_update_idle_window(bfqd, bfqq, bic);
+	bfq_clear_bfqq_just_split(bfqq);
 
 	bfq_log_bfqq(bfqd, bfqq,
 		     "rq_enqueued: idle_window=%d (seeky %d, mean %llu)",
@@ -2191,14 +2734,48 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 static void bfq_insert_request(struct request_queue *q, struct request *rq)
 {
 	struct bfq_data *bfqd = q->elevator->elevator_data;
-	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq;
 
 	assert_spin_locked(bfqd->queue->queue_lock);
 
+	/*
+	 * An unplug may trigger a requeue of a request from the device
+	 * driver: make sure we are in process context while trying to
+	 * merge two bfq_queues.
+	 */
+	if (!in_interrupt()) {
+		new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
+		if (new_bfqq != NULL) {
+			if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
+				new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1);
+			/*
+			 * Release the request's reference to the old bfqq
+			 * and make sure one is taken to the shared queue.
+			 */
+			new_bfqq->allocated[rq_data_dir(rq)]++;
+			bfqq->allocated[rq_data_dir(rq)]--;
+			atomic_inc(&new_bfqq->ref);
+			bfq_put_queue(bfqq);
+			if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
+				bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
+						bfqq, new_bfqq);
+			rq->elv.priv[1] = new_bfqq;
+			bfqq = new_bfqq;
+		}
+	}
+
 	bfq_init_prio_data(bfqq, RQ_BIC(rq));
 
 	bfq_add_request(rq);
 
+	/*
+	 * Here a newly-created bfq_queue has already started a weight-raising
+	 * period: clear raising_time_left to prevent bfq_bfqq_save_state()
+	 * from assigning it a full weight-raising period. See the detailed
+	 * comments about this field in bfq_init_icq().
+	 */
+	if (bfqq->bic != NULL)
+		bfqq->bic->wr_time_left = 0;
 	rq->fifo_time = jiffies + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &bfqq->fifo);
 
@@ -2347,6 +2924,32 @@ static void bfq_put_request(struct request *rq)
 }
 
 /*
+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
+ * was the last process referring to said bfqq.
+ */
+static struct bfq_queue *
+bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
+
+	put_io_context(bic->icq.ioc);
+
+	if (bfqq_process_refs(bfqq) == 1) {
+		bfqq->pid = current->pid;
+		bfq_clear_bfqq_coop(bfqq);
+		bfq_clear_bfqq_split_coop(bfqq);
+		return bfqq;
+	}
+
+	bic_set_bfqq(bic, NULL, 1);
+
+	bfq_put_cooperator(bfqq);
+
+	bfq_put_queue(bfqq);
+	return NULL;
+}
+
+/*
  * Allocate bfq data structures associated with this request.
  */
 static int bfq_set_request(struct request_queue *q, struct request *rq,
@@ -2359,6 +2962,7 @@ static int bfq_set_request(struct request_queue *q, struct request *rq,
 	struct bfq_queue *bfqq;
 	struct bfq_group *bfqg;
 	unsigned long flags;
+	bool split = false;
 
 	might_sleep_if(gfp_mask & __GFP_WAIT);
 
@@ -2371,10 +2975,20 @@ static int bfq_set_request(struct request_queue *q, struct request *rq,
 
 	bfqg = bfq_bic_update_cgroup(bic);
 
+new_queue:
 	bfqq = bic_to_bfqq(bic, is_sync);
 	if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) {
 		bfqq = bfq_get_queue(bfqd, bfqg, is_sync, bic, gfp_mask);
 		bic_set_bfqq(bic, bfqq, is_sync);
+	} else {
+		/* If the queue was seeky for too long, break it apart. */
+		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
+			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
+			bfqq = bfq_split_bfqq(bic, bfqq);
+			split = true;
+			if (!bfqq)
+				goto new_queue;
+		}
 	}
 
 	bfqq->allocated[rw]++;
@@ -2385,6 +2999,26 @@ static int bfq_set_request(struct request_queue *q, struct request *rq,
 	rq->elv.priv[0] = bic;
 	rq->elv.priv[1] = bfqq;
 
+	/*
+	 * If a bfq_queue has only one process reference, it is owned
+	 * by only one bfq_io_cq: we can set the bic field of the
+	 * bfq_queue to the address of that structure. Also, if the
+	 * queue has just been split, mark a flag so that the
+	 * information is available to the other scheduler hooks.
+	 */
+	if (bfqq_process_refs(bfqq) == 1) {
+		bfqq->bic = bic;
+		if (split) {
+			bfq_mark_bfqq_just_split(bfqq);
+			/*
+			 * If the queue has just been split from a shared
+			 * queue, restore the idle window and the possible
+			 * weight raising period.
+			 */
+			bfq_bfqq_resume_state(bfqq, bic);
+		}
+	}
+
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
 	return 0;
@@ -2565,6 +3199,8 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
 	bfqd->idle_slice_timer.data = (unsigned long)bfqd;
 
+	bfqd->rq_pos_tree = RB_ROOT;
+
 	INIT_WORK(&bfqd->unplug_work, bfq_kick_queue);
 
