1 files changed, 43 insertions, 81 deletions

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index e2f80463ed0d..023f4e69a337 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -42,16 +42,13 @@ 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           8 * 1024
+#define CFQQ_SEEKY(cfqq)        ((cfqq)->seek_mean > CFQQ_SEEK_THR)
+
 #define RQ_CIC(rq)              \
         ((struct cfq_io_context *) (rq)->elevator_private)
 #define RQ_CFQQ(rq)             (struct cfq_queue *) ((rq)->elevator_private2)
@@ -137,7 +134,6 @@ struct cfq_queue {
         u64 seek_total;
         sector_t seek_mean;
         sector_t last_request_pos;
-        unsigned long seeky_start;
 
         pid_t pid;
 
@@ -208,8 +204,6 @@ struct cfq_data {
         /* Root service tree for cfq_groups */
         struct cfq_rb_root grp_service_tree;
         struct cfq_group root_group;
-        /* Number of active cfq groups on group service tree */
-        int nr_groups;
 
         /*
          * The priority currently being served
@@ -294,8 +288,7 @@ static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
 
 static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,
                                             enum wl_prio_t prio,
-                                            enum wl_type_t type,
-                                            struct cfq_data *cfqd)
+                                            enum wl_type_t type)
 {
         if (!cfqg)
                 return NULL;
@@ -317,6 +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 */
 };
@@ -345,6 +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
@@ -842,7 +837,6 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 
         __cfq_group_service_tree_add(st, cfqg);
         cfqg->on_st = true;
-        cfqd->nr_groups++;
         st->total_weight += cfqg->weight;
 }
 
@@ -863,7 +857,6 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 
         cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
         cfqg->on_st = false;
-        cfqd->nr_groups--;
         st->total_weight -= cfqg->weight;
         if (!RB_EMPTY_NODE(&cfqg->rb_node))
                 cfq_rb_erase(&cfqg->rb_node, st);
@@ -1150,7 +1143,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 #endif
 
         service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
-                                                cfqq_type(cfqq), cfqd);
+                                                cfqq_type(cfqq));
         if (cfq_class_idle(cfqq)) {
                 rb_key = CFQ_IDLE_DELAY;
                 parent = rb_last(&service_tree->rb);
@@ -1513,9 +1506,6 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
         struct cfq_io_context *cic;
         struct cfq_queue *cfqq;
 
-        /* Deny merge if bio and rq don't belong to same cfq group */
-        if ((RQ_CFQQ(rq))->cfqg != cfq_get_cfqg(cfqd, 0))
-                return false;
         /*
          * Disallow merge of a sync bio into an async request.
          */
@@ -1574,6 +1564,15 @@ __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)) {
@@ -1616,7 +1615,7 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
 {
         struct cfq_rb_root *service_tree =
                 service_tree_for(cfqd->serving_group, cfqd->serving_prio,
-                                        cfqd->serving_type, cfqd);
+                                        cfqd->serving_type);
 
         if (!cfqd->rq_queued)
                 return NULL;
@@ -1671,17 +1670,18 @@ 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)
+                               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;
 }
 
@@ -1709,7 +1709,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
          * will contain the closest sector.
          */
         __cfqq = rb_entry(parent, struct cfq_queue, p_node);
-        if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
+        if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
                 return __cfqq;
 
         if (blk_rq_pos(__cfqq->next_rq) < sector)
@@ -1720,7 +1720,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
                 return NULL;
 
         __cfqq = rb_entry(node, struct cfq_queue, p_node);
-        if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
+        if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
                 return __cfqq;
 
         return NULL;
@@ -1807,7 +1807,7 @@ 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)
@@ -1963,8 +1963,7 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
 }
 
 static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
-                                struct cfq_group *cfqg, enum wl_prio_t prio,
-                                bool prio_changed)
+                                struct cfq_group *cfqg, enum wl_prio_t prio)
 {
         struct cfq_queue *queue;
         int i;
@@ -1972,24 +1971,9 @@ static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
         unsigned long lowest_key = 0;
         enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;
 
-        if (prio_changed) {
-                /*
-                 * When priorities switched, we prefer starting
-                 * from SYNC_NOIDLE (first choice), or just SYNC
-                 * over ASYNC
-                 */
-                if (service_tree_for(cfqg, prio, cur_best, cfqd)->count)
-                        return cur_best;
-                cur_best = SYNC_WORKLOAD;
-                if (service_tree_for(cfqg, prio, cur_best, cfqd)->count)
-                        return cur_best;
-
-                return ASYNC_WORKLOAD;
-        }
-
-        for (i = 0; i < 3; ++i) {
-                /* otherwise, select the one with lowest rb_key */
-                queue = cfq_rb_first(service_tree_for(cfqg, prio, i, cfqd));
+        for (i = 0; i <= SYNC_WORKLOAD; ++i) {
+                /* select the one with lowest rb_key */
+                queue = cfq_rb_first(service_tree_for(cfqg, prio, i));
                 if (queue &&
                     (!key_valid || time_before(queue->rb_key, lowest_key))) {
                         lowest_key = queue->rb_key;
@@ -2003,8 +1987,6 @@ static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 
 static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
-        enum wl_prio_t previous_prio = cfqd->serving_prio;
-        bool prio_changed;
         unsigned slice;
         unsigned count;
         struct cfq_rb_root *st;
@@ -2032,24 +2014,19 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
          * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
          * expiration time
          */
-        prio_changed = (cfqd->serving_prio != previous_prio);
-        st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type,
-                                cfqd);
+        st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
         count = st->count;
 
         /*
-         * If priority didn't change, check workload expiration,
-         * and that we still have other queues ready
+         * check workload expiration, and that we still have other queues ready
          */
-        if (!prio_changed && count &&
-            !time_after(jiffies, cfqd->workload_expires))
+        if (count && !time_after(jiffies, cfqd->workload_expires))
                 return;
 
         /* otherwise select new workload type */
         cfqd->serving_type =
-                cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio, prio_changed);
-        st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type,
-                                cfqd);
+                cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
+        st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
         count = st->count;
 
         /*
@@ -3027,19 +3004,6 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
         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;
-        }
 }
 
 /*
@@ -3104,6 +3068,12 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
                 return true;
 
         /*
+         * Don't allow a non-RT request to preempt an ongoing RT cfqq timeslice.
+         */
+        if (cfq_class_rt(cfqq) && !cfq_class_rt(new_cfqq))
+                return false;
+
+        /*
          * if the new request is sync, but the currently running queue is
          * not, let the sync request have priority.
          */
@@ -3143,7 +3113,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
          * if this request is as-good as one we would expect from the
          * current cfqq, let it preempt
          */
-        if (cfq_rq_close(cfqd, cfqq, rq))
+        if (cfq_rq_close(cfqd, cfqq, rq, true))
                 return true;
 
         return false;
@@ -3474,14 +3444,6 @@ 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.
@@ -3490,9 +3452,9 @@ 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;
         }
 
@@ -3531,7 +3493,7 @@ 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)