Network-Attached Memory: Virtualization for Java Environments

By Dennis Barker

October 6, 2008

Easing application scalability across a cluster is a problem being solved in a variety of ways. Terracotta does it with memory – network-attached memory, to be exact. The company’s infrastructure software creates an expandable/retractable pool of shared memory that Java applications can tap to meet increasing demand.

Network-attached memory is analogous to network-attached storage (NAS) in that it provides a service to thousands of connected clients transparently. As NAS is transparent underneath the file system, network-attached memory is transparent underneath the Java language, says Jeff Hartley, vice president of products and marketing at Terracotta. Objects are manipulated and kept consistent in memory like files are in NAS, but in Terracotta’s memory pool, everything can be massively scaled out.

“Another way to think of it is virtualization for the Java environment,” Hartley says. “In the same way that a hypervisor slices a machine into several logical machines, Terracotta takes many physical machines and connects them as one logical machine.”

Developers don’t have to change their applications to get clustering behavior. A clustered application looks the same as a Java application. Essentially, users tell Terracotta what to do in a config file, Hartley says, and the software injects that behavior into the application at runtime. Not only is there is no API required to send messages across the cluster, he says, there is no API at all. Terracotta uses plain old Java objects and plugs into familiar frameworks like Spring, Hibernate and EHcache so developers can continue using the same tools, stacks and development models.

“We provide an open source clustering solution,” says Hartley. “It’s scalability and high availability for Java enterprise apps, without having to change your application code. We actually hook into the Java virtual machine and share data.”

Beside simplified clustering and scalable performance, Hartley says Terracotta’s approach also brings “high availability without tradeoffs” — the possibility of reducing database bottlenecks, achieving better use of hardware, lowering maintenance costs, and, because the software takes care of adding clustering capabilities, focusing on developing new applications rather than retooling old ones.

“We’re working at the level of memory. If you have App Server A die, the user gets sent to App Server B, and all the data is sent from memory to B without the user even realizing it,” Hartley says. “We provide high availability by putting everything in memory instead of adding racks of servers.”

When you add a server to handle demand, it just “joins the group.” “You don’t have to implement anything. Just add the servers and we make them members of the cluster’s shared memory pool. Our server keeps your server’s data in sync,” Hartley says. Changes to one virtual machine are instantaneously reflected to every virtual machine throughout the cluster that needs to know.

Because data can be shared between Java virtual machines and processed at in-memory speeds, some customers use the software to take load off their databases. Transient data like user session info or shopping cart info can be kept and processed in memory, while only critical results are sent to and kept in the database. “Terracotta is used to handle the work-in-progress data while a process is running, and only the completed data goes to the database. As a result, some of our users have been able to reduce database utilization by as much as 70 percent and not have to buy more database licenses to meet increased workload,” Hartley says.

Eliminating mundane work for IT staff is one of Terracotta’s other major selling points. As company CTO Ari Zilka explains in a video tour of the software, “You don’t have to write the plumbing or maintain the plumbing. …You can run an app on two servers at midnight and on 20 servers at noon. It frees IT to run apps the way they need to run them” and focus development time on more important business issues, he says.

Deployment involves two primary components: client nodes and the Terracotta server array. Nodes run on standard Java VMs, and each node corresponds to a Java process in the cluster (e.g., the application server). Terracotta is loaded into each VM at startup. The Terracotta server array provides the intelligence to orchestrate all the nodes in the cluster, synchronize activity between them, replicate data and handle storing data to disk. The array can run in an active-passive pair configuration for high availability that can achieve tens of thousands of requests per second, the company says. Running multiple instances of the Terracotta server in active-passive mode guarantees that a failure won’t compromise the cluster, the company says.

“We’re a very fundamental technology. We’re not a grid solution, we’re not a cloud solution. We’re network-attached memory — distributed memory that sits right below the applications, and can be used for all kinds of things,” explains Hartley.

Demanding Customers

Customers running Terracotta typically have one thing in common: unpredictable numbers of demanding users. (Zilka used to be chief architect at, so he knows about building infrastructure to deal with traffic spikes of epic proportion.) The user list includes big names familiar with meeting heavy online demand, including Adobe, MapQuest, BBC, Electronic Arts, PartyGaming (, etc.), and financial services companies like JP Morgan and Mizuho Securities.

