[Top] [All Lists]

Re: [PATCH] Improve behaviour of Netlink Sockets

To: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Subject: Re: [PATCH] Improve behaviour of Netlink Sockets
From: jamal <hadi@xxxxxxxxxx>
Date: 27 Sep 2004 23:06:12 -0400
Cc: Pablo Neira <pablo@xxxxxxxxxxx>, "David S. Miller" <davem@xxxxxxxxxx>, netdev@xxxxxxxxxxx
In-reply-to: <20040928024614.GA9911@xxxxxxxxxxxxxxxxxxx>
Organization: jamalopolous
References: <20040922000503.GA13218@xxxxxxxxxxxxxxxxxxx> <4150E7E5.2000001@xxxxxxxxxxx> <20040922045239.GA19573@xxxxxxxxxxxxxxxxxxx> <1095854920.1047.64.camel@xxxxxxxxxxxxxxxx> <20040923120707.GB32624@xxxxxxxxxxxxxxxxxxx> <1095995042.1044.34.camel@xxxxxxxxxxxxxxxx> <20040924032440.GB6384@xxxxxxxxxxxxxxxxxxx> <1096289189.1075.37.camel@xxxxxxxxxxxxxxxx> <20040927213607.GD7243@xxxxxxxxxxxxxxxxxxx> <1096339407.8660.33.camel@xxxxxxxxxxxxxxxx> <20040928024614.GA9911@xxxxxxxxxxxxxxxxxxx>
Reply-to: hadi@xxxxxxxxxx
Sender: netdev-bounce@xxxxxxxxxxx
On Mon, 2004-09-27 at 22:46, Herbert Xu wrote:
> On Mon, Sep 27, 2004 at 10:43:27PM -0400, jamal wrote:
> > On Mon, 2004-09-27 at 17:36, Herbert Xu wrote:
> > 
> > > You still haven't told me what you're going to use 3) for yet...
> > 
> > Sorry, keep forgetting to retrieve it from other remote non-networked
> > test machine. The idea is:
> > Create something that generates lots of messages. Make socket buffer
> > small (4096 is good nuf)
> No that's not what I meant.  What I mean is what is the real-world
> scenario where you're going to be doing 3).

The real world scenario is just that: Massive events generated from the
kernel for example

> Only when we know where the messages are coming from and what they
> are can we decide on a meaningful method of limiting their rate.

Ok, heres a sample testcase i created just now following those same
instructions i gave you ;->


ifconfig dummy0 netmask broadcast up
ifconfig dummy0:0
for ((i = 1 ; i <= $1 ; i++))
        ifconfig dummy0:$i 1.2.1.$i

pass 100 to it to create 100 aliases; you may not need to setsock to
4096, but thats what i did. 

down dummy0:0 and see the overrun.


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