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>

5 files changed, 198 insertions, 130 deletions

diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index 630879cd9a42..ed04fe9cce1a 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/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
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 9af7257f429c..6797df508821 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -18,6 +18,8 @@
 #include <linux/blkdev.h>
 #include "blk-cgroup.h"
 
+#define MAX_KEY_LEN 100
+
 static DEFINE_SPINLOCK(blkio_list_lock);
 static LIST_HEAD(blkio_list);
 
@@ -56,24 +58,27 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 }
 EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
 
+void blkio_group_init(struct blkio_group *blkg)
+{
+        spin_lock_init(&blkg->stats_lock);
+}
+EXPORT_SYMBOL_GPL(blkio_group_init);
+
 /*
  * 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)
+static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction,
+                                bool sync)
 {
-        if (flags & REQ_RW)
-                stat[IO_WRITE] += add;
+        if (direction)
+                stat[BLKIO_STAT_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;
+                stat[BLKIO_STAT_READ] += add;
+        if (sync)
+                stat[BLKIO_STAT_SYNC] += add;
         else
-                stat[IO_ASYNC] += add;
+                stat[BLKIO_STAT_ASYNC] += add;
 }
 
 void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time)
@@ -86,23 +91,25 @@ 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)
+void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
+                                uint64_t bytes, bool direction, bool sync)
 {
         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);
+        stats->sectors += bytes >> 9;
+        blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICED], 1, direction,
+                        sync);
+        blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_BYTES], bytes,
+                        direction, sync);
         spin_unlock_irqrestore(&blkg->stats_lock, flags);
 }
+EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats);
 
-void blkiocg_update_request_completion_stats(struct blkio_group *blkg,
-                                                struct request *rq)
+void blkiocg_update_completion_stats(struct blkio_group *blkg,
+        uint64_t start_time, uint64_t io_start_time, bool direction, bool sync)
 {
         struct blkio_group_stats *stats;
         unsigned long flags;
@@ -110,16 +117,15 @@ void blkiocg_update_request_completion_stats(struct blkio_group *blkg,
 
         spin_lock_irqsave(&blkg->stats_lock, flags);