An online multiplayer gaming company that wishes to remain unnamed uses clustered servers to not just host games, but also to coordinate and track player activities. It chose Terracotta as its scale-out solution for several reasons: (1) it works behind the scenes, at byte-code level, providing distributed heap memory across multiple Java VMs; (2) developers can use the standard Java semantics for synchronizing access to shared objects; (3) “impressive horizontal scalability” enabled by just adding more server nodes and not having to use databases and caches to manage shared data; (4) no single point of failure; and (5) it’s open source, so the software doesn’t add to the bottom line and doesn’t require a purchase order to get started.

Mark Turansky, a software architect currently working in the health care industry, has written about his experience using Terracotta. “With enabling software like Terracotta, clustering becomes easy. You’ve still got to design your software to take advantage of parallelism, but the act of running programs in parallel is no longer difficult. …It invisibly and magically clusters your Java classes via configuration,” Turansky writes. “Distributing code and running massively parallel programs used to be difficult. It required complex architectures and expensive application servers. This is accidental complexity. Advances in software development — like Terracotta, GridGain, Spring, and other FOSS [free open source] programs — dramatically reduce if not eliminate the accidental complexity of distributing your programs to a cluster of machines.”

Gnip, a service that aggregates and distributes feeds from sites like Twitter and Digg to users of services like Plaxo, runs its system on Amazon’s EC2 but chose Terracotta for node replication at the memory level. A post on the company’s site explains: “The prospect of just writing our app and thinking of it as a single thing, rather than ‘how does all this state get replicated across n number of nodes’ was soooo appealing.”

Terracotta has just released version 2.7, which the company says is more tightly integrated with frameworks like Spring and Glassfish, and adds better management and visualization features, improved garbage collection and the ability to apply hot patches. It is available for download at www.

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!

Tuning InfiniBand Interconnects Using Congestion Control

July 26, 2017

InfiniBand is among the most common and well-known cluster interconnect technologies. However, the complexities of an InfiniBand (IB) network can frustrate the most experienced cluster administrators. Maintaining a balan Read more…

By Adam Dorsey

NSF Project Sets Up First Machine Learning Cyberinfrastructure – CHASE-CI

July 25, 2017

Earlier this month, the National Science Foundation issued a $1 million grant to Larry Smarr, director of Calit2, and a group of his colleagues to create a community infrastructure in support of machine learning research Read more…

By John Russell

DARPA Continues Investment in Post-Moore’s Technologies

July 24, 2017

The U.S. military long ago ceded dominance in electronics innovation to Silicon Valley, the DoD-backed powerhouse that has driven microelectronic generation for decades. With Moore's Law clearly running out of steam, the Read more…

By George Leopold

HPE Extreme Performance Solutions

HPE Servers Deliver High Performance Remote Visualization

Whether generating seismic simulations, locating new productive oil reservoirs, or constructing complex models of the earth’s subsurface, energy, oil, and gas (EO&G) is a highly data-driven industry. Read more…

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 2017 with scale-up production for enterprise datacenters and Read more…

By Tiffany Trader

Tuning InfiniBand Interconnects Using Congestion Control

July 26, 2017

InfiniBand is among the most common and well-known cluster interconnect technologies. However, the complexities of an InfiniBand (IB) network can frustrate the Read more…

By Adam Dorsey

NSF Project Sets Up First Machine Learning Cyberinfrastructure – CHASE-CI

July 25, 2017

Earlier this month, the National Science Foundation issued a $1 million grant to Larry Smarr, director of Calit2, and a group of his colleagues to create a comm Read more…

By John Russell

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

Fujitsu Continues HPC, AI Push

July 19, 2017

Summer is well under way, but the so-called summertime slowdown, linked with hot temperatures and longer vacations, does not seem to have impacted Fujitsu's out Read more…

By Tiffany Trader

Researchers Use DNA to Store and Retrieve Digital Movie

July 18, 2017

From abacus to pencil and paper to semiconductor chips, the technology of computing has always been an ever-changing target. The human brain is probably the com Read more…

By John Russell

The Exascale FY18 Budget – The Next Step

July 17, 2017

On July 12, 2017, the U.S. federal budget for its Exascale Computing Initiative (ECI) took its next step forward. On that day, the full Appropriations Committee Read more…

