Last week, over 50 ESnet employees gathered at Berkeley Lab for a week of strategizing and socializing. Here are some pictures from their adventures!
Photo by: Rae Pendergrass Featuring: Kapil Agrawal, Fatema Bannat WalaPhoto by: Unknown Featuring: (counter-clockwise around table from front): Ed Balas, Samir Faci, Biju Jacob, Bruce Mah, Katrina Turner, Jeremy Randolph, Sarah Larsen, Sowmya BalasubramanianPhoto by: Andrew Wiedlea Featuring: Eli Dart, Jason Zurawski, and Ken MillerPhoto by: Dale W. Carder Featuring (clockwise around table from left): Andy Lake, Sarah Larsen, Samir Faci, Sartaj Baveja, Sowmya Balasubramanian, Biju Jacob, James Kafader, Katrina Turner, Bruce Mah, Sasank Maganti, Jeremy Randolph, Ed BalasPhoto by: Ed Balas Featuring: Biju Jacob, Bruce Mah, wSasank Maganti, Sarah Larsen, Andy Lake, Asma Aldaghar, Dale Carder, Chris Cummings, Evangelos (Vangelis) Chaniotakis , Ryan VredenburgPhoto by: Ed Balas Featuring: Biju Jacob, Sowmya Balasubramanian, Sasaki Maganti, Katrina Turner, Joyce Johnson, Yoshi TurnerPhoto by: bmwt Featuring: Anne WhitePhoto by: bmwt Featuring: Charles Shiflett, Sam Moats, Jason Kang, Dhiva M, Goran Pejovic, Deb HellerPhoto by: bmwt Featuring: George B. Robb IIIPhoto by: bmwt Featuring: Charles Shiflett, Jason Kang, Goran Pejovic, Dhiva M.Photo by: bmwt Featuring: George B. Robb III, Giselle Jiles, Shawn KwangPhoto by: bmwt Featuring: Deb Heller, Dhiva M., Paul PorterPhoto by: bmwt Featuring: Deb Heller, Dhiva M., Paul Porter, Luke Baker, Goran PejovicPhoto by: bmwt Featuring: Anne White, Remy DoucetPhoto by: Dale Carder Featuring: Derek Howard
A combined team from ESnet and Lehigh University was awarded the best paper for Exploring the BBRv2 Congestion Control Algorithm for use on Data Transfer Nodes at the 8th IEEE/ACM International Workshop on Innovating the Network for Data-Intensive Science (INDIS 2021), which was held in conjunction with the 2021 IEEE/ACM International Conference for High Performance Computing, Networking, Storage and Analysis (SC21) on Monday, November 15, 2021.
The team was comprised of:
Brian Tierney, Energy Sciences Network (ESnet)
Eli Dart, Energy Sciences Network (ESnet)
Ezra Kissel, Energy Sciences Network (ESnet)
Eashan Adhikarla, Lehigh University
The paper can be found here. Slides from the presentation are here. In this Q+A, ESnet spoke with the award-winning team about their research — answers are from the team as a whole.
The paper is based on extensive testing and controlled experiments with the BBR (Bottleneck Bandwidth and Round-trip propagation time), BBRv2 and the Cubic Function Binary Increase Congestion Control (CUBIC) Transmission Control Protocol (TCP) Internet congestion algorithms. What was the biggest lesson from this testing?
BBRv2 represents a fundamentally different approach to TCP congestion control. CUBIC (as well as Hamilton, Reno, and many others) are loss-based, meaning that they interpret packet loss as congestion and therefore require significant network engineering effort to achieve high performance. BBRv2 is different in that it measures the network path and builds a model of the path – it then paces itself to avoid loss and queueing. In practical terms, this means that BBRv2 is resilient to packet loss in a way that CUBIC is not. This comes through loud and clear in our data.
What part of the testing was the most difficult and/or interesting?
We ran a large number of tests in a wide range of scenarios. It can be difficult to keep track of all the test configurations, so we wrote a “test harness” in python that allowed us to keep track of all the testing parameters and resulting data sets.
The harness also allowed us to better compare results collected over real-world paths to those in our testbed environments. Managing the deployment of the testing environment though containers also allowed for rapid setup and improved reproducibility.
You provide readers with links to great resources so they can do their own testing and learn more about BBRv2. What do you hope readers will learn?
We hope others will test BBRv2 in high-performance research and education environments. There are still some things that we don’t fully understand, for example there are some cases where CUBIC outperforms BBRv2 on paths with very large buffers. It would be great for this to be better characterized, especially in R&E network environments.
