All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jakub Kicinski <kuba@kernel.org>
To: Radhey Shyam Pandey <radheys@xilinx.com>,
	Robert Hancock <robert.hancock@calian.com>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"davem@davemloft.net" <davem@davemloft.net>,
	"edumazet@google.com" <edumazet@google.com>,
	"pabeni@redhat.com" <pabeni@redhat.com>,
	Michal Simek <michals@xilinx.com>,
	"linux-arm-kernel@lists.infradead.org"
	<linux-arm-kernel@lists.infradead.org>,
	Harini Katakam <harinik@xilinx.com>
Subject: Re: [PATCH net-next] net: axienet: Use NAPI for TX completion path
Date: Wed, 4 May 2022 19:20:28 -0700	[thread overview]
Message-ID: <20220504192028.2f7d10fb@kernel.org> (raw)
In-Reply-To: <SA1PR02MB856018755A47967B5842A4C4C7C19@SA1PR02MB8560.namprd02.prod.outlook.com>

On Mon, 2 May 2022 19:30:51 +0000 Radhey Shyam Pandey wrote:
> > This driver was using the TX IRQ handler to perform all TX completion
> > tasks. Under heavy TX network load, this can cause significant irqs-off
> > latencies (found to be in the hundreds of microseconds using ftrace).
> > This can cause other issues, such as overrunning serial UART FIFOs when
> > using high baud rates with limited UART FIFO sizes.
> > 
> > Switch to using the NAPI poll handler to perform the TX completion work
> > to get this out of hard IRQ context and avoid the IRQ latency impact.  
> 
> Thanks for the patch. I assume for simulating heavy network load we
> are using netperf/iperf. Do we have some details on the benchmark
> before and after adding TX NAPI? I want to see the impact on
> throughput.

Seems like a reasonable ask, let's get the patch reposted 
with the numbers in the commit message.

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

WARNING: multiple messages have this Message-ID (diff)
From: Jakub Kicinski <kuba@kernel.org>
To: Radhey Shyam Pandey <radheys@xilinx.com>,
	Robert Hancock <robert.hancock@calian.com>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"davem@davemloft.net" <davem@davemloft.net>,
	"edumazet@google.com" <edumazet@google.com>,
	"pabeni@redhat.com" <pabeni@redhat.com>,
	Michal Simek <michals@xilinx.com>,
	"linux-arm-kernel@lists.infradead.org" 
	<linux-arm-kernel@lists.infradead.org>,
	Harini Katakam <harinik@xilinx.com>
Subject: Re: [PATCH net-next] net: axienet: Use NAPI for TX completion path
Date: Wed, 4 May 2022 19:20:28 -0700	[thread overview]
Message-ID: <20220504192028.2f7d10fb@kernel.org> (raw)
In-Reply-To: <SA1PR02MB856018755A47967B5842A4C4C7C19@SA1PR02MB8560.namprd02.prod.outlook.com>

On Mon, 2 May 2022 19:30:51 +0000 Radhey Shyam Pandey wrote:
> > This driver was using the TX IRQ handler to perform all TX completion
> > tasks. Under heavy TX network load, this can cause significant irqs-off
> > latencies (found to be in the hundreds of microseconds using ftrace).
> > This can cause other issues, such as overrunning serial UART FIFOs when
> > using high baud rates with limited UART FIFO sizes.
> > 
> > Switch to using the NAPI poll handler to perform the TX completion work
> > to get this out of hard IRQ context and avoid the IRQ latency impact.  
> 
> Thanks for the patch. I assume for simulating heavy network load we
> are using netperf/iperf. Do we have some details on the benchmark
> before and after adding TX NAPI? I want to see the impact on
> throughput.

Seems like a reasonable ask, let's get the patch reposted 
with the numbers in the commit message.

  reply	other threads:[~2022-05-05  2:21 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-29 22:28 [PATCH net-next] net: axienet: Use NAPI for TX completion path Robert Hancock
2022-04-29 22:28 ` Robert Hancock
2022-05-02 19:30 ` Radhey Shyam Pandey
2022-05-02 19:30   ` Radhey Shyam Pandey
2022-05-05  2:20   ` Jakub Kicinski [this message]
2022-05-05  2:20     ` Jakub Kicinski
2022-05-05 17:33     ` Robert Hancock
2022-05-05 17:33       ` Robert Hancock
2022-05-05 18:08       ` Jakub Kicinski
2022-05-05 18:08         ` Jakub Kicinski
2022-05-05 18:56         ` Robert Hancock
2022-05-05 18:56           ` Robert Hancock
2022-05-05 20:15           ` Robert Hancock
2022-05-05 20:15             ` Robert Hancock

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=20220504192028.2f7d10fb@kernel.org \
    --to=kuba@kernel.org \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=harinik@xilinx.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=michals@xilinx.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=radheys@xilinx.com \
    --cc=robert.hancock@calian.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 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.