Wednesday Feb 10 8:00pm Pacific Standard Time, Thursday Feb 11, 2016 9:00am Pakistan time, Thursday Feb 11 2016 12:00noon Malaysian time, Thursday Feb 11 2016 02:00am Rio Standard Time.
See: http://pinger.unimas.my/pinger/contact.php
Hassaan Khaliq, Kashif, Raja, Samad Riaz (SEECS); Saqib+, Aqsa (UOA); Johari+, Nara, Adnan Khan+ (UNIMAS); Abdullah, Badrul, Anjum, Ridzuan, Ibrahim (UM); Hanan (UTM); Adib+, Fatima (UUM); Fizi Jalil (MYREN); Thiago, Les+, Bebo (SLAC).
Note returned to original time on the hour since no longer need to accomodate Johari.
+ Confirmed attendance
- Responded but Unable to attend:
? Individual emails sent
Saqib (but lost connection), Johari, Adnan, Adib, Les
Huffington Post article on PingER and African Internet performance, see http://www.huffingtonpost.com/david-tereshchuk/a-giant-leap-in-2016-africa_b_8901556.html
Anjum said it would be good for Hassaan to attach this to his proposal. Any action?
Les is working with the SLAC CIO to try and put something together for publicity concerning the life of PingER.
Survey on Big Data Indexing strategies, also SLAC-PUB-16460, Fatima Bintu Adama, Adib Habbal, Suhaidi Hassan, R. Les Cottrell. Bebo White, Ibrahim Abdullahi, , submitted to NETAPPS 2015.
Worldwide Internet Performance Measurements Using Lightweight Measurement Platforms, alsoSLAC-PUB-16461,R. Les Cottrell, Thiago Barbosa, Bebo White, Johari Abdullah and Topher White, submitted to NETAPPS 2015.
PingER Malaysia-Internet Performance Measuring Project: A Case Study, also see SLAC-PUB-16462, Saqib Ali, R. Les Cottrell, Anjum Naveed, submitted to NETAPPS 2015.
Adaptive Geolocation of Internet Hosts, also SLAC-PUB-16463, Raja A.A. Khan, Roger L.A. Cottrell, Anjum Naveed, SLAC-PUB-16360, submitted to NETAPPS 2015.
9 students from Amity University near New Delhi in India interested in coming to SLAC. Bebo sent reminder recently, response below:
They have gone through the installation instructions for traceroute.pl, ping_data.pl and pinger2.pl. pinger2.pl appears to work, however we cannot access eth data by ping_data.pl. There is also a problem that their web server appears to be local, see Setting up PingER servers at Amity
This is a proposed project for one of the Indian students.
Bebo has set up a Github codebase as a new project. It contains the PingER MA (pinger2.pl and the traceroute/ping server). Anyone needs to sign up for a Github account (if you don't already have one), so you can be added as a project member.
Name: Aqsa Hameed
Title: visualization of PingER historical data using warehouse
Status: Our idea is to develop a warehouse in our university and make it publicly available.
Name: Sara Masood
Title: PingER Internet Performance Monitoring Agent On Android Device
Status: She sent you & Dr Bebo the mockup screens of the proposed Android Monitoring Agent. She is waiting for your review. Further, she requires web services to get and save PingER data.
Name: Saba Muzamil
Title: She is interested to work on Environment that supports the execution of analytical distributed queries in Hadoop Cluster.
Name: Tahseen
Title: Handling Missing Data in PingER by using Artificial Intelligence
Status: He is doing the literature review to find out the best algorithm to handle missing data in PingER.
About IoT:
Title: Air Quality measuring network in University of Agriculture Faisalabad.
Status: Now we have two Raspberry Pi-2 and few air quality measuring sensor i.e.; NO, CO, O3. Currently, working on the configuration and programming of the Pi-2 and the sensors.
Project on Internet performance has been accepted, but no funding yet.
Saqib's old supervisor Dr. Md Asri is agreed to appoint a master student to take of PingER in UTM.