What’s the next step for ESnet research into BBRv2? How will you top things next year?
We want to further explore how well BBRv2 performs at 100G and 400G. We would also like to spend additional time performing a deeper analysis of the current (and newly generated) results to gain insights into how BBRv2 performs compared to other algorithms across varied networking infrastructure. Ideally we would like to provide strongly substantiated recommendations on where it makes sense to deploy BBRv2 in the context of research and educational network applications.
Nearly two months into California’s shelter-in-place order, we’ve all been in more than our fair share of video conferences. To boost morale during this difficult time, the Energy Sciences Network (ESnet) staff held a Zoom Background Competition during their all-to-all meeting on Monday, April 27.
Staff were encouraged to create their own backgrounds and display them during the meeting. There were 21 entries. ESnet employees voted. Submissions were judged on overall artistry, functionality (not too distracting as a background), whether it elevated the voter’s mood, and if it made them feel included in the ESnet community.
The top three winners got bragging rights. Here they are:
First place: Jeff Berman, NOC Engineer
This Zoom challenge inspired Berman, an avid sailor, to take to the sea. He won this competition with an hour video of the San Francisco skyline, one he filmed while sailing on the Bay. Although he typically likes to go sailing with friends and family, he says that sailing solo brings him a sense of peace, calm, and tranquility.
“What is sailing? Most books define it as hours of sheer boredom scattered with white knuckle periods of terror. On a good day, both are true. Both give you an equal sense of accomplishment. How to be with yourself with nothing to do, good training for our current situation,” said Berman.
Second Place: Sartaj Baveja, Software Engineer
This challenge inspired Baveja to create a background meme of office life. In the background, someone (Baveja) is looking over your shoulder to catch a glimpse of your screen and make sure you don’t procrastinate.
Third Place: Joe Metzger, Network Engineer
This challenge inspired Metzger to use a picture that he took in Barcelona. The focal point of the picture (the blur) is a little girl in a red coat, black dress and white tights who was just running back and forth between the pools of light and shadow created by the stone arches and rosette windows, while her family was sitting in the cafe.
“I used this as my zoom background because I think it is a really cool picture. It brings to mind a fun evening strolling around the little squares and back streets in Barcelona and sitting in cafes with a good glass of wine relaxing,” said Metzger.
Written by Linda Vu, Berkeley Lab Computing Sciences.
At ESnet, we believe that a diverse workforce results in creative ideas and innovations. So we aim to create an inclusive working environment where people feel valued and can share their thoughts and ideas. In this series, we’ll be sharing perspectives from our staff in hopes of sharing our lessons learned and igniting conversations.
As part of ESnet’s ongoing inclusion effort, we held a workshop, “Empathy: A Building Block for Inclusiveness,” last month to discuss proactive approaches to understanding others. Mukundagiri Kandadai Ramanujam (‘Ram’ for short), Lead Trainer with Love To Share Foundation, facilitated the discussion. Michael Sinatra, a network engineer at ESnet, shares his thoughts on the workshop.
Michael Sinatra, ESnet Network Engineer
Michael Sinatra, ESnet Network Engineer
At ESnet, we deal with a lot of complex issues, which generate a lot of subtle risks and benefits. We also have a diverse staff that has different communication styles. I have found Ram’s seminars really helpful in reminding us of the benefit of understanding employees’ underlying concerns when we communicate.
In the seminar, Ram made the distinction in interpersonal communication among statements that are intellectual or state neutral facts, versus those that evaluate, judge and eventually label. By using empathy to understand the underlying needs being expressed by our coworkers, we can better convey the important things that need to be communicated in our organization without causing emotional issues to block out the underlying needs of the organization. Emotions have a place at work, but they can also cloud our ability to see important issues in our jobs.
The discussion reminded me of an example from a previous workplace. When I was 21 I had a summer job at a factory where, as one of my assignments, I had to do some work with the plant machinist, who had been told by the plant managers that he had an “attitude problem.” In the course of our work, when my colleague began grumbling about something I was doing, I, aware of this person’s alleged attitude problem, tried to be as emotionally neutral as I could to find out—on an intellectual level— why he was grumbling. It turns out that my colleague had identified a serious safety issue in what I was doing. We were able to correct the issue quickly before it caused more problems. I realized that my colleague might not have an attitude problem at all, but he might just have had some trouble communicating important issues to others, and then he would get frustrated when people didn’t take his concerns seriously.
