As part of a broader organisational restructure, data networking research at Swinburne University of Technology has moved from the Centre for Advanced Internet Architecture (CAIA) to the Internet For Things (I4T) Research Lab.

Although CAIA no longer exists, this website reflects CAIA's activities and outputs between March 2002 and February 2017, and is being maintained as a service to the broader data networking research community.


This page is part of the BART project.

Interface Configuration for Optimal Time Stamp Performance On fxp0


The following section discusses optimising the time stamp accuracy of the fxp0 interface and whether the presence of sis0 may influence its time stamp results. For the following results the line speed, if statically set, was configured to be 100Mbit/sec and the packet inter-arrival time for all results set to 1msec on the SmartBits2000.

We can see from Figure 13 that before the fxp0 interface was added and the line speed explicitly set for 100Mbit/sec traffic, the maximum time stamp errors were approximately 20usec. From Figure 37 where the same test was repeated but this time on the added fxp0 interface (sis0 present but not configured), the maximum time stamp errors reached up to 8msec (measured from the theoretical time stamp value of 1008.3usec). In an attempt to reduce possible error in time stamps (where only the fxp0 interface is used), the sis0 interface is set to 100Mbit/sec. Figures 22 and 23 below show that explicitly setting the unused sis0 interface improves on the time stamp errors (from Figure 13) both with and without IP address being set on the sis0 interface. The maximum time stamp errors now peak at 4msec. Although SmartBits2000 sent packets to interface fxp0 and interface sis0 was not connected to any cables, simply setting sis0 to a static line speed improved interface fxp0's time stamp performance.

Figure 22: Unused Interface sis0
set to 100Mbit/sec with IP address configured
Figure 23: Unused Interface sis0 set
to 100Mbit/sec without IP address configured

sis0: flags=8843 mtu 1500
inet 136.186.229.238
netmask 0xffff0000
broadcast 136.186.255.255
inet6 fe80::20c:6eff:fed1:58f3%sis0
prefixlen 64 scopeid 0x1
ether 00:0c:6e:d1:58:f3
media: Ethernet 100baseTX
status: no carrier

fxp0: flags=8802mtu 1500
inet 136.186.229.237 netmask 0xffff0000
broadcast 136.186.255.255
inet6 fe80::202:b3ff:fee7:bc26%fxp0
prefixlen 64 scopeid 0x2
ether 00:02:b3:e7:bc:26
media: Ethernet 100baseTX (100baseTX )
status: active
sis0: flags=8843 mtu 1500
ether 00:0c:6e:d1:58:f3
media: Ethernet 100baseTX
status: no carrier

fxp0: flags=8802mtu 1500
inet 136.186.229.237 netmask 0xffff0000
broadcast 136.186.255.255
inet6 fe80::202:b3ff:fee7:bc26%fxp0
prefixlen 64 scopeid 0x2
ether 00:02:b3:e7:bc:26
media: Ethernet 100baseTX (100baseTX )
status: active

To reduce the severity of the time stamp errors, interface fxp0 was statically set to 100Mbit/sec and connected to SmartBits2000. The unused sis0 interface was also statically set to 100Mbit/sec and connected to the SmartBits2000 but did not receive any traffic. All packets were sent to interface fxp0 and as can be seen in Figure 24, by allowing interface sis0 to be active and setting its line speed to 100Mbit/sec but not having it participate in the test, the time stamp errors dramatically reduced to a maximum of about 45usec on the fxp0 interface.

The last test was to determine whether fxp0 would interfere with interface sis0 time stamps. Figure 25 shows the result of connecting interface sis0 to the SmartBits2000 and sending traffic to it. Interface fxp0 was, unlike in the Set A results, also present and set to automatic line speed negotiation (fxp0 was not active). As we can see, the presence of interface fxp0 had no negative influence on interface sis0's time stamp accuracy. The maximum time stamp error of interface sis0 was only approximately 17usec.

Figure 24: Both interfaces active and
connected to SmartBits2000
Figure 25: Testing interface sis0 with
interface fxp0 not active

sis0: flags=8843 mtu 1500
inet 136.186.229.238
netmask 0xffff0000
broadcast 136.186.255.255
inet6 fe80::20c:6eff:fed1:58f3%sis0
prefixlen 64 scopeid 0x1
ether 00:0c:6e:d1:58:f3
media: Ethernet 100baseTX
status: active

fxp0: flags=8802mtu 1500
inet 136.186.229.237 netmask 0xffff0000
broadcast 136.186.255.255
inet6 fe80::202:b3ff:fee7:bc26%fxp0
prefixlen 64 scopeid 0x2
ether 00:02:b3:e7:bc:26
media: Ethernet 100baseTX (100baseTX )
status: active
sis0: flags=8843 mtu 1500
inet 136.186.229.238
netmask 0xffff0000
broadcast 136.186.255.255
inet6 fe80::20c:6eff:fed1:58f3%sis0
prefixlen 64 scopeid 0x1
ether 00:0c:6e:d1:58:f3
media: Ethernet 100baseTX
status: active

fxp0: flags=8802 mtu 1500
ether 00:02:b3:e7:bc:26
media: Ethernet autoselect (none)
status: no carrier






Swinburne Homepage Site Map Search Index
 

Swinburne Copyright and disclaimer Privacy Feedback

Last Updated: Tuesday 2-Dec-2003 09:47:12 AEDT
URL:
Maintained by: Ana Pavlicic apavlicic@groupwise.swin.edu.au
Authorised by: Grenville Armitage garmitage@swin.edu.au

IndexSearchSite MapSwinburne Home Page