A Blueprint for Centralized Research Data Storage and Sharing

By Becky Yeager, Thomas Hauser, Peter Ruprecht, and Dan Milroy, University of Colorado, Boulder

March 3, 2014

The University of Colorado Boulder PetaLibrary storage system was recently deployed by the CU Research Computing (RC) group to address the increasing challenges that researchers face regarding large-scale data storage and data management. The PetaLibrary, in part funded by the National Science Foundation, provides a variety of services to campus researchers including high-performance short-term storage, long-term archive storage, and the ability to share data with collaborators at CU-Boulder and across the country.

The PetaLibrary offers several petabytes of data storage using an expandable and modular hardware design. Currently, more than a dozen research groups are using over 100 TB of data on the PetaLibrary system. Researchers and Data Scientists in disciplines ranging from Humanities to Biology, as well as the University of Colorado Boulder Libraries (CU-Boulder Libraries), are using the PetaLibrary storage services. These researchers all have one thing in common, the need for large-scale and low-cost data storage. Usage of the PetaLibrary is expected to double in the next few months.

The two main categories of service offered to customers of the PetaLibrary are Active storage for data that needs to be accessed frequently and Archive storage for data that is accessed infrequently. Active data is always stored on disk and is accessible to researchers on compute resources managed by RC. Archive storage consists of a two level hierarchical storage management (HSM) solution, with disk storage for data that is more likely to be accessed and tape for data that is less likely to be accessed frequently. The HSM configuration was developed in collaboration between RC and a consultant from Re-Store LLC to produce a cost effective solution for allowing automatic transfer between disk and tape.  For data whose importance warrants multiple copies, options for replication to separate tape cartridges or even to a disk-based storage system in a remote datacenter are available.

Disk storage for the PetaLibrary resides on scalable high-density DDN SFA10K and IBM DCS3700 RAID-6 systems.  These are grouped into GPFS clusters for high performance and reliability.  The tape storage system consists of an IBM TS-3584 library with four LTO-6 drives.  We use Tivoli Storage Manager to move data to and from tape.  TSM’s HSM module, plus a number of custom scripts, enables policy-based migration of files between the GPFS filesystem and the tape storage.

Large scale storage on its own is only useful if the associated network infrastructure is designed with large data transfers in mind. Therefore, RC in collaboration with CU’s Office of Information Technology, has deployed a ScienceDMZ, funded by a NSF CC-NIE grant. The core of this science network can perform at 80 Gbps and data on the PetaLibrary is accessed through secure, high-performance file transfer programs. With a fast science network, data can be easily retrieved and sent directly to each researcher’s desktop.  In order to facilitate web-mediated transfers the PetaLibrary utilizes tools provided by Globus. Globus makes robust file transfer capabilities, traditionally available only on expensive, special-purpose software systems, accessible to any researcher with an Internet connection and a laptop.  It also facilitates sharing data between collaborators both on- and off-campus. The current ScienceDMZ, is a 10 Gbps ethernet dedicated layer-2 network serving as a critical infrastructure for a number of data transfer services provided by RC to the CU-Boulder campus community. The NSF funded improvements of the ScienceDMZ include upgraded border routers with 100 Gbps and OpenFlow capabilities, up to 80 Gbps for the DMZ core, performance monitoring and security monitoring.

Clients of the PetaLibrary have been pleased with the services they have received so far. The CU-Boulder Libraries was one of the early adopters of the PetaLibrary services. As one of the larger users, the CU-Boulder Libraries uses the PetaLibrary to build digital collections in a variety of media types for research and study. According to digital initiatives librarian Holley Long, “The CU-Boulder Libraries digitizes audio, video, images, text and soon 3D objects, according to nationally-accepted archival standards.” Large-scale storage is important to these projects because of the initial size of the uncompressed files, often as large as 120 GB per hour of digitized video. In 2014 the estimated production capacity for the library’s digital collections could exceed 80 TB (https://content.cu.edu/digitallibrary/cuAuraria.html).

The University of Colorado Museum of Natural History is using the services provided by the PetaLibrary to store digitized copies of their entire collection. The collection includes 4.5 million objects, including the oldest documented Navajo textile, the Aiken bird collection, and Colorado’s largest collection of bees, along with the metadata associated with each object. The metadata for each distinct object includes notes on who found it, where it was found, when it was located, what it is, and pictures of what it looks like. Every object in the museum has its own interesting backstory, one that comes to life when an object is viewed in relationship with its complex metadata. Because we now live in a digital age the museum is attempting to democratize their exhibits (http://cumuseum.colorado.edu/research/databases). This means that every visitor to the museum will have the opportunity to view the collection in its entirety in a digital format.

