...
Wednesday June 25th, 2014 9:00pm Pacific Standard Time, Thursday June 26th 2014 9:00am Pakistan time, Thursday June 26th, 2014 12:00 noon Malaysian time, Thursday June 26th, 2014 1:00am Rio Standard Time.
Attendees
Invitees:
Anjum+, Hassaan Khaliq+, Kashif+, Raja+, Johari+, Nara, Abdullah, Badrul, Ridzuan-, Ibrahim+, Hanan, Saqib+, Adib, Les+, Renan, Bebo+
+ Confirmed attendance
- Responded but Unable to attend:
Actual attendees:
Administration
Anjum, Hassaan, Kashif, Raja, Ibrahim, Saqib, Bebo, Les
The meeting had several interruptions, high noise events and some people being unable to be heard so not everyone was on all the time.
Administration
- Anjum reports (6/23/2014) that "the proposal for conference has been submitted for approval and Pinger has been added in the agenda. Travel expenses for Les and Bebo have also been included in the conference proposal. We are awaiting the proposal approval. If the proposal gets approved, we can then decide on wether to actually conduct the Pinger Workshop at UM or at another place. I am saying this because I believe a stand alone pinger workshop will be more preferable." It has been approved by the dean, next it goes to the chancellor. Hope to have decision in a couple of weeks. Once the approval is given the venus for the conference can be at UM or UUM.
As discussed earlier, the only twist here is Adib is waiting to hear from colleague (Dr. Nordin: chair of ISTT2014), there was no update as of this meeting. The conference is 2 days so the workshop may be squeezed to one day. The conference will be held in Langkawi between 24-26 Nov.
Hopefully, this will help us to attract good number of participants and get sponsor/support to cover our expenditure. Other option is to conduct the workshop in UUM, we are ready to provide Local Arrangement (lab, local transportation, and food). But there is no funding provided by the school to support the transportation/accommodation of the speakers.
- Anjum reports (6/23/2014) that "the proposal for conference has been submitted for approval and Pinger has been added in the agenda. Travel expenses for you and Bebo have also been included in the conference proposal. We are awaiting the proposal approval. If the proposal gets approved, we can then decide on wether to actually conduct the Pinger Workshop at UM or at another place. I am saying this because I believe a stand alone pinger workshop will be more preferable.
As discussed earlier, the only twist here is that Pinger will be seen as a case study for big data. This is good in a sense that people interested in doing research in the domain of big data can deploy pinger monitoring nodes at their respective universities/organisations and in return, play around with the data.
We have to wait for the approval of proposal for conducting the workshop at UM. Tentative Dates are 24th and 25th November 2014." Les will be in Burkina Faso Nov 13-21. He flies back to London on Nov 22nd. He can get to Malaysia mid morning November 24th. Thus the workshop should be at the end of the ISTT2014 meeting if Les is to attend.
- We agreed that it looked like the 25th would be a good day for the PingER workshop. Les should be able to make it from Burkina Faso, and Bebo should be able to get back to the US for Thanksgiving. There would be back to back presentation on how PingER gathers, archives data, what data there is, the data types, how to access etc. by Les followed by Bebo on Google Tools for Big data.
Les will be in Burkina Faso Nov 13-21. He flies back to London on Nov 22nd. He can get to Malaysia mid morning November 24th.
- Bebo will be in Western Australia, Okinawa and possibly Singapore Bebo will be in Western Australia, Okinawa and possibly Singapore in November. Bebo says: "A workshop beginning on November 17 (or that week) would be ideal for me." I think that conflicts with Les who is in Burkina Faso that week.
- Anjum suggested putting together a paper on metrics provided by PingER for Sigmetrix. The due date is in November.
Renan
...
The continuation of Renan's work on access toPingER data via Linked Open data is now an official project on the Reference Center on Big Data at UFRJ. That is good news, as we have three students working on it (one more than initially planned during Renan and Luiza's trip to Stanford, California). Up to this moment, Renan has
...
just explained with more details what we have done so far and what needs to be done.
...
