students

Summer at ESnet: student notes, part 3

~ Ezra Kissel

Eashan Adhikarla is pursuing a Ph.D. at Lehigh University and joined my group this summer to work on our “DTN as a Service” project. He contributed a lot of energy and novel insights into our work over the summer and I hope we have the opportunity to collaborate again in the near future. Here are some thoughts from Eashan on the summer student experience at ESnet.

This is my second internship at Berkeley Lab and my first at the Scientific Networking Division (SND). It has been full of excitement, thrills, challenges, and surprises, and it is a dream place to be.

This summer, I have been working on the intersection of machine learning and high-performance computing in data transfer nodes (DTNs). ESnet connects 40 DOE sites to 140 other networks and therefore has a high demand for data transfers ranging from megabytes to petabytes. The team is designing DTN-as-a-Service (DTNaaS), where the goal is to deploy and optimize the performance of the data movement across various sites. Managing the transmission control protocol (TCP) flows is a key factor in achieving good performance of transfers over a wide range of network infrastructure. My research helps automate DTN performance via machine learning – thus improving the overall DTNaaS framework.

At present, most DTN software is deployed on bare metal servers, limiting the flexibility for operational configuration changes and automation of transfer configurations. Manually inferring best tuning parameters for a dynamic network is a challenge. To optimize the throughput over TCP flow, we currently often use a pacing rate-function to control packet inter-arrival time. A part of my work proposes two different alternative approaches (supervised or sparse regression-based models) to better predict pacing rate, as well as automate change of related DTN settings based on the nature of the transfers.

Overall, my summer research involved getting experience with a wide set of networking areas of interest:

  • Improving the DTN-as-a-Service agent traffic control API with profiles and setting pacing
  • Creating a method for statistics retrieval for the harness toolkit for dynamic data visualization and analysis, and preparing these statistics to train the pacing model
  • Developing a pacing prediction approach that reduces much of the effort for manual pacing rate configuration.

I was also able to contribute to a separate team’s project on exploring the use of network congestion control algorithms for DTNs; the resulting paper will be submitted to an SC21 workshop.

For me, one of the best things at ESnet is that the summer interns get to work directly with quintessential research scientists and research engineers in the lab and learn a variety of skills to tackle the most challenging problems on a real-world scale. It’s a place from which I always come out as a better version of myself.

If you are interested in learning more about future summer opportunities with ESnet, please see this link (https://cs.lbl.gov/careers/summer-student-and-faculty-program/). We typically post notices and application information starting in January or February.

Summer at ESnet: The view from our students, Part 2

~ ESnetComms

Pratyush Muthukumar is a student intern with our Prototypes & Testbed Team. He is a 2021 Goldwater Scholar at UC Irvine, working toward a BS in Computer Science. 

Pratyush Muthukumar

My time as an intern at ESnet has been thrilling and rewarding. Over the last seven months as an intern here, I have learned many valuable research, scholarly, and professional skills that I will undoubtedly use in the future. 

I have primarily been working on the SENSE (Software Defined Networking [SDN] for End-to-End Networked Science at the Exascale) project with my amazing mentors, Xi Yang and Tom Lehman, and this has been exciting and fascinating. I’ve learned a plethora of new research skills and frameworks, including multi-domain monitoring, software-defined networking, network polling, scripting, and virtualization. My project mentors have provided great guidance and supported me throughout every stage of the project. What I enjoy best about being an intern at ESnet is the resources, guidance, and tools available to support my research. I’m excited to work on such a challenging yet rewarding tool that will soon have real-world impact when deployed on ESnet.

The environment as an ESnet intern has been extremely friendly and inviting. I feel a part of the community within ESnet and I really enjoy attending the frequent seminars and brown bag lunches held multiple times weekly. Learning about new research developments from other teams at ESnet and guest lecturers from the Computer Science and Mathematics department at UC Berkeley has broadened my knowledge and interests greatly.

While my experiences may have been different during an in-person internship at ESnet, I appreciate the numerous networking and social activities that ESnet has facilitated to make remote interns feel connected. I have really enjoyed my time as an ESnet intern thus far, and I’m looking forward to the rest of my time at ESnet!

If you are interested in learning more about future summer opportunities with ESnet, please see this link (https://cs.lbl.gov/careers/summer-student-and-faculty-program/). We typically post notices and accept applications for the next summer starting in January or February.

Summer at ESnet: the view from our students: Part 1

~ Richard Cziva

Summer students are a key part of growing ESnet and supporting the scientific networking community. Every year, we host research projects with talented students working on important research topics. We benefit tremendously from their enthusiasm, talent, and fresh ideas, and they work directly with our staff across a wide set of disciplines.  Here are some thoughts from two current students on what it is like to work with ESnet, and what research excites them.

Sandesh Dhawaskar Sathyanarayana:

I am thrilled with my summer internship at ESnet. During my Multipath Transmission Control Protocol (TCP) research, I used in-kernel programs to implement receiver-based network controllers and have always wanted to work more on it as it allows one to hook into the kernel and innovate the different network protocols. Software Defined Networking (SDN) along with dataplane and kernel network programming is trending as it enables the telecom world to save billions of dollars and operate the network more efficiently. 

My goal for this summer was to work and innovate in the SDN field, and ESnet was the perfect fit for it. At ESnet, I work on the Q-factor project using technologies such as eBPF (extended Berkeley Packet Filters) and XDP (eXpress Data Path) to improve data transfer speeds in science networks. I get to play with the state-of-the-art P4 dataplane programming language for switches and programmable NICs. The project is a collaboration with Florida International University (FIU), so I get to work with amazing people. Our team is small, with great mentors like Richard Cziva and Jeronimo Bezerra. 

What I love the most is the freedom to think and solve problems with great support. Having to work in different labs, I used to be stressed most of the time to complete the work. This summer has been a very different experience with excellent mentorship. I also had other offers and chose ESnet as my advisor and co-advisors insisted strongly, and I am happy I went with ESnet.

Elias Joseph:

Interning at ESnet has been a really good learning experience for me. The regular seminars from researchers in the lab about their current projects have allowed me to learn about a lot of topics I usually wouldn’t have much exposure to, as well as see how the concepts I have learned about in school are being applied in a professional environment. It is really interesting to see how machine learning is actively being used at the laboratory, and what current advancements are being made with it.

As much as I’m learning from the seminars, I’m learning even more from the project I’m working on. This internship is giving me experience using a lot of tools that are prevalent in computer science but are underutilized in my master’s program, and my mentor has been extremely helpful in getting me up to speed on these tools.

I’ve also found working on my project very fulfilling. Primarily I’ve been working on a tool that displays internet traffic, as well as predictions for future traffic, and seeing it come together over the past month and a half has been really cool.

I do miss the social aspect of working in an office, but the networking and social activities that have been organized have done a lot to alleviate that, and overall, I have grown a lot in the first half of my internship.

If you are interested in learning more about future summer opportunities with ESnet, please see this link — we typically post notices and accept applications for the next summer starting in January or February.