From: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
To: Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
Cc: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>,
Jens Axboe <axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>,
Josef Bacik <josef-DigfWCa+lFGyeJad7bwFQA@public.gmane.org>,
linux-block-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: switch blk-cgroup to work on gendisk
Date: Thu, 19 Jan 2023 18:05:26 +0100 [thread overview]
Message-ID: <20230119170526.GA5050@lst.de> (raw)
In-Reply-To: <Y8l34/qeHPLV4rKJ-NiLfg/pYEd1N0TnZuCh8vA@public.gmane.org>
On Thu, Jan 19, 2023 at 07:03:31AM -1000, Tejun Heo wrote:
> On Tue, Jan 17, 2023 at 09:12:42AM +0100, Christoph Hellwig wrote:
> > blk-cgroup works on only on live disks and "file system" I/O from bios.
> > This all the information should be in the gendisk, and not the
> > request_queue that also exists for pure passthrough request based
> > devices.
>
> Can't blk-throttle be used w/ bio based ones tho? I always thought that was
> the reason why we didn't move it into rq-qos framework.
Yes, it can. Not sure if my sentence was unclear, but:
- everything doing non-passthrough I/O only should be in the gendisk
- everything related to blk-mq, including infrastruture for passthrough
should remain in the request_queue
The idea that the request_queue will eventually become a blk-mq only
data structure and not exist (or just have a very leight weight stub)
for bio based drivers.
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
Josef Bacik <josef@toxicpanda.com>,
linux-block@vger.kernel.org, cgroups@vger.kernel.org
Subject: Re: switch blk-cgroup to work on gendisk
Date: Thu, 19 Jan 2023 18:05:26 +0100 [thread overview]
Message-ID: <20230119170526.GA5050@lst.de> (raw)
In-Reply-To: <Y8l34/qeHPLV4rKJ@slm.duckdns.org>
On Thu, Jan 19, 2023 at 07:03:31AM -1000, Tejun Heo wrote:
> On Tue, Jan 17, 2023 at 09:12:42AM +0100, Christoph Hellwig wrote:
> > blk-cgroup works on only on live disks and "file system" I/O from bios.
> > This all the information should be in the gendisk, and not the
> > request_queue that also exists for pure passthrough request based
> > devices.
>
> Can't blk-throttle be used w/ bio based ones tho? I always thought that was
> the reason why we didn't move it into rq-qos framework.
Yes, it can. Not sure if my sentence was unclear, but:
- everything doing non-passthrough I/O only should be in the gendisk
- everything related to blk-mq, including infrastruture for passthrough
should remain in the request_queue
The idea that the request_queue will eventually become a blk-mq only
data structure and not exist (or just have a very leight weight stub)
for bio based drivers.
next prev parent reply other threads:[~2023-01-19 17:05 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-17 8:12 switch blk-cgroup to work on gendisk Christoph Hellwig
[not found] ` <20230117081257.3089859-1-hch-jcswGhMUV9g@public.gmane.org>
2023-01-17 8:12 ` [PATCH 01/15] blk-cgroup: don't defer blkg_free to a workqueue Christoph Hellwig
2023-01-17 8:12 ` Christoph Hellwig
2023-01-20 8:54 ` Andreas Herrmann
2023-01-27 6:59 ` Hannes Reinecke
2023-01-27 6:59 ` Hannes Reinecke
[not found] ` <b4622942-67e7-969b-4439-0aea7c5bd165-l3A5Bk7waGM@public.gmane.org>
2023-01-27 7:07 ` Christoph Hellwig
2023-01-27 7:07 ` Christoph Hellwig
2023-01-27 7:43 ` Hannes Reinecke
2023-01-27 7:43 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 02/15] block: don't call blk_throtl_stat_add for non-READ/WRITE commands Christoph Hellwig
2023-01-17 8:12 ` Christoph Hellwig
[not found] ` <20230117081257.3089859-3-hch-jcswGhMUV9g@public.gmane.org>
2023-01-20 8:55 ` Andreas Herrmann
2023-01-20 8:55 ` Andreas Herrmann
2023-01-27 7:00 ` Hannes Reinecke
2023-01-27 7:00 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 04/15] blk-cgroup: pin the gendisk in struct blkcg_gq Christoph Hellwig
2023-01-17 8:12 ` Christoph Hellwig
[not found] ` <20230117081257.3089859-5-hch-jcswGhMUV9g@public.gmane.org>
2023-01-20 8:57 ` Andreas Herrmann
2023-01-20 8:57 ` Andreas Herrmann
2023-01-27 7:02 ` Hannes Reinecke
2023-01-27 7:02 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 06/15] blk-wbt: pass a gendisk to wbt_{enable,disable}_default Christoph Hellwig
