blkio: Changes to IO controller additional stats patches

that include some minor fixes and addresses all comments.

Changelog: (most based on Vivek Goyal's comments)
o renamed blkiocg_reset_write to blkiocg_reset_stats
o more clarification in the documentation on io_service_time and io_wait_time
o Initialize blkg->stats_lock
o rename io_add_stat to blkio_add_stat and declare it static
o use bool for direction and sync
o derive direction and sync info from existing rq methods
o use 12 for major:minor string length
o define io_service_time better to cover the NCQ case
o add a separate reset_stats interface
o make the indexed stats a 2d array to simplify macro and function pointer code
o blkio.time now exports in jiffies as before
o Added stats description in patch description and
  Documentation/cgroup/blkio-controller.txt
o Prefix all stats functions with blkio and make them static as applicable
o replace IO_TYPE_MAX with IO_TYPE_TOTAL
o Moved #define constant to top of blk-cgroup.c
o Pass dev_t around instead of char *
o Add note to documentation file about resetting stats
o use BLK_CGROUP_MODULE in addition to BLK_CGROUP config option in #ifdef
  statements
o Avoid struct request specific knowledge in blk-cgroup. blk-cgroup.h now has
  rq_direction() and rq_sync() functions which are used by CFQ and when using
  io-controller at a higher level, bio_* functions can be added.

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

Documentation/cgroups/blkio-controller.txt

@@ -77,7 +77,6 @@ Details of cgroup files
 =======================
 - blkio.weight
 	- Specifies per cgroup weight.
-
 	  Currently allowed range of weights is from 100 to 1000.
 
 - blkio.time
@@ -92,6 +91,49 @@ Details of cgroup files
 	  third field specifies the number of sectors transferred by the
 	  group to/from the device.
 
+- blkio.io_service_bytes
+	- Number of bytes transferred to/from the disk by the group. These
+	  are further divided by the type of operation - read or write, sync
+	  or async. First two fields specify the major and minor number of the
+	  device, third field specifies the operation type and the fourth field
+	  specifies the number of bytes.
+
+- blkio.io_serviced
+	- Number of IOs completed to/from the disk by the group. These
+	  are further divided by the type of operation - read or write, sync
+	  or async. First two fields specify the major and minor number of the
+	  device, third field specifies the operation type and the fourth field
+	  specifies the number of IOs.
+
+- blkio.io_service_time
+	- Total amount of time between request dispatch and request completion
+	  for the IOs done by this cgroup. This is in nanoseconds to make it
+	  meaningful for flash devices too. For devices with queue depth of 1,
+	  this time represents the actual service time. When queue_depth > 1,
+	  that is no longer true as requests may be served out of order. This
+	  may cause the service time for a given IO to include the service time
+	  of multiple IOs when served out of order which may result in total
+	  io_service_time > actual time elapsed. This time is further divided by
+	  the type of operation - read or write, sync or async. First two fields
+	  specify the major and minor number of the device, third field
+	  specifies the operation type and the fourth field specifies the
+	  io_service_time in ns.
+
+- blkio.io_wait_time
+	- Total amount of time the IOs for this cgroup spent waiting in the
+	  scheduler queues for service. This can be greater than the total time
+	  elapsed since it is cumulative io_wait_time for all IOs. It is not a
+	  measure of total time the cgroup spent waiting but rather a measure of
+	  the wait_time for its individual IOs. For devices with queue_depth > 1
+	  this metric does not include the time spent waiting for service once
+	  the IO is dispatched to the device but till it actually gets serviced
+	  (there might be a time lag here due to re-ordering of requests by the
+	  device). This is in nanoseconds to make it meaningful for flash
+	  devices too. This time is further divided by the type of operation -
+	  read or write, sync or async. First two fields specify the major and
+	  minor number of the device, third field specifies the operation type
+	  and the fourth field specifies the io_wait_time in ns.
+
 - blkio.dequeue
 	- Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. This
 	  gives the statistics about how many a times a group was dequeued
@@ -99,6 +141,10 @@ Details of cgroup files
 	  and minor number of the device and third field specifies the number
 	  of times a group was dequeued from a particular device.
 
+- blkio.reset_stats
+	- Writing an int to this file will result in resetting all the stats
+	  for that cgroup.
+
 CFQ sysfs tunable
 =================
 /sys/block/<disk>/queue/iosched/group_isolation

block/blk-cgroup.h

@@ -23,12 +23,31 @@ extern struct cgroup_subsys blkio_subsys;
 #define blkio_subsys_id blkio_subsys.subsys_id
 #endif
 