Ibrahim has extracted the PingER Zip manually. He is reconstructing 11Gb of data, has 15GBytes of data there. He is trying to use SPAR to classify the data. He also was looking at RDF. the next step is to use MapReduce to organize and reduce the output of data so can visualize it. He will be using a the same techniques he used for looking at 1996-2006 weather data. However at the moment he cannot access his VMs from myren for the last two weeks, even for the myren site, He has emailed them but till now they have not fixed the issue. He has updated all his data in their cloud. No update 1/6/2016
No update 8/12/2015, no Update 9/2/2015. No update Jan 2016. Should we try and revive? The hosts all look fine. Johari will send email to Fitzi. Adib has a meeting with MYREN will see if he can make cotact
Hassaan reports: "There are total of 48 active nodes for Pakistan out of which 18 nodes are working properly whereas 4 nodes have configuration issues. Lahore college for Woman has changed its data center and they want to know what do have to do with the new one. Faisalabad PERN had some critical issues and burnt their power supply so they also wanted to know what can be done to overcome that damage. FAST University Karachi and Air University, Islamabad are not in a mood to help as they say that they will put the node up, but haven’t done that in past 2 months [Hassaan would like to discuss this with Dr. Anjum for excluding them from the list]. Last but not the least Quetta HEC regional center wanted to change their static IP to 121.52.157.148."
namal.seecs.edu.pk is working once again
No responses for over 30 days from
Put together a web page on the Fertility Rate and PingER measured Internet performance. The concern is the high Fertility rate in Sub-Saharan which is dominating the global growth in population and could result in over 6B people in Africa and 11B people on the planet by 2100. This puts a huge strain on resources. To reduce the Fertility Rate one needs education and information which is greatly enabled by the Internet. Unfortunately Internet performance is generally at its worst in West, Middle and East Africa where the Fertility Rates are highest.
Also put together a web page on ways of providing Internet access in hard to reach places, e.g. weather balloons, drones, low earth satellites.
The 2016 annual report on network monitoring is almost ready, it includes a section on PingER.
| Host | State | last seen | Status |
|---|---|---|---|
| web.hepgrid.uerj.edu | emails 5/1/2016, still no response 1/30/2016, email 1/30/2016 | Dec, 2014 | does not ping electrical problems |
| pinger.arn.dz | email 1/30/2016 | Nov 2015 | Does not ping |
| Pinger.stanford.edu | email 1/6/2016 | May 2015 | does not ping |
Gathering data from the following Pakistani monitoring hosts that we (pinger.slac.stanford.edu) have been unable to gather data from for 6 months or more has been disabled:
Are there any of these that are likely to return to service?
Last month we Disabled the following (not responding to ping and no data for 12 months)
Next Meeting
Next meeting: Wednesday Mar 9th 8:00pm Pacific Standard Time, Thursday Mar 10th, 2016 9:00am Pakistan time, Thursday Mar 10th 2016 12:00noon Malaysian time, Thursday Mar 10th 2016 02:00am Rio Standard Time.
UOA (Saqib) placed here 2/3/2016.
Sara Massoud came up with ideas to improve the info put together by Amity
Sabah Massoumil working on Linked Open Data (please excuse spelling)
Aqsa Hameed working on big data/analysis of PingER data. The initial idea was to set up a big data/big analysis
Aqsa Hameed has been working with Anjum to look at a project to create a Hadoop/Cloudera PingER warehouse to enable easier, more powerful access to PingER historical data.
Thinking a bit on Aqsa her work appears to be related to the work done by Thiago on PingER warehouse using a cluster/Cloudera/HDFS/Impala earlier this year. In particular see the presentation at NETAPPS2015 (see https://confluence.slac.stanford.edu/download/attachments/123309267/NETAPPS_PRESENTATIONrevLuiza.pptx. Once the paper is published we can also provide her with that (Adib will let us know when this is OK).
Les emailed the relevant people to put them in contact with one another. It appears there is a lot of overlap between what Aqsa proposed as a Masters project and what Thiago has already done. However Thiago's system was mainly a proof of concept and not in production. We need to look at the next steps: Internet access, auto-updating of information in near realtime, production service, maintainable etc. With this in place one could really mine the data looking for all kinds of interesting correlations, clustering, event impacts, comparisons etc.
