Commit 5f275713 authored by Yu Kuai's avatar Yu Kuai Committed by Jens Axboe
Browse files

block: count 'ios' and 'sectors' when io is done for bio-based device



While using iostat for raid, I observed very strange 'await'
occasionally, and turns out it's due to that 'ios' and 'sectors' is
counted in bdev_start_io_acct(), while 'nsecs' is counted in
bdev_end_io_acct(). I'm not sure why they are ccounted like that
but I think this behaviour is obviously wrong because user will get
wrong disk stats.

Fix the problem by counting 'ios' and 'sectors' when io is done, like
what rq-based device does.

Fixes: 394ffa50 ("blk: introduce generic io stat accounting help function")
Signed-off-by: default avatarYu Kuai <yukuai3@huawei.com>
Reviewed-by: default avatarChristoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20230223091226.1135678-1-yukuai1@huaweicloud.com


Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent 60303631
Loading
Loading
Loading
Loading
+6 −10
Original line number Diff line number Diff line
@@ -959,16 +959,11 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end)
	}
}

unsigned long bdev_start_io_acct(struct block_device *bdev,
				 unsigned int sectors, enum req_op op,
unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op,
				 unsigned long start_time)
{
	const int sgrp = op_stat_group(op);

	part_stat_lock();
	update_io_ticks(bdev, start_time, false);
	part_stat_inc(bdev, ios[sgrp]);
	part_stat_add(bdev, sectors[sgrp], sectors);
	part_stat_local_inc(bdev, in_flight[op_is_write(op)]);
	part_stat_unlock();

@@ -984,13 +979,12 @@ EXPORT_SYMBOL(bdev_start_io_acct);
 */
unsigned long bio_start_io_acct(struct bio *bio)
{
	return bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio),
				  bio_op(bio), jiffies);
	return bdev_start_io_acct(bio->bi_bdev, bio_op(bio), jiffies);
}
EXPORT_SYMBOL_GPL(bio_start_io_acct);

void bdev_end_io_acct(struct block_device *bdev, enum req_op op,
		      unsigned long start_time)
		      unsigned int sectors, unsigned long start_time)
{
	const int sgrp = op_stat_group(op);
	unsigned long now = READ_ONCE(jiffies);
@@ -998,6 +992,8 @@ void bdev_end_io_acct(struct block_device *bdev, enum req_op op,

	part_stat_lock();
	update_io_ticks(bdev, now, true);
	part_stat_inc(bdev, ios[sgrp]);
	part_stat_add(bdev, sectors[sgrp], sectors);
	part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration));
	part_stat_local_dec(bdev, in_flight[op_is_write(op)]);
	part_stat_unlock();
@@ -1007,7 +1003,7 @@ EXPORT_SYMBOL(bdev_end_io_acct);
void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
			      struct block_device *orig_bdev)
{
	bdev_end_io_acct(orig_bdev, bio_op(bio), start_time);
	bdev_end_io_acct(orig_bdev, bio_op(bio), bio_sectors(bio), start_time);
}
EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped);

+3 −3
Original line number Diff line number Diff line
@@ -512,10 +512,10 @@ static void dm_io_acct(struct dm_io *io, bool end)
		sectors = io->sectors;

	if (!end)
		bdev_start_io_acct(bio->bi_bdev, sectors, bio_op(bio),
				   start_time);
		bdev_start_io_acct(bio->bi_bdev, bio_op(bio), start_time);
	else
		bdev_end_io_acct(bio->bi_bdev, bio_op(bio), start_time);
		bdev_end_io_acct(bio->bi_bdev, bio_op(bio), sectors,
				 start_time);

	if (static_branch_unlikely(&stats_enabled) &&
	    unlikely(dm_stats_used(&md->stats))) {
+4 −4
Original line number Diff line number Diff line
@@ -123,9 +123,8 @@ void nvme_mpath_start_request(struct request *rq)
		return;

	nvme_req(rq)->flags |= NVME_MPATH_IO_STATS;
	nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0,
					blk_rq_bytes(rq) >> SECTOR_SHIFT,
					req_op(rq), jiffies);
	nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, req_op(rq),
						      jiffies);
}
EXPORT_SYMBOL_GPL(nvme_mpath_start_request);

@@ -136,6 +135,7 @@ void nvme_mpath_end_request(struct request *rq)
	if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS))
		return;
	bdev_end_io_acct(ns->head->disk->part0, req_op(rq),
			 blk_rq_bytes(rq) >> SECTOR_SHIFT,
			 nvme_req(rq)->start_time);
}

+2 −3
Original line number Diff line number Diff line
@@ -1446,11 +1446,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter)
		wake_up_process(waiter);
}

unsigned long bdev_start_io_acct(struct block_device *bdev,
				 unsigned int sectors, enum req_op op,
unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op,
				 unsigned long start_time);
void bdev_end_io_acct(struct block_device *bdev, enum req_op op,
		unsigned long start_time);
		      unsigned int sectors, unsigned long start_time);

unsigned long bio_start_io_acct(struct bio *bio);
void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,