block: Seperate read and write statistics of in_flight requests v2

Commit a9327cac440be4d8333bba975cbbf76045096275 added seperate read
and write statistics of in_flight requests. And exported the number
of read and write requests in progress seperately through sysfs.

But  Corrado Zoccolo <czoccolo@gmail.com> reported getting strange
output from "iostat -kx 2". Global values for service time and
utilization were garbage. For interval values, utilization was always
100%, and service time is higher than normal.

So this was reverted by commit 0f78ab9899e9d6acb09d5465def618704255963b

The problem was in part_round_stats_single(), I missed the following:
        if (now == part->stamp)
                return;

-       if (part->in_flight) {
+       if (part_in_flight(part)) {
                __part_stat_add(cpu, part, time_in_queue,
                                part_in_flight(part) * (now - part->stamp));
                __part_stat_add(cpu, part, io_ticks, (now - part->stamp));

With this chunk included, the reported regression gets fixed.

Signed-off-by: Nikanth Karthikesan <knikanth@suse.de>

--
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

1 files changed, 10 insertions, 6 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 23e76fe0d359..376f1ab48a24 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -130,7 +130,7 @@ struct mapped_device {
         /*
          * A list of ios that arrived while we were suspended.
          */
-        atomic_t pending;
+        atomic_t pending[2];
         wait_queue_head_t wait;
         struct work_struct work;
         struct bio_list deferred;
@@ -453,13 +453,14 @@ static void start_io_acct(struct dm_io *io)
 {
         struct mapped_device *md = io->md;
         int cpu;
+        int rw = bio_data_dir(io->bio);
 
         io->start_time = jiffies;
 
         cpu = part_stat_lock();
         part_round_stats(cpu, &dm_disk(md)->part0);
         part_stat_unlock();
-        dm_disk(md)->part0.in_flight = atomic_inc_return(&md->pending);
+        dm_disk(md)->part0.in_flight[rw] = atomic_inc_return(&md->pending[rw]);
 }
 
 static void end_io_acct(struct dm_io *io)
@@ -479,8 +480,9 @@ static void end_io_acct(struct dm_io *io)
          * After this is decremented the bio must not be touched if it is
          * a barrier.
          */
-        dm_disk(md)->part0.in_flight = pending =
-                atomic_dec_return(&md->pending);
+        dm_disk(md)->part0.in_flight[rw] = pending =
+                atomic_dec_return(&md->pending[rw]);
+        pending += atomic_read(&md->pending[rw^0x1]);
 
         /* nudge anyone waiting on suspend queue */
         if (!pending)
@@ -1785,7 +1787,8 @@ static struct mapped_device *alloc_dev(int minor)
         if (!md->disk)
                 goto bad_disk;
 
-        atomic_set(&md->pending, 0);
+        atomic_set(&md->pending[0], 0);
+        atomic_set(&md->pending[1], 0);
         init_waitqueue_head(&md->wait);
         INIT_WORK(&md->work, dm_wq_work);
         init_waitqueue_head(&md->eventq);
@@ -2088,7 +2091,8 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible)
                                 break;
                         }
                         spin_unlock_irqrestore(q->queue_lock, flags);
-                } else if (!atomic_read(&md->pending))
+                } else if (!atomic_read(&md->pending[0]) &&
+                                        !atomic_read(&md->pending[1]))
                         break;
 
                 if (interruptible == TASK_INTERRUPTIBLE &&