Changes between Version 4 and Version 5 of PlasticSlices/BaselineEvaluation/Baseline7Details


Ignore:
Timestamp:
07/11/11 21:11:12 (13 years ago)
Author:
hdempsey@bbn.com
Comment:

minor style, typo edits

Legend:

Unmodified
Added
Removed
Modified
  • PlasticSlices/BaselineEvaluation/Baseline7Details

    v4 v5  
    33Here are the details of [wiki:PlasticSlices/BaselineEvaluation#Baseline7 Baseline 7], divided by slice.
    44
    5 In this baseline, we intended to run multiple rounds of experiments, one for each set of Emergency Stop tests, but we only ended up running one round. We left the "round" structure (on this page and in the log directory) in place for simplicity. We'll run additional rounds after GEC 11 in the continuation phase of this project.
    6 
    7 We conducted two Emergency Stop tests: One in which the GMOC contacted the site admins about supsicious traffic from a slice (plastic-104 in this example) and asked them to cut it off; and one to simulate the situation in which the GMOC is unable to contact any site admins, and cuts off traffic in the core. We used BBN as the site for both tests, and uncovered a variety of issues, which we've discussed with the GMOC, who are updating their documentation and procedures.
     5In this baseline, we intended to run multiple rounds of experiments simulating Emergency Stop requests at different campuses.  We completed one round with the GMOC and agreed to test with other sites after making some improvements to procedures and documentation. We left the "round" structure (on this page and in the log directory) in place for simplicity. We'll run additional rounds after GEC 11 in the continuation phase of this project.
     6
     7We conducted two Emergency Stop tests: One in which the GMOC contacted the site admins about suspicious traffic from a slice (plastic-104 in this example) and asked them to cut it off; and one to simulate the situation in which the GMOC is unable to contact any site admins, and cuts off traffic in the core. We used BBN as the site for both tests, and uncovered a variety of procedural and documentation issues, which the GMOC is addressing.
    88
    99The raw logs of each experiment are at http://www.gpolab.bbn.com/plastic-slices/baseline-logs/baseline-7/, with a subdirectory for the logs from each round.
    1010
    11 The logs from this baseline are somewhat misleading, because we forgot to stop the experiments immediately after the Emergency Stop tests, so they show disruptions from the following day (e.g. from the NLR OpenFlow stack migration) that are entirely unrelated to the Emergency Stop tests themselves.
     11The raw logs from this baseline are somewhat misleading, because we did not stop the experiments immediately after the Emergency Stop tests, so they show disruptions from the following day (e.g. from the NLR OpenFlow stack migration) that are entirely unrelated to the Emergency Stop tests themselves.  We will separate the Emergency Stop period for the remainder of the experiment duration in our final analysis.
    1212
    1313= plastic-101 =
     
    113113=== Analysis ===
    114114
    115 The high packet loss was caused by the NLR OpenFlow software stack migration, not the Emergency Stop test itsef.
     115The high packet loss was caused by the NLR !OpenFlow software stack migration, not the Emergency Stop test itself.
    116116
    117117= plastic-102 =