From: Andrew Lunn <andrew@lunn.ch>
To: Paolo Abeni <pabeni@redhat.com>
Cc: David Laight <David.Laight@aculab.com>,
'Pavan Chebbi' <pavan.chebbi@broadcom.com>,
Michael Chan <michael.chan@broadcom.com>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
"mchan@broadcom.com" <mchan@broadcom.com>,
David Miller <davem@davemloft.net>
Subject: Re: tg3 dropping packets at high packet rates
Date: Thu, 19 May 2022 15:54:42 +0200 [thread overview]
Message-ID: <YoZMInrha8Sux61Q@lunn.ch> (raw)
In-Reply-To: <5cc5353c518e27de69fc0d832294634c83f431e5.camel@redhat.com>
> If the packet processing is 'bursty', you can have idle time and still
> hit now and the 'rx ring is [almost] full' condition. If pause frames
> are enabled, that will cause the peer to stop sending frames: drop can
> happen in the switch, and the local NIC will not notice (unless there
> are counters avaialble for pause frames sent).
You can control pause with ethtool
ethtool -a|--show-pause devname
ethtool -A|--pause devname [autoneg on|off] [rx on|off] [tx on|off]
But it depends on the driver implementing these options. So you might
want to try autoneg on, rx off, tx off, for testing.
ethtool should also show you want has been negotiated for pause, if
the driver has implemented that part of the ethtool API.
Andrew
next prev parent reply other threads:[~2022-05-19 13:57 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-05-18 16:08 tg3 dropping packets at high packet rates David Laight
2022-05-18 17:27 ` Paolo Abeni
2022-05-18 21:31 ` David Laight
2022-05-19 0:52 ` Michael Chan
2022-05-19 8:44 ` David Laight
2022-05-19 10:20 ` Pavan Chebbi
2022-05-19 13:14 ` David Laight
2022-05-19 13:29 ` Paolo Abeni
2022-05-19 13:54 ` Andrew Lunn [this message]
2022-05-19 14:11 ` David Laight
2022-05-19 14:35 ` Pavan Chebbi
2022-05-19 14:42 ` David Laight
2022-05-20 16:08 ` David Laight
2022-05-23 16:01 ` David Laight
2022-05-23 16:14 ` Pavan Chebbi
2022-05-23 21:23 ` David Laight
2022-05-25 7:28 ` David Laight
2022-05-25 15:56 ` Jakub Kicinski
2022-05-25 21:48 ` David Laight
2022-05-22 23:22 ` Michael Chan
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=YoZMInrha8Sux61Q@lunn.ch \
--to=andrew@lunn.ch \
--cc=David.Laight@aculab.com \
--cc=davem@davemloft.net \
--cc=mchan@broadcom.com \
--cc=michael.chan@broadcom.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=pavan.chebbi@broadcom.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).