Re: linux bypass loopback - got to dead end

From: Michael Heiming (michael+USENET_at_www.heiming.de)
Date: 10/31/05 

Date: Mon, 31 Oct 2005 21:27:26 +0100

In comp.os.linux.networking ronybaryo@gmail.com:
> Hi,

> I want to force tcp traffic to go out even that the dest ip
> is on the same machine.

> I have eth0 with ip 10.56.211.89 and eth1 with 10.56.211.90 (for
> example).
> I want to open socket from 10.56.211.89 to 10.56.211.90 and bypass the
> loopback, I mean that the packet will leave the linux on one interface
> and reach the second.

> so far couldn't do it.
> any idea will be appreciated.

No way without modifying the source, the kernel is clever enough
to mention the device/IP is local and won't route a single packet
through the wire as you found out.

Should be easier to put a second (old) box in service. 

-- 
Michael Heiming (X-PGP-Sig > GPG-Key ID: EDD27B94)
mail: echo zvpunry@urvzvat.qr | perl -pe 'y/a-z/n-za-m/'
#bofh excuse 144: Too few computrons available.

Relevant Pages

  • Re: RELENG_6 No buffer space available [udp stream]
    ... Thanks for your explanation, i don't have ideas about with sendwork on freebsd and linux, ... The output queue for a network interface was full. ... ENOBUFS is the error returned when a process is sending packets faster than the transmitting interface can actually transmit them. ... As UDP is a lossy datagram protocol without flow control, your process doesn't block, but it does get back an error telling it that the packet could not be transmitted. ...
    (freebsd-net)
  • Re: I really need to know...
    ... >>to my linux box. ... you can then reduce the MTU used by that interface to ... > for the common link to the Internet to 296. ... > packet has the same overhead as before, ...
    (comp.os.linux.misc)
  • Re: Linux 2.6.9 pktgen module causes INIT process respawning and sickness
    ... > I can sustain full line rate gigabit on two adapters at the tsame time ... > current DMA architectures on 400 Mhz buses with Linux. ... > overhead of serializing writes to the adapter ring buffer IO ... overhead than a simple packet generator or pktgen. ...
    (Linux-Kernel)
  • Re: TCP/IP stack performance
    ... > I am interested in knowing IP forwarding performance when a Linux ... especially when MIPs isn't a very scientific measure. ... drivers seem to swamp the system at a certain packet rate, ... this corresponds to 6329 instructions per 64 byte packet. ...
    (comp.os.linux)
  • Re: PCI transaction rate question.
    ... Ethernet frames, the card can only receive about 70,000 packets/sec ... I've always blamed the rate at which the CPU can ... I've done the speed tests and Linux is downright awful at packet ...
    (comp.arch)