From: Tang Yizhou Now when I/O is submitted to a partition, the per-CPU in_flight[] counter is incremented only on the partition's block_device, not on the underlying whole disk. This leads to a problem which can be shown by a fio test: lsblk NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINTS mydev 252:1 0 20G 0 disk └─mydev1 259:0 0 10G 0 part iostat -xp 1 Device r/s rkB/s ... aqu-sz %util mydev 128153.00 512612.00 ... 13.22 72.20 mydev1 128154.00 512616.00 ... 13.22 100.00 %util is different between mydev and mydev1, which is unexpected. This is the cumulative effect of a series of patches. The root cause is commit e016b78201a2 ("block: return just one value from part_in_flight"), which deleted the branch in part_in_flight() that aggregated the whole-disk in_flight count on top of the partition's. Then the second commit is commit 10ec5e86f9b8 ("block: merge part_{inc,dev}_in_flight into their only callers"), which folded the whole-disk in_flight accounting into generic_start_io_acct() and generic_end_io_acct(). Those two helpers were then removed by commit e722fff238bb ("block: remove generic_{start,end}_io_acct"), and from that point on the whole disk's in_flight is no longer accounted at all. In update_io_ticks(), if calling bdev_count_inflight() finds that the inflight value of the whole device is 0, the accumulation of io_ticks will be skipped, causing the reported util% value to be underestimated. Fix it by restoring the whole-disk in_flight accounting. Fixes: e016b78201a2 ("block: return just one value from part_in_flight") Suggested-by: Leon Hwang Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Tang Yizhou Reviewed-by: Christoph Hellwig --- v2: Update commit message. v3: Take Christoph's advice and factor the common code into two helpers. v4: Remove my redundant new line in blk.h. Add Christoph's Reviewed-by tag. v5: Remove the changelog from the commit message. v6: Accept Keith's suggestion and fix the bug in bdev_end_io_acct(). v7: Address the review feedback from Claude Opus 4.7 and update blk_account_io_merge_request(). block/blk-core.c | 4 ++-- block/blk-merge.c | 3 +-- block/blk-mq.c | 5 ++--- block/blk.h | 21 +++++++++++++++++++++ 4 files changed, 26 insertions(+), 7 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 17450058ea6d..cee4e4a37503 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1042,7 +1042,7 @@ unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, { part_stat_lock(); update_io_ticks(bdev, start_time, false); - part_stat_local_inc(bdev, in_flight[op_is_write(op)]); + bdev_inc_in_flight(bdev, op); part_stat_unlock(); return start_time; @@ -1073,7 +1073,7 @@ void bdev_end_io_acct(struct block_device *bdev, enum req_op op, 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)]); + bdev_dec_in_flight(bdev, op); part_stat_unlock(); } EXPORT_SYMBOL(bdev_end_io_acct); diff --git a/block/blk-merge.c b/block/blk-merge.c index fcf09325b22e..62d68a72f569 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -723,8 +723,7 @@ static void blk_account_io_merge_request(struct request *req) if (req->rq_flags & RQF_IO_STAT) { 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))]); + bdev_dec_in_flight(req->part, req_op(req)); part_stat_unlock(); } } diff --git a/block/blk-mq.c b/block/blk-mq.c index d0c37daf568f..6bdfe642bd93 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1082,8 +1082,7 @@ 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))]); + bdev_dec_in_flight(req->part, req_op(req)); part_stat_unlock(); } } @@ -1143,7 +1142,7 @@ 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))]); + bdev_inc_in_flight(req->part, req_op(req)); part_stat_unlock(); } diff --git a/block/blk.h b/block/blk.h index b998a7761faf..11245a494c43 100644 --- a/block/blk.h +++ b/block/blk.h @@ -4,6 +4,7 @@ #include #include +#include #include #include /* for max_pfn/max_low_pfn */ #include @@ -485,6 +486,26 @@ static inline void req_set_nomerge(struct request_queue *q, struct request *req) q->last_merge = NULL; } +static inline void bdev_inc_in_flight(struct block_device *bdev, + enum req_op op) +{ + bool rw = op_is_write(op); + + part_stat_local_inc(bdev, in_flight[rw]); + if (bdev_is_partition(bdev)) + part_stat_local_inc(bdev_whole(bdev), in_flight[rw]); +} + +static inline void bdev_dec_in_flight(struct block_device *bdev, + enum req_op op) +{ + bool rw = op_is_write(op); + + part_stat_local_dec(bdev, in_flight[rw]); + if (bdev_is_partition(bdev)) + part_stat_local_dec(bdev_whole(bdev), in_flight[rw]); +} + /* * Internal io_context interface */ -- 2.43.0