Osaka University, Scality and Fujitsu in Joint Intercontinental Data Center Coordination Field Trial Using Cold Storage

Osaka University, Scality Inc., and Fujitsu Limited announced that the three organizations are jointly executing a cold storage-focused field trial of intercontinental data center coordination, together with partners in Japan and Europe.

Based on a consortium for collaboration between academia and industry established in April 2016, the field trial will be conducted from November 2016 through to December 2017, and carried out between the data centers in Osaka University’s Cybermedia Center and the data centers owned by Paris-based AntemetA SAS.

In this field trial, the partners will build and test the effectiveness of a storage platform coordinated across remote locations, which offers improvements in throughput¹, disaster resilience, and lower costs by eliminating redundancy within individual data centers. This is done by duplicating data that is not updated very often, known as cold data, in data centers on each continent, and applying a data sharing technology from Scality called conflict-free replicated data type (CRDT)², which is used in distributed computing environments.

Background
Currently, in order to coordinate data between data centers, two methods are used: one in which coordination is done through synchronous communications over short distances where data transfer delays are small, and another is to make backups through asynchronous communication over long distances. When using synchronous communication over short distances, there is a high probability that multiple data centers might be simultaneously affected by large-scale disasters. When asynchronous communication is used over long distances, there are large delays in transmitting data between data centers, so the only option was standby redundancy coordination for backups or DR.

At the same time, against the backdrop of changes such as the spread of technologies like AI and the IoT, data which is generally not updated, called cold data, has taken up more than half of all data, primarily in the form of image and video data, and there is an increasing demand for ways to accumulate new data and share it between multiple locations. In order to achieve data center coordination between multiple locations, however, there have been issues in achieving data synchronization between data centers, and in improving response speed when reading the data.

Summary of the Field Trial

Trial Period
November 2016 – December 2017

Field Trial Details
The participants will develop the ‘Geo Replication’ system to realize the layering and data redundancy, which had only been achieved between data centers in close proximity or within a stand-alone data center, at long distances such as between continents. By layering and storing not only continually updated hot data and infrequently updated warm data, but also cold data, which is seldom updated, across multiple types of storage devices, long-term storage functionality, lowered costs, and increased responsiveness and overall throughput can be achieved across the system as a whole.

The companies participating in this consortium will advance the development of the geo replication system, and the field trial will be carried out, aiming for commercialization, with partners in Europe, using data that is actually in use in Osaka University’s data centers.

Academic and industrial consortium participants implementing this trial:

Acutus Software, Inc.
Chuo Electronics Co., Ltd.
Commissariat à l’énergie atomique et aux énergies alternatives
Engineering Ingegneria Informatica S.p.A.
FESTIVAL Project
French Institute for Research in Computer Science and Automation (Inria)
Fujitsu Limited
Institut Pasteur
Osaka University
Panasonic Corporation
Raritan Japan, Inc.
Scality Inc.
Yahoo Japan Corporation

Division of Roles

Osaka University

Responsible for controlling data layering between cold storage and the Scality Ring storage software, which is used to manage massive volumes of data.
Technology for determining hot and cold data.
Building the Osaka site (in the Osaka University Cybermedia Center).

Scality

Responsible for data replication between storage functionality through Scality Ring and remote sites.
Providing Scality Ring.
Developing and providing replication functionality for this operational trial.
Building the site in France (data centers owned by AntemetA outside Paris).

Fujitsu

Responsible for managing the whole project, for implementing hot and cold storage, and for a high-speed search system for archive data.
Providing hardware such as the Fujitsu Storage Eternus DA700, a form of cold storage, high performance servers like Fujitsu Server Primergy RX2530, and high functionality switches.
Building the Fujitsu Intelligent Data Service SmartContentsManager high-speed archive data search system.

Future Developments

By the end of March 2017, the three organizations will confirm the basic operation of the system, and publish a paper on the research results from this trial during fiscal 2017. In addition, from April 2017 through December 2017, together with joint field trial partners in Japan and Europe, they will perform a usage trial for specific applications, with a variety of data types.

Based on the trial’s research results, the three organizations will each aim to develop cold storage services, a storage platform coordinated between remote locations, and other practical technologies.

Toshinori Kishi, director of the storage division, AVC Networks company, Panasonic, said: “Panasonic is participating in the Geo Replication consortium, which offers a new way of using the Eternus DA700, a Panasonic OEM product for Fujitsu, and is very pleased to see this field trial move forward.”

“Looking at the global market, Panasonic’s data archive system using optical discs has been used by the largest social network company in the US, demonstrating that it is already becoming a realistic option for companies and public sector institutions that need long-term storage. By adding a new way of using it for remote coordination among data centers, we expect it will also become an option in new fields, such as academic research and storage services.”

Marc Shapiro, Ph.D., senior researcher, the French Institute for Research in Computer Science and Automation, said: “I welcome this new proof-of-concept announcement, which builds upon collaboration between academia and industry, in France and Japan. The growing data needs of modern society carry the fundamental challenge of scaling both in volume and geographically. CRDTs represent a technology base for sharing data consistently across long distances in a way that is both economical and understandable to users and developers. I trust that this technology will contribute to the success of this PoC.”

¹ Throughput: The volume of data that can be transmitted in one second.
² Conflict-free Replicated Data Type (CRDT). A computational algorithm used in a distributed environment for efficient data distribution and replication. Proposed in 2007 by Marc Shapiro, Ph.D., senior researcher of the French Institute for Research in Computer Science and Automation.