...
Bold face, topics for coming meeting that we need to address
Future
- Les has his Pakistan visa and airline tickets. There are problems getting authorization from DoE. How do things look following the Lahore American consulate incident?
- The draft letters of invitation for Sadia and Amber are with SLAC's international services. I have given expected dates of arrival, phone # and email addresses to SLAC international office. Current plan is for arrival April 1st.
- Sadia, Amber and Bilal have their SLAC computer and Wiki accounts. Amber had a problem with her Windows password. She is still having problems, Sadia is OK.
- Zafar received his DS-2019 on Dec 10 (Fri). Applied for visa on Dec 13 (Mon). Interview date was Jan 3, it has been delayed to 24 Jan. Visa accepted now await clearance. Expect ~3 weeks. Hope start march.
Pakistani case study - Zafar, Anjum
- Nodes wise details
- Pakistani case study is done for the moment.
- A summary of the case study is in the ICFA report.
- UETTaxila Zafar Amber is working on the Pakistani Case study.
- Zafar has started taking and archiving traceroutes between Pakistani monitoring hosts on a daily bases.
- There is an explanation for differences at the end of the year. A summary of the case study will go in the ICFA report.
. Amber making 24-30 Dec 14 plotsoverlay the daily information. She has sent new spreadsheet including all remaining metrics. Uploaded on wiki. - Amber has analyzed te patterns are confusing since UETTaxila had a strike, then there were exams, then off for the winter break. They will be back after coming Monday. The early morning load Sadia has seen maybe to students studying for exams. Umar will get the dates of the events at UETTaxila, and Amber and Zafar will update the wiki report.
- This is based on running long series of pings (1 week, 3 pings every 10 minutes). Amber will generate graphs to uncover the trends. Zafar has written some script and has some data, he needs to put into a format for Amber.
- Average 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 pingtableworking on prm.pl to add alpha and MOS. She has a local copy, when done will update on the server.
ICFA Report
- Progress on ICFA Report 2011, next steps The ICFA report has been submitted - Zafar
- Les needs to reviewZafar is working with Les on a case study for Egypt. Services have now been restored so we have more information to add. Umar suggested posting the study when ready on SlashDot.
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 as a landmark to TULIP.
- We are working on getting pinger2.pl working. The pinger.xml page needs to be fixed
- PingER archive site: Ghulam and Farhan couldn't discuss database architecture with Umar Kalim. They have however created have created two ERDs. One is a simple design (relatively inefficient) and another is a complex design (relatively efficient though it might introduce some redundancy) with multiple normalized tables that can be joined. 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.
Visualization pinger map - Faisal
- Colors for connected links
- Range and Colors configuration
- Layout revamp to provide more space for map
- have done some stress testing. The simple design is faster to load, the more complex design is faster to load data from. They will probably go with the more complex design.
TULIP
- 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.
- 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 CBG Bilal went to home time after exams, so far changed CBG to integrate into TULIP. ope to get to him by end of this week, when he returns meet on Monday.
PerfSONAR
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
- Faisal is working with Yee.
- Arrows for tracerouts being implemented by Faisal.
- Working with Yee to get Lat long of perfSONAR host corrected.
- 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
...
See \ [https://confluence.slac.stanford.edu/display/IEPM/Future+Projects\]. Zafar will talk to the students about these projects.
- Extend the NODEDETAILS data base to allow entry support for whether the host is currenty pingable.
Wiki Markup Wiki Markup - Improve the PingER2 installation procedures to make it more robust. This might be something for the person(s) in Pakistan who are responsible for installing PingER2 at the Pakistani monitoring sites. They probably have found where the failures occurs. Also look at the FAQ, and ping_data.pl which has been improved to assist in debugging, could it be further improved (e.g. provide access to the httpd.conf file so one can see if it properly configured)? There are 2 students working on the PingER archive. *Is this something they could work on?*
- Fix PingER archiving/analysis package to be IPv6 conformant|display/IEPM/Make+PingER+IPV6+compliant|\. Will build a proposal for an IPv6 testbed. They will try various transition techniques. A proposal has been prepared and that has been submitted to PTA. Adnan is a co PI. It is being evaluated today. A small testbed has been established in SEECS and the plan to shift some of the network to IPv6. Bilal is part of 3 students involved with PingER and they will be involved with IPv6. They are porting the PingER archive site site to using a database. They have redeveloped the archive site using Umar's documentation. They have set up a small test archive site. They have gathering, archiving, analysis. They will design a new database. They will also try a port of PingER to IPv6.
- Look at RRD event detection based on thresholds and how to extend, maybe adding plateau algorithm. Umar's algorithm did not work in a predictable manner.
- Provide near realtime plots of current pinger data using getdata_all.pl/wget. It will work as a CGI script with a form to select the host, the ping size, and the time frame to plot. It will use wget or getdata_all.pl to get the relevant data and possibly RRD/smokeping to display the data.
Paper - Umar, Fida, Zafar
...
Future meeting time - Les
The next meeting in Wednesday 26th January Wednesday February 11th 2011 for people in US and 27th January for people in Pakistan.