DANCES with Big Data: Progress Update from XSEDE Meeting

By John Russell

July 22, 2016

Moving large datasets around HPC networks such as those of XSEDE is often challenging. While Internet2, the most commonly used backbone, is fast at 100GBS, local traffic to campuses often slows to 10GBS. At this week’s XSEDE meeting the DANCES (Developing Applications with Networking Capabilities via End-to-End SDN) project leaders reported first successful testing of hardware components needed as well as results of vendor bakeoff for switches.

The NSF-funded DANCES[i] project is intended to investigate and develop the ability to add network bandwidth scheduling via software- defined networking (SDN) programmability to selected cyberinfrastructure services and applications intended to develop a software/hardware infrastructure that speeds and smoothes high-speed traffic. The recent test involved transfer of “Big Data” between two XSEDE sites, the Pittsburgh Supercomputing Center (PSC) and the National Institute for Computational Sciences (NICS) at the University of Tennessee.

Victor Hazlewood
Victor Hazlewood

“If you think about [high-performance computing] users and their end-to-end workflow, they need to do it by breaking their projects into pieces,” says Victor Hazlewood of NICS, principal author of the peer-reviewed article accompanying the presentation. “One of these pieces inevitably involves moving data into and out of where researchers do their computation.”

Today’s research wide-area networks (WAN) are more a free-for-all than their compute and storage counterparts, which are scheduled and managed, according to Hazlewood. By design, the protocol software that regulates the network data flow treats all data packets as equal. When the networks are not crowded it’s like an empty freeway. When they are crowded, though, the situation becomes much like a convoy of buses getting broken apart by other traffic. For large datasets traveling across the WAN, that can mean slow movement or even failures to move the data completely in a reasonable amount of time.

DANCES DIAGRAM

Project leaders presented a DANCES progress update and their paper[ii] at the XSEDE. In addition to reviewing the technology investigated, the paper details the evaluation of several vendors for use in the project. Corsa Technology, a Canadian technology start-up, was selected. “We were … interested in devices that supported bandwidth reservation,” said coauthor Kathy Benninger of PSC. “Part of that has to do with adoption of the newest OpenFlow versions by switch vendors.”

OpenFlow 1.3, the latest commonly deployed version of the standard network communications interface, has features that support such bandwidth management. But the problem, Benninger explains, is that “compliance” with a given version of OpenFlow doesn’t require a particular network switch to support every facet of that version’s specification. The researchers had to test a number of switch products, eventually choosing the Corsa DP6410 as most fully compatible with the DANCES requirements, successfully testing the combination in a number of data-transfer scenarios between PSC and NICS. Next, the group plans to test the full set of end-to-end system functions that will be needed to support real data transfers by XSEDE users.

Here’s an excerpt from the paper describing target device and application characteristics:

“The SDN capabilities would be provided by a network device that implements OpenFlow 1.3 including per-flow meters and per-port queuing required by DANCES. The bandwidth control and scheduling capability will be used to mitigate congestion – induced throughput problems on end site networks. The prototype environment setup has been done in two phases. The first phase was done by setting up and testing in a virtual environment and the second phase was done by creating a WAN test environment.

“The cyberinfrastructure applications chosen for investigation and potential performance enhancement by DANCES include (1) SCP and GridFTP data transfers and (2) wide area distributed file system data transfers initiated by, and integrated with, job scheduling and resource management. In addition, SLASH2, the wide area distributed file system targeted for DANCES integration, natively supports scheduled remote file replication. Coupling the SLASH2native file transfer scheduling with the network bandwidth scheduling capability of DANCES increases the efficiency of both network and file system resources.

“The project set out to deploy a prototype environment to extend the TORQUE/Moab scheduling and management currently in use at several XSEDE supercomputing sites to support networking as a schedulable resource. The wide area distributed file systems selected for bandwidth scheduling integration were the XSEDE-wide File System built on IBM’s General Parallel File System (GPFS) and SLASH2 developed at Pittsburgh Supercomputing Center. Since the award of DANCES, XSEDE has decided to no longer support the XSEDE-wide file system based on GPFS and, therefore, DANCES modified its goals to test and prototype using GridFTP, SLASH2 and now SCP as the replacement for GPFS.”

Shown below is an early test DANCES WAN configuration:

DANCES-WAN-env

The authors note that Software Defined Networking has become broadly used terminology, including open and vendor proprietary protocols for network device control communication. Early in the project, OpenFlow was selected as the switch control protocol because it was the most widely deployed and supported, as well as being an open standard. DANCES team identified the version 1.3.0 specification as the minimum target for switch selection in order to provide for complex quality of service frameworks (e.g. rate limiting) that could be provided by implementation of the specification’s per-flow meters in section and per-port queues in section. The per-switch port buffer space was also an important consideration.

Product specifications from Arista, Brocade, Cisco, Dell, Noviflow, and Pica8 were assessed and determined not to “sufficiently meet all the selection criteria while remaining within the project budget.” Five OpenFlow switches were selected for field test, including an early-release Netronome Network Flow Processing Platform (NFPP-1U), a Juniper EX9204, a Juniper MX80-48T, an HP5920 (now HPE), and a Corsa DP6410, which was eventually selected for the project deployment.

