Changes between Version 8 and Version 9 of GENIEducation/SampleAssignments/TcpAssignment/onepage


Ignore:
Timestamp:
08/09/13 14:05:26 (6 years ago)
Author:
epittore@bbn.com
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • GENIEducation/SampleAssignments/TcpAssignment/onepage

    v8 v9  
    166166}}}
    167167 Run an Iperf client on the Right node with 10 parallel TCP connections (use the -P option), connecting to an Iperf server on the Left node for 60 seconds. Simultaneously, run a 20 Mbps UDP Iperf client on the Top node connecting to an UDP Iperf server session running on the Left node for 60 seconds.
    168   '''1. Question:''' What are the throughput shown by the UDP and TCP Iperf server sessions? Why are they what they are?
    169   '''2. Question:''' Provide the necessary steps and commands to enable queueing disciplines that enforce fairness among all the 11 flows in the network, and demonstrate that your solution is effective.
     168  1. '''Question:''' What are the throughput shown by the UDP and TCP Iperf server sessions? Why are they what they are?
     169  2. '''Question:''' Provide the necessary steps and commands to enable queueing disciplines that enforce fairness among all the 11 flows in the network, and demonstrate that your solution is effective.
    170170
    171171'''3.3 Reordering [[BR]]'''
     
    176176}}}
    177177 As before, run a TCP Iperf client on the Right node connecting an Iperf server on the Left for 60 seconds.
    178  - 1. Question: What is the TCP goodput?
    179  - 2. Question: Introduce packet reordering, adding a 75 ms delay variance to the interface L with the following command:
     178  1. '''Question:''' What is the TCP goodput?
     179  2. '''Question:''' Introduce packet reordering, adding a 75 ms delay variance to the interface L with the following command:
    180180 {{{
    181  sudo /sbin/tc qdisc change dev L root handle 1:0 netem delay 100ms 75ms
     181  sudo /sbin/tc qdisc change dev L root handle 1:0 netem delay 100ms 75ms
    182182 }}}
    183  What is the TCP goodput now?
    184  - 3. Question: By tweaking the parameters in the file ''/proc/sys/net/ipv4/tcp_reordering'', how much can the TCP goodput be improved? What is the best goodput you can show? Why is too high or two low value bad for TCP?
     183  What is the TCP goodput now?
     184  3. '''Question:''' By tweaking the parameters in the file ''/proc/sys/net/ipv4/tcp_reordering'', how much can the TCP goodput be improved? What is the best goodput you can show? Why is too high or two low value bad for TCP?
    185185
    186186'''3.4 Performance of SACK under Lossy Conditions'''
     
    190190sudo /sbin/tc qdisc add dev L root handle 1:0 netem loss 10%
    191191}}}
    192  - 1. Question: What kind of goodput do you get using CUBIC with SACK (the default configuration)? Why do you see this performance?
    193  - 2. Question: Disable SACK at the sender using this command:
    194 {{{
    195 echo 0 | sudo tee /proc/sys/net/ipv4/tcp sack
    196 }}}
    197   What is the goodput without SACK? In what circumstances is SACK most beneficial? Remember that, due to the random nature of loss events, these experiments must be repeated at least five times to draw any conclusions.
     192  1. '''Question:''' What kind of goodput do you get using CUBIC with SACK (the default configuration)? Why do you see this performance?
     193  2. '''Question:''' Disable SACK at the sender using this command:
     194{{{
     195  echo 0 | sudo tee /proc/sys/net/ipv4/tcp sack
     196}}}
     197   What is the goodput without SACK? In what circumstances is SACK most beneficial? Remember that, due to the random nature of loss events, these experiments must be repeated at least five times to draw any conclusions.
    198198
    199199'''3.5 An Experimental Congestion Avoidance module for Linux'''[[BR]]