...
Overview
| Info |
|---|
The overview portion of this document has been created by BadgerNet / AT&T and edited by WiscNet. Its intent is to explain the requirements needed in order to procure accurate circuit testing results |
...
- Tool used to test
- Location of testing laptop/PC in the network
- Time of day when test is run
Speed Testing Tools
Most of our members test their internet connection speeds using online browser based tests against servers hosted somewhere on the Internet, for example, http://speedtest.wiscnet.net/ . These tests work fine for low bandwidth internet services but don’t scale well for high speed internet connections. In order to get an accurate speed test a different testing tool like iperf should be used.
Location of testing laptop/PC in the network
Location of the testing PC/Laptop is critical for accurate test results. Note, from the diagram below, that location D is the best place to test your Internet speed from. The reliability of test results go down as we move the test point to C, B and A.
The configuration and capacity of the laptop is equally critical for the accuracy of circuit testing. Please ensure your laptop network cards and configuration are Gig/Capable.
Time of Day
Browser-based speed test results can also vary based on time of day, depending on the bandwidth consumed by the site users at the time the tests are run. For example, if a site has a 100Mbps connection and the users at the site are already consuming 60Mbps download and 25 Mbps upload sustained bandwidth for their business use, the test results will only show 40Mbps download and 75Mbps upload speeds. Therefore, it is recommended that these tests are run before and after business hours if you are using a browser base testing tool.
Mid-day Testing
Some WiscNet members desire to run speed test during business hours to see if they are getting full bandwidth during the day. In others instances, WiscNet will require the test to by-pass any LAN equipment in order to isolate the testing entirely to the circuit. Note that an accurate mid-day test with iperf will be service impacting. In order to run an accurate test during the day, a test window with be scheduled with WiscNet and in some cases with AT&T and WiscNet. The test will entail disconnecting the red cable, as shown in the drawing below, and connecting a laptop to the juniper switch at point D, thus effectively isolating the WAN from the site LAN. Disconnecting the red cable will disrupt service for the site users.
Image Removed
WiscNet hosted speedtest.net
For a quick and easy speed test you may use WiscNet's HTML based browser test here speedtest.wiscnet.net.
| Note |
|---|
Please note: The accuracy of this speed test diminishes with larger bandwidth circuits The hardware performance of the client running this test has a significant impact on results |
WiscNet hosted Iperf
Iperf is a network testing tool used to help measure network throughput. It's developed by ESnet / Lawrence Berkeley National Laboratory. For more information please visit http://software.es.net/iperf/ and https://github.com/esnet/iperf
...
| title | Click here to expand technical details... |
|---|
WiscNet hosted speedtest.net
For a quick and easy speed test you may use WiscNet's HTML based browser test here speedtest.wiscnet.net.
| Note |
|---|
Please note: The accuracy of this speed test diminishes with larger bandwidth circuits The hardware performance of the client running this test has a significant impact on results |
WiscNet hosted Iperf
Iperf is a network testing tool used to help measure network throughput. It's developed by ESnet / Lawrence Berkeley National Laboratory. For more information please visit http://software.es.net/iperf/ and https://github.com/esnet/iperf
| Expand |
|---|
| title | Click here to expand technical details... |
|---|
|
Overview - Iperf is an open source tool. There are clients for Mac, Linux, BSD, etc. There is a port for Windows; however, in our testing we found it to lack certain features and to lag in performance.
- Iperf operates where one end is the client, the other is the server.
WiscNet Server Details TCP vs UDP Testing Iperf uses TCP by default. TCP has built in congestion avoidance. If TCP detects any packet loss, it assumes that the link capacity has been reached, and it slows down. This works very well, unless there is packet loss caused by something other than congestion. If there is packet loss due to errors, TCP will back off even if there is plenty of capacity. iperf allows TCP to send as fast as it can, which generally works to fill a clean, low latency link with packets. If a path is not clean/error free or has high latency, TCP will have a difficult time filling it. For testing higher capacity links and for links with higher latency, you will want to adjust the window size (-w option). - By using the -u option, you have told iperf to use UDP packets, rather than TCP. UDP has no built in congestion avoidance, and iperf doesn't implement it either. When doing a UDP test, iperf requires that the bandwidth of the test be specified. If it isn't, it defaults to 1Mb/s. You can use the -b option to specify bandwidth to test. iperf will then send packets at the request rate for the requested period of time. The other end measures how many packets are received vs how many were sent and reports its results.