Being able to digitally store their entire collection provides the museum with the best of both worlds. Pat Kociolek, Director of the Museum of Natural History, describes the importance of the PetaLibrary to their archives, “It allows the museum the opportunity to make these digital dreams come to life. Visitors can physically view individual items, and when our work is complete visitors will also be able to access the entire collection online. Digital collections also allow remote visitors such as teachers, scientists, and students the chance to browse the collection even if they are unable to visit the museum in person”.  As the data needs of the museum reached over 100 TB, they could no longer rely on local storage resources. The PetaLibrary became an important resource for the museum staff allowing them to archive, and keep safe, those digital resources that have been developed as a way to serve all of their constituents. As a centralized facility on campus the PetaLibrary can provide the museum with the security they need to store these items and to share them widely.

On the CU-Boulder campus researchers are producing large amounts of data in diverse areas such as digital humanities, simulation studies, to global climate modeling. Researchers on campus need ways to preserve this data and to make the data accessible to others. Transparency and the ability to share data and resources with others are important parts of any research plan. The PetaLibrary provides the campus with a centralized location to consolidate this data, and the means to share this data with others through Globus Connect Server.

The PetaLibrary is an important part of the evolving data management ecosystem on campus. It allows researchers to use a high-speed network to move data in and out of storage across campus, and around the nation. The Globus software suite makes it easy to transfer data sets, and to share securely with collaborators. A common practice has been for researchers to store data sets on PCs in labs or on USB-connected drives.  The PetaLibrary, by contrast, provides the security of enterprise storage systems with redundant disk arrays in data centers with environmental and access controls, at a comparable cost through the subsidies of the NSF Grant.

The future vision for the PetaLibrary is to expand the storage capabilities of the system and to enable tools that will help with metadata management and data discovery, and enhance sharing options on campus and with public facing data portals.  The PetaLibrary is an important new service that is at the forefront of the campus discussion on how to deal with the challenges of research data, and it is helping to address the current research needs of the campus and the growth that is anticipated in these areas. A newly created faculty committee is discussing the how to bring additional services to researchers including data curation, metadata management, and data management planning, at a reasonable and sustainable cost.

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!

Data Vortex Users Contemplate the Future of Supercomputing

October 19, 2017

Last month (Sept. 11-12), HPC networking company Data Vortex held its inaugural users group at Pacific Northwest National Laboratory (PNNL) bringing together about 30 participants from industry, government and academia t Read more…

By Tiffany Trader

AI Self-Training Goes Forward at Google DeepMind

October 19, 2017

DeepMind, Google’s AI research organization, announced today in a blog that AlphaGo Zero, the latest evolution of AlphaGo (the first computer program to defeat a Go world champion) trained itself within three days to play Go at a superhuman level (i.e., better than any human) – and to beat the old version of AlphaGo – without leveraging human expertise, data or training. Read more…

By Doug Black

Researchers Scale COSMO Climate Code to 4888 GPUs on Piz Daint

October 17, 2017

Effective global climate simulation, sorely needed to anticipate and cope with global warming, has long been computationally challenging. Two of the major obstacles are the needed resolution and prolonged time to compute Read more…

By John Russell

HPE Extreme Performance Solutions

Transforming Genomic Analytics with HPC-Accelerated Insights

Advancements in the field of genomics are revolutionizing our understanding of human biology, rapidly accelerating the discovery and treatment of genetic diseases, and dramatically improving human health. Read more…

Student Cluster Competition Coverage New Home

October 16, 2017

Hello computer sports fans! This is the first of many (many!) articles covering the world-wide phenomenon of Student Cluster Competitions. Finally, the Student Cluster Competition coverage has come to its natural home: H Read more…

By Dan Olds

Data Vortex Users Contemplate the Future of Supercomputing

October 19, 2017

Last month (Sept. 11-12), HPC networking company Data Vortex held its inaugural users group at Pacific Northwest National Laboratory (PNNL) bringing together ab Read more…

By Tiffany Trader

AI Self-Training Goes Forward at Google DeepMind

October 19, 2017

DeepMind, Google’s AI research organization, announced today in a blog that AlphaGo Zero, the latest evolution of AlphaGo (the first computer program to defeat a Go world champion) trained itself within three days to play Go at a superhuman level (i.e., better than any human) – and to beat the old version of AlphaGo – without leveraging human expertise, data or training. Read more…

