User login

Stephen Eichler's blog

24

Aug

2015

Responded to critique and updated the chapters: "Analysis of fields other than the classic five tuple" and "Detection of black holes in load balancers". Changes included improved description of tables and interpretation of figures. The chapters were reread once the changes were made.

18

Aug

2015

Updates to the chapter of my thesis on load balancing by non classic 5-tuple fields have been carried out. The question arose as to what my strongest conclusions were. A further analysis was carried on by finding all of the cases where there were no cases of a node seen as load balancing occurring as non load balancing i.e. there were hits but no misses at each occurrence of an interface in trace data. These cases of non per-packet hits with no misses were summarised and presented as stronger evidence of this type of load balancing, than when non load balancing cases of the interface were found. Two cases of load balancing on a number of non 5-tuple fields occurred where there were no misses at all.

13

Aug

2015

I responded to critique of the chapters on "efficient analysis of per destination load balancers" and "load balancer turnover in the Internet". In the main, there were improvements in precision and detail to be made.

03

Aug

2015

I received feedback on two chapters and made changes based on this. The chapters were data collection and load balancer prevalence in the Internet.

27

Jul

2015

An update to the CDF analysis at the 99.99% joint confidence MDA data was required. When the multipath detection algorithm runs sometimes flow IDs are repeated to test for per packet load balancers. It was necessary to take these repeats out of the analysis that estimates stopping values from real world Internet data.

Another change to this analysis was to include comparison between doing the analysis with and without allowing repeats of the same load balancing interface. On one hand it is desirable to avoid repeated analysis of the same part of the Internet for sample integrity, and on the other hand processing larger numbers of load balancers to produce CDF data allows for more data points beyond the cut off probability, a desirable outcome.

I have made updates to the chapter on stopping values in my thesis, based on Richards critique.

16

Jul

2015

A modification was made to the diamond detection part of Megatree. This was a minor upgrade to better find the convergence points of asymmetric load balancer diamonds. In particular what was added, was a step to find the maximum value for probe TTL for a given link node. Doing this seems to reduce the chance of finding a node further downstream from the convergence interface as convergence. The updated analysis is running at present, and counts of convergence points found for a given divergence point will be compared with results before the modification.

I finished the initial checking of my thesis draft and so I am now hoping for some feedback to help finalise things.

07

Jul

2015

The IS0 thesis chapter update was completed with the new validation results and checked.

The chapter on load balancer prevalence thesis chapter was updated to rely on validation from the per destination load balancer analysis with limited flow IDs. Basically this analysis relies on finding diamond divergence points confidently without discovering all successors or nested load balancers confidently. This vastly reduces the amount of traffic required while still providing some key information.

A literature search for more relevant papers was carried out. Discussion and references were added to the related work thesis chapter as appropriate.

01

Jul

2015

This week has focused on the check-paths routine for validating the IS0 simulator. I recently found that this routine was getting into an endless loop, though it did not exhibit runaway memory usage. The problem was that it was looking for a next hop and replying not found, and so on. It turned out that it was not reading missing hop identifiers from the hops-dest file of hop information, and so there were gaps in some traces when read into the hash tables. Another problem was that reading the TTL value from the log file looked for an equals sign that didn't exist, and so the whole line was read as the TTL value causing the hash table to be corrupted. Finally the simulator message string was too short to print some of the longer messages. This also resulted in some errors when analysing the trace log file, as for example some addresses were truncated and were flagged as incorrect by the program.

23

Jun

2015

I have written a chapter on efficient discovery of load balancer diamond divergence points at the expense of internal diamond nodes. This used a restricted set of flow IDs. There is now also a corresponding section in the discussion chapter.

I also wrote a chapter on improving the efficiency of MDA analysis by changing the way in which the source port flow ID is chosen. The three methods were incrementing, random and sequential bit flipping. Sequential bit flipping did not appear to offer any advantage in discovering the successor set of a load balancer sooner. However it was hard to know what to expect as there are likely to be a number of different hashing algorithms used by different types of routers.

08

Jun

2015

The IS0 Doubletree chapter was updated. Now included is data on link usage and global stop set hits. This information is available because of the greater complexity of IS0 than the trace based simulator and it also helps with validation to some extent.

Fuller results were added for the CAIDA data based Doubletree trace based simulator.

In the Megatree chapter graphs formatting was improved and the introduction and validation sections were double checked and updated.

A new run of the black hole detector was initiated. Also all of my warts files were compressed.