Given that such a warehouse is available, then the next step would be to automatically create queries that would produce in near real-time the plots we produce manually for the PingER annual reports.
Following this publish the data in RDF to tie in with the Southampton RDF web observatory repository (similar to what Renan did as a proof of concept).
Since Thiago's warehouse is only available at SLAC, it may assist to get Aqsa an account at SLAC, alternatively Aqsa will need to set up a repository at here home base.
There is some documentation written by Les on the usage of the warehouse at SLAC. It is at: PingER Data Warehouse using Big Data with Cloudera on Nebula.
Les will contact Thiago to see if there is other documentation or where to find the programs etc.
We need to put together all we know:
Paper from Thiago on PingER warehouse presented in Malaysia at NETAPP2015 Thiago M. Da S. Barbosa, Renan F. Souza, Sergio M. S. Da Cruz, Maria L. Campos and R. Les Cottrell. Applying Data Warehousing and Big Data Techniques to Analyze Internet Performance
Document on Warehouse
Documents on PingERLOD
Linked Open Data Publication Strategies: Application in Networking PPerformance Measurement Data, Renan Souza, Les Cottrell, Bebo White, Maria Campos, Marta Mattoso, poster presented at the BigDataScience - Stanford conference, CA, USA May 27-31, 2014.
Reviews/proposals/ from Aqsa/Fatima
Survey on Big Data Indexing strategies, Fatima Bintu Adama, Adib Habbal, Suhaidi Hassan, R. Les Cottrell. Bebo White, Ibrahim Abdullahi.
Saqib will provide Aqsa's
Tehseen is working on missing PingER data.
Project is accepted.
working on a project to develop a node using Raspberry Pi 2 and IoT to measure the air and soil quality.
Have 2 RPis and setting up air quality with sensors from market, idea is to distribute on campus.
Currently, students are analyzing the project to develop a problem statement for their research project.
For the GeoLocation Saqib should contact Anjum
Others
Jan 5, 2015 Hassaan reports "I have received revisions on my proposal and these days I am revising my proposal. In the meanwhile, I have also added another student (Anas Abrar) on this project. He is in learning phase and will follow the nodes which are not working. I shall give you an update very soon. "
Hassaan has re-submitted the proposal after revisions. He would like to get Anas Abrar more trained on monitoring operation and then will inform us to add him to the mailing list at http://pinger.unimas.my/pinger/contact.php.
Oct 2015. Following the last meeting, Anjum, Hassaan and Les met to discuss the way forward.
Hassaan is waiting to hear from HEC about the comments on the proposal.
Thiago completed setting up the PingER data SQL Impala warehouse running on a Nebula/Cloudera cluster using the Hadoop File System (HDFS). Unfortunately it is not currently accessible from outside SLAC. There have been several attempts to provide outside access, but no success yet, we need to engage the subject matter experts. Thiago is now a SLAC associate so he still has an account at SLAC. There was a cyber security alert on the version of java installed with Cloudera. Les has replaced the cloudera version of java which should fix the vulnerability. However the new version has not been tested.
Anjum believes the TULIP Geolocation application can be improved significantly. At least there are few ideas that we can try. For this, either a group of undergraduate students or an active masters student is required. The resultant work can easily be the thesis of masters level. Who is interested?
Saqib at Faisalabad has an MS student interested to work on Geolocation project. He requests an initial paper on the project. Les has responded to Saqib. He also has some other students. Anjum will contact him. Potential projects/asks include: take over management of PingER monitoring in Pakistan (say 5 monitors/student; case study of how Pakistan's network performance/connectivity has improved over thea years especially as function of funding etc; geolocation with variable alpha; indoor geolocation
Johari will contact Anjum to learn more of the requirements. Update Johari/Adnan
See http://www.slac.stanford.edu/comp/net/tulip/. Basically TULIP uses pings to a target from landmarks at known locations and converts the minimum RTTs to estimate the distances. Then uses the distances with mulitlateration to estimate the location of the target
To improve TULIP one needs the right selection of landmarks, i.e. good (working landmarks) at the right locations (not too far from the target), straddling the target, and with a a reasonable estimate of the indirectness (directivity or alpha) of the path from the landmark to the target (so we can reasonably accurately estimate the distance). One also needs a reasonable density of landmarks (e.g. number of targets/100,000sq km)
The landmarks come from PingER and perfSONAR sites. We have a reasonable density in the US, Pakistan and Europe. Currently Anjum is getting better than 20km accuracy for Pakistani targets
As the number of landmarks goes up so does the accuracy, but so does the time to make the measurements (pings).
