[Top] [All Lists]

Re: [BUG] overflow in net/ipv4/route.c rt_check_expire()

To: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>
Subject: Re: [BUG] overflow in net/ipv4/route.c rt_check_expire()
From: Eric Dumazet <dada1@xxxxxxxxxxxxx>
Date: Sat, 02 Apr 2005 16:10:10 +0200
Cc: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>, davem@xxxxxxxxxxxxx, netdev@xxxxxxxxxxx
In-reply-to: <>
References: <> <> <>
Sender: netdev-bounce@xxxxxxxxxxx
User-agent: Mozilla Thunderbird 1.0 (Windows/20041206)
Robert Olsson a écrit :
Eric Dumazet writes:

Yes thats a pretty much load. Very short flows some reason?

Well... yes. This is a real server, not a DOS simulation. 1 million TCP flows, and about 3 million peers using UDP frames.

What's your ip_rt_gc_min_interval? GC should be allowed to run frequent to smoothen out the GC load. Also good idea to decrease gc_thresh and you hash is really huge.

No. As soon as I lower gc_thresh (and let gc running), the machine starts to drop connections and crash some seconds later. I found I had to make the hash table very large (but lowering elasticity, ie chain length) . It needs lot of ram, but at least CPU usage of net/ipv4/route.c is close to 0.

# grep . /proc/sys/net/ipv4/route/*

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