[Udpcast] UDPcast performance on high speed networks?

Felix Rauch rauch at inf.ethz.ch
Tue Dec 17 18:36:42 CET 2002


On Tue, 17 Dec 2002, Alain Knaff wrote:
> There are several ways around this:
> 1. Maybe your switch does understand IGMP, but this is just switched
> off? Can you check what happens if you enable it (IGMP snooping)?
> N.B. Some 3com switches, and maybe others as well, do have a config
> option for IGMP snooping, but it is not actually implemented...
> (i.e. even if enabled, it doesn't work).
>
> 2. Or if the above doesn't work, try disabling flow control in the
> switch. With that config, the switch will just drop the packets that
> it cannot transmit on the 10Mb/s ports (but the 100 Mb/s ports still
> enjoy the complete transmission).

Unfortunately our switch is unmanaged, so I couldn't change the above.

> 3. If that doesn't help either (or is unavailable), try unplugging all
> devices that do not participate in the communication.

I did this and I got 94 Mbps for 2, 4 and 8 clients. So indeed, it
seems to be a problem with the switch.

> Not sure that this is the same problem as on 100Mbit/s. Indeed, as
> this technology is much more recent, most Gigabit switches (hopefully)
> should know how to correctly switch multicast traffic.

The switch is somewhat old (from the days when Gigabit Ethernet was
still a new technology), but it should do the multicasting right. But
it seems that the problem is not related to multicast (see below).

> But maybe a different problem is occuring (but it might still be worth
> trying to disconnect from the Gigabit switch all devices that are
> unrelated to the transfer).

There are only 16 Gigabit Ethernet ports used on the switch (plus a
management port).

> Can you also retry this with the half-duplex flag, just in case?

I did so but it didn't help. What surprises me somewhat, is the fact
the the performance is also very low for only 1 sender and 1
receiver. Here's what I tried:

On the receiver:
node02:~/src/udpcast> time ./udp-receiver --file /dev/null --interface eth1
Udp-receiver 2001-12-31
UDP receiver for /dev/null at 172.25.1.102
172.25.1.102 on eth1
received message, cap=00000019
Connected as #0 to 172.25.1.101
172.25.1.102
Listening to multicast on 236.25.1.101
Press any key to start receiving data!
bytes=        425 152  (  0.42 Mbps)
Cancelled by user
0.000u 0.010s 1:25.11 0.0%      0+0k 0+0io 138pf+0w

And on the sender:
node01:~/src/udpcast> time ./udp-sender --file /dev/zero --half-duplex --interface eth1
Udp-sender 2001-12-31
172.25.1.101
Using mcast address 236.25.1.101
UDP sender for /dev/zero at 172.25.1.101
172.25.1.101 on eth1
Broadcasting control to 172.25.255.255
New connection from 172.25.1.102  (#0) 00000019
Ready. Press any key to start sending data.
[RETURN]
Starting transfer: 00000019
[CTRL-C about 80 seconds later]
0.000u 0.000s 1:22.93 0.0%mits=00+0k 0+0io 155pf+0we=0202                 -   0

This should be a unicast transmission if I understand you right, but
still I see much less than even 1 Mbps.

Regards,
Felix
-- 
Felix Rauch                      | Email: rauch at inf.ethz.ch
Institute for Computer Systems   | Homepage: http://www.cs.inf.ethz.ch/~rauch/
ETH Zentrum / RZ H18             | Phone: +41 1 632 7489
CH - 8092 Zuerich / Switzerland  | Fax:   +41 1 632 1307




More information about the Udpcast mailing list