-enum io_type {
-	IO_READ = 0,
-	IO_WRITE,
-	IO_SYNC,
-	IO_ASYNC,
-	IO_TYPE_MAX
+enum stat_type {
+	/* Total time spent (in ns) between request dispatch to the driver and
+	 * request completion for IOs doen by this cgroup. This may not be
+	 * accurate when NCQ is turned on. */
+	BLKIO_STAT_SERVICE_TIME = 0,
+	/* Total bytes transferred */
+	BLKIO_STAT_SERVICE_BYTES,
+	/* Total IOs serviced, post merge */
+	BLKIO_STAT_SERVICED,
+	/* Total time spent waiting in scheduler queue in ns */
+	BLKIO_STAT_WAIT_TIME,
+	/* All the single valued stats go below this */
+	BLKIO_STAT_TIME,
+	BLKIO_STAT_SECTORS,
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	BLKIO_STAT_DEQUEUE
+#endif
+};
+
+enum stat_sub_type {
+	BLKIO_STAT_READ = 0,
+	BLKIO_STAT_WRITE,
+	BLKIO_STAT_SYNC,
+	BLKIO_STAT_ASYNC,
+	BLKIO_STAT_TOTAL
 };
 
 struct blkio_cgroup {
@@ -42,13 +61,7 @@ struct blkio_group_stats {
 	/* total disk time and nr sectors dispatched by this group */
 	uint64_t time;
 	uint64_t sectors;
-	/* Total disk time used by IOs in ns */
-	uint64_t io_service_time[IO_TYPE_MAX];
-	uint64_t io_service_bytes[IO_TYPE_MAX]; /* Total bytes transferred */
-	/* Total IOs serviced, post merge */
-	uint64_t io_serviced[IO_TYPE_MAX];
-	/* Total time spent waiting in scheduler queue in ns */
-	uint64_t io_wait_time[IO_TYPE_MAX];
+	uint64_t stat_arr[BLKIO_STAT_WAIT_TIME + 1][BLKIO_STAT_TOTAL];
 #ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* How many times this group has been removed from service tree */
 	unsigned long dequeue;
@@ -65,7 +78,7 @@ struct blkio_group {
 	char path[128];
 #endif
 	/* The device MKDEV(major, minor), this group has been created for */
-	dev_t   dev;
+	dev_t dev;
 
 	/* Need to serialize the stats in the case of reset/update */
 	spinlock_t stats_lock;
@@ -128,21 +141,21 @@ extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
 extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
 						void *key);
+void blkio_group_init(struct blkio_group *blkg);
 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);
+void blkiocg_update_dispatch_stats(struct blkio_group *blkg, uint64_t bytes,
+						bool direction, bool sync);
+void blkiocg_update_completion_stats(struct blkio_group *blkg,
+	uint64_t start_time, uint64_t io_start_time, bool direction, bool sync);
 #else
 struct cgroup;
 static inline struct blkio_cgroup *
 cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
 
+static inline void blkio_group_init(struct blkio_group *blkg) {}
 static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-			struct blkio_group *blkg, void *key, dev_t dev)
-{
-}
+			struct blkio_group *blkg, void *key, dev_t dev) {}
 
 static inline int
 blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
@@ -151,9 +164,10 @@ 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) {}
+static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
+				uint64_t bytes, bool direction, bool sync) {}
+static inline void blkiocg_update_completion_stats(struct blkio_group *blkg,
+		uint64_t start_time, uint64_t io_start_time, bool direction,
+		bool sync) {}
 #endif
 #endif /* _BLK_CGROUP_H */

block/cfq-iosched.c

@@ -955,6 +955,7 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	for_each_cfqg_st(cfqg, i, j, st)
 		*st = CFQ_RB_ROOT;
 	RB_CLEAR_NODE(&cfqg->rb_node);
+	blkio_group_init(&cfqg->blkg);
 
 	/*
 	 * Take the initial reference that will be released on destroy
@@ -1865,7 +1866,8 @@ 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);
+	blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq),
+					rq_data_dir(rq), rq_is_sync(rq));
 }
 
 /*
@@ -3286,7 +3288,9 @@ 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);
+	blkiocg_update_completion_stats(&cfqq->cfqg->blkg, rq_start_time_ns(rq),
+			rq_io_start_time_ns(rq), rq_data_dir(rq),
+			rq_is_sync(rq));
 
 	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 

include/linux/blkdev.h

@@ -1209,9 +1209,27 @@ static inline void set_io_start_time_ns(struct request *req)
 {
 	req->io_start_time_ns = sched_clock();
 }
+
+static inline uint64_t rq_start_time_ns(struct request *req)
+{
+        return req->start_time_ns;
+}
+
+static inline uint64_t rq_io_start_time_ns(struct request *req)
+{
+        return req->io_start_time_ns;
+}
 #else
 static inline void set_start_time_ns(struct request *req) {}
 static inline void set_io_start_time_ns(struct request *req) {}
+static inline uint64_t rq_start_time_ns(struct request *req)
+{
+	return 0;
+}
+static inline uint64_t rq_io_start_time_ns(struct request *req)
+{
+	return 0;
+}
 #endif
 
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \