Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

We have sent email to Yahoo giving them an update on TULIP and how it might be extended to meet their needs.

Raja has found a further ~48 perfSONAR landmarks mainly in Europe and N. America. We now have 228 active unique landmarks. He now checks for new landmarks on a monthly basis. We have also created Taiwan as another region for which we can get good location information. We now work for N. America, Europe, Pakistan and Taiwan. He also uses the options feature of traceroute.pl to reduce the time for the PingER/perfSONAR landmarks to make the pings by a factor of 5. Given this we probably need to review the timeouts.

...

Raja  uses the options feature of traceroute.pl to reduce the time for the PingER/perfSONAR landmarks to make the pings by a factor of 5. Given this we probably need to review the timeouts.

We are looking at submitting a paper to IMC 2014. April 30, 2014 (see http://conferences2.sigcomm.org/imc/2014/cfp.html) is the submission date. this would discuss how TULIP works and share our experiences. Thus we might focus on: managing the appearance/disappearance of landmarks; the selecting of optimum timeouts for speedup plus any other ideas for speedup; where one could go next (e.g. colocation of landmarks on Yahoo, Google, Hotmail ... sites; impacts of heavy use and scaling (e.g. need for cluster for reflector, multiple landmarks at sites to not overwhelm a given landmark); concerns about network utilization); the relation of accuracy to landmark density (big item). Also more on potential uses such as visual traceroute, identifying proxies. Also maybe a bit more on the actual user interface (results from multiple sources besides TULIP) and implementation (parallel threads, tiering and adding new regions). The paper would assume we have a working TULIP as described in the other paper.

 

Raja has found 30 more PerfSONAR landmarks but they are all in North America so I haven't added them just yet

...

.

As the ICFA report winds down and Raja's work on TULIP begins to go into testing he will be engaging more with Renan and Linked Open Data. Raja has  sent email to Renan and has a list of things from Renan that Raja should look at.

...