linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Matthew Wilcox <willy@infradead.org>
To: Christoph Hellwig <hch@infradead.org>
Cc: Joe Damato <jdamato@fastly.com>,
	netdev@vger.kernel.org, mkarsten@uwaterloo.ca,
	amritha.nambiar@intel.com, sridhar.samudrala@intel.com,
	sdf@fomichev.me, Alexander Viro <viro@zeniv.linux.org.uk>,
	Christian Brauner <brauner@kernel.org>, Jan Kara <jack@suse.cz>,
	"open list:FILESYSTEMS (VFS and infrastructure)"
	<linux-fsdevel@vger.kernel.org>,
	open list <linux-kernel@vger.kernel.org>
Subject: Re: [RFC net-next 4/5] eventpoll: Trigger napi_busy_loop, if prefer_busy_poll is set
Date: Mon, 12 Aug 2024 17:17:38 +0100	[thread overview]
Message-ID: <Zro1onXfGkKoIRbY@casper.infradead.org> (raw)
In-Reply-To: <ZroL54bAzdR-Vr4d@infradead.org>

On Mon, Aug 12, 2024 at 06:19:35AM -0700, Christoph Hellwig wrote:
> On Mon, Aug 12, 2024 at 12:57:07PM +0000, Joe Damato wrote:
> > From: Martin Karsten <mkarsten@uwaterloo.ca>
> > 
> > Setting prefer_busy_poll now leads to an effectively nonblocking
> > iteration though napi_busy_loop, even when busy_poll_usecs is 0.
> 
> Hardcoding calls to the networking code from VFS code seems like
> a bad idea.   Not that I disagree with the concept of disabling
> interrupts during busy polling, but this needs a proper abstraction
> through file_operations.

I don't understand what's going on with this patch set.  Is it just
working around badly designed hardware?  NVMe is specified in a way that
lets it be completely interruptless if the host is keeping up with the
incoming completions from the device (ie the device will interrupt if a
completion has been posted for N microseconds without being acknowledged).
I assumed this was how network devices worked too, but I didn't check.

  reply	other threads:[~2024-08-12 16:17 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-08-12 12:57 [RFC net-next 0/5] Suspend IRQs during preferred busy poll Joe Damato
2024-08-12 12:57 ` [RFC net-next 4/5] eventpoll: Trigger napi_busy_loop, if prefer_busy_poll is set Joe Damato
2024-08-12 13:19   ` Christoph Hellwig
2024-08-12 16:17     ` Matthew Wilcox [this message]
2024-08-12 17:49       ` Joe Damato
2024-08-12 17:46     ` Joe Damato
2024-08-12 12:57 ` [RFC net-next 5/5] eventpoll: Control irq suspension for prefer_busy_poll Joe Damato
2024-08-12 20:20   ` Stanislav Fomichev
2024-08-12 21:47     ` Martin Karsten
2024-08-12 20:19 ` [RFC net-next 0/5] Suspend IRQs during preferred busy poll Stanislav Fomichev
2024-08-12 21:46   ` Martin Karsten
2024-08-12 23:03     ` Stanislav Fomichev
2024-08-13  0:04       ` Martin Karsten
2024-08-13  1:54         ` Stanislav Fomichev
2024-08-13  2:35           ` Martin Karsten
2024-08-13  4:07             ` Stanislav Fomichev
2024-08-13 13:18               ` Martin Karsten
2024-08-14  3:16                 ` Willem de Bruijn
2024-08-14 14:19                   ` Joe Damato
2024-08-14 15:08                     ` Willem de Bruijn
2024-08-14 15:46                       ` Joe Damato
2024-08-14 19:53                 ` Samiullah Khawaja
2024-08-14 20:42                   ` Martin Karsten
2024-08-16 14:27                     ` Willem de Bruijn
2024-08-16 14:59                       ` Willem de Bruijn
2024-08-16 15:25                         ` Joe Damato
2024-08-16 17:01                           ` Willem de Bruijn
2024-08-16 20:03                             ` Martin Karsten
2024-08-16 20:58                               ` Willem de Bruijn
2024-08-17 18:15                                 ` Martin Karsten
2024-08-18 12:55                                   ` Willem de Bruijn
2024-08-18 14:51                                     ` Martin Karsten
2024-08-20  2:36                                       ` Jakub Kicinski
2024-08-20 14:28                                         ` Martin Karsten
2024-08-17 10:00                             ` Joe Damato
2024-08-14  0:10     ` Jakub Kicinski
2024-08-14  1:14       ` Martin Karsten
2024-08-20  2:07         ` Jakub Kicinski
2024-08-20 14:27           ` Martin Karsten

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=Zro1onXfGkKoIRbY@casper.infradead.org \
    --to=willy@infradead.org \
    --cc=amritha.nambiar@intel.com \
    --cc=brauner@kernel.org \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=jdamato@fastly.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mkarsten@uwaterloo.ca \
    --cc=netdev@vger.kernel.org \
    --cc=sdf@fomichev.me \
    --cc=sridhar.samudrala@intel.com \
    --cc=viro@zeniv.linux.org.uk \
    /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;
as well as URLs for NNTP newsgroup(s).