One needs to find the optimal density
Anjum proposes to speed up the measurements using a cluster for parallelization and also proposes to improve the adaptation of alpha based region. He regards the adaptive geolocation and parallelization as MS projects.
He is also interested in geolocation in small proximity (e.g.indoors), e.g. using cell tower signals. This is a new area of research. It is possible that the port of PingER to an Android could be related to this. This is a PhD project
Anjum reports he can supervise the students on Geolocation. He will need to know when the students are ready. We can start with a joint meeting involving Les and the students. Later on, Anjum can have the meeting with students every week while Les can join if he has time.
Pink Background indicates host was bad last month, strike through says it is fixed, yellow is an new bad host.
Current status of Pakistani Hosts 7/1/2015
|
Is it time to start paring down the list of PingER monitor hosts in Pakistan, starting with those that have been down for a while and despite your efforts they are not cooperating. One might also look at the coverage by region in Pakistan and try and keep good coverage for all regions.
The traceroute problem regarding maximum reachable hops ( i.e. 11 hopes ) may be since the Unix/Linux/OSX traceroute uses UDP to send the requests. The first request is sent to a particular port (33434), with a ttl to tell it how many hops to go to. The ttl starts at 1 is incremented as it tries the next hop, also the port is incremented (up to 33465). It looks like the first few UDP ports are enabled and then they are blocked. The Windows traceroute uses ICMP to send the probes so does not see the problem.
Cristiane reports (7/1/2015): "I am trying to automatize the triplification of PingER data on Kettle. For now, part of the transformation is made on Kettle and another is made by a Java code. Although this solution works for a data sample, is important to have the entire process on Kettle because it facilitates to understand, modify and control the triplification process."
Feb 2015
The plan is still the one seen before (see project proposal), experimenting those alternatives. Right now, they managed to triplify the data according to a new ontology that takes advantage of a combination of a current standard for multidimensional data (called data cube vocabulary) and a revised version of Renan's Moment ontology adaptation. With this we expect to have a better data organization than the previous solution.
They are now preparing a test plan (like a small benchmark) to be used on all alternatives so that we can compare the results accordingly.
Aug 2014
Renan finished the new pingerlod web site. The new thing is that it should be much easier now to modify the info texts. What Renan did was to put the texts into a separate file. The new version has been loaded on the server and some text added to describe how to use the map. However there is a bug that prevents it from executing the map. Renan reports that the bugs should be easy to fix. He has talked to his professor who suggested trying RDF Owlink, it should have faster responses to queries. Renan will research this. It will probably mean reloading the PingER data so is a lot of work, hopefully this will improve performance. Before the rebuild he will make the fixes and provide a new WAR for us to load on pingerlod.slac.stanford.edu. He is also working on documentation (he has finished the ontology and has a nice interactive tool for visualizing it, since the ontology is the core of the data model of our semantic solution, this will be very helpful for anyone who uses our system, both a developer of the system and a possible user) and his thesis. Bebo pointed out that to get publicity and for people to know about the data, we will need to add pingerlod to lod.org.
Things he will soon do regarding documentation:
For the Linked Open Data / RDF which is in pre-alpha days, you can go to http://pingerlod.slac.stanford.edu. As can be seen this page is not ready for prime time. However the demos work as long as one carefully elects what to look at:
Renan is using OWLIM as RDF Repository. He is using an evaluation version right now. Renan looked into the price for OWLIM (that excellent RDF Database Management System he told us about). It would cost 1200EUR minimum (~ 1620 USD, according to Google's rate for today) for a one time eternal license. It seems too expensive. No wonder it is so good. Anyhow, he heard about a different free alternative. Just not sure how good it would be for our PingER data. He will try it out and evaluate. He will also get a new evaluation of the free OWLIM lite.
