Patch "block: count 'ios' and 'sectors' when io is done for bio-based device" has been added to the 6.2-stable tree

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



This is a note to let you know that I've just added the patch titled

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

to the 6.2-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     block-count-ios-and-sectors-when-io-is-done-for-bio-.patch
and it can be found in the queue-6.2 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.



commit 45cf60482f9f7be5b749b7908a03886c0449583a
Author: Yu Kuai <yukuai3@xxxxxxxxxx>
Date:   Thu Feb 23 17:12:26 2023 +0800

    block: count 'ios' and 'sectors' when io is done for bio-based device
    
    [ Upstream commit 5f27571382ca42daa3e3d40d1b252bf18c2b61d2 ]
    
    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: 394ffa503bc4 ("blk: introduce generic io stat accounting help function")
    Signed-off-by: Yu Kuai <yukuai3@xxxxxxxxxx>
    Reviewed-by: Christoph Hellwig <hch@xxxxxx>
    Link: https://lore.kernel.org/r/20230223091226.1135678-1-yukuai1@xxxxxxxxxxxxxxx
    Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
    Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

diff --git a/block/blk-core.c b/block/blk-core.c
index 5a0049215ee72..597293151cd11 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -946,16 +946,11 @@ 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();
 
@@ -971,13 +966,12 @@ 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);
@@ -985,6 +979,8 @@ 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();
@@ -994,7 +990,7 @@ 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);
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e290d6d970474..03ef03e10618d 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -2108,9 +2108,9 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_offset = 0;
 
 	start_time = bdev_start_io_acct(bdev->bd_disk->part0,
-			SECTORS_PER_PAGE, op, jiffies);
+			op, jiffies);
 	ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL);
-	bdev_end_io_acct(bdev->bd_disk->part0, op, start_time);
+	bdev_end_io_acct(bdev->bd_disk->part0, op, SECTORS_PER_PAGE, start_time);
 out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 605662935ce91..fdcf42554e2a9 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -510,10 +510,10 @@ 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))) {
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index fc39d01e7b63b..9171452e2f6d4 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -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);
 
@@ -136,7 +135,8 @@ 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),
-		nvme_req(rq)->start_time);
+			 blk_rq_bytes(rq) >> SECTOR_SHIFT,
+			 nvme_req(rq)->start_time);
 }
 
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 43d4e073b1115..c3e066242941d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1434,11 +1434,10 @@ 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,

--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://listman.redhat.com/mailman/listinfo/dm-devel




[Index of Archives]     [DM Crypt]     [Fedora Desktop]     [ATA RAID]     [Fedora Marketing]     [Fedora Packaging]     [Fedora SELinux]     [Yosemite Discussion]     [KDE Users]     [Fedora Docs]

  Powered by Linux