Hazlewood expects that the SDN technology employed by DANCES may be adopted by major coordinated HPC networks such as XSEDE within the next five years, with more mainstream use in five to 10 years.

References

[i] Developing Applications with Networking Capabilities via End-to-End SDN (DANCES) project is a collaboration between The  University  of  Tennessee’s  National  Institute  for  Computational   Sciences (UT-NICS), Pittsburgh Supercomputing Center (PSC), Pennsylvania State University (Penn State), the National Center for Supercomputing Applications (NCSA), Texas Advanced Computing Center (TACC), Georgia Institute of Technology (Georgia Tech), the Extreme Science and Engineering Discovery Environment (XSEDE), and Internet2 to investigate and develop the ability to add network bandwidth scheduling via software- defined networking (SDN) programmability to selected cyberinfrastructure services and applications. DANCES, funded by the   National   Science   Foundation’s   Campus Cyberinfrastructure – Network Infrastructure and Engineering (CC-NIE) program award numbers 1341005, 1340953, and 1340981, has field tested five vendor network devices in order to determine which implements the DANCES requirements of the OpenFlow 1.3 standard to provide the network reservation and rate-limiting capability desired to implement the goals of DANCES.

[ii] Developing Applications with Networking Capabilities via End-to-End SDN

(DANCES), by Victor Hazlewood, Kathy Benninger, Greg Peterson, Jason Charcalla, Benny Sparks, Jesse Hanley, Andrew Adams, Bryan Learn, Robert Budden, Derek Simmel, Joseph Lappa, Jared Yanovich; http://www.psc.edu/images/news/XSEDE16-DANCES-final.pdf

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Nvidia’s Jensen Huang Delivers Vision for the New HPC

November 14, 2018

For nearly two hours on Monday at SC18, Jensen Huang, CEO of Nvidia, presented his expansive view of the future of HPC (and computing in general) as only he can do. Animated. Backstopped by a stream of data charts, produ Read more…

By John Russell

New Panasas High Performance Storage Straddles Commercial-Traditional HPC

November 13, 2018

High performance storage vendor Panasas has launched a new version of its ActiveStor product line this morning featuring what the company said is the industry’s first plug-and-play, portable parallel file system that d Read more…

By Doug Black

SC18 Student Cluster Competition – Revealing the Field

November 13, 2018

It’s November again and we’re almost ready for the kick-off of one of the greatest computer sports events in the world – the SC Student Cluster Competition. This is the twelfth time that teams of university undergr Read more…

By Dan Olds

HPE Extreme Performance Solutions

AI Can Be Scary. But Choosing the Wrong Partners Can Be Mortifying!

As you continue to dive deeper into AI, you will discover it is more than just deep learning. AI is an extremely complex set of machine learning, deep learning, reinforcement, and analytics algorithms with varying compute, storage, memory, and communications needs. Read more…

IBM Accelerated Insights

New Data Management Techniques for Intelligent Simulations

The trend in high performance supercomputer design has evolved – from providing maximum compute capability for complex scalable science applications, to capacity computing utilizing efficient, cost-effective computing power for solving a small number of large problems or a large number of small problems. Read more…

US Leads Supercomputing with #1, #2 Systems & Petascale Arm

November 12, 2018

The 31st Supercomputing Conference (SC) - commemorating 30 years since the first Supercomputing in 1988 - kicked off in Dallas yesterday, taking over the Kay Bailey Hutchison Convention Center and much of the surrounding Read more…

By Tiffany Trader

Nvidia’s Jensen Huang Delivers Vision for the New HPC

November 14, 2018

For nearly two hours on Monday at SC18, Jensen Huang, CEO of Nvidia, presented his expansive view of the future of HPC (and computing in general) as only he can Read more…

By John Russell

New Panasas High Performance Storage Straddles Commercial-Traditional HPC

November 13, 2018

High performance storage vendor Panasas has launched a new version of its ActiveStor product line this morning featuring what the company said is the industry Read more…

By Doug Black

SC18 Student Cluster Competition – Revealing the Field

November 13, 2018

It’s November again and we’re almost ready for the kick-off of one of the greatest computer sports events in the world – the SC Student Cluster Competitio Read more…

By Dan Olds

US Leads Supercomputing with #1, #2 Systems & Petascale Arm

November 12, 2018

The 31st Supercomputing Conference (SC) - commemorating 30 years since the first Supercomputing in 1988 - kicked off in Dallas yesterday, taking over the Kay Ba Read more…

By Tiffany Trader

OpenACC Talks Up Summit and Community Momentum at SC18

November 12, 2018

OpenACC – the directives-based parallel programing model for optimizing applications on heterogeneous architectures – is showcasing user traction and HPC im Read more…

By John Russell

How ASCI Revolutionized the World of High-Performance Computing and Advanced Modeling and Simulation

November 9, 2018

The 1993 Supercomputing Conference was held in Portland, Oregon. That conference and it’s show floor provided a good snapshot of the uncertainty that U.S. supercomputing was facing in the early 1990s. Many of the companies exhibiting that year would soon be gone, either bankrupt or acquired by somebody else. Read more…