The next steps are to define a work plan for the next months.
about to start new experiments and researches. Renan reports "Our whole country is working a bit differently these past days because of the World Cup. We are having lots and lots of holidays, which slows down a bit our production".
...
Ibrahim Abaker is planning to work on a topic initially entitled " leveraging pingER big data with a modified pingtable for event-correlation and clustering". Ibrahim has a proposal, see https://confluence.slac.stanford.edu/download/attachments/17162/leveraging+pingER+big+data+with+a+modified+pingtable+for+event-correlation+and+clustering.docx. He is currently spending time reading about RDF storage and its retrieval, also he is trying to setup Hadoop clusters for the experiment. He is in email discussion with Renan on which part to work on first. He plans to collaborate with Renan to make the pinger store and process more efficient. Les has sent him documentation of PinGER which is very helpful. Ridzuans' work is more to do with hosting the data and stream data analysis. Ibrahim is looking more at applying MapReduce ( programming model for processing large data sets with a parallel, distributed algorithm on a cluster), reducing the storage needs and providing querying of the data. No word from Ibrahim 6/4/2014. Requested update 6/23/2014.
UNIMAS
Ibrahim reported that in the last few months he has tried to come up with the scenario to pre-process RDF format using N-Triple and store in Key-value store database in Hadoop platform. He installed hadoop but in a Single not using CMC which is cloud services provided by UM Single Node.
UNIMAS
Johari was unable to attend so there was no update 9/25/2014. Johari has compleetd his PhD and is Dr. Johari Abdullah now. He has alos been appointed Dean. This means his life is filled with meetings and less free time. He plans to nominate someone to fill in for UNIMAS. Johari will try to attend the skype meeting but at the same time bring Dr. Adnan Shahid Khan who recently joined UNIMAS, will be joining our PingER group and will help with the current PingER initiative in UNIMAS. Once he is up to speed on PingER he will join the group to the meeting as well. Adnan is coming up to speed.
The Raspberry Pi is at the data centre and has a public IP address. It was working last week, until the UPS failed over the weekend. It did not reboot itself. Johari will look at the problem.
...
Johari has a research student who finalized a proposal in order to officially apply for his masters. He will start in February. He is currently working on threshold/anomaly detection, and will extend to correlating performance over multiple routes. He will share the proposal with Les and others April. No progress 6/4/2014.
UTM
No updates regarding traceroute problem at UTM. However, Saqib thinks the problem is still in CICT firewall or router as tcp traceroute command works fine from UTM.
Les has reviewed the Malaysian Case Study and sent suggestions. Saqib will incorporate. Saqib met with MYREN who have made many topology changes. Saqib will also incoporate these into the Malaysian case study.
Saqib is in discussions with his PhD superviser to get the requirements for a PingER proposal and to see where to submit it.
UUM
...
Johari has a research student who finalized a proposal in order to officially apply for his masters. He will start in February. He is currently working on threshold/anomaly detection, and will extend to correlating performance over multiple routes. He will share the proposal with Les and others April. No progress 6/4/2014.
UTM
No updates regarding traceroute problem at UTM. However, Saqib thinks the problem is still in CICT firewall or router as tcp traceroute command works fine from UTM.
Saqib met with MYREN who have made many topology changes. Saqib will also incorporate these into the Malaysian case study. He is seeing anomalously long delays between mainland Malaysia and Sarawak. It does not appear to be due to congestion. We need to understand the routing and which undersea cables are being used. Saqib will send more details after the meeting. He will also contact MYREN.
Saqib's proposal is almost ready however we do not see somewhere (funding agency) to submit it to. The next round of the FRGS may be the next opportunity
UUM
Regarding the monitoring host in UUM, Adib has assigned one student to prepare the configuration/installation plan including how to secure their host from attack. He has a public IP address. He needs to the DNS registration by Sunday 25th May or Monday. He is in the last stage of working with the Computer Center. Adib requested Johari to share the UNIMAS setting so it is easier for the student to follow. No update 6/5/2014, 6/25/2014.
UUM pinger is almost ready. Adib has got an public IP address together with a dns name. Once this is settled the tracreoute.pl will follow. This will increase the number of landmarks in mainland Malaysia by 50% and improve geolocation. Adib plans to get to this next week when he returns from vacation.
