block: support to account io_ticks precisely

[ Upstream commit 99dc422335 ]

Currently, io_ticks is accounted based on sampling, specifically
update_io_ticks() will always account io_ticks by 1 jiffies from
bdev_start_io_acct()/blk_account_io_start(), and the result can be
inaccurate, for example(HZ is 250):

Test script:
fio -filename=/dev/sda -bs=4k -rw=write -direct=1 -name=test -thinktime=4ms

Test result: util is about 90%, while the disk is really idle.

This behaviour is introduced by commit 5b18b5a737 ("block: delete
part_round_stats and switch to less precise counting"), however, there
was a key point that is missed that this patch also improve performance
a lot:

Before the commit:
part_round_stats:
  if (part->stamp != now)
   stats |= 1;

  part_in_flight()
  -> there can be lots of task here in 1 jiffies.
  part_round_stats_single()
   __part_stat_add()
  part->stamp = now;

After the commit:
update_io_ticks:
  stamp = part->bd_stamp;
  if (time_after(now, stamp))
   if (try_cmpxchg())
    __part_stat_add()
    -> only one task can reach here in 1 jiffies.

Hence in order to account io_ticks precisely, we only need to know if
there are IO inflight at most once in one jiffies. Noted that for
rq-based device, iterating tags should not be used here because
'tags->lock' is grabbed in blk_mq_find_and_get_req(), hence
part_stat_lock_inc/dec() and part_in_flight() is used to trace inflight.
The additional overhead is quite little:

 - per cpu add/dec for each IO for rq-based device;
 - per cpu sum for each jiffies;

And it's verified by null-blk that there are no performance degration
under heavy IO pressure.

Fixes: 5b18b5a737 ("block: delete part_round_stats and switch to less precise counting")
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240509123717.3223892-2-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>

block/blk-core.c

@@ -950,10 +950,11 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end)
 	unsigned long stamp;
 again:
 	stamp = READ_ONCE(part->bd_stamp);
-	if (unlikely(time_after(now, stamp))) {
-		if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now)))
-			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
-	}
+	if (unlikely(time_after(now, stamp)) &&
+	    likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) &&
+	    (end || part_in_flight(part)))
+		__part_stat_add(part, io_ticks, now - stamp);
+
 	if (part->bd_partno) {
 		part = bdev_whole(part);
 		goto again;

block/blk-merge.c

@@ -783,6 +783,8 @@ static void blk_account_io_merge_request(struct request *req)
 	if (blk_do_io_stat(req)) {
 		part_stat_lock();
 		part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
+		part_stat_local_dec(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }

block/blk-mq.c

@@ -994,6 +994,8 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 		update_io_ticks(req->part, jiffies, true);
 		part_stat_inc(req->part, ios[sgrp]);
 		part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
+		part_stat_local_dec(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }
@@ -1016,6 +1018,8 @@ static inline void blk_account_io_start(struct request *req)
 
 		part_stat_lock();
 		update_io_ticks(req->part, jiffies, false);
+		part_stat_local_inc(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }

block/blk.h

@@ -344,6 +344,7 @@ static inline bool blk_do_io_stat(struct request *rq)
 }
 
 void update_io_ticks(struct block_device *part, unsigned long now, bool end);
+unsigned int part_in_flight(struct block_device *part);
 
 static inline void req_set_nomerge(struct request_queue *q, struct request *req)
 {

block/genhd.c

@@ -118,7 +118,7 @@ static void part_stat_read_all(struct block_device *part,
 	}
 }
 
-static unsigned int part_in_flight(struct block_device *part)
+unsigned int part_in_flight(struct block_device *part)
 {
 	unsigned int inflight = 0;
 	int cpu;