blkio: Add more debug-only per-cgroup stats

1) group_wait_time - This is the amount of time the cgroup had to wait to get a
  timeslice for one of its queues from when it became busy, i.e., went from 0
  to 1 request queued. This is different from the io_wait_time which is the
  cumulative total of the amount of time spent by each IO in that cgroup waiting
  in the scheduler queue. This stat is a great way to find out any jobs in the
  fleet that are being starved or waiting for longer than what is expected (due
  to an IO controller bug or any other issue).
2) empty_time - This is the amount of time a cgroup spends w/o any pending
   requests. This stat is useful when a job does not seem to be able to use its
   assigned disk share by helping check if that is happening due to an IO
   controller bug or because the job is not submitting enough IOs.
3) idle_time - This is the amount of time spent by the IO scheduler idling
   for a given cgroup in anticipation of a better request than the exising ones
   from other queues/cgroups.

All these stats are recorded using start and stop events. When reading these
stats, we do not add the delta between the current time and the last start time
if we're between the start and stop events. We avoid doing this to make sure
that these numbers are always monotonically increasing when read. Since we're
using sched_clock() which may use the tsc as its source, it may induce some
inconsistency (due to tsc resync across cpus) if we included the current delta.

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

1 files changed, 54 insertions, 0 deletions

diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index bea7f3b..bfce085 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -43,6 +43,9 @@ enum stat_type {
 	BLKIO_STAT_SECTORS,
 #ifdef CONFIG_DEBUG_BLK_CGROUP
 	BLKIO_STAT_AVG_QUEUE_SIZE,
+	BLKIO_STAT_IDLE_TIME,
+	BLKIO_STAT_EMPTY_TIME,
+	BLKIO_STAT_GROUP_WAIT_TIME,
 	BLKIO_STAT_DEQUEUE
 #endif
 };
@@ -55,6 +58,13 @@ enum stat_sub_type {
 	BLKIO_STAT_TOTAL
 };
 
+/* blkg state flags */
+enum blkg_state_flags {
+	BLKG_waiting = 0,
+	BLKG_idling,
+	BLKG_empty,
+};
+
 struct blkio_cgroup {
 	struct cgroup_subsys_state css;
 	unsigned int weight;
@@ -74,6 +84,21 @@ struct blkio_group_stats {
 	uint64_t avg_queue_size_samples;
 	/* How many times this group has been removed from service tree */
 	unsigned long dequeue;
+
+	/* Total time spent waiting for it to be assigned a timeslice. */
+	uint64_t group_wait_time;
+	uint64_t start_group_wait_time;
+
+	/* Time spent idling for this blkio_group */
+	uint64_t idle_time;
+	uint64_t start_idle_time;
+	/*
+	 * Total time when we have requests queued and do not contain the
+	 * current active queue.
+	 */
+	uint64_t empty_time;
+	uint64_t start_empty_time;
+	uint16_t flags;
 #endif
 };
 
@@ -137,12 +162,41 @@ static inline char *blkg_path(struct blkio_group *blkg)
 void blkiocg_update_set_active_queue_stats(struct blkio_group *blkg);
 void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
 				unsigned long dequeue);
+void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg);
+void blkiocg_update_idle_time_stats(struct blkio_group *blkg);
+void blkiocg_set_start_empty_time(struct blkio_group *blkg, bool ignore);
+
+#define BLKG_FLAG_FNS(name)						\
+static inline void blkio_mark_blkg_##name(				\
+		struct blkio_group_stats *stats)			\
+{									\
+	stats->flags |= (1 << BLKG_##name);				\
+}									\
+static inline void blkio_clear_blkg_##name(				\
+		struct blkio_group_stats *stats)			\
+{									\
+	stats->flags &= ~(1 << BLKG_##name);				\
+}									\
+static inline int blkio_blkg_##name(struct blkio_group_stats *stats)	\
+{									\
+	return (stats->flags & (1 << BLKG_##name)) != 0;		\
+}									\
+
+BLKG_FLAG_FNS(waiting)
+BLKG_FLAG_FNS(idling)
+BLKG_FLAG_FNS(empty)
+#undef BLKG_FLAG_FNS
 #else
 static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }
 static inline void blkiocg_update_set_active_queue_stats(
 						struct blkio_group *blkg) {}
 static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
 						unsigned long dequeue) {}
+static inline void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg)
+{}
+static inline void blkiocg_update_idle_time_stats(struct blkio_group *blkg) {}
+static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg,
+						bool ignore) {}
 #endif
 
 #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)