netdev
[Top] [All Lists]

Re: [Fwd: Re: possible bug x86 2.4.2 SMP in IP receive stack]

To: kuznet@xxxxxxxxxxxxx
Subject: Re: [Fwd: Re: possible bug x86 2.4.2 SMP in IP receive stack]
From: Bob Felderman <feldy@xxxxxxxx>
Date: Thu, 8 Mar 2001 11:38:08 -0800 (PST)
Cc: Bob Felderman <feldy@xxxxxxxx>, ak@xxxxxx, andrewm@xxxxxxxxxx, davem@xxxxxxxxxx, netdev@xxxxxxxxxxx, pp@xxxxxxxxxxxxxx
In-reply-to: <200103081914.WAA26654@ms2.inr.ac.ru>
Sender: owner-netdev@xxxxxxxxxxx

On Thu, 8 Mar 2001 kuznet@xxxxxxxxxxxxx wrote:
> the more pressure on backlog. Negative feedback, equilibrium value
> is unpredicatble. 8) Look into /proc/net/softnet_stat,
> the second column. What does it show?

[root@rcc intel_linux]# cat /proc/net/softnet_stat
00fe20ec 0000ae4e 00000ece 000000b6 00000000 00000000 00000000 00000000
0012e228
00eff495 0000b941 000010d0 000000cc 00000000 00000000 00000000 00000000
0006f8bd

> 
> 
> > track it down. When I used DaveM's zero-copy patches on
> 
> Wow! Did you test _without_ it?
> How was zerocopyless kernel able to hold 1.5Gig? It copies all twice!

linux-2.4.0 has always been SIGNIFICANTLY better than linux-2.2
even with a single processor, I'm able to get above 1.5Gbit/sec
UDP and nearly 1.0Gbit/sec tcp.


> 
> 
> > a linux-2.4.0 kernel, most, if not all, of these
> > packet receive errors went away. 
> 
> They must disappear completely. Each loss on LAN is bug.
> User has right to expect that no losses happen.

I'd like them to go away, but UDP losees due to socket overflows
are quite common on most operating systems.


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