Some Common Iperf Flags - Enter iperf -h or man iperf depending on your operating system. Here are some common flags:
| Flag | Details | Example |
|---|
| -c | Client mode | -c | | -t | Time to run the test in seconds | -t 30 | | -P | Number of parallel connections | -P 2 | | -u | UDP (default is TCP) | -u | | -b | Bandwidth per thread | -b 250m | | -i | Interval between bandwidth reports in seconds | -i 1 | -L | Listen on port | -L 5001 | -r | bidirectional test (individually) | -r | -d | bidirectional test (simultaneously) | -d |
|
| Note |
|---|
Please note: The hardware performance of the client running this test has a significant impact on results WiscNet has noticed that the Iperf clients for Linux, Unix, and macOS perform better than the ports for Windows |
Unidirectional UDP 1Gbps circuit test
Command
| Code Block |
|---|
iperf -c iperf.wiscnet.net -t 60 -P 20 -u -b 50m -i1 |
| Info |
|---|
" -t 10 " = 10 seconds. Since graphs.wiscnet.net pools every 5 minutes, you can modify the -t parameter to run it long enough for the graphs to reflect the speeds.
On some windows platforms, the above command works great for the upload and the command below generates more traffic for the download | Code Block |
|---|
iperf -c iperf.wiscnet.net -t 60 -P 10 -u -b 100m -i1 |
|
Results
| Expand |
|---|
| title | Click here to expand results... |
|---|
|
When runing multiple threads you must look at the SUM lines for total throughput. Output below shows successfully getting 953Mbits/sec through | No Format |
|---|
$ iperf -c iperf.wiscnet.net -t 10 -P 4 -u -b 250m -i1
------------------------------------------------------------
Client connecting to iperf.wiscnet.net, UDP port 5001
Sending 1470 byte datagrams
UDP buffer size: 208 KByte (default)
------- |
|
Overview
- Iperf is an open source tool. There are clients for Mac, Linux, BSD, etc. There is a port for Windows; however, in our testing we found it to lack certain features and to lag in performance.
- Iperf operates where one end is the client, the other is the server.
WiscNet Server Details
- WiscNet runs an Iperf version 2 server in Eau Claire, WI
- The server is restricted to WiscNet IP addresses
- Iperf2 and iperf3 are incompatible
- iperf.wiscnet.net runs a TCP Iperf server on the default port 5001
- iperf.wiscnet.net runs a UDP Iperf server on port 5001
- iperf.ipv6.wiscnet.net runs a v6 TCP Iperf server on port 5001
- iperf.ipv6.wiscnet.net runs a v6 UDP Iperf server on port 5001
TCP vs UDP Testing
Iperf uses TCP by default. TCP has built in congestion avoidance. If TCP detects any packet loss, it assumes that the link capacity has been reached, and it slows down. This works very well, unless there is packet loss caused by something other than congestion. If there is packet loss due to errors, TCP will back off even if there is plenty of capacity. iperf allows TCP to send as fast as it can, which generally works to fill a clean, low latency link with packets. If a path is not clean/error free or has high latency, TCP will have a difficult time filling it. For testing higher capacity links and for links with higher latency, you will want to adjust the window size (-w option).
- By using the -u option, you have told iperf to use UDP packets, rather than TCP. UDP has no built in congestion avoidance, and iperf doesn't implement it either. When doing a UDP test, iperf requires that the bandwidth of the test be specified. If it isn't, it defaults to 1Mb/s. You can use the -b option to specify bandwidth to test. iperf will then send packets at the request rate for the requested period of time. The other end measures how many packets are received vs how many were sent and reports its results.
Some Common Iperf Flags
- Enter iperf -h or man iperf depending on your operating system. Here are some common flags:
...
