Message ID | 20220530064059.1120058-1-haisuwang@tencent.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | blk-mq: do not update io_ticks with passthrough requests | expand |
Looks good:
Reviewed-by: Christoph Hellwig <hch@lst.de>
On Mon, 30 May 2022 14:40:59 +0800, iamhswang@gmail.com wrote: > From: Haisu Wang <haisuwang@tencent.com> > > Flush or passthrough requests are not accounted as normal IO in completion. > To reflect iostat for slow IO, io_ticks is updated when stat show called > based on inflight numbers. > It may cause inconsistent io_ticks calculation result. > > [...] Applied, thanks! [1/1] blk-mq: do not update io_ticks with passthrough requests commit: b81c14ca14b631aa1abae32fb5ae75b5e9251012 Best regards,
diff --git a/block/blk-mq.c b/block/blk-mq.c index ae116b755648..3912cae42da3 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -133,7 +133,8 @@ static bool blk_mq_check_inflight(struct request *rq, void *priv, { struct mq_inflight *mi = priv; - if ((!mi->part->bd_partno || rq->part == mi->part) && + if (rq->part && blk_do_io_stat(rq) && + (!mi->part->bd_partno || rq->part == mi->part) && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) mi->inflight[rq_data_dir(rq)]++;