By Doug Black

Student Cluster Competition Coverage New Home

October 16, 2017

Hello computer sports fans! This is the first of many (many!) articles covering the world-wide phenomenon of Student Cluster Competitions. Finally, the Student Read more…

By Dan Olds

Intel Delivers 17-Qubit Quantum Chip to European Research Partner

October 10, 2017

On Tuesday, Intel delivered a 17-qubit superconducting test chip to research partner QuTech, the quantum research institute of Delft University of Technology (TU Delft) in the Netherlands. The announcement marks a major milestone in the 10-year, $50-million collaborative relationship with TU Delft and TNO, the Dutch Organization for Applied Research, to accelerate advancements in quantum computing. Read more…

By Tiffany Trader

Fujitsu Tapped to Build 37-Petaflops ABCI System for AIST

October 10, 2017

Fujitsu announced today it will build the long-planned AI Bridging Cloud Infrastructure (ABCI) which is set to become the fastest supercomputer system in Japan Read more…

By John Russell

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Intel Debuts Programmable Acceleration Card

October 5, 2017

With a view toward supporting complex, data-intensive applications, such as AI inference, video streaming analytics, database acceleration and genomics, Intel i Read more…

By Doug Black

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

NERSC Scales Scientific Deep Learning to 15 Petaflops

August 28, 2017

A collaborative effort between Intel, NERSC and Stanford has delivered the first 15-petaflops deep learning software running on HPC platforms and is, according Read more…

By Rob Farber

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

Oracle Layoffs Reportedly Hit SPARC and Solaris Hard

September 7, 2017

Oracle’s latest layoffs have many wondering if this is the end of the line for the SPARC processor and Solaris OS development. As reported by multiple sources Read more…

By John Russell

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

Google Releases Deeplearn.js to Further Democratize Machine Learning

August 17, 2017

Spreading the use of machine learning tools is one of the goals of Google’s PAIR (People + AI Research) initiative, which was introduced in early July. Last w Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Graphcore Readies Launch of 16nm Colossus-IPU Chip

July 20, 2017

A second $30 million funding round for U.K. AI chip developer Graphcore sets up the company to go to market with its “intelligent processing unit” (IPU) in Read more…

By Tiffany Trader

Leading Solution Providers

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

Amazon Debuts New AMD-based GPU Instances for Graphics Acceleration

September 12, 2017

Last week Amazon Web Services (AWS) streaming service, AppStream 2.0, introduced a new GPU instance called Graphics Design intended to accelerate graphics. The Read more…

By John Russell

EU Funds 20 Million Euro ARM+FPGA Exascale Project

September 7, 2017

At the Barcelona Supercomputer Centre on Wednesday (Sept. 6), 16 partners gathered to launch the EuroEXA project, which invests €20 million over three-and-a-half years into exascale-focused research and development. Led by the Horizon 2020 program, EuroEXA picks up the banner of a triad of partner projects — ExaNeSt, EcoScale and ExaNoDe — building on their work... Read more…

By Tiffany Trader

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Cray Moves to Acquire the Seagate ClusterStor Line

July 28, 2017

This week Cray announced that it is picking up Seagate's ClusterStor HPC storage array business for an undisclosed sum. "In short we're effectively transitioning the bulk of the ClusterStor product line to Cray," said CEO Peter Ungaro. Read more…

By Tiffany Trader

Intel Launches Software Tools to Ease FPGA Programming

September 5, 2017

Field Programmable Gate Arrays (FPGAs) have a reputation for being difficult to program, requiring expertise in specialty languages, like Verilog or VHDL. Easin Read more…

By Tiffany Trader

IBM Advances Web-based Quantum Programming

September 5, 2017

IBM Research is pairing its Jupyter-based Data Science Experience notebook environment with its cloud-based quantum computer, IBM Q, in hopes of encouraging a new class of entrepreneurial user to solve intractable problems that even exceed the capabilities of the best AI systems. Read more…

By Alex Woodie

Intel, NERSC and University Partners Launch New Big Data Center

August 17, 2017

A collaboration between the Department of Energy’s National Energy Research Scientific Computing Center (NERSC), Intel and five Intel Parallel Computing Cente Read more…

By Linda Barney

  • arrow
  • Click Here for More Headlines
  • arrow
Share This