-b 250m
...
-L
...
-r
...
-d
...
| Note |
|---|
Please note: The hardware performance of the client running this test has a significant impact on results WiscNet has noticed that the Iperf clients for Linux, Unix, and macOS perform better than the ports for Windows |
...
Command
| Code Block |
|---|
iperf -c iperf.wiscnet.net -t 60 -P 20 -u -b 50m -i1 |
...
" -t 10 " = 10 seconds. Since graphs.wiscnet.net pools every 5 minutes, you can modify the -t parameter to run it long enough for the graphs to reflect the speeds.
On some windows platforms, the above command works great for the upload and the command below generates more traffic for the download
| Code Block |
|---|
iperf -c iperf.wiscnet.net -t 60 -P 10 -u -b 100m -i1 |
Results
| Expand |
|---|
| title | Click here to expand results... |
|---|
|
When runing multiple threads you must look at the SUM lines for total throughput. Output below shows successfully getting 953Mbits/sec through | No Format |
|---|
$ iperf -c iperf.wiscnet.net -t 10 -P 4 -u -b 250m -i1
------------------------------------------------------------
Client connecting to iperf.wiscnet.net, UDP port 5001
Sending 1470 byte datagrams
UDP buffer size: 208 KByte (default)
------------------------------------------------------------
[ 5] local 10.0.10.105 port 44098 connected with 205.213.14.56 port 5001
[ 3] local 10.0.10.105 port 46090 connected with 205.213.14.56 port 5001
[ 4] local 10.0.10.105 port 38200 connected with 205.213.14.56 port 5001
[ 6] local 10.0.10.105 port 59296 connected with 205.213.14.56 port 5001
[ ID] Interval Transfer Bandwidth
[ 5] 0.0- 1.0 sec 28.4 MBytes 238 Mbits/sec
[ 3] 0.0- 1.0 sec 28.5 MBytes 239 Mbits/sec
[ 4] 0.0- 1.0 sec 28.6 MBytes 240 Mbits/sec
[ 6] 0.0- 1.0 sec 28.6 MBytes 240 Mbits/sec
[SUM] 0.0- 1.0 sec 114 MBytes 957 Mbits/sec
[ 5] 1.0- 2.0 sec 28.5 MBytes 239 Mbits/sec
[ 3] 1.0- 2.0 sec 28.4 MBytes 238 Mbits/sec
[ 4] 1.0- 2.0 sec 28.5 MBytes 239 Mbits/sec
[ 6] 1.0- 2.0 sec 28.2 MBytes 236 Mbits/sec
[SUM] 1.0- 2.0 sec 114 MBytes 953 Mbits/sec
[ 5] 2.0- 3.0 sec 28.4 MBytes 238 Mbits/sec
[ 3] 2.0- 3.0 sec 28.2 MBytes 237 Mbits/sec
[ 4] 2.0- 3.0 sec 28.6 MBytes 240 Mbits/sec
[ 6] 2.0- 3.0 sec 28.5 MBytes 239 Mbits/sec
[SUM] 2.0- 3.0 sec 114 MBytes 953 Mbits/sec
[ 5] 3.0- 4.0 sec 28.3 MBytes 238 Mbits/sec
[ 3] 3.0- 4.0 sec 28.3 MBytes 238 Mbits/sec
[ 4] 3.0- 4.0 sec 28.5 MBytes 239 Mbits/sec
[ 6] 3.0- 4.0 sec 28.4 MBytes 239 Mbits/sec
[SUM] 3.0- 4.0 sec 114 MBytes 952 Mbits/sec
[ 5] 4.0- 5.0 sec 28.3 MBytes 237 Mbits/sec
[ 3] 4.0- 5.0 sec 28.3 MBytes 238 Mbits/sec
[ 4] 4.0- 5.0 sec 28.3 MBytes 238 Mbits/sec
[ 6] 4.0- 5.0 sec 28.7 MBytes 241 Mbits/sec
[SUM] 4.0- 5.0 sec 114 MBytes 954 Mbits/sec
[ 5] 5.0- 6.0 sec 28.6 MBytes 240 Mbits/sec
[ 3] 5.0- 6.0 sec 28.4 MBytes 238 Mbits/sec
[ 4] 5.0- 6.0 sec 28.3 MBytes 238 Mbits/sec
[ 6] 5.0- 6.0 sec 28.5 MBytes 239 Mbits/sec
[SUM] 5.0- 6.0 sec 114 MBytes 955 Mbits/sec
[ 5] 6.0- 7.0 sec 28.5 MBytes 239 Mbits/sec
[ 3] 6.0- 7.0 sec 28.3 MBytes 238 Mbits/sec
[ 4] 6.0- 7.0 sec 28.5 MBytes 239 Mbits/sec
[ 6] 6.0- 7.0 sec 28.3 MBytes 237 Mbits/sec
[SUM] 6.0- 7.0 sec 114 MBytes 953 Mbits/sec
[ 5] 7.0- 8.0 sec 28.4 MBytes 238 Mbits/sec
[ 3] 7.0- 8.0 sec 28.4 MBytes 238 Mbits/sec
[ 4] 7.0- 8.0 sec 28.3 MBytes 238 Mbits/sec
[ 6] 7.0- 8.0 sec 28.5 MBytes 239 Mbits/sec
[SUM] 7.0- 8.0 sec 114 MBytes 953 Mbits/sec
[ 5] 8.0- 9.0 sec 28.5 MBytes 239 Mbits/sec
[ 3] 8.0- 9.0 sec 28.3 MBytes 237 Mbits/sec
[ 4] 8.0- 9.0 sec 28.4 MBytes 238 Mbits/sec
[ 6] 8.0- 9.0 sec 28.4 MBytes 238 Mbits/sec
[SUM] 8.0- 9.0 sec 114 MBytes 953 Mbits/sec
read failed: Connection refused
[ 3] WARNING: did not receive ack of last datagram after 1 tries.
[ 5] 9.0-10.0 sec 28.5 MBytes 239 Mbits/sec
[ 5] 0.0-10.0 sec 284 MBytes 239 Mbits/sec
[ 5] Sent 202875 datagrams
[ 3] 0.0-10.0 sec 284 MBytes 238 Mbits/sec
[ 3] Sent 202276 datagrams
[ 4] 0.0-10.0 sec 284 MBytes 239 Mbits/sec
[ 4] Sent 202852 datagrams
[ 6] 0.0-10.0 sec 285 MBytes 239 Mbits/sec
[ 6] Sent 203078 datagrams
[SUM] 0.0-10.0 sec 1.11 GBytes 954 Mbits/sec
read failed: Connection refused
[ 5] WARNING: did not receive ack of last datagram after 5 tries.
