From: Andrew Morton <akpm@digeo.com>
To: "David S. Miller" <davem@redhat.com>
Cc: manfred@colorfullife.com, netdev@oss.sgi.com,
linux-kernel@vger.kernel.org
Subject: Re: Info: NAPI performance at "low" loads
Date: Tue, 17 Sep 2002 14:58:52 -0700 [thread overview]
Message-ID: <3D87A59C.410FFE3E@digeo.com> (raw)
In-Reply-To: 20020917.143947.07361352.davem@redhat.com
"David S. Miller" wrote:
>
> From: Andrew Morton <akpm@digeo.com>
> Date: Tue, 17 Sep 2002 14:45:08 -0700
>
> "David S. Miller" wrote:
> > Well, it is due to the same problems manfred saw initially,
> > namely just a crappy or buggy NAPI driver implementation. :-)
>
> It was due to additional inl()'s and outl()'s in the driver fastpath.
>
> How many? Did the implementation cache the register value in a
> software state word or did it read the register each time to write
> the IRQ masking bits back?
>
Looks like it cached it:
- outw(SetIntrEnb | (inw(ioaddr + 10) & ~StatsFull), ioaddr + EL3_CMD);
vp->intr_enable &= ~StatsFull;
+ outw(vp->intr_enable, ioaddr + EL3_CMD);
> It is issues like this that make me say "crappy or buggy NAPI
> implementation"
>
> Any driver should be able to get the NAPI overhead to max out at
> 2 PIOs per packet.
>
> And if the performance is really concerning, perhaps add an option to
> use MEM space in the 3c59x driver too, IO instructions are constant
> cost regardless of how fast the PCI bus being used is :-)
Yup. But deltas are interesting.
next prev parent reply other threads:[~2002-09-17 21:54 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-09-17 19:53 Info: NAPI performance at "low" loads Manfred Spraul
2002-09-17 20:59 ` David S. Miller
2002-09-17 21:32 ` Andrew Morton
2002-09-17 21:26 ` David S. Miller
2002-09-17 21:45 ` Andrew Morton
2002-09-17 21:39 ` David S. Miller
2002-09-17 21:54 ` Jeff Garzik
2002-09-17 21:49 ` David S. Miller
2002-09-18 2:11 ` Jeff Garzik
2002-09-18 2:06 ` David S. Miller
2002-09-18 2:36 ` Jeff Garzik
2002-09-17 21:58 ` Andrew Morton [this message]
2002-09-18 0:57 ` jamal
2002-09-18 1:00 ` David S. Miller
2002-09-18 2:16 ` Andrew Morton
2002-09-18 17:27 ` Eric W. Biederman
2002-09-18 17:50 ` Alan Cox
2002-09-19 14:58 ` Eric W. Biederman
2002-09-18 20:23 ` David S. Miller
2002-09-18 20:43 ` Alan Cox
2002-09-18 20:46 ` David S. Miller
2002-09-18 21:15 ` Alan Cox
2002-09-18 21:22 ` David S. Miller
2002-09-19 15:03 ` Eric W. Biederman
2002-09-19 15:53 ` Alan Cox
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=3D87A59C.410FFE3E@digeo.com \
--to=akpm@digeo.com \
--cc=davem@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=manfred@colorfullife.com \
--cc=netdev@oss.sgi.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).