From: Florian Fainelli <f.fainelli@gmail.com>
To: Andrew Lunn <andrew@lunn.ch>, David Miller <davem@davemloft.net>
Cc: netdev <netdev@vger.kernel.org>,
Heiner Kallweit <hkallweit1@gmail.com>,
fugang.duan@nxp.com, Chris Heally <cphealy@gmail.com>
Subject: Re: [PATCH net-next v2 1/3] net: ethernet: fec: Replace interrupt driven MDIO with polled IO
Date: Sat, 18 Apr 2020 14:06:44 -0700 [thread overview]
Message-ID: <d64d4d6e-3ee4-c192-e2cf-4487b4143263@gmail.com> (raw)
In-Reply-To: <20200418000355.804617-2-andrew@lunn.ch>
On 4/17/2020 5:03 PM, Andrew Lunn wrote:
> Measurements of the MDIO bus have shown that driving the MDIO bus
> using interrupts is slow. Back to back MDIO transactions take about
> 90uS, with 25uS spent performing the transaction, and the remainder of
> the time the bus is idle.
>
> Replacing the completion interrupt with polled IO results in back to
> back transactions of 40uS. The polling loop waiting for the hardware
> to complete the transaction takes around 27uS. Which suggests
> interrupt handling has an overhead of 50uS, and polled IO nearly
> halves this overhead, and doubles the MDIO performance.
>
> Suggested-by: Chris Heally <cphealy@gmail.com>
> Signed-off-by: Andrew Lunn <andrew@lunn.ch>
You should support both modes and let an user decide whether they want
to use interrupts or polling mode by specifying or omitting the
'interrupts' property in their Device Tree.
--
Florian
next prev parent reply other threads:[~2020-04-18 21:06 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-18 0:03 [PATCH net-next v2 0/3] FEC MDIO speedups Andrew Lunn
2020-04-18 0:03 ` [PATCH net-next v2 1/3] net: ethernet: fec: Replace interrupt driven MDIO with polled IO Andrew Lunn
2020-04-18 13:55 ` [EXT] " Andy Duan
2020-04-18 22:39 ` Chris Healy
2020-04-19 0:35 ` Andrew Lunn
2020-04-19 6:22 ` Andy Duan
2020-04-19 20:47 ` Andrew Lunn
2020-04-18 16:21 ` Fabio Estevam
2020-04-18 21:06 ` Florian Fainelli [this message]
2020-04-18 0:03 ` [PATCH net-next v2 2/3] net: ethernet: fec: Allow configuration of MDIO bus speed Andrew Lunn
2020-04-18 0:34 ` Florian Fainelli
2020-04-18 14:23 ` Andrew Lunn
2020-04-18 16:01 ` Florian Fainelli
2020-04-18 16:49 ` Andrew Lunn
2020-04-18 21:07 ` Florian Fainelli
2020-04-18 21:08 ` Florian Fainelli
2020-04-18 0:03 ` [PATCH net-next v2 3/3] net: ethernet: fec: Allow the MDIO preamble to be disabled Andrew Lunn
2020-04-18 0:39 ` Florian Fainelli
2020-04-18 14:27 ` Andrew Lunn
2020-04-18 16:02 ` Florian Fainelli
2020-04-18 21:09 ` Florian Fainelli
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=d64d4d6e-3ee4-c192-e2cf-4487b4143263@gmail.com \
--to=f.fainelli@gmail.com \
--cc=andrew@lunn.ch \
--cc=cphealy@gmail.com \
--cc=davem@davemloft.net \
--cc=fugang.duan@nxp.com \
--cc=hkallweit1@gmail.com \
--cc=netdev@vger.kernel.org \
/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).