2023-01-17 8:12 ` Christoph Hellwig
2023-01-20 9:10 ` Andreas Herrmann
2023-01-27 7:04 ` Hannes Reinecke
2023-01-27 7:04 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 07/15] blk-wbt: pass a gendisk to wbt_init Christoph Hellwig
2023-01-17 8:12 ` Christoph Hellwig
2023-01-20 9:53 ` Andreas Herrmann
[not found] ` <20230117081257.3089859-8-hch-jcswGhMUV9g@public.gmane.org>
2023-01-27 7:05 ` Hannes Reinecke
2023-01-27 7:05 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 08/15] blk-wbt: open code wbt_queue_depth_changed in wbt_update_limits Christoph Hellwig
2023-01-17 8:12 ` Christoph Hellwig
2023-01-20 9:21 ` Andreas Herrmann
[not found] ` <20230117081257.3089859-9-hch-jcswGhMUV9g@public.gmane.org>
2023-01-27 7:07 ` Hannes Reinecke
2023-01-27 7:07 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 11/15] blk-rq-qos: store a gendisk instead of request_queue in struct rq_qos Christoph Hellwig
2023-01-17 8:12 ` Christoph Hellwig
2023-01-20 10:19 ` Andreas Herrmann
2023-01-27 7:09 ` Hannes Reinecke
2023-01-27 7:09 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 03/15] blk-cgroup: delay blk-cgroup initialization until add_disk Christoph Hellwig
[not found] ` <20230117081257.3089859-4-hch-jcswGhMUV9g@public.gmane.org>
2023-01-20 8:56 ` Andreas Herrmann
2023-01-20 8:56 ` Andreas Herrmann
2023-01-27 7:01 ` Hannes Reinecke
2023-01-27 7:01 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 05/15] blk-cgroup: store a gendisk to throttle in struct task_struct Christoph Hellwig
2023-01-20 9:00 ` Andreas Herrmann
2023-01-27 7:03 ` Hannes Reinecke
2023-01-27 7:03 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 09/15] blk-rq-qos: make rq_qos_add and rq_qos_del more useful Christoph Hellwig
[not found] ` <20230117081257.3089859-10-hch-jcswGhMUV9g@public.gmane.org>
2023-01-20 9:57 ` Andreas Herrmann
2023-01-20 9:57 ` Andreas Herrmann
2023-01-27 7:08 ` Hannes Reinecke
2023-01-27 7:08 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 10/15] blk-rq-qos: constify rq_qos_ops Christoph Hellwig
2023-01-20 10:01 ` Andreas Herrmann
[not found] ` <20230117081257.3089859-11-hch-jcswGhMUV9g@public.gmane.org>
2023-01-27 7:08 ` Hannes Reinecke
2023-01-27 7:08 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 12/15] blk-cgroup: pass a gendisk to blkcg_{de,}activate_policy Christoph Hellwig
2023-01-20 10:26 ` Andreas Herrmann
2023-01-27 7:10 ` Hannes Reinecke
2023-01-27 7:10 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 13/15] blk-cgroup: pass a gendisk to pd_alloc_fn Christoph Hellwig
[not found] ` <20230117081257.3089859-14-hch-jcswGhMUV9g@public.gmane.org>
2023-01-20 10:37 ` Andreas Herrmann
2023-01-20 10:37 ` Andreas Herrmann
2023-01-27 7:10 ` Hannes Reinecke
2023-01-27 7:10 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 14/15] blk-cgroup: pass a gendisk to blkg_lookup Christoph Hellwig
[not found] ` <20230117081257.3089859-15-hch-jcswGhMUV9g@public.gmane.org>
2023-01-20 11:07 ` Andreas Herrmann
2023-01-20 11:07 ` Andreas Herrmann
2023-01-27 7:11 ` Hannes Reinecke
2023-01-27 7:11 ` Hannes Reinecke
2023-01-17 8:12 ` [PATCH 15/15] blk-cgroup: move the cgroup information to struct gendisk Christoph Hellwig
[not found] ` <20230117081257.3089859-16-hch-jcswGhMUV9g@public.gmane.org>
2023-01-20 11:07 ` Andreas Herrmann
2023-01-20 11:07 ` Andreas Herrmann
2023-01-27 7:12 ` Hannes Reinecke
2023-01-27 7:12 ` Hannes Reinecke
2023-01-19 17:03 ` switch blk-cgroup to work on gendisk Tejun Heo
[not found] ` <Y8l34/qeHPLV4rKJ-NiLfg/pYEd1N0TnZuCh8vA@public.gmane.org>
2023-01-19 17:05 ` Christoph Hellwig [this message]
2023-01-19 17:05 ` Christoph Hellwig
[not found] ` <20230119170526.GA5050-jcswGhMUV9g@public.gmane.org>
2023-01-19 17:13 ` Tejun Heo
2023-01-19 17:13 ` Tejun Heo
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=20230119170526.GA5050@lst.de \
--to=hch-jcswghmuv9g@public.gmane.org \
--cc=axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org \
--cc=cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=josef-DigfWCa+lFGyeJad7bwFQA@public.gmane.org \
--cc=linux-block-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.