1 files changed, 83 insertions, 111 deletions

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index ee130f14d1fc..dee9d9378fee 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -19,7 +19,7 @@
  * tunables
  */
 /* max queue in one round of service */
-static const int cfq_quantum = 4;
+static const int cfq_quantum = 8;
 static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
 /* maximum backwards seek, in KiB */
 static const int cfq_back_max = 16 * 1024;
@@ -42,16 +42,14 @@ static const int cfq_hist_divisor = 4;
  */
 #define CFQ_MIN_TT		(2)
 
-/*
- * Allow merged cfqqs to perform this amount of seeky I/O before
- * deciding to break the queues up again.
- */
-#define CFQQ_COOP_TOUT		(HZ)
-
 #define CFQ_SLICE_SCALE		(5)
 #define CFQ_HW_QUEUE_MIN	(5)
 #define CFQ_SERVICE_SHIFT       12
 
+#define CFQQ_SEEK_THR		(sector_t)(8 * 100)
+#define CFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
+#define CFQQ_SEEKY(cfqq)	(hweight32(cfqq->seek_history) > 32/8)
+
 #define RQ_CIC(rq)		\
 	((struct cfq_io_context *) (rq)->elevator_private)
 #define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private2)
@@ -80,11 +78,12 @@ struct cfq_rb_root {
 	struct rb_root rb;
 	struct rb_node *left;
 	unsigned count;
+	unsigned total_weight;
 	u64 min_vdisktime;
 	struct rb_node *active;
-	unsigned total_weight;
 };
-#define CFQ_RB_ROOT	(struct cfq_rb_root) { RB_ROOT, NULL, 0, 0, }
+#define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, .left = NULL, \
+			.count = 0, .min_vdisktime = 0, }
 
 /*
  * Per process-grouping structure
@@ -118,11 +117,11 @@ struct cfq_queue {
 	/* time when queue got scheduled in to dispatch first request. */
 	unsigned long dispatch_start;
 	unsigned int allocated_slice;
+	unsigned int slice_dispatch;
 	/* time when first request from queue completed and slice started. */
 	unsigned long slice_start;
 	unsigned long slice_end;
 	long slice_resid;
-	unsigned int slice_dispatch;
 
 	/* pending metadata requests */
 	int meta_pending;
@@ -133,14 +132,11 @@ struct cfq_queue {
 	unsigned short ioprio, org_ioprio;
 	unsigned short ioprio_class, org_ioprio_class;
 
-	unsigned int seek_samples;
-	u64 seek_total;
-	sector_t seek_mean;
-	sector_t last_request_pos;
-	unsigned long seeky_start;
-
 	pid_t pid;
 
+	u32 seek_history;
+	sector_t last_request_pos;
+
 	struct cfq_rb_root *service_tree;
 	struct cfq_queue *new_cfqq;
 	struct cfq_group *cfqg;
@@ -227,8 +223,8 @@ struct cfq_data {
 
 	unsigned int busy_queues;
 
-	int rq_in_driver[2];
-	int sync_flight;
+	int rq_in_driver;
+	int rq_in_flight[2];
 
 	/*
 	 * queue-depth detection
@@ -314,6 +310,7 @@ enum cfqq_state_flags {
 	CFQ_CFQQ_FLAG_slice_new,	/* no requests dispatched in slice */
 	CFQ_CFQQ_FLAG_sync,		/* synchronous queue */
 	CFQ_CFQQ_FLAG_coop,		/* cfqq is shared */
+	CFQ_CFQQ_FLAG_split_coop,	/* shared cfqq will be splitted */
 	CFQ_CFQQ_FLAG_deep,		/* sync cfqq experienced large depth */
 	CFQ_CFQQ_FLAG_wait_busy,	/* Waiting for next request */
 };
@@ -342,6 +339,7 @@ CFQ_CFQQ_FNS(prio_changed);
 CFQ_CFQQ_FNS(slice_new);
 CFQ_CFQQ_FNS(sync);
 CFQ_CFQQ_FNS(coop);
+CFQ_CFQQ_FNS(split_coop);
 CFQ_CFQQ_FNS(deep);
 CFQ_CFQQ_FNS(wait_busy);
 #undef CFQ_CFQQ_FNS
@@ -419,11 +417,6 @@ static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,
 static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
 						struct io_context *);
 
-static inline int rq_in_driver(struct cfq_data *cfqd)
-{
-	return cfqd->rq_in_driver[0] + cfqd->rq_in_driver[1];
-}
-
 static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
 					    bool is_sync)
 {
@@ -953,10 +946,6 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
 	unsigned int major, minor;
 
-	/* Do we need to take this reference */
-	if (!blkiocg_css_tryget(blkcg))
-		return NULL;;
-
 	cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
 	if (cfqg || !create)
 		goto done;
@@ -987,7 +976,6 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
 
 done:
-	blkiocg_css_put(blkcg);
 	return cfqg;
 }
 
@@ -1422,9 +1410,9 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 
-	cfqd->rq_in_driver[rq_is_sync(rq)]++;
+	cfqd->rq_in_driver++;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
-						rq_in_driver(cfqd));
+						cfqd->rq_in_driver);
 
 	cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
 }
@@ -1432,12 +1420,11 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
-	const int sync = rq_is_sync(rq);
 
-	WARN_ON(!cfqd->rq_in_driver[sync]);
-	cfqd->rq_in_driver[sync]--;
+	WARN_ON(!cfqd->rq_in_driver);
+	cfqd->rq_in_driver--;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
-						rq_in_driver(cfqd));
+						cfqd->rq_in_driver);
 }
 
 static void cfq_remove_request(struct request *rq)
@@ -1566,6 +1553,15 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	cfq_clear_cfqq_wait_busy(cfqq);
 
 	/*
+	 * If this cfqq 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 (cfq_cfqq_coop(cfqq) && CFQQ_SEEKY(cfqq))
+		cfq_mark_cfqq_split_coop(cfqq);
+
+	/*
 	 * store what was left of this slice, if the queue idled/timed out
 	 */
 	if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
@@ -1663,22 +1659,10 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 		return cfqd->last_position - blk_rq_pos(rq);
 }
 
-#define CFQQ_SEEK_THR		8 * 1024
-#define CFQQ_SEEKY(cfqq)	((cfqq)->seek_mean > CFQQ_SEEK_THR)
-
 static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			       struct request *rq, bool for_preempt)
 {
-	sector_t sdist = cfqq->seek_mean;
-
-	if (!sample_valid(cfqq->seek_samples))
-		sdist = CFQQ_SEEK_THR;
-
-	/* if seek_mean is big, using it as close criteria is meaningless */
-	if (sdist > CFQQ_SEEK_THR && !for_preempt)
-		sdist = CFQQ_SEEK_THR;
-
-	return cfq_dist_from_last(cfqd, rq) <= sdist;
+	return cfq_dist_from_last(cfqd, rq) <= CFQQ_SEEK_THR;
 }
 
 static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
@@ -1803,7 +1787,7 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * Otherwise, we do only if they are the last ones
 	 * in their service tree.
 	 */
-	return service_tree->count == 1;
+	return service_tree->count == 1 && cfq_cfqq_sync(cfqq);
 }
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
@@ -1874,8 +1858,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
 	cfqq->dispatched++;
 	elv_dispatch_sort(q, rq);
 
-	if (cfq_cfqq_sync(cfqq))
-		cfqd->sync_flight++;
+	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
 	cfqq->nr_sectors += blk_rq_sectors(rq);
 }
 
@@ -2215,6 +2198,19 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 	return dispatched;
 }
 
+static inline bool cfq_slice_used_soon(struct cfq_data *cfqd,
+	struct cfq_queue *cfqq)
+{
+	/* the queue hasn't finished any request, can't estimate */
+	if (cfq_cfqq_slice_new(cfqq))
+		return 1;
+	if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
+		cfqq->slice_end))
+		return 1;
+
+	return 0;
+}
+
 static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	unsigned int max_dispatch;
@@ -2222,16 +2218,16 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	/*
 	 * Drain async requests before we start sync IO
 	 */
-	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC])
+	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_flight[BLK_RW_ASYNC])
 		return false;
 
 	/*
 	 * If this is an async queue and we have sync IO in flight, let it wait
 	 */
-	if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
+	if (cfqd->rq_in_flight[BLK_RW_SYNC] && !cfq_cfqq_sync(cfqq))
 		return false;
 
-	max_dispatch = cfqd->cfq_quantum;
+	max_dispatch = max_t(unsigned int, cfqd->cfq_quantum / 2, 1);
 	if (cfq_class_idle(cfqq))
 		max_dispatch = 1;
 
@@ -2248,13 +2244,22 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		/*
 		 * We have other queues, don't allow more IO from this one
 		 */
-		if (cfqd->busy_queues > 1)
+		if (cfqd->busy_queues > 1 && cfq_slice_used_soon(cfqd, cfqq))
 			return false;
 
 		/*
 		 * Sole queue user, no limit
 		 */
-		max_dispatch = -1;
+		if (cfqd->busy_queues == 1)
+			max_dispatch = -1;
+		else
+			/*
+			 * Normally we start throttling cfqq when cfq_quantum/2
+			 * requests have been dispatched. But we can drive
+			 * deeper queue depths at the beginning of slice
+			 * subjected to upper limit of cfq_quantum.
+			 * */
+			max_dispatch = cfqd->cfq_quantum;
 	}
 
 	/*
@@ -2976,43 +2981,20 @@ static void
 cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		       struct request *rq)
 {
-	sector_t sdist;
-	u64 total;
-
-	if (!cfqq->last_request_pos)
-		sdist = 0;
-	else if (cfqq->last_request_pos < blk_rq_pos(rq))
-		sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
-	else
-		sdist = cfqq->last_request_pos - blk_rq_pos(rq);
+	sector_t sdist = 0;
+	sector_t n_sec = blk_rq_sectors(rq);
+	if (cfqq->last_request_pos) {
+		if (cfqq->last_request_pos < blk_rq_pos(rq))
+			sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
+		else
+			sdist = cfqq->last_request_pos - blk_rq_pos(rq);
+	}
 