read failed: Connection refused
[ 6] WARNING: did not receive ack of last datagram after 9 tries.
[ 4] WARNING: did not receive ack of last datagram after 10 tries. |
|
...
| Expand |
|---|
| title | Click here to expand the Ubuntu example... |
|---|
|
Many Lunix and Unix distros will have iperf in official repositories. Make sure to install iperf2 (iperf), not iperf3, to have compatability with WiscNet's iPerf server. Ubuntu - Install | Code Block |
|---|
| $ apt-cache search iperf | grep -i iperf
iperf - Internet Protocol bandwidth measuring tool
iperf3 - Internet Protocol bandwidth measuring tool
$ sudo apt-get install iperf |
Ubuntu - Example | Code Block |
|---|
| $ iperf -c iperf.wiscnet.net -t 10 -P 20 -u -b 50m -i1
------------------------------------------------------------
Client connecting to iperf.wiscnet.net, UDP port 5001
Sending 1470 byte datagrams
UDP buffer size: 208 KByte (default)
------------------------------------------------------------
[ 21] local 10.0.10.105 port 33836 connected with 205.213.14.56 port 5001
[ 5] local 10.0.10.105 port 39264 connected with 205.213.14.56 port 5001
[ 4] local 10.0.10.105 port 55180 connected with 205.213.14.56 port 5001
[ 6] local 10.0.10.105 port 41089 connected with 205.213.14.56 port 5001
[ 3] local 10.0.10.105 port 48475 connected with 205.213.14.56 port 5001
[ 7] local 10.0.10.105 port 37402 connected with 205.213.14.56 port 5001
[ 8] local 10.0.10.105 port 35544 connected with 205.213.14.56 port 5001
[ 9] local 10.0.10.105 port 38899 connected with 205.213.14.56 port 5001
[ 11] local 10.0.10.105 port 55616 connected with 205.213.14.56 port 5001
[ 10] local 10.0.10.105 port 45343 connected with 205.213.14.56 port 5001
[ 12] local 10.0.10.105 port 52147 connected with 205.213.14.56 port 5001
[ 15] local 10.0.10.105 port 48943 connected with 205.213.14.56 port 5001
[ 13] local 10.0.10.105 port 55655 connected with 205.213.14.56 port 5001
[ 14] local 10.0.10.105 port 37942 connected with 205.213.14.56 port 5001
[ 16] local 10.0.10.105 port 44809 connected with 205.213.14.56 port 5001
[ 17] local 10.0.10.105 port 37378 connected with 205.213.14.56 port 5001
[ 18] local 10.0.10.105 port 60936 connected with 205.213.14.56 port 5001
[ 20] local 10.0.10.105 port 54895 connected with 205.213.14.56 port 5001
[ 19] local 10.0.10.105 port 47884 connected with 205.213.14.56 port 5001
[ 22] local 10.0.10.105 port 46874 connected with 205.213.14.56 port 5001
[ ID] Interval Transfer Bandwidth
[ 5] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 4] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 6] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 3] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 7] 0.0- 1.0 sec 5.96 MBytes 50.0 Mbits/sec
[ 8] 0.0- 1.0 sec 5.96 MBytes 50.0 Mbits/sec
[ 9] 0.0- 1.0 sec 5.96 MBytes 50.0 Mbits/sec
[ 11] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 10] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 12] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 15] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 13] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 14] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 16] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 17] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 18] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 20] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 19] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 22] 0.0- 1.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 21] 0.0- 1.0 sec 5.97 MBytes 50.1 Mbits/sec
[SUM] 0.0- 1.0 sec 119 MBytes 1.00 Gbits/sec