I have tried to apply some of these concepts by being more open about my underlying motivations, especially when expressing concerns about something. At the same time, I have tried to better, and more neutrally, understand my colleagues’ concerns and motivations. Ram showed us that empathy works both ways–by better exposing our own needs and concerns, we can better communicate about the issues that are important to ESnet, and by applying the principles of empathy to our colleagues, we can better understand where they’re coming from, regardless of differences in communication style or culture.
On January 10, 2017, Berkeley Lab’s Scientific Networking Division hosted an “Empathy: A Building Block for Inclusion” discussion, facilitated by Mukundagiri Kandadai Ramanujam, Lead Trainer with Love to Share Foundation. (Photo Credit: Sowmya Balasubramanian, ESnet)
Women in Networking @SC (WINS) Kicks off this week in Salt Lake City!
(Left to Right) Julia Locke (LANL), Debbie Fligor (SC15 WINS returning participant, University of Illinois at Urbana-Champaign), Jessica Schaffer (Georgia Tech), Indira Kassymkhanova (LBNL), Denise Grayson (Sandia), Kali McLennan (Univ. of Oklahoma), Angie Asmus (CSU). Not in photo: Amber Rasche (N. Dakota State) and Julie Staats (CENIC).
Funded through a grant from the National Science Foundation (NSF) and directly from ESnet, the program funds eight early to mid-career women in the research and education (R&E) network community to participate in the 2016 setup, build out and live operation of SCinet, the Supercomputing Conference’s (SC) ultra high performance network. SCinet supports large-scale computing demonstrations at SC, the premier international conference on high performance computing, networking, data storage and data analysis and is attended by over 10,000 of the leading minds in these fields.
The SC16 WINS program kicked off this week as the selected participants from across the U.S., headed to Salt Lake City, the site of the 2016 conference to begin laying the groundwork for SCinet inside the Salt Palace Convention Center. The WINS participants join over 250 volunteers that make up the SCinet engineering team and will work side by side with the team and their mentors to put the network into full production service when the conference begins on November 12. The women will return to Salt Lake City a week before the conference to complete the installation of the network.
“We are estimating that SCinet will be outfitted with a massive 3.5 Terabits per second (Tbps) of bandwidth for the conference and will be built from the ground up with leading edge network equipment and services (even pre-commercial in some instances) and will be considered the fastest network in the world during its operation,” said Corby Schmitz, SC16 SCinet Chair.
The WINS participants will support a wide range of technical areas that comprise SCinet’s incredible operation, including wide area networking, network security, wireless networking, routing, network architecture and other specialties.
Several WINS participants hard at work with their mentors configuring routers & switches
“While demand for jobs in IT continues to increase, the number of women joining the IT workforce has been on the decline for many years,” said Marla Meehl, Network Director from UCAR and co-PI of the NSF grant. “WINS aims to help close this gap and help to build and diversify the IT workforce giving women professionals a truly unique opportunity to gain hands-on expertise in a variety of networking roles while also developing mentoring relationships with recognized technical leaders.”
Funds are being provided by the NSF through a $135,000 grant and via direct funding from ESnet supported by Advanced Scientific Computing Research (ASCR) in DOE Office of Science. Funding covers all travel expenses related to participating in the setup and operation of SCinet and will also provide travel funds for the participants to share their experiences at events like The Quilt Member Meetings, Regional Networking Member meetings, and the DOE National Lab Information Technology Annual Meeting.
“Not only is WINS providing hands-on engineering training to the participants but also the opportunity to present their experiences with the broader networking community throughout the year. This experience helps to expand important leadership and presentations skills and grow their professional connections with peers and executives alike,” said Wendy Huntoon, president and CEO of KINBER and co-PI of the NSF grant.
The program also represents a unique cross-agency collaboration between the NSF and DOE. Both agencies recognize that the pursuit of knowledge and science discovery that these funding organizations support depends on bringing the best ideas from people of various backgrounds to the table.
“Bringing together diverse voices and perspectives to any team in any field has been proven to lead to more creative solutions to achieve a common goal,” says Lauren Rotman, Science Engagement Group Lead, ESnet. “It is vital to our future that we bring every expert voice, every new idea to bear if our community is to tackle some of our society’s grandest challenges from understanding climate change to revolutionizing cancer treatment.”
