udp expected behaviour not responding to test result
- by ernst
I have a local network topology that is structured as follows:
three hosts and a switch in the middle.
I am using a switch that supports 10,100,1000 Mbit/s full/half duplex connection.
I have configured the hosts with a static ip 172.16.0.1-2-3/25.
This is the output of ifconfig
eth0 Link encap:
Ethernet HWaddr ***** inet addr:172.16.0.3 Bcast:172.16.0.127 Mask:255.255.255.128
UP BROADCAST MULTICAST MTU:1500
Metric:1 RX packets:0 errors:0 dropped:0 overruns:0 frame:0 TX packets:0 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:0 (0.0 B) TX bytes:0 (0.0 B) Interrupt:16
The output on H1 and H2 is perfectly matchable
They are mutually reachable since i have tested the network with ping.
I have forced the ethernet interface to work at 10M with
ethtool -s eth0 speed 10 duplex full autoneg on
this is the output of ethtool eth0
supported ports: [ TP ]
Supported link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Half 1000baseT/Full S
upported pause frame use: No
Supports auto-negotiation: Yes
Advertised link modes: 10baseT/Full
Advertised pause frame use: Symmetric A
dvertised auto-negotiation: Yes
Speed: 10Mb/s
Duplex: Full
Port: Twisted Pair
PHYAD: 1
Transceiver: internal
Auto-negotiation: on
MDI-X: Unknown Supports Wake-on: g Wake-on: d
Current message level: 0x000000ff (255)
drv probe link timer ifdown ifup rx_err tx_err
Link detected: yes –
I am doing an experimental test using nttcp to calculate the GOODPUT in the case that H1 and H2 at the same time send data to H3.
Since the three links have the same forced capability and the amount of arrving data speed is 10 from H1+10 from H2--20M to H3 it would be expected a bottleneck effect and, due to the non reliable nature of udp, a packet loss.
But this doesn't appen since the output of nttcp application shows the same number of byte sended and received.
this is the output of nttcp on h3
nttcp -T -r -u 172.16.0.2 & nttcp -T -r -u 172.16.0.1
[1] 4071
Bytes Real s CPU s Real-MBit/s CPU-MBit/s Calls Real-C/s CPU-C/s
l 8388608 13.74 0.05 4.8848 1398.0140 2049 149.14 42684.8
Bytes Real s CPU s Real-MBit/s CPU-MBit/s Calls Real-C/s CPU-C/s
l 8388608 14.02 0.05 4.7872 1398.0140 2049 146.17 42684.8
1 8388608 13.56 0.06 4.9500 1118.4065 2051 151.28 34181.1
1 8388608 13.89 0.06 4.8310 1198.3084 2051 147.65 36623.0 –
How is this possible?
Am i missing something?
Any help will be gratefully apprecciated,
Best regards