By Alex R. Larzelere

Women in HPC Luncheon Shines Light on Female-Friendly Hiring Practices

July 13, 2017

The second annual Women in HPC luncheon was held on June 20, 2017, during the International Supercomputing Conference in Frankfurt, Germany. The luncheon provid Read more…

By Tiffany Trader

Satellite Advances, NSF Computation Power Rapid Mapping of Earth’s Surface

July 13, 2017

New satellite technologies have completely changed the game in mapping and geographical data gathering, reducing costs and placing a new emphasis on time series Read more…

By Ken Chiacchia and Tiffany Jolley

Google Pulls Back the Covers on Its First Machine Learning Chip

April 6, 2017

This week Google released a report detailing the design and performance characteristics of the Tensor Processing Unit (TPU), its custom ASIC for the inference Read more…

By Tiffany Trader

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

Quantum Bits: D-Wave and VW; Google Quantum Lab; IBM Expands Access

March 21, 2017

For a technology that’s usually characterized as far off and in a distant galaxy, quantum computing has been steadily picking up steam. Just how close real-wo Read more…

By John Russell

HPC Compiler Company PathScale Seeks Life Raft

March 23, 2017

HPCwire has learned that HPC compiler company PathScale has fallen on difficult times and is asking the community for help or actively seeking a buyer for its a Read more…

By Tiffany Trader

Trump Budget Targets NIH, DOE, and EPA; No Mention of NSF

March 16, 2017

President Trump’s proposed U.S. fiscal 2018 budget issued today sharply cuts science spending while bolstering military spending as he promised during the cam Read more…

By John Russell

CPU-based Visualization Positions for Exascale Supercomputing

March 16, 2017

In this contributed perspective piece, Intel’s Jim Jeffers makes the case that CPU-based visualization is now widely adopted and as such is no longer a contrarian view, but is rather an exascale requirement. Read more…

By Jim Jeffers, Principal Engineer and Engineering Leader, Intel

Nvidia’s Mammoth Volta GPU Aims High for AI, HPC

May 10, 2017

At Nvidia's GPU Technology Conference (GTC17) in San Jose, Calif., this morning, CEO Jensen Huang announced the company's much-anticipated Volta architecture a Read more…

By Tiffany Trader

Facebook Open Sources Caffe2; Nvidia, Intel Rush to Optimize

April 18, 2017

From its F8 developer conference in San Jose, Calif., today, Facebook announced Caffe2, a new open-source, cross-platform framework for deep learning. Caffe2 is the successor to Caffe, the deep learning framework developed by Berkeley AI Research and community contributors. Read more…

By Tiffany Trader

Leading Solution Providers

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

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

Russian Researchers Claim First Quantum-Safe Blockchain

May 25, 2017

The Russian Quantum Center today announced it has overcome the threat of quantum cryptography by creating the first quantum-safe blockchain, securing cryptocurrencies like Bitcoin, along with classified government communications and other sensitive digital transfers. Read more…

By Doug Black

MIT Mathematician Spins Up 220,000-Core Google Compute Cluster

April 21, 2017

On Thursday, Google announced that MIT math professor and computational number theorist Andrew V. Sutherland had set a record for the largest Google Compute Engine (GCE) job. Sutherland ran the massive mathematics workload on 220,000 GCE cores using preemptible virtual machine instances. Read more…

By Tiffany Trader

Google Debuts TPU v2 and will Add to Google Cloud

May 25, 2017

Not long after stirring attention in the deep learning/AI community by revealing the details of its Tensor Processing Unit (TPU), Google last week announced the Read more…

By John Russell

Groq This: New AI Chips to Give GPUs a Run for Deep Learning Money

April 24, 2017

CPUs and GPUs, move over. Thanks to recent revelations surrounding Google’s new Tensor Processing Unit (TPU), the computing world appears to be on the cusp of Read more…

By Alex Woodie

Six Exascale PathForward Vendors Selected; DoE Providing $258M

June 15, 2017

The much-anticipated PathForward awards for hardware R&D in support of the Exascale Computing Project were announced today with six vendors selected – AMD Read more…

By John Russell

Top500 Results: Latest List Trends and What’s in Store

June 19, 2017

Greetings from Frankfurt and the 2017 International Supercomputing Conference where the latest Top500 list has just been revealed. Although there were no major Read more…

By Tiffany Trader

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