[ 21] 1.0- 2.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 5] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 4] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 6] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 3] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 7] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 8] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 9] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 11] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 10] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 12] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 15] 1.0- 2.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 13] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 14] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 16] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 17] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 18] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 20] 1.0- 2.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 19] 1.0- 2.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 22] 1.0- 2.0 sec 5.97 MBytes 50.0 Mbits/sec
[SUM] 1.0- 2.0 sec 119 MBytes 1.00 Gbits/sec
[ 21] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 5] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 4] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 6] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 3] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 7] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 8] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 9] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 11] 2.0- 3.0 sec 5.96 MBytes 50.0 Mbits/sec
[ 10] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 12] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 15] 2.0- 3.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 13] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 14] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 16] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 17] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 18] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 20] 2.0- 3.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 19] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 22] 2.0- 3.0 sec 5.97 MBytes 50.0 Mbits/sec
[SUM] 2.0- 3.0 sec 119 MBytes 1.00 Gbits/sec
[ 21] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 5] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 4] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 6] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 3] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 7] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 8] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 9] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 11] 3.0- 4.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 10] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 12] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 15] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 13] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 14] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 16] 3.0- 4.0 sec 5.95 MBytes 49.9 Mbits/sec
[ 17] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 18] 3.0- 4.0 sec 5.95 MBytes 49.9 Mbits/sec
[ 20] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 19] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 22] 3.0- 4.0 sec 5.97 MBytes 50.0 Mbits/sec
[SUM] 3.0- 4.0 sec 119 MBytes 1.00 Gbits/sec
[ 21] 4.0- 5.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 5] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 4] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 6] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 3] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 7] 4.0- 5.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 8] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 9] 4.0- 5.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 11] 4.0- 5.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 10] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 12] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 15] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 13] 4.0- 5.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 14] 4.0- 5.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 16] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 17] 4.0- 5.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 18] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 20] 4.0- 5.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 19] 4.0- 5.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 22] 4.0- 5.0 sec 5.97 MBytes 50.1 Mbits/sec
