ESnet heads to international conference to share expertise with colleagues at TNC22
By Rae Pendergrass
ESnet will be in Trieste, Italy from June 13-17, 2022 sharing their knowledge about software-defined networking at TNC22, the research and education networking conference.
Here's a look at where to find ESnet at the conference:
Wednesday 6/15 - 8:30-16:30 CEST | Room B
ESnet executive director Inder Monga will join 70 CEOs from research networks around the world for a conversation about best practices, advancements in technology, and the future of scientific networking.
Data Mobility Exhibition
Wednesday 6/15 - 10:30-11:00 CEST | Demonstration Area
Data mobility is a critical component of the process of science. Being able to predictably and efficiently move scientific data between experimental source, processing facilities, long term storage, and collaborators is a common use case that transcends the boundaries of research disciplines. The demo transfers reference data sets from well-tuned Data Transfer Nodes (DTNs) to existing campus CI components. Participants will upload, download, measure, and potentially improve their scientific data movement capabilities as well as review previous tests.
Session: Real Life Network Orchestration
Building a Realistic Orchestration Validation Environment for netwoRks (ROVER)
Thursday 6/16 - 09:00-10:30 CEST | Auditorium
Speakers:Chris Cummings,Nick Buraglio
Building software that controls network equipment has many similarities to traditional software engineering, however, testing this software introduces many complexities unique to the network orchestration world. Join this talk to learn how we approached these challenges by building a Realistic Orchestration Validation Environment for netwoRks (ROVER) at ESnet.
Session: Data Driven Networking
Superfacility - A Blueprint for Supporting Large-Scale Scientific Workflows
Thursday 6/16 - 11:00 – 12:30 CEST | Auditorium
Data-intensive workflows have been a mainstay of large scale collaborative scientific research for several decades. However, with the growing exponential rate of data that instruments can produce today, there needs to be a paradigm shift in how distributed resources are requested and utilized across the various facilities that contribute to these data-intensive workflows. A "Superfacility" model, which seamlessly integrates instrument, computing, storage, and networking facilities, is required to more effectively support these increasingly demanding workflows. This talk will present on the desired characteristics for a Superfacility, discuss specific use cases, and highlight some activities and initiatives in this area.
Exploring the BBRv2 Congestion Control Algorithm for use on Data Transfer Nodes
Thursday 6/16 - 11:00-12:30 CEST | Auditorium
It is well known that loss-based TCP congestion control algorithms are problematic for high-speed, high-latency flows that are common in Big Science. In 2016 Google released a new congestion control algorithm called "BBR" (Bottleneck Bandwidth and Round-trip time) that uses a model-based approach, and the design has since been refined in an alpha release of BBRv2. In this paper, we describe and perform a set of experiments that assess the suitability of BBRv2 for use on Data Transfer Nodes (DTNs).
Registration deadlines for TNC are coming up! Registration for regular in-person passes is open until June 6(unless you want to pay via bank transfer – registration for that closed on May 30th). Free online passes are also available!