He has also made some modifications on the ontology of the project (under supervision of his professor in Rio) hence he will have to modify the code to load the data accordingly.
Maria and Renan are advancing in some approaches to deal with PingER data, making it easier to be analyzed and integrated. In particular they have been busy studying and evaluating alternatives, analyzing results from the latest benchmarks on NoSQL (including RDF and graph based storages) database management, distributed processing and mediated solutions over relational databases, and also other experiments with multidimensional analyses on Linked Data. The new students involved are now understanding better the scenario and they have been interacting with Renan regularly.
Cristiane has studied the PinGER data and how to cast it into Linked Open Data form. The size of the PingER hourly data for 1998-Sep 2014 archived via FTP in text form amounts to ~ 5.12GB and this corresponds to 15.66*10^9 (billion) triples. Then using 5 triples for each measurement and using Turtle without compression gives us 685 Gbytes or an inflation factor of ~ 200.
When Christiane made the estimation of PingER triples, she wrote two documents that explain the process but they were in Portuguese. She has written the new versions in English.
Christiane's report is at: Size Inflation of PingER Data for use in PingER LOD
Moved here 3/4/2015:
Ibrahim has setup distributed hadoop clusters. He has 2TB of disk space. Les has provided information on getting a subset of PingER data by anonymous ftp via ftp://ftp.slac.stanford.edu/users/cottrell. It was put there last September. Information on how the data was put together is at https://confluence.slac.stanford.edu/display/IEPM/Archiving+PingER+data+by+tar+for+retrieval+by+anonymous+ftp. There is information on formatting etc at http://www-iepm.slac.stanford.edu/pinger/tools/retrievedata.html and some on the dataflows at https://confluence.slac.stanford.edu/display/IEPM/PingER+data+flow+at+SLAC. Renan at UFRJ has successfully used this data, he has also characterized the data in terms of bytes/metric per year etc.
Ibrahim has started downloading all zip files in the local machines. 6 weeks ago he downloaded 2 GB of Weather data to test his nodes cluster, he wrote a simple Java program (Map, Reduce) to find the Average and it was working fine.
Anjum reported that UM had experienced a TCP syn DOS attack prior to Mar 12th (when an IDS was put in place). It occurred mainly for several days before between the hours on noon- 2pm and 7-7 in the evening (Malaysia time). He suggested looking to see if PingER could spit the effect. Ibrahim, Les and Anjum will look at. Les analyzed the data and sent it to Anjum
The following is from Samad 2/24/2015.
The IP of "pingerqta.pern.edu.pk" has been changed, Les has updated the databas at SLAC with the following
Old IP: 121.52.157.157
New IP: 121.52.157.148
The Next step in funding is to go for bigger research funding, such as LRGS or eScience. Such proposals must lead to publications in high quality journals. They will need an infrastructure such as the one we are building. We can use the upcoming workshop (1 specific session) to brainstorm and come up with such proposal. We need to do some groundwork before that as well. Johari will take the lead in putting together 1/2 page descriptions of the potential research projects.
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.
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. Ibrahim reports 7/15/2014 "I have spent the last few months trying to understand the concept of big data storage and its retrieval as well as the traditional approach of storing RDF data. I have integrated a single hadoop cluster in our cloud. but for this project we need multiple clusters, which I have already discussed with Dr. Badrul and he will provide me with big storage for the experiment." No Update 8/20/2014.
"I have come up with initial proposed solution model. This model consists of several parts. The upper parts of the Figure below shows the data source, in which PingER data will be convert into RDF format. Then the data pre-processor will take care of converting RDF/XML into N-triples serialization formats using N-triples convertor module. This N-triple file of an RDF graph will be as an input and stores the triples in storage as a key value pair using MapReduce jobs"
 | ping to ping from avg rtt pkt loss get data |
| namal.seecs.edu.pk |