-	/*
-	 * Don't allow the seek distance to get too large from the
-	 * odd fragment, pagein, etc
-	 */
-	if (cfqq->seek_samples <= 60) /* second&third seek */
-		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*1024);
+	cfqq->seek_history <<= 1;
+	if (blk_queue_nonrot(cfqd->queue))
+		cfqq->seek_history |= (n_sec < CFQQ_SECT_THR_NONROT);
 	else
-		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*64);
-
-	cfqq->seek_samples = (7*cfqq->seek_samples + 256) / 8;
-	cfqq->seek_total = (7*cfqq->seek_total + (u64)256*sdist) / 8;
-	total = cfqq->seek_total + (cfqq->seek_samples/2);
-	do_div(total, cfqq->seek_samples);
-	cfqq->seek_mean = (sector_t)total;
-
-	/*
-	 * If this cfqq 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 (cfq_cfqq_coop(cfqq)) {
-		if (CFQQ_SEEKY(cfqq) && !cfqq->seeky_start)
-			cfqq->seeky_start = jiffies;
-		else if (!CFQQ_SEEKY(cfqq))
-			cfqq->seeky_start = 0;
-	}
+		cfqq->seek_history |= (sdist > CFQQ_SEEK_THR);
 }
 
 /*
@@ -3037,8 +3019,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		cfq_mark_cfqq_deep(cfqq);
 
 	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
-	    (!cfq_cfqq_deep(cfqq) && sample_valid(cfqq->seek_samples)
-	     && CFQQ_SEEKY(cfqq)))
+	    (!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq)))
 		enable_idle = 0;
 	else if (sample_valid(cic->ttime_samples)) {
 		if (cic->ttime_mean > cfqd->cfq_slice_idle)
@@ -3224,14 +3205,14 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 
-	if (rq_in_driver(cfqd) > cfqd->hw_tag_est_depth)
-		cfqd->hw_tag_est_depth = rq_in_driver(cfqd);
+	if (cfqd->rq_in_driver > cfqd->hw_tag_est_depth)
+		cfqd->hw_tag_est_depth = cfqd->rq_in_driver;
 
 	if (cfqd->hw_tag == 1)
 		return;
 
 	if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
-	    rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
+	    cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
 		return;
 
 	/*
@@ -3241,7 +3222,7 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 	 */
 	if (cfqq && cfq_cfqq_idle_window(cfqq) &&
 	    cfqq->dispatched + cfqq->queued[0] + cfqq->queued[1] <
-	    CFQ_HW_QUEUE_MIN && rq_in_driver(cfqd) < CFQ_HW_QUEUE_MIN)
+	    CFQ_HW_QUEUE_MIN && cfqd->rq_in_driver < CFQ_HW_QUEUE_MIN)
 		return;
 
 	if (cfqd->hw_tag_samples++ < 50)
@@ -3294,13 +3275,12 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 
 	cfq_update_hw_tag(cfqd);
 
-	WARN_ON(!cfqd->rq_in_driver[sync]);
+	WARN_ON(!cfqd->rq_in_driver);
 	WARN_ON(!cfqq->dispatched);
-	cfqd->rq_in_driver[sync]--;
+	cfqd->rq_in_driver--;
 	cfqq->dispatched--;
 
-	if (cfq_cfqq_sync(cfqq))
-		cfqd->sync_flight--;
+	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 
 	if (sync) {
 		RQ_CIC(rq)->last_end_request = now;
@@ -3354,7 +3334,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		}
 	}
 
-	if (!rq_in_driver(cfqd))
+	if (!cfqd->rq_in_driver)
 		cfq_schedule_dispatch(cfqd);
 }
 
@@ -3453,14 +3433,6 @@ cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic,
 	return cic_to_cfqq(cic, 1);
 }
 
-static int should_split_cfqq(struct cfq_queue *cfqq)
-{
-	if (cfqq->seeky_start &&
-	    time_after(jiffies, cfqq->seeky_start + CFQQ_COOP_TOUT))
-		return 1;
-	return 0;
-}
-
 /*
  * Returns NULL if a new cfqq should be allocated, or the old cfqq if this
  * was the last process referring to said cfqq.
@@ -3469,9 +3441,9 @@ static struct cfq_queue *
 split_cfqq(struct cfq_io_context *cic, struct cfq_queue *cfqq)
 {
 	if (cfqq_process_refs(cfqq) == 1) {
-		cfqq->seeky_start = 0;
 		cfqq->pid = current->pid;
 		cfq_clear_cfqq_coop(cfqq);
+		cfq_clear_cfqq_split_coop(cfqq);
 		return cfqq;
 	}
 
@@ -3510,7 +3482,7 @@ new_queue:
 		/*
 		 * If the queue was seeky for too long, break it apart.
 		 */
-		if (cfq_cfqq_coop(cfqq) && should_split_cfqq(cfqq)) {
+		if (cfq_cfqq_coop(cfqq) && cfq_cfqq_split_coop(cfqq)) {
 			cfq_log_cfqq(cfqd, cfqq, "breaking apart cfqq");
 			cfqq = split_cfqq(cic, cfqq);
 			if (!cfqq)