 	INIT_LIST_HEAD(&bfqd->active_list);
@@ -2918,7 +3554,7 @@ static int __init bfq_init(void)
 	device_speed_thresh[1] = (R_fast[1] + R_slow[1]) / 2;
 
 	elv_register(&iosched_bfq);
-	pr_info("BFQ I/O-scheduler version: v2");
+	pr_info("BFQ I/O-scheduler version: v6");
 
 	return 0;
 }
diff --git a/block/bfq.h b/block/bfq.h
index 7d6e4cb..bda1ecb3 100644
--- a/block/bfq.h
+++ b/block/bfq.h
@@ -1,5 +1,5 @@
 /*
- * BFQ-v2 for 3.15.0: data structures and common functions prototypes.
+ * BFQ-v6 for 3.15.0: data structures and common functions prototypes.
  *
  * Based on ideas and code from CFQ:
  * Copyright (C) 2003 Jens Axboe <axboe at kernel.dk>
@@ -164,6 +164,10 @@ struct bfq_group;
  * struct bfq_queue - leaf schedulable entity.
  * @ref: reference counter.
  * @bfqd: parent bfq_data.
+ * @new_bfqq: shared bfq_queue if queue is cooperating with
+ *           one or more other queues.
+ * @pos_node: request-position tree member (see bfq_data's @rq_pos_tree).
+ * @pos_root: request-position tree root (see bfq_data's @rq_pos_tree).
  * @sort_list: sorted list of pending requests.
  * @next_rq: if fifo isn't expired, next request to serve.
  * @queued: nr of requests queued in @sort_list.
@@ -196,18 +200,26 @@ struct bfq_group;
  * @service_from_backlogged: cumulative service received from the @bfq_queue
  *                           since the last transition from idle to
  *                           backlogged
+ * @bic: pointer to the bfq_io_cq owning the bfq_queue, set to %NULL if the
+ *	 queue is shared
  *
  * A bfq_queue is a leaf request queue; it can be associated with an
- * io_context or more, if it is async. @cgroup holds a reference to the
- * cgroup, to be sure that it does not disappear while a bfqq still
- * references it (mostly to avoid races between request issuing and task
- * migration followed by cgroup destruction). All the fields are protected
- * by the queue lock of the containing bfqd.
+ * io_context or more, if it  is  async or shared  between  cooperating
+ * processes. @cgroup holds a reference to the cgroup, to be sure that it
+ * does not disappear while a bfqq still references it (mostly to avoid
+ * races between request issuing and task migration followed by cgroup
+ * destruction).
+ * All the fields are protected by the queue lock of the containing bfqd.
  */
 struct bfq_queue {
 	atomic_t ref;
 	struct bfq_data *bfqd;
 
+	/* fields for cooperating queues handling */
+	struct bfq_queue *new_bfqq;
+	struct rb_node pos_node;
+	struct rb_root *pos_root;
+
 	struct rb_root sort_list;
 	struct request *next_rq;
 	int queued[2];
@@ -232,6 +244,7 @@ struct bfq_queue {
 	sector_t last_request_pos;
 
 	pid_t pid;
+	struct bfq_io_cq *bic;
 
 	/* weight-raising fields */
 	unsigned long wr_cur_max_time;
@@ -261,12 +274,24 @@ struct bfq_ttime {
  * @icq: associated io_cq structure
  * @bfqq: array of two process queues, the sync and the async
  * @ttime: associated @bfq_ttime struct
+ * @wr_time_left: snapshot of the time left before weight raising ends
+ *                for the sync queue associated to this process; this
+ *		  snapshot is taken to remember this value while the weight
+ *		  raising is suspended because the queue is merged with a
+ *		  shared queue, and is used to set @raising_cur_max_time
+ *		  when the queue is split from the shared queue and its
+ *		  weight is raised again
+ * @saved_idle_window: same purpose as the previous field for the idle
+ *                     window
  */
 struct bfq_io_cq {
 	struct io_cq icq; /* must be the first member */
 	struct bfq_queue *bfqq[2];
 	struct bfq_ttime ttime;
 	int ioprio;
+
+	unsigned int wr_time_left;
+	unsigned int saved_idle_window;
 };
 
 enum bfq_device_speed {
@@ -278,6 +303,9 @@ enum bfq_device_speed {
  * struct bfq_data - per device data structure.
  * @queue: request queue for the managed device.
  * @root_group: root bfq_group for the device.
+ * @rq_pos_tree: rbtree sorted by next_request position, used when
+ *               determining if two or more queues have interleaving
+ *               requests (see bfq_close_cooperator()).
  * @busy_queues: number of bfq_queues containing requests (including the
  *		 queue in service, even if it is idling).
  * @wr_busy_queues: number of weight-raised busy @bfq_queues.
@@ -344,6 +372,7 @@ struct bfq_data {
 	struct request_queue *queue;
 
 	struct bfq_group *root_group;
+	struct rb_root rq_pos_tree;
 
 	int busy_queues;
 	int wr_busy_queues;
@@ -418,6 +447,9 @@ enum bfqq_state_flags {
 					 * may need softrt-next-start
 					 * update
 					 */
+	BFQ_BFQQ_FLAG_coop,		/* bfqq is shared */
+	BFQ_BFQQ_FLAG_split_coop,	/* shared bfqq will be split */
+	BFQ_BFQQ_FLAG_just_split,	/* queue has just been split */
 };
 
 #define BFQ_BFQQ_FNS(name)						\
@@ -443,6 +475,9 @@ BFQ_BFQQ_FNS(prio_changed);
 BFQ_BFQQ_FNS(sync);
 BFQ_BFQQ_FNS(budget_new);
 BFQ_BFQQ_FNS(constantly_seeky);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
+BFQ_BFQQ_FNS(just_split);
 BFQ_BFQQ_FNS(softrt_update);
 #undef BFQ_BFQQ_FNS
 
-- 
1.9.2



More information about the Containers mailing list