2016 WINS Participants are:
Denise Grayson, Sandia National Labs (Network Security Team), DOE-funded
Julia Locke, Los Alamos National Lab (Fiber and Edge Network Teams), DOE-funded
Angie Asmus, Colorado State (Edge Network Team), NSF-funded
Kali McLennan, University of Oklahoma (WAN Transport Team), NSF-funded
Amber Rasche, North Dakota State University (Communications Team), NSF-funded
Jessica Shaffer, Georgia Institute of Tech (Routing Team), NSF-funded
Julia Staats, CENIC (DevOps Team), NSF-funded
Indira Kassymkhanova, Lawrence Berkeley National Lab (DevOps and Routing Teams), DOE-funded
The WINS Supporting Organizations: The University Corporation for Atmospheric Research (UCAR) http://www2.ucar.edu/
The Keystone Initiative for Network Based Education and Research (KINBER) http:www.kinber.org
THe Department of Energy’s Energy Sciences Network (ESnet) http://www.es.net
BioTeam and ESnet are partnering to offer a webinar on the Science DMZ architectural paradigm. While streamlining a network design to facilitate “friction free” research paths, the Science DMZ has been widely adopted by the research and education (R&E) community and is being implemented at many locations around the world. Using this approach, the task of data mobility becomes less of a mystery, and more of a routine part of scientific networks.
This event will occur on Monday, May 18th, between 2pm and 4pm EDT and is open to the general public. We would like to encourage network operators and researchers (including, but not limited to, life science researchers) to attend this no-cost event. For complete information on registration and logistical details, visit: http://bioteam.net/2015/04/science-dmz-101/. Registration will close when the number of registration slots has been exhausted.
BioTeam is a high-performance consulting practice. They are dedicated to delivering objective, technology agnostic solutions to life science researchers by leveraging technologies customized for scientific objectives.
The Energy Sciences Network (ESnet) is a high-performance, unclassified network built to support scientific research. ESnet provides services to more than 40 DOE research sites, and peers with over 140 research and commercial networks.
Berkeley Lab staff from five divisions will share their expertise in a panel discussion on “Creating Super-facilities: a Coupled Facility Model for Data-Intensive Science”at the Internet2 Global Summit to be held April 26-30 in Washington, D.C. The panel was organized by Lauren Rotman of ESnet and includes Alexander Hexemer of the Advanced Light Source (ALS), Craig Tull of CRD, David Skinner of NERSC and Rune Stromsness of the IT Division.
The session will highlight the concept of a coupled science facility or “super-facility,” a new model that links together experimental facilities like the ALS with computing facilities like NERSC via a Science DMZ architecture and advanced workflow and analysis software, such as SPOT Suite developed by Tull’s group. The session will share best practices, lessons learned and future plans to expand this effort.
Also at the conference, ESnet’s Brian Tierney will speak in a session oh “perfSONAR: Meeting the Community’s Needs.” Co-developed by ESnet, perfSONAR is a tool for end-to-end monitoring and troubleshooting of multi-domain network performance. The session will give an overview of the perfSONAR project, including an overview of the 3.4 release, a preview of the 3.5 release, an overview of the product plan, and an overview of perfSONAR training plan.
ESnet’s Eli Dart (left), Salman Habib (center) of Argonne National Lab and Joel Brownstein of the University of Utah compare ideas during a workshop break.
ESnet and Internet2 hosted last week’s CrossConnects Workshop on “Improving Data Mobility & Management for International Cosmology,” a two-day meeting ESnet Director Greg Bell described as the best one yet in the series. More than 50 members of the cosmology and networking research community turned out for the event hosted at Lawrence Berkeley National Laboratory, while another 75 caught the live stream from the workshop.
The Feb. 10-11 workshop provided a forum for discussing the growing data challenges associated with the ever-larger cosmological and observational data sets, which are already reaching the petabyte scale. Speakers noted that network bandwidth is no longer the bottleneck into the major data centers, but storage capacity and performance from the network to storage remain a challenge. In addition, network connectivity to telescope facilities is often limited and expensive due to the remote location of the facilities. Science collaborations use a variety of techniques to manage these issues, but improved connectivity to telescope sites would have a significant scientific benefit in many cases.
In his opening keynote talk, Peter Nugent of Berkeley Lab’s Computational Research Division said that astrophysics is transforming from a data-starved to a data-swamped discipline. Today, when searching for supernovae, one object in the database consists of thousands of images, each 32 MB in size. That data needs to be processed and studied quickly so when an object of interest is found, telescopes around the world can begin tracking it in less than 24 hours, which is critical as the supernovae are at their most visible for just a few weeks. Specialized pipelines have been developed to handle this flow of images to and from NERSC.
