| To: | Karsten Desler <kdesler@xxxxxxxxxx> |
|---|---|
| Subject: | Re: _High_ CPU usage while routing (mostly) small UDP packets |
| From: | Robert Olsson <Robert.Olsson@xxxxxxxxxxx> |
| Date: | Tue, 7 Dec 2004 13:38:56 +0100 |
| Cc: | P@xxxxxxxxxxxxxx, "David S. Miller" <davem@xxxxxxxxxxxxx>, netdev@xxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx |
| In-reply-to: | <20041207112139.GA3610@xxxxxxxxxx> |
| References: | <20041206205305.GA11970@xxxxxxxxxx> <20041206134849.498bfc93.davem@xxxxxxxxxxxxx> <20041206224107.GA8529@xxxxxxxxxx> <41B58A58.8010007@xxxxxxxxxxxxxx> <20041207112139.GA3610@xxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
Hello!
Well my experience is that it very hard not to say almost impossible to
extrapolate idle cpu into any network system capacity. I guess this is
what you are trying to do?
Rather load and overload the system with traffic having the characteristics
you expect as a bonus you will get some kind proof of robustness and
responsiveness a max load. There are tools for this type of tests.
Pádraig! Very funny... I started hacking 2 hours ago on idea I
had for long time, This to do a light version of skb recycling based
skb->users (the pktgen trick) with very minimal kernel change..
> Anyway attached is a small patch that I used to make the e1000
> "own" the packet buffers, and hence it does not alloc/free
> per packet at all. Now this has only been tested in one
> configuration where I was just sniffing the packets, so
> definitely YMMV.
--ro
|
| Previous by Date: | Re: _High_ CPU usage while routing (mostly) small UDP packets, jamal |
|---|---|
| Next by Date: | Re: [PATCH] rtnetlink & address family problem, Thomas Graf |
| Previous by Thread: | Re: _High_ CPU usage while routing (mostly) small UDP packets, Karsten Desler |
| Next by Thread: | Re: _High_ CPU usage while routing (mostly) small UDP packets, Karsten Desler |
| Indexes: | [Date] [Thread] [Top] [All Lists] |