NUST
The Bahawalpur site for new PingER Monitoring node: Kashif contacted once again tohe Director IT, and this time he replied positively and he is waiting for the new machine and hopefully the installation of PingER node will be done in next week.
...
- duhs.seecs.edu.pk, Kashif recommends to drop they do not seem interestedinterested. This has been done.
- pinger.kohat.edu.pk, System issue, we are sending new motherboard in this week.
- pingerkhi-uok.pern.edu.pk, SFP Connector Problem, We are sending new one in this week.
- sau.seecs.edu.pk, System Issue, New system is ready and will send in this week.
- uaf.seecs.edu.pk, Drop (IP blocked frequently so currently not good as a PingER)
Raja
- are sending new one in this week.
- sau.seecs.edu.pk, System Issue, New system is ready and will send in this week.
- uaf.seecs.edu.pk, Drop (IP blocked frequently so currently not good as a PingER). Anjum recommended that if we do not have another host in faislabad then this host may be very important. Since Kashif is from Faisalabad, Anjum suggested we try a bit more if there is no other host. Looking at the map (see http://www-wanmon.slac.stanford.edu/wan-mon/viper/pinger-coverage-gmap.html), it appears PK.PERNFSBDPOP.EDU.N1 is nearby. Thus UAF has been dropped.
Raja
Raja has added an optional feature to exclude water areas from the acceptable area. this reduces the error (proportional to area), but sometimes leads to a less accurate centroid. Currently it is only available for N. America. He will update the documentation with examples. The number of working, usable landmarks is now up to 340. Raja has improved improving the GUI for TULIP. In particular visualizing the intersection region (showing both the minimum and maximal circles), showing landmarks, adding Google analytics. Raja has added undns (a tool for guessing the location from the router name) to TULIP and also to VTrace. It is not very successful, its heuristics are outdated (last update 2005)
PingER at SLAC
Les requested an update from Yahoo about TULIP's geolocation. They answered "We are very much interested in getting IP triangulation at internet scale, we will have internal sync-up on how we can leverage this initiative if there is rate limit and get back. Regarding opening up yahoo sites for deploying ping server requires some more time to discuss this with relevant stake holders with in yahoo." No word, sent a reminder 5/19/2014. No response 6/4/2014, 6/25/2014. Sent an update on the applicability to visual traceroute..
Les sent email to Google as follows: "I would like to bring to your attention that we have developed a geolocation tool using delay based (using RTTs from known ping server landmarks) distance estimates to triangulate the location of an IP host target. The tool is accessible at: http://www-wanmon.slac.stanford.edu/cgi-wrap/reflex.cgi. We have identified that the accuracy of the geolocation is directly related to the landmark density (e.g. # of landmarks/ million sq km). The higher the density the smaller the error and the fall off is exponential. We currently have over 1000 registered landmarks, of which at any given time ~300 are working. The tool not only finds the location of the target, it also gives an estimated error. To the best of our knowledge it is the only freely available delay based measurement geolocation service publicly available today. A drawback (compared to database methods such as those based on GeoMind) is the time taken to make the measurements. We have worked on this from many directions including parallelization of the ping requests, caching, tiering to get the rough location (i.e. region of the world) then zooming in using all landmarks in the region. We are putting together a publication on this." Les sent an update to his contact at Google 6/23/2014, stressing the applicability to traceroute visualization.
...
Anjum suggested Saqib, Badrul and Johari put together a paper on user experiences with using the Internet in Malaysia as seen from Malaysian universities. In particular round trip time, losses, jitter, reliability, routing/peering, in particular anomalies, and the impact on VoIP, throughput etc. It would be good to engage someone from MYREN.
Potential projects
Future meeting - Les
Next meeting Wednesday July 16th 2014 9:00pm Pacific Standard Time, Thursday July 17th 2014 9:00am Pakistan time, Thursday July 17th, 2014 noon Malaysian time, Thursday July 17th, 2014 01:00am Rio Standard Time.
...