Salman Habib of Argonne National Laboratory’s High Energy Physics and the Mathematics and Computer Science Divisions opened the second day of the workshop, focused on cosmology simulations and workflows. Habib leads DOE’s Computation-Driven Discovery for the Dark Universe project. Habib pointed out that large-scale simulations are critical for understanding observational data and that the size and scale of simulation datasets far exceed those of observational data. “To be able to observe accurately, we need to create accurate simulations,” he said. Simulations will soon create 100 petabyte sets of raw data, and the limiting factor for handling these will be the amount of available storage, so smaller “snapshots” of the datasets will need to be created. And while one person can run the simulation itself, analyzing the resulting data will involve the whole community.
Reijo Keskitalo of Berkeley Lab’s Computational Cosmology Center described how computational support for the Planck Telescope has relied on HPC to generate the largest and most complete simulation maps of the cosmic microwave background, or CMB. In 2006, the project was the first to run on all 6,000 CPUs of Seaborg, NERSC’s IBM flagship at the time. It took six hours on the machine to produce one map. Now, running on 32,000 CPUs on Edison, the project can generate 10,000 maps in just one hour.
Mike Norman, head of the San Diego Supercomputer Center, offered that high performance computing can become distorted by “chasing the almighty FLOP,” or floating point operations per second. “We need to focus on science outcomes, not TOP500 scores.”
Over the course of the workshop, ESnet Director Greg Bell noted that observation and simulation are no longer separate scientific endeavors.
The workshop drew a stellar group of participants. In addition to the leading lights mentioned above, attendees included Larry Smarr, founder of NCSA and current leader of the California Institute for Telecommunications and Information Technology, a $400 million academic research institution jointly run by the University of California, San Diego and UC Irvine; and Ian Foster, who leads the Computation Institute at the University of Chicago and is a senior scientist at Argonne National Lab. Foster is also recognized as one of the inventors of grid computing.
The next step for the workshop organizers is to publish a report and identify areas for further study and collaboration. Looming over them will be the thoughts of Steven T. Myers of the National Radio Astronomy Observatory after describing the data challenges coming with the Square Kilometer Array radio telescope: “The future is now. And the data is scary. Be afraid. But resistance is futile.”
A joint effort between ESnet, Internet2, Indiana University, and GEANT, the pan-European research network, perfSONAR is a tool for end-to-end monitoring and troubleshooting of multi-domain network performance. In January 2014, perfSONAR reached a milestone with 1,000 instances of the diagnostic software installed on networking hosts around the U.S. and in 13 other countries. perfSONAR provides network engineers with the ability to test and measure network performance, as well as to archive data in order to pinpoint and solve service problems that may span multiple networks and international boundaries.
At the workshop, Tierney will give an introduction to perfSONAR and present a session on debugging using the software. Zurawski will talk about maintaining a perfSONAR node, describe some user case studies and success stories, discuss “Pulling it All Together – perfSONAR as a Regional Asset” and conclude with “perfSONAR at 10 Years: Cleaning Networks & Disrupting Operation.”
Registration is now open for a workshop on “Improving Data Mobility and Management for International Cosmology” to be held Feb. 10-11 at Lawrence Berkeley National Laboratory in California. The workshop, one in a series of Cross-Connects workshops, is sponsored the by the Dept. of Energy’s ESnet and Internet2.
Early registration is encouraged as attendance is limited and the past two workshops were filled and had waiting lists. Registration is $200 including breakfast, lunch and refreshments for both days. Visit the Cross-Connects Workshop website for more information.
Cosmology data sets are already reaching into the petabyte scale and this trend will only continue, if not accelerate. This data is produced from sources ranging from supercomputing centers—where large-scale cosmological modeling and simulations are performed—to telescopes that are producing data daily. The workshop is aimed at helping cosmologists and data managers who struggle with data workflow, especially as the need for real-time analysis of cosmic events increases.
Renowned cosmology experts Peter Nugent and Salman Habib will give keynote speeches at the workshop.
Nugent, Senior Scientist and Division Deputy for Science Engagement in the Computational Research Division at Lawrence Berkeley National Laboratory, will deliver a talk on “The Palomar Transient Factory” and how observational data in astrophysics, integrated with high-performance computing resources, benefits the discovery pipeline for science.
Habib, a member of the High Energy Physics and Mathematics and Computer Science Divisions at Argonne National Laboratory, a Senior Member of the Kavli Institute for Cosmological Physics at the University of Chicago, and a Senior Fellow in the Computation Institute, will give the second keynote on “Cosmological Simulations and the Data Big Crunch.”
This challenge inspired Metzger to use a picture that he took in Barcelona. Th
You must be logged in to post a comment.