[SUM] 4.0- 5.0 sec 119 MBytes 1.00 Gbits/sec
[ 21] 5.0- 6.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 5] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 4] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 6] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 3] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 7] 5.0- 6.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 8] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 9] 5.0- 6.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 11] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 10] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 12] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 15] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 13] 5.0- 6.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 14] 5.0- 6.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 16] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 17] 5.0- 6.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 18] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 20] 5.0- 6.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 19] 5.0- 6.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 22] 5.0- 6.0 sec 5.97 MBytes 50.0 Mbits/sec
[SUM] 5.0- 6.0 sec 119 MBytes 1.00 Gbits/sec
[ 21] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 5] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 4] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 6] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 3] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 7] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 8] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 9] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 11] 6.0- 7.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 10] 6.0- 7.0 sec 5.96 MBytes 50.0 Mbits/sec
[ 12] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 15] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 13] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 14] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 16] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 17] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 18] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 20] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 19] 6.0- 7.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 22] 6.0- 7.0 sec 5.97 MBytes 50.1 Mbits/sec
[SUM] 6.0- 7.0 sec 119 MBytes 1.00 Gbits/sec
[ 21] 7.0- 8.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 5] 7.0- 8.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 4] 7.0- 8.0 sec 5.96 MBytes 50.0 Mbits/sec
[ 6] 7.0- 8.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 3] 7.0- 8.0 sec 5.96 MBytes 50.0 Mbits/sec
[ 7] 7.0- 8.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 8] 7.0- 8.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 9] 7.0- 8.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 11] 7.0- 8.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 10] 7.0- 8.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 12] 7.0- 8.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 15] 7.0- 8.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 13] 7.0- 8.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 14] 7.0- 8.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 16] 7.0- 8.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 17] 7.0- 8.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 18] 7.0- 8.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 20] 7.0- 8.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 19] 7.0- 8.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 22] 7.0- 8.0 sec 5.97 MBytes 50.0 Mbits/sec
[SUM] 7.0- 8.0 sec 119 MBytes 1.00 Gbits/sec
