blkio: Increment the blkio cgroup stats for real now

We also add start_time_ns and io_start_time_ns fields to struct request
here to record the time when a request is created and when it is
dispatched to device. We use ns uints here as ms and jiffies are
not very useful for non-rotational media.

Signed-off-by: Divyesh Shah<dpshah@google.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

4 files changed, 76 insertions, 8 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index ad6843f2e0ab..9af7257f429c 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -15,6 +15,7 @@
 #include <linux/kdev_t.h>
 #include <linux/module.h>
 #include <linux/err.h>
+#include <linux/blkdev.h>
 #include "blk-cgroup.h"
 
 static DEFINE_SPINLOCK(blkio_list_lock);
@@ -55,6 +56,26 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 }
 EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
 
+/*
+ * Add to the appropriate stat variable depending on the request type.
+ * This should be called with the blkg->stats_lock held.
+ */
+void io_add_stat(uint64_t *stat, uint64_t add, unsigned int flags)
+{
+        if (flags & REQ_RW)
+                stat[IO_WRITE] += add;
+        else
+                stat[IO_READ] += add;
+        /*
+         * Everywhere in the block layer, an IO is treated as sync if it is a
+         * read or a SYNC write. We follow the same norm.
+         */
+        if (!(flags & REQ_RW) || flags & REQ_RW_SYNC)
+                stat[IO_SYNC] += add;
+        else
+                stat[IO_ASYNC] += add;
+}
+
 void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time)
 {
         unsigned long flags;
@@ -65,6 +86,41 @@ void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time)
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);
 
+void blkiocg_update_request_dispatch_stats(struct blkio_group *blkg,
+                                                struct request *rq)
+{
+        struct blkio_group_stats *stats;
+        unsigned long flags;
+
+        spin_lock_irqsave(&blkg->stats_lock, flags);
+        stats = &blkg->stats;
+        stats->sectors += blk_rq_sectors(rq);
+        io_add_stat(stats->io_serviced, 1, rq->cmd_flags);
+        io_add_stat(stats->io_service_bytes, blk_rq_sectors(rq) << 9,
+                        rq->cmd_flags);
+        spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+
+void blkiocg_update_request_completion_stats(struct blkio_group *blkg,
+                                                struct request *rq)
+{
+        struct blkio_group_stats *stats;
+        unsigned long flags;
+        unsigned long long now = sched_clock();
+
+        spin_lock_irqsave(&blkg->stats_lock, flags);
+        stats = &blkg->stats;
+        if (time_after64(now, rq->io_start_time_ns))
+                io_add_stat(stats->io_service_time, now - rq->io_start_time_ns,
+                                rq->cmd_flags);
+        if (time_after64(rq->io_start_time_ns, rq->start_time_ns))
+                io_add_stat(stats->io_wait_time,
+                                rq->io_start_time_ns - rq->start_time_ns,
+                                rq->cmd_flags);
+        spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_request_completion_stats);
+
 void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
                         struct blkio_group *blkg, void *key, dev_t dev)
 {
@@ -325,12 +381,12 @@ SHOW_FUNCTION_PER_GROUP(dequeue, get_stat, get_dequeue_stat, 0);
 #undef SHOW_FUNCTION_PER_GROUP
 
 #ifdef CONFIG_DEBUG_BLK_CGROUP
-void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg,
+void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
                         unsigned long dequeue)
 {
         blkg->stats.dequeue += dequeue;
 }
-EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_dequeue_stats);
+EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats);
 #endif
 
 struct cftype blkio_files[] = {
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 5c5e5294b506..80010ef64ab0 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -112,12 +112,12 @@ static inline char *blkg_path(struct blkio_group *blkg)
 {
         return blkg->path;
 }
-void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg,
+void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
                                 unsigned long dequeue);
 #else
 static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }
-static inline void blkiocg_update_blkio_group_dequeue_stats(
-                        struct blkio_group *blkg, unsigned long dequeue) {}
+static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
+                                                unsigned long dequeue) {}
 #endif
 
 #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
@@ -130,6 +130,10 @@ extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
                                                 void *key);
 void blkiocg_update_timeslice_used(struct blkio_group *blkg,
                                         unsigned long time);
+void blkiocg_update_request_dispatch_stats(struct blkio_group *blkg,
+                                                struct request *rq);
+void blkiocg_update_request_completion_stats(struct blkio_group *blkg,
+                                                struct request *rq);
 #else
 struct cgroup;
 static inline struct blkio_cgroup *
@@ -147,5 +151,9 @@ static inline struct blkio_group *
 blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; }
 static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg,
                                                 unsigned long time) {}
+static inline void blkiocg_update_request_dispatch_stats(
+                struct blkio_group *blkg, struct request *rq) {}
+static inline void blkiocg_update_request_completion_stats(
+                struct blkio_group *blkg, struct request *rq) {}
 #endif
 #endif /* _BLK_CGROUP_H */
diff --git a/block/blk-core.c b/block/blk-core.c
index 9fe174dc74d1..1d94f15d7f0d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -127,6 +127,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
         rq->tag = -1;
         rq->ref_count = 1;
         rq->start_time = jiffies;
+        set_start_time_ns(rq);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -1855,8 +1856,10 @@ void blk_dequeue_request(struct request *rq)
          * and to it is freed is accounted as io that is in progress at
          * the driver side.
          */
-        if (blk_account_rq(rq))
+        if (blk_account_rq(rq)) {
                 q->in_flight[rq_is_sync(rq)]++;
+                set_io_start_time_ns(rq);
+        }
 }
 
 /**
@@ -2517,4 +2520,3 @@ int __init blk_dev_init(void)
 
         return 0;
 }
-
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index c5161bbf2fe9..42028e7128a7 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -855,7 +855,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
         if (!RB_EMPTY_NODE(&cfqg->rb_node))
                 cfq_rb_erase(&cfqg->rb_node, st);
         cfqg->saved_workload_slice = 0;
-        blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1);
+        blkiocg_update_dequeue_stats(&cfqg->blkg, 1);
 }
 
 static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
@@ -1865,6 +1865,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
         elv_dispatch_sort(q, rq);
 
         cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
+        blkiocg_update_request_dispatch_stats(&cfqq->cfqg->blkg, rq);
 }
 
 /*
@@ -3285,6 +3286,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
         WARN_ON(!cfqq->dispatched);
         cfqd->rq_in_driver--;
         cfqq->dispatched--;
+        blkiocg_update_request_completion_stats(&cfqq->cfqg->blkg, rq);
 
         cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;