netdev
[Top] [All Lists]

Re: Tx queueing

To: Andrew Morton <andrewm@xxxxxxxxxx>
Subject: Re: Tx queueing
From: Jeff Garzik <jgarzik@xxxxxxxxxxxxxxxx>
Date: Sat, 20 May 2000 13:30:48 -0400
Cc: "netdev@xxxxxxxxxxx" <netdev@xxxxxxxxxxx>
Organization: MandrakeSoft
References: <392407D4.BE586507@xxxxxxxxxx> <3925BA01.CC49AC1@xxxxxxxxxxxxxxxx> <3925D985.51472B30@xxxxxxxxxx>
Sender: owner-netdev@xxxxxxxxxxx
Andrew Morton wrote:
> Jeff Garzik wrote:
> > Which [drivers have wrong softnet logic]?  They need fixing..

> 3c50?.c.  Probably others...
> 
> I'm disinclined to change these:
> 
> - They're slow anyway.
> - Increased possiblity of breaking them
> - Broken 2.2/kcompat24 compatibility

I should note that drivers with the logic in question (start_xmit:
stop... start if not full) caused transmit timeouts and other nasties
when used in modern PCI drivers.  That's why I consider such logic a
bug, not just a correctness or performance issue.


> So.
> 
> - No performance tweaks for [E]ISA drivers in 2.3.
> - Correctness fixes if they're obvious.
> - If the SMP-safety fixes are not obvious, mark the driver as UP-only.
> 
> Sound sensible?

* highly agree with the first
* and the second
* I think we should go through drivers and mark them SMP-safe... :)

        Jeff



-- 
Jeff Garzik              | Liberty is always dangerous, but
Building 1024            | it is the safest thing we have.
MandrakeSoft, Inc.       |      -- Harry Emerson Fosdick

<Prev in Thread] Current Thread [Next in Thread>