[ 21] 8.0- 9.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 5] 8.0- 9.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 4] 8.0- 9.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 6] 8.0- 9.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 3] 8.0- 9.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 7] 8.0- 9.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 8] 8.0- 9.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 9] 8.0- 9.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 11] 8.0- 9.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 10] 8.0- 9.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 12] 8.0- 9.0 sec 5.97 MBytes 50.0 Mbits/sec
[ 15] 8.0- 9.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 13] 8.0- 9.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 14] 8.0- 9.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 16] 8.0- 9.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 17] 8.0- 9.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 18] 8.0- 9.0 sec 5.96 MBytes 50.0 Mbits/sec
[ 20] 8.0- 9.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 19] 8.0- 9.0 sec 5.97 MBytes 50.1 Mbits/sec
[ 22] 8.0- 9.0 sec 5.97 MBytes 50.0 Mbits/sec
[SUM] 8.0- 9.0 sec 119 MBytes 1.00 Gbits/sec
[ 21] 9.0-10.0 sec 5.96 MBytes 50.0 Mbits/sec
[ 21] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 21] Sent 42549 datagrams
[ 5] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 5] Sent 42548 datagrams
[ 4] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 4] Sent 42547 datagrams
[ 6] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 6] Sent 42549 datagrams
[ 3] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 3] Sent 42547 datagrams
[ 7] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 7] Sent 42549 datagrams
[ 8] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 8] Sent 42549 datagrams
[ 9] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 9] Sent 42550 datagrams
[ 11] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 11] Sent 42547 datagrams
[ 10] 0.0-10.0 sec 59.7 MBytes 50.0 Mbits/sec
[ 10] Sent 42551 datagrams
[ 12] 0.0-10.0 sec 59.7 MBytes 50.0 Mbits/sec
[ 12] Sent 42551 datagrams
[ 15] 0.0-10.0 sec 59.7 MBytes 50.0 Mbits/sec
[ 15] Sent 42551 datagrams
[ 13] 0.0-10.0 sec 59.7 MBytes 50.0 Mbits/sec
[ 13] Sent 42551 datagrams
[ 14] 0.0-10.0 sec 59.7 MBytes 50.0 Mbits/sec
[ 14] Sent 42552 datagrams
[ 16] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 16] Sent 42538 datagrams
[ 17] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 17] Sent 42547 datagrams
[ 18] 0.0-10.0 sec 59.6 MBytes 50.0 Mbits/sec
[ 18] Sent 42541 datagrams
[ 20] 0.0-10.0 sec 59.7 MBytes 50.0 Mbits/sec
[ 20] Sent 42553 datagrams
[ 19] 0.0-10.0 sec 59.7 MBytes 50.0 Mbits/sec
[ 19] Sent 42553 datagrams
[ 22] 0.0-10.0 sec 59.7 MBytes 50.0 Mbits/sec
[ 22] Sent 42553 datagrams
[SUM] 0.0-10.0 sec 1.17 GBytes 1.00 Gbits/sec
[ 5] Server Report:
[ 5] 0.0-10.0 sec 58.1 MBytes 48.7 Mbits/sec 0.173 ms 1100/42547 (2.6%)
[ 5] 0.0-10.0 sec 8 datagrams received out-of-order
[ 3] Server Report:
[ 3] 0.0-10.0 sec 57.6 MBytes 48.2 Mbits/sec 0.156 ms 1473/42546 (3.5%)
[ 3] 0.0-10.0 sec 4 datagrams received out-of-order
[ 13] Server Report:
[ 13] 0.0-10.0 sec 56.3 MBytes 47.2 Mbits/sec 0.164 ms 2368/42550 (5.6%)
[ 13] 0.0-10.0 sec 3 datagrams received out-of-order
[ 9] Server Report:
[ 9] 0.0-10.0 sec 57.1 MBytes 47.8 Mbits/sec 0.153 ms 1826/42549 (4.3%)
[ 9] 0.0-10.0 sec 2 datagrams received out-of-order
[ 15] Server Report:
[ 15] 0.0-10.0 sec 56.0 MBytes 46.9 Mbits/sec 0.148 ms 2596/42550 (6.1%)
[ 15] 0.0-10.0 sec 5 datagrams received out-of-order
[ 10] Server Report:
[ 10] 0.0-10.0 sec 56.9 MBytes 47.6 Mbits/sec 0.161 ms 1971/42550 (4.6%)
[ 10] 0.0-10.0 sec 2 datagrams received out-of-order
[ 7] Server Report:
[ 7] 0.0-10.0 sec 57.1 MBytes 47.8 Mbits/sec 0.161 ms 1827/42547 (4.3%)
[ 7] 0.0-10.0 sec 1 datagrams received out-of-order
[ 16] Server Report:
[ 16] 0.0-10.0 sec 55.7 MBytes 46.7 Mbits/sec 0.212 ms 2770/42537 (6.5%)
[ 16] 0.0-10.0 sec 11 datagrams received out-of-order
[ 17] Server Report:
[ 17] 0.0-10.0 sec 55.8 MBytes 46.7 Mbits/sec 0.159 ms 2756/42546 (6.5%)
[ 17] 0.0-10.0 sec 4 datagrams received out-of-order
[ 21] Server Report:
[ 21] 0.0-10.0 sec 57.5 MBytes 48.1 Mbits/sec 0.178 ms 1546/42548 (3.6%)
