Grid Computing

Grid computing is the practice of leveraging multiple computers, often geographically distributed but connected by networks, to work together to accomplish joint tasks. It is typically run on a “data grid,” a set of computers that directly interact with each other to coordinate jobs.

How Does Grid Computing Work?

Grid computing works by running specialized software on every computer that participates in the data grid. The software acts as the manager of the entire system and coordinates various tasks across the grid. Specifically, the software assigns subtasks to each computer so they can work simultaneously on their respective subtasks. After the completion of subtasks, the outputs are gathered and aggregated to complete a larger-scale task. The software lets each computer communicate over the network with the other computers so they can share information on what portion of the subtasks each computer is running, and how to consolidate and deliver outputs.

How Does Grid Computing Work?
With grid computing, specialized software runs on every computer that participates in the data grid. This controller software acts as the manager of the entire system and coordinates various tasks across the grid.

How is Grid Computing Used?

Grid computing is especially useful when different subject matter experts need to collaborate on a project but do not necessarily have the means to immediately share data and computing resources in a single site. By joining forces despite the geographical distance, the distributed teams are able to leverage their own resources that contribute to a bigger effort. This means that all computing resources do not have to work on the same specific task, but can work on sub-tasks that collectively make up the end goal. For example, a research team might analyze weather patterns in the North Atlantic region, while another team analyzes the south Atlantic region, and both results can be combined to deliver a complete picture of Atlantic weather patterns.

While often seen as a large-scale distributed computing endeavor, grid computing can also be leveraged at a local level. For example, a corporation that allocates a set of computer nodes running in a cluster to jointly perform a given task is a simple example of grid computing in action. A specific type of local data grid is an in-memory data grid (IMDG) in which computers are tightly connected via coordination software and a network connection to collectively process data in memory. The advantage is that the data is stored in memory across all computers in the data grid, so all data accesses are very fast. IMDGs like Hazelcast IMDG are especially useful when the grid computing tasks require extremely high throughput and extremely low latency.

In-Memory Data Grid Diagram
In-Memory Data Grids enhance the performance of grid computing by enabling higher throughput and lower latency.

Related Topics

Data Grid

Key-Value Store

In-Memory Database

In-Memory Computation

In-Memory Processing

In-Memory Data Grid

Further Reading

In-Memory Data Grids Popularity Trend Continues Upward

Transformational Drivers and In-Memory Data Grids

Relevant Resources

| Video
| 60 minutes

Introduction to In-Memory Data Grids

The speed at which today’s evolving data is exploding (90% of all data was collected in the last 2 years) imposes complex business problems that prevailing technology platforms can not address. This is preventing Enterprises from quickly extracting business value from this data. This poses further challenges as the value of data and the insights we can get from them decrease if it takes too long to take action.

In this talk, we will learn how Hazelcast® addresses these problems and helps Enterprises overcome the challenges of extracting business value from massive scale data.

You will be introduced to Distributed Systems and In-Memory Computing with Hazelcast. This talk will cover some familiar distributed data structures like Maps, Lists, Queues, etc., along with running complex business algorithms in parallel over a Hazelcast cluster by using Distributed Executor Service, EntryProcessors and In-Memory MapReduce.

White Paper

In-Memory Database vs In-Memory Data Grid

In-Memory Databases (IMDB) and In-Memory Data Grids (IMDG) are two technologies that address real-time computing and big data needs without having to start over with an entirely new set of IT systems. While they may sound similar, the differences are significant and understanding your options will help you make better decisions.

Your business operates in an environment with constantly evolving technology. For business and IT leaders, it can be overwhelming to keep up with new developments and determine what is critical to implement immediately, and what technologies can or should wait. In-memory processing technologies are becoming pervasive and have a direct and indirect effect on how a business operates. Hazelcast has created this whitepaper to discusses these technologies and the respective implications.

| Video
| 60 minutes

Time to Make the Move to In-Memory Data Grids

DRAM is dirt cheap. That’s why in-memory databases, analytics, and data grids are surging in popularity among firms that have an insatiable need for performance and scalability. But, databases, analytics platforms, and data grids target very different use cases. In-memory data grids, in particular, are often misunderstood because they support an extensive set of use cases that often overlap other technologies. Join guest speaker Mike Gualtieri, Principal Analyst at Forrester Research, Greg Luck, CEO of Hazelcast®, and Ken Kolda, Software Architect of Ellie Mae on this radio-show style webinar to boost your in-memory IQ.

Case Study

Hazelcast for E-Commerce

E-commerce is now in an era of radically multichannel and omnichannel stack deployments, with middleware supporting mobile, in-store environments, kiosk and web stores. To support the
extreme scale and unpredictability of multichannel consumer behavior while at the same time providing microsecond performance characteristics requires in-memory technology.

Hazelcast® is an in-memory technology for scaling your e-commerce and inventory management systems to handle burst behavior from events such as on Black Friday and Cyber Monday.

View All Resources