By Alex R. Larzelere

At SC18: GM, Boeing, Deere, BP Talk Enterprise HPC Strategies

November 9, 2018

SC18 in Dallas (Nov.11-16) will feature an impressive series of sessions focused on the enterprise HPC deployments at some of the largest industrial companies: Read more…

By Doug Black

SC 30th Anniversary Perennials 1988-2018

November 8, 2018

Many conferences try, fewer succeed. Thirty years ago, no one knew if the first SC would also be the last. Thirty years later, we know it’s the biggest annual Read more…

By Doug Black & Tiffany Trader

Cray Unveils Shasta, Lands NERSC-9 Contract

October 30, 2018

Cray revealed today the details of its next-gen supercomputing architecture, Shasta, selected to be the next flagship system at NERSC. We've known of the code-name "Shasta" since the Argonne slice of the CORAL project was announced in 2015 and although the details of that plan have changed considerably, Cray didn't slow down its timeline for Shasta. Read more…

By Tiffany Trader

TACC Wins Next NSF-funded Major Supercomputer

July 30, 2018

The Texas Advanced Computing Center (TACC) has won the next NSF-funded big supercomputer beating out rivals including the National Center for Supercomputing Ap Read more…

By John Russell

IBM at Hot Chips: What’s Next for Power

August 23, 2018

With processor, memory and networking technologies all racing to fill in for an ailing Moore’s law, the era of the heterogeneous datacenter is well underway, Read more…

By Tiffany Trader

Requiem for a Phi: Knights Landing Discontinued

July 25, 2018

On Monday, Intel made public its end of life strategy for the Knights Landing "KNL" Phi product set. The announcement makes official what has already been wide Read more…

By Tiffany Trader

House Passes $1.275B National Quantum Initiative

September 17, 2018

Last Thursday the U.S. House of Representatives passed the National Quantum Initiative Act (NQIA) intended to accelerate quantum computing research and developm Read more…

By John Russell

CERN Project Sees Orders-of-Magnitude Speedup with AI Approach

August 14, 2018

An award-winning effort at CERN has demonstrated potential to significantly change how the physics based modeling and simulation communities view machine learni Read more…

By Rob Farber

Summit Supercomputer is Already Making its Mark on Science

September 20, 2018

Summit, now the fastest supercomputer in the world, is quickly making its mark in science – five of the six finalists just announced for the prestigious 2018 Read more…

By John Russell

New Deep Learning Algorithm Solves Rubik’s Cube

July 25, 2018

Solving (and attempting to solve) Rubik’s Cube has delighted millions of puzzle lovers since 1974 when the cube was invented by Hungarian sculptor and archite Read more…

By John Russell

Leading Solution Providers

US Leads Supercomputing with #1, #2 Systems & Petascale Arm

November 12, 2018

The 31st Supercomputing Conference (SC) - commemorating 30 years since the first Supercomputing in 1988 - kicked off in Dallas yesterday, taking over the Kay Ba Read more…

By Tiffany Trader

TACC’s ‘Frontera’ Supercomputer Expands Horizon for Extreme-Scale Science

August 29, 2018

The National Science Foundation and the Texas Advanced Computing Center announced today that a new system, called Frontera, will overtake Stampede 2 as the fast Read more…

By Tiffany Trader

HPE No. 1, IBM Surges, in ‘Bucking Bronco’ High Performance Server Market

September 27, 2018

Riding healthy U.S. and global economies, strong demand for AI-capable hardware and other tailwind trends, the high performance computing server market jumped 28 percent in the second quarter 2018 to $3.7 billion, up from $2.9 billion for the same period last year, according to industry analyst firm Hyperion Research. Read more…

By Doug Black

Intel Announces Cooper Lake, Advances AI Strategy

August 9, 2018

Intel's chief datacenter exec Navin Shenoy kicked off the company's Data-Centric Innovation Summit Wednesday, the day-long program devoted to Intel's datacenter Read more…

By Tiffany Trader

Germany Celebrates Launch of Two Fastest Supercomputers

September 26, 2018

The new high-performance computer SuperMUC-NG at the Leibniz Supercomputing Center (LRZ) in Garching is the fastest computer in Germany and one of the fastest i Read more…

By Tiffany Trader

Houston to Field Massive, ‘Geophysically Configured’ Cloud Supercomputer

October 11, 2018

Based on some news stories out today, one might get the impression that the next system to crack number one on the Top500 would be an industrial oil and gas mon Read more…

By Tiffany Trader

D-Wave Breaks New Ground in Quantum Simulation

July 16, 2018

Last Friday D-Wave scientists and colleagues published work in Science which they say represents the first fulfillment of Richard Feynman’s 1982 notion that Read more…

By John Russell

MLPerf – Will New Machine Learning Benchmark Help Propel AI Forward?

May 2, 2018

Let the AI benchmarking wars begin. Today, a diverse group from academia and industry – Google, Baidu, Intel, AMD, Harvard, and Stanford among them – releas Read more…

By John Russell

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This