Posts: 5,362
Threads: 2,998
Joined: Feb 2011
presented by:
ABUBAKAR MUSA
[attachment=9480]
RELIABILITY ARRAY OF INDEPENDENT NODES (RAIN) TECHNOLOGY
ABSTRACT
The topic of the research paper is RAIN TECHNOLOGY. RAIN stands for Reliable Array of Independent Nodes. The goal of the RAIN seminar presentation is to identify key software building blocks for creating reliable distributed applications using off-the-shelf hardware. The focus of the research is on high-performance, fault-tolerant and portable clustering technology for space-borne computing.
SECTION ONE
OVERVIEW OF RAIN TECHNOLOGY
1.0 INTRODUCTION
RAIN (Reliability Array for Independent Nodes) technology originated in a research project at the California Institute of Technology (Caltech), in collaboration with National Aeronautics and Space Administration – NASA’s Jet Propulsion Laboratory and the Defense Advanced Research Projects Agency (DARPA). The name of the original research project was RAIN, which stands for Reliable Array of Independent Nodes. In short, the RAIN project intended to relate distributed computing with networking protocols. It became obvious that RAIN technology was well-suited for Internet applications.
During the RAIN project, two important assumptions were made, and these two assumptions reflect the differentiations between RAIN and a number of existing solutions both in the industry and in academia:
1. The most general share-nothing model is assumed. There is no shared storage accessible from all computing nodes. The only way for the computing nodes to share state is to communicate via a network. This differentiates RAIN technology from existing back-end server clustering solutions such as SUNcluster, HP MC Serviceguard or Microsoft Cluster Server.
2. The distributed application is not an isolated system. The distributed protocols interact closely with existing networking protocols so that a RAIN cluster is able to interact with the environment. Specifically, technological modules were created to handle high-volume network-based transactions. This differentiates it from traditional distributed computing projects such as Beowulf.
In short, the RAIN project intended to marry distributed computing with networking protocols. It became obvious that RAIN technology was well-suited for Internet applications. During the RAIN project, key components were built to fulfill this vision. A patent was filed and granted for the RAIN technology. Rainfinity was spun off from Caltech in 1998, and the company has exclusive intellectual property rights to the RAIN technology. After the formation of the company, the RAIN technology has been further augmented, and additional patents have been filed.
1.1 AIMS AND OBJECTIVES
1. The major aim of the research work is to identify key software building blocks for creating reliable distributed applications using off-the-shelf hardware.
2. To lay emphasis on the need to build a reliable space-borne computer capable of overcoming the consequence of malfunction in existing space-borne computers.
3. To see into developing an alternative to the costly special-purpose computer systems used in space missions.
1.2 HISTORY OF RAIN TECHNOLOGY
RAIN traces its origins to 1994, when Shuki Bruck, professor of computation and neural systems and electrical engineering at Caltech, and Leon Alkalai, director of JPL’s Center for Integrated Space Microsystems, came up with an idea to improve NASA’s computer systems, both on the ground and in space.
“In the past, NASA would customize every computer component—both hardware and software—for each job, which is extremely expensive,” says Bruck, an expert in parallel and distributed computing and fault-tolerant computing. “It made sense to us to propose a project to use commercial, off-the-shelf components.”
Bruck and Alkalai went to Washington, pitched the idea to officials with the Defense Advanced Research Projects Agency (DARPA), and by 1995 got funding from NASA and DARPA to develop an alternative to the costly, special-purpose computer systems used in space missions. Bruck gathered a team of five graduate students, and by 1997 they had built a prototype of a system called the Redundant Array of Independent Nodes, or RAIN.
In the spring of 1998, Bruck approached the five graduate students who had worked on RAIN and asked them if they wanted to start a company with him. Two opted to pursue academic careers, but three signed on—Vincent Bohossian, PhD ’98, Charles Fan, PhD ’01, and Paul LeMahieu, MS ’96. In addition, Phil Love, PhD ’99, then a graduate student in applied mathematics, was recruited for the team.
Bruck, together with his business partners, then found several investors to provide a total of $2 million to launch the company, which they named Rain-finity. With the money, they set up a research office in the Old Town section of Pasadena in September 1998. They then began creating a software product so that companies would no longer have to rely on single Internet gateways to their Web sites. A com-pany’s Web site could be accessed faster, and many more people could get into the site at the same time. There would be multiple pathways to route traffic, and the system would also serve as a so--called firewall against outside security breaches and viruses. The system, called Rain-wall, was completed in 1999. It sells for $5,000 to $20,000, depending on the number of processors supported.
1.3 RAIN PROTOTYPE
The RAIN prototype was finished at a time when more people had begun going online, to shop or check out companies and products, and businesses began to recognize the Internet as a tool that was vital to their future. Bruck realized that companies that relied on the Web for business were subject to dire consequences if their systems crashed, since competition was now just a click away. And Internet sites crashed often because the computer systems handling Internet connections were not built to manage the Internet onslaught. Bruck figured that RAIN could be applied to the Internet and he began investigating the possibility of starting a company to commercialize RAIN.
1.4 FROM RAIN TO RAINFINITY
As previously stated; the RAIN project was a research collaboration between Caltech and NASA-JPL on distributed computing, communication and data storage systems for future spaceborne missions. The goal of the project was to identify and develop key building blocks for reliable distributed systems built with inexpensive off-the-shelf components. The RAIN software components run in conjunction with operating system services and standard network protocols. Through software-implemented fault tolerance, the system tolerates multiple node, link, and switch failures, with no single point of failure. The RAIN technology has been transferred to Rainfinity, a start-up company focusing on creating clustered solutions for improving the performance, availability and scalability of Internet data centers.
SECTION TWO
2.0 RAINFINITY HIGH AVAILABILITY SOLUTIONS
In June 10, 2002, Network resources software provider Rainfinity (Rainfinity.com) announced on Monday that it has introduced new versions of its RainWall and RainConnect high availability software solutions.
The new products, says Rainfinity, are designed to make non-stop firewall operation and Internet connectivity practical standard network components for any business facility, making high availability easy and affordable enough for small companies, along with multinational corporations, to deploy beyond the data center at virtually any location, including remote offices, branch locations, warehouses and partner sites.
RainWall 3.0, the latest version of the company’s high availability and load balancing software for firewalls and VPN gateways, says Rainfinity, is easier to use, integrates more tightly with Check Point’s NG firewalls, can fail over to nodes distributed across a campus or metro-wide LAN and can be embedded into network appliances and applications.
The company says RainWall also integrates closely with the new RainConnect 3.0 Internet connectivity product, designed to maintain Internet connectivity despite ISP connection disruptions.
