From: Ming Lei <ming.lei@redhat.com>
To: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>,
"Martin K. Petersen" <martin.petersen@oracle.com>,
linux-block@vger.kernel.org, linux-scsi@vger.kernel.org
Subject: Re: [PATCH 01/12] blk-mq: do not include passthrough requests in I/O accounting
Date: Wed, 23 Feb 2022 15:02:08 +0800 [thread overview]
Message-ID: <YhXb8CrfBqQZhYyZ@T590> (raw)
In-Reply-To: <20220223064226.GA31307@lst.de>
On Wed, Feb 23, 2022 at 07:42:26AM +0100, Christoph Hellwig wrote:
> On Wed, Feb 23, 2022 at 10:08:20AM +0800, Ming Lei wrote:
> > > - return (rq->rq_flags & RQF_IO_STAT) && rq->q->disk;
> > > + return (rq->rq_flags & RQF_IO_STAT) && !blk_rq_is_passthrough(rq);
> >
> > I guess this way may cause regression for workloads with lots of userspace IO
> > from user viewpoint?
>
> I'd say it fixes it as the accounting right now is completely bogus.
There are small amount of in-kernel passthrough requests(admin, or driver
private) which shouldn't be accounted, but passthrough RW IO requests from
userspace can be lots of, and user may rely on diskstat to account them.
Thanks,
Ming
next prev parent reply other threads:[~2022-02-23 7:02 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-22 14:14 move more work to disk_release Christoph Hellwig
2022-02-22 14:14 ` [PATCH 01/12] blk-mq: do not include passthrough requests in I/O accounting Christoph Hellwig
2022-02-23 2:08 ` Ming Lei
2022-02-23 6:42 ` Christoph Hellwig
2022-02-23 7:02 ` Ming Lei [this message]
2022-02-23 7:36 ` Christoph Hellwig
2022-02-22 14:14 ` [PATCH 02/12] blk-mq: handle already freed tags gracefully in blk_mq_free_rqs Christoph Hellwig
2022-02-22 14:14 ` [PATCH 03/12] scsi: don't use disk->private_data to find the scsi_driver Christoph Hellwig
2022-02-22 14:14 ` [PATCH 04/12] sd: make use of ->free_disk to simplify refcounting Christoph Hellwig
2022-02-22 14:14 ` [PATCH 05/12] sd: remove the extra sdev_gendev reference Christoph Hellwig
2022-02-22 14:14 ` [PATCH 06/12] sr: implement ->free_disk Christoph Hellwig
2022-02-22 14:14 ` [PATCH 07/12] block: move blkcg initialization/destroy into disk allocation/release handler Christoph Hellwig
2022-02-22 14:14 ` [PATCH 08/12] block: don't remove hctx debugfs dir from blk_mq_exit_queue Christoph Hellwig
2022-02-23 4:06 ` Bart Van Assche
2022-02-23 6:41 ` Ming Lei
2022-02-22 14:14 ` [PATCH 09/12] block: move q_usage_counter release into blk_queue_release Christoph Hellwig
2022-02-22 14:14 ` [PATCH 10/12] block: move blk_exit_queue into disk_release Christoph Hellwig
2022-02-22 18:29 ` Bart Van Assche
2022-02-23 6:56 ` Ming Lei
2022-02-23 20:04 ` Bart Van Assche
2022-02-24 7:25 ` Christoph Hellwig
2022-02-25 1:26 ` Ming Lei
2022-02-22 14:14 ` [PATCH 11/12] block: do more work in elevator_exit Christoph Hellwig
2022-02-22 14:14 ` [PATCH 12/12] block: move rq_qos_exit() into disk_release() Christoph Hellwig
2022-02-26 4:46 ` move more work to disk_release Bart Van Assche
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=YhXb8CrfBqQZhYyZ@T590 \
--to=ming.lei@redhat.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=linux-block@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox