Versions Compared

Old Version 2

changes.mady.by.user Les Cottrell

Saved on

compared with

New Version 3

changes.mady.by.user Les Cottrell

Saved on

Key

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

...

  • Nodes wise details
  • Amber is working on the Pakistani Case study.
    • Zafar has started taking and archiving traceroutes between Pakistani monitoring hosts on a daily bases.
    • A summary of the case study is in the ICFA report.
  • UETTaxila Zafar
    • Zafar has started taking and archiving traceroutes between Pakistani monitoring hosts on a daily bases.
    • Amber has analyzed, apart from high congestion it is hard to get patterns of useAverage RTT decreased since the nodes shifted to PERN network but the packet loss increased. This is usually apparent for Peshawar and Quetta. One major reason is the shift of these nodes to PERN network. Since PERN is a federated network and due to the shift of nodes, traffic on the network increased (PERN is up to its maximum utilization). Due to this though the RTTs decreased (since it is a federated environment), the packet loss increased due to congestion. Another possible reasons could be increase of nodes (especially in Peshawar region), due to which network congestion increases and thus packet loss increases.
  • Amber will need to get up to speed on Linux.
  • Need to get TCP configuration parameters for transmit and receive buffer lengths at end sites, and also at edge routers. Adnan talking to Zeeshan to get an update to see if he has talked to people.
  • Need table of monitors vs remote sites for Pakistan. Do for a typical month, e.g. November. Amber will include this in the case study.
  • Need a trend plot Jun-Dec 2010. - PROGRESS?
  • Need number of hosts etc, see (https://confluence.slac.stanford.edu/display/IEPM/Pakistani+Case+Study+2010-2011). This will be added to the Pakistani case study.
  • Look at NUST trends over last year, which sites have improved
  • Sadia is looking at adding MOS and alpha into pingtable.

ICFA Report

  • The ICFA report has been submitted - Zafar
  • Zafar is working on a case study for Egypt
  • Progress on ICFA Report 2011, next steps - Zafar
  • Les needs to review.

PingER

  • I have extended The traceroute server and ping_data.pl to provide more debugging capabilities, based on experience with UERJ, AMPATH and ACME.
  • No progress on a monitor in Sarawak. It was using Linux selinux that blocks pings & traceroutes. That has been disabled. Now the webserver is down.
  • have been installed and working in Sarawak.
    • The traceroute/ping server needs to be added to TULIP.
  • We are working on getting pinger2.pl working. The pinger.xml page needs to be fixedFahad made some small changes to http://www-wanmon.slac.stanford.edu/cgi-wrap/checkremote.cgi. He will add some help and also an allyearly tick. It looks quite useful.
  • PingER archive site: Ghulam and Farhan couldn't discuss database architecture with Umar Kalim. They have however created two ERDs. One is a simple design (relatively inefficient) and another is a complex design (relatively efficient though it might introduce some redundancy). They have created MySQL databases following both ERDs and will start work on stress testing it as soon as they are free from exams. Zafar has discussed stress testing with them already and they have a fair idea of what to do.

...

  • With the move to the new host Faisal had to get a new cookie to allow scriptroute to run scripts on the PlanetLab infrastructure. Still needs testing.
  • Get the MatLab license at SEECS and put up a CGB server using it. Do not have license for MatLab will do on own machines to test and will migrate when have license. Zafar will contact Arshad and Ali. Basically the client will call the reflector with the target. The reflector will return the landmarks and RTTs. The client will then call the CBG/MatLab server with the relevant RTTs, lat/longs etc.   Progress
  • Bilal has read the TULIP architecture. He has a moderate understanding of how it works. He is modifying CBG code. Now it is ready for integration with TULIP. I sent the reflector/eventhandler, tulip-viz.cgi, & Faisal sent the Java code to Zafar. A student was given a task. Zafar needs to answer where we are, and the progress. Adnan will get back to us ibn a day or so to tell progress. There will be exams in the coming week, so progress may be stalled for a while. May be an issue with the MatLab

...

Problems were fixed. NTP servers were causing considerable clock delay. Added close-by Stratum 1 NTP servers to solve the problem. Nodes were updated to PerfSONAR version 3.2 (Fedora distro). Nodes however are offline since they were disrupting normal traffic. We are waiting for 10 Mbps dedicated connection to switch the nodes back on. - Update

  1. Faisal is working with Yee.
    1. Arrows for tracerouts being implemented by Faisal.
    2. Working with Yee to get Lat long of perfSONAR host corrected.
  2. Zafar - deploy PerfSONAR nodes at SEECS. Second step is to find whether the same can be done at HEC on PERN's network. It is working, congratulations! Internet2 Joint Techs meeting at the end of Jan. Can Pak PerfSONAR nodes be up by then?

Possible projects

Wiki Markup
See \[https://confluence.slac.stanford.edu/display/IEPM/Future+Projects\]. Zafar will talk to the students about these projects.

...