public inbox for linux-nvme@lists.infradead.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@infradead.org>
To: Keith Busch <kbusch@kernel.org>
Cc: "Ewan D. Milne" <emilne@redhat.com>,
	linux-nvme@lists.infradead.org, tsong@purestorage.com
Subject: Re: [PATCH 2/3] nvme: multipath: only update ctrl->nr_active when using queue-depth iopolicy
Date: Wed, 8 Nov 2023 00:09:33 -0800	[thread overview]
Message-ID: <ZUtCPeDYRaGszXnE@infradead.org> (raw)
In-Reply-To: <ZUqx7JoyPG1QxYeY@kbusch-mbp.dhcp.thefacebook.com>

On Tue, Nov 07, 2023 at 02:53:48PM -0700, Keith Busch wrote:
> On Tue, Nov 07, 2023 at 04:23:30PM -0500, Ewan D. Milne wrote:
> > The atomic updates of ctrl->nr_active are unnecessary when using
> > numa or round-robin iopolicy, so avoid that cost on a per-request basis.
> > Clear nr_active when changing iopolicy and do not decrement below zero.
> > (This handles changing the iopolicy while requests are in flight.)
> 
> Oh, here's restricting it to that policy. Any reason not to fold it in
> the first one?

It should, and I agree with all the other comments.

But I'm also pretty deeply unhappy with the whole thing.  This is a
controller-wise atomic taken for every I/O.  How slow are the subsystems
people want to use it for?  And is a global max active really the
right measure, or would e a per-cpu, or at least batched per-cpu as
used by the percpu counters by a better option?



  parent reply	other threads:[~2023-11-08  8:09 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-07 21:23 [PATCH 1/3] nvme: multipath: Implemented new iopolicy "queue-depth" Ewan D. Milne
2023-11-07 21:23 ` [PATCH 2/3] nvme: multipath: only update ctrl->nr_active when using queue-depth iopolicy Ewan D. Milne
2023-11-07 21:42   ` Chaitanya Kulkarni
2023-11-07 21:53   ` Keith Busch
2023-11-07 22:03     ` Ewan Milne
2023-11-08  8:09     ` Christoph Hellwig [this message]
2023-11-08 16:58       ` John Meneghini
2023-11-08 18:38       ` Ewan Milne
2023-11-10  1:18   ` Uday Shankar
2023-11-13 21:16     ` Ewan Milne
2023-11-07 21:23 ` [PATCH 3/3] nvme: multipath: Invalidate current_path when changing iopolicy Ewan D. Milne
2023-11-08  8:10   ` Christoph Hellwig
2023-11-07 21:40 ` [PATCH 1/3] nvme: multipath: Implemented new iopolicy "queue-depth" Chaitanya Kulkarni
2023-11-07 21:46 ` Chaitanya Kulkarni
2023-11-07 21:56   ` Ewan Milne
2023-11-07 23:32     ` John Meneghini
2023-11-08  4:14     ` Chaitanya Kulkarni
2023-11-07 21:49 ` Keith Busch
2023-11-07 22:01   ` Ewan Milne
2023-11-07 22:14     ` Keith Busch
2024-05-09 20:29 ` [PATCH v2 0/3] nvme: queue-depth multipath iopolicy John Meneghini
2024-05-09 20:29 ` [PATCH v2 1/3] nvme: multipath: Implemented new iopolicy "queue-depth" John Meneghini
2024-05-09 20:29 ` [PATCH v2 2/3] nvme: multipath: only update ctrl->nr_active when using queue-depth iopolicy John Meneghini
2024-05-09 20:29 ` [PATCH v2 3/3] nvme: multipath: Invalidate current_path when changing iopolicy John Meneghini

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=ZUtCPeDYRaGszXnE@infradead.org \
    --to=hch@infradead.org \
    --cc=emilne@redhat.com \
    --cc=kbusch@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=tsong@purestorage.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