CS 244 '15: Reproducing Mosh Paper Results Team: Kevin McKenzie (kmckenzi) Patrick Harvey (p1harvey) Setting up the test server on EC2: Create an EC2 instance following the intstructions listed here: http://web.stanford.edu/class/cs244/ec2setup.html Select the AMI CS244-Spr15-Mininet or ami-cba48cfb on us-west-2 Select the c3.large instance type Configure the security group to allow SSH access Log into your EC2 instance and verify mininet by running: sudo mn --link tc,bw=10 --test iperf For more detailed instructions, see the link above. Setup: git clone https://github.com/kjtmckenzie/mosh_test.git cd mosh_test sudo ./setup.sh Running the setup.sh script will install all the relevant packages needed for the Mosh experiment. It may ask you for a "y" or "yes" to confirm the package installation. Run the experiment: sudo ./run.sh This will take roughly 2 hours, and it will generate 5 graphs in the mosh_test directory: 3G.png, 3G_FLAKY.png, 4G_LTE.png, 4G_LTE_FLAKY.png and WIFI.png. These show the same results of the Mosh paper for various mobile technologies. The original Mosh-paper only included results for 3G, so the 3G and 3G_FLAKY results are the most representative of the results were are trying to emulate. We used the following statistics gathered from real-world data by using the FCC Speed Test app at various locations around Escondido Village. Note: DELAY measures 1/2 of the RTT. JITTER is the amount any one link's bandwidth can change. A JITTER_FACTOR of .5 means a link could go from .5x bandwidth to 1.5x bandwidth. Bandwidth and delay are in milliseconds. Tech: 4G_LTE BANDWIDTH = 26.0 DELAY = 44.5 JITTER_FACTOR = .22 DROP_RATE = 0.0 Tech: 4G_LTE_FLAKY BANDWIDTH = 3.0 DELAY = 67.5 JITTER_FACTOR = 0.60 DROP_RATE = 0.063 Tech: 3G BANDWIDTH = 3.0 DELAY = 61.5 JITTER_FACTOR = 0.48 DROP_RATE = 0.013 Tech: 3G_FLAKY BANDWIDTH = 0.9 DELAY = 74.5 JITTER_FACTOR = 0.80 DROP_RATE = 0.087 Tech: WIFI BANDWIDTH = 68 DELAY = 4.0 JITTER_FACTOR = 0.76 DROP_RATE = 0.0