netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jakub Kicinski <jakub.kicinski@netronome.com>
To: Robert Beckett <bob.beckett@collabora.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>,
	davem@davemloft.net, netdev@vger.kernel.org, nhorman@redhat.com,
	sassmann@redhat.com, Aaron Brown <aaron.f.brown@intel.com>
Subject: Re: [net-next 2/7] igb: add rx drop enable attribute
Date: Thu, 17 Oct 2019 08:44:33 -0700	[thread overview]
Message-ID: <20191017084433.18bce3d4@cakuba.netronome.com> (raw)
In-Reply-To: <a575469d3b2a12d24161d0c6b0a6bff538e066b6.camel@collabora.com>

On Thu, 17 Oct 2019 12:24:03 +0100, Robert Beckett wrote:
> On Wed, 2019-10-16 at 16:55 -0700, Jakub Kicinski wrote:
> > On Wed, 16 Oct 2019 16:47:06 -0700, Jeff Kirsher wrote:  
> > > From: Robert Beckett <bob.beckett@collabora.com>
> > > 
> > > To allow userland to enable or disable dropping packets when
> > > descriptor
> > > ring is exhausted, add RX_DROP_EN private flag.
> > > 
> > > This can be used in conjunction with flow control to mitigate
> > > packet storms
> > > (e.g. due to network loop or DoS) by forcing the network adapter to
> > > send
> > > pause frames whenever the ring is close to exhaustion.
> > > 
> > > By default this will maintain previous behaviour of enabling
> > > dropping of
> > > packets during ring buffer exhaustion.
> > > Some use cases prefer to not drop packets upon exhaustion, but
> > > instead
> > > use flow control to limit ingress rates and ensure no dropped
> > > packets.
> > > This is useful when the host CPU cannot keep up with packet
> > > delivery,
> > > but data delivery is more important than throughput via multiple
> > > queues.
> > > 
> > > Userland can set this flag to 0 via ethtool to disable packet
> > > dropping.
> > > 
> > > Signed-off-by: Robert Beckett <bob.beckett@collabora.com>
> > > Tested-by: Aaron Brown <aaron.f.brown@intel.com>
> > > Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>  
> > 
> > How is this different than enabling/disabling flow control..
> > 
> > ethtool -a/-A  
> 
> Enabling flow control enables the advertisement of flow control
> capabilites and allows negotiation with link partner.

More or less. If autoneg is on it controls advertised bits,
if autoneg is off it controls the enabled/disable directly.

> It does not dictate under which circumstances those pause frames will
> be emitted.

So you're saying even with pause frames on igb by default will not
backpressure all the way to the wire if host RX ring is full/fill ring
is empty?

> This patch enables an igb specific feature that can cause flow control
> to be used. The default behaviour is to drop packets if the rx ring
> buffer fills. This flag tells the driver instead to emit pause frames
> and not drop packets, which is useful when reliable data delivery is
> more important than throughput.

The feature looks like something easily understood with a standard NIC
model in mind. Therefore it should have a generic config knob not a
private flag.

  reply	other threads:[~2019-10-17 15:44 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-16 23:47 [net-next 0/7][pull request] 1GbE Intel Wired LAN Driver Updates 2019-10-16 Jeff Kirsher
2019-10-16 23:47 ` [net-next 1/7] igb/igc: Don't warn on fatal read failures when the device is removed Jeff Kirsher
2019-10-16 23:58   ` Jakub Kicinski
2019-10-16 23:47 ` [net-next 2/7] igb: add rx drop enable attribute Jeff Kirsher
2019-10-16 23:55   ` Jakub Kicinski
2019-10-17 11:24     ` Robert Beckett
2019-10-17 15:44       ` Jakub Kicinski [this message]
2019-10-17 17:04         ` Robert Beckett
2019-10-17 17:40           ` Jakub Kicinski
2019-10-16 23:47 ` [net-next 3/7] igc: Add SCTP CRC checksumming functionality Jeff Kirsher
2019-10-16 23:47 ` [net-next 4/7] e1000e: Add support for S0ix Jeff Kirsher
2019-10-17  0:02   ` Jakub Kicinski
2019-10-17  5:09     ` Neftin, Sasha
2019-10-16 23:47 ` [net-next 5/7] igc: Add set_rx_mode support Jeff Kirsher
2019-10-16 23:47 ` [net-next 6/7] igc: Add Rx checksum support Jeff Kirsher
2019-10-16 23:47 ` [net-next 7/7] igc: Clean up unused shadow_vfta pointer Jeff Kirsher

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=20191017084433.18bce3d4@cakuba.netronome.com \
    --to=jakub.kicinski@netronome.com \
    --cc=aaron.f.brown@intel.com \
    --cc=bob.beckett@collabora.com \
    --cc=davem@davemloft.net \
    --cc=jeffrey.t.kirsher@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=nhorman@redhat.com \
    --cc=sassmann@redhat.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;
as well as URLs for NNTP newsgroup(s).