[ 21] 0.0-10.0 sec 1 datagrams received out-of-order
[ 22] Server Report:
[ 22] 0.0-10.0 sec 56.9 MBytes 47.6 Mbits/sec 0.204 ms 1969/42552 (4.6%)
[ 22] 0.0-10.0 sec 13 datagrams received out-of-order
[ 4] Server Report:
[ 4] 0.0-10.0 sec 57.3 MBytes 48.0 Mbits/sec 0.178 ms 1656/42545 (3.9%)
[ 4] 0.0-10.0 sec 10 datagrams received out-of-order
[ 8] Server Report:
[ 8] 0.0-10.0 sec 57.2 MBytes 47.9 Mbits/sec 0.159 ms 1763/42548 (4.1%)
[ 8] 0.0-10.0 sec 1 datagrams received out-of-order
[ 6] Server Report:
[ 6] 0.0-10.0 sec 57.3 MBytes 48.0 Mbits/sec 0.170 ms 1644/42548 (3.9%)
[ 6] 0.0-10.0 sec 5 datagrams received out-of-order
[ 11] Server Report:
[ 11] 0.0-10.0 sec 58.6 MBytes 49.1 Mbits/sec 0.160 ms 736/42546 (1.7%)
[ 11] 0.0-10.0 sec 2 datagrams received out-of-order
[ 14] Server Report:
[ 14] 0.0-10.0 sec 56.2 MBytes 47.0 Mbits/sec 0.180 ms 2481/42551 (5.8%)
[ 14] 0.0-10.0 sec 5 datagrams received out-of-order
[ 20] Server Report:
[ 20] 0.0-10.0 sec 55.8 MBytes 46.7 Mbits/sec 0.211 ms 2736/42552 (6.4%)
[ 20] 0.0-10.0 sec 2 datagrams received out-of-order
[ 18] Server Report:
[ 18] 0.0-10.0 sec 56.0 MBytes 46.9 Mbits/sec 0.213 ms 2582/42540 (6.1%)
[ 18] 0.0-10.0 sec 10 datagrams received out-of-order
[ 19] Server Report:
[ 19] 0.0-10.0 sec 55.6 MBytes 46.6 Mbits/sec 0.215 ms 2887/42552 (6.8%)
[ 19] 0.0-10.0 sec 9 datagrams received out-of-order
[ 12] Server Report:
[ 12] 0.0-10.0 sec 56.8 MBytes 47.5 Mbits/sec 0.200 ms 2048/42550 (4.8%)
[ 12] 0.0-10.0 sec 1 datagrams received out-of-order |
|
BadgerNet Overview
| Info |
|---|
The overview portion of this document has been created by BadgerNet / AT&T and edited by WiscNet. Its intent is to explain the requirements needed in order to procure accurate circuit testing results |
Internet speed tests results may be impacted by several variables, including
- Tool used to test
- Location of testing laptop/PC in the network
- Time of day when test is run
Speed Testing Tools
Most of our members test their internet connection speeds using online browser based tests against servers hosted somewhere on the Internet, for example, http://speedtest.wiscnet.net/ . These tests work fine for low bandwidth internet services but don’t scale well for high speed internet connections. In order to get an accurate speed test a different testing tool like iperf should be used.
Location of testing laptop/PC in the network
Location of the testing PC/Laptop is critical for accurate test results. Note, from the diagram below, that location D is the best place to test your Internet speed from. The reliability of test results go down as we move the test point to C, B and A.
The configuration and capacity of the laptop is equally critical for the accuracy of circuit testing. Please ensure your laptop network cards and configuration are Gig/Capable.
Time of Day
Browser-based speed test results can also vary based on time of day, depending on the bandwidth consumed by the site users at the time the tests are run. For example, if a site has a 100Mbps connection and the users at the site are already consuming 60Mbps download and 25 Mbps upload sustained bandwidth for their business use, the test results will only show 40Mbps download and 75Mbps upload speeds. Therefore, it is recommended that these tests are run before and after business hours if you are using a browser base testing tool.
Mid-day Testing
Some WiscNet members desire to run speed test during business hours to see if they are getting full bandwidth during the day. In others instances, WiscNet will require the test to by-pass any LAN equipment in order to isolate the testing entirely to the circuit. Note that an accurate mid-day test with iperf will be service impacting. In order to run an accurate test during the day, a test window with be scheduled with WiscNet and in some cases with AT&T and WiscNet. The test will entail disconnecting the red cable, as shown in the drawing below, and connecting a laptop to the juniper switch at point D, thus effectively isolating the WAN from the site LAN. Disconnecting the red cable will disrupt service for the site users.
Image Added