Azul Systems Eliminates Application Pauses; Liberates Enterprise Java Developers


Nearly 200 GB Memory Heap with Pauseless Garbage Collection Turbocharges Application Scalability and Enables More Innovative Applications to Drive Business Growth, Competitiveness, and Revenue Opportunities

MOUNTAIN VIEW, Calif., May 8 / -- Azul Systems, the pioneer of the industry's first network attached processing solution, today announced an upgrade to the Azul system software suite. The upgrade allows Java(TM) based- applications to access more pauseless memory heaps than ever before, enhances integration capabilities with enterprise management frameworks, and includes a sophisticated performance analysis and optimization tool. Network attached processing is the ideal platform that enables developers to create more capable, more efficient, and higher performing web-enabled applications that will drive business growth, competitiveness, and revenue opportunities.

Until now, the amount of memory available to Java applications had to be elaborately determined and artificially restricted because of application pauses due to garbage collection and physical memory limitations. Garbage collection is the recovery of allocated memory when an application process no longer needs it and is a requirement of all application virtual machines, such as the Java Virtual Machine. It is an extremely complex task that traditionally required the application to stop while the garbage collection process runs and completes itself.

A large memory heap allows an application to access more data more readily, delivering more throughput and minimizing the load its puts on the database, an expensive resource. But it also causes very long pauses (on the order of tens of seconds). A small memory heap, on the other hand, must access the database frequently which often forces organizations to buy additional expensive systems to run the database. It also results in pauses that are shorter in length but too frequent. Either way, unacceptable performance degradation creates cost and complexity, forcing many companies to decide they cannot scale applications as they hoped or to slow down their adoption of the Java platform.

With hardware-assisted Pauseless Garbage Collection, Azul is the only solution that keeps pauses short enough and infrequent enough to finally make it possible to deploy applications that require or can benefit from large memory heaps. The larger heap size, 199 GB, opens the door to a whole new era of innovative applications development while minimizing the cost and overhead associated with it.

"Application pauses caused by Java garbage collection have seriously limited the ability of developers to create larger and fundamentally more capable applications," said Shyam Pillalamarri, vice president software engineering and co-founder at Azul Systems. "Only Azul has combined an enormous memory heap with an approach to garbage collection that lets developers expand their applications without fear of performance degradation -- no other existing compute platform in the industry comes close to this kind of breakthrough innovation."

Additional feature upgrades in the Azul system software suite include:

Enhanced Integration Capabilities: The Azul Compute Pool Manager (CPM) now includes an application programming interface (API) that enables customized integration with enterprise management and orchestration frameworks such as OpenView, Tivoli, Unicenter, Opsware, or Enigmatec. This allows IT organizations to leverage their knowledge of these tools to simplify Azul system management and speed time-to-deployment for new installations.

The API supports features critical to the success of online transaction processing systems and paves the way for deployment of service-oriented architectures (SOA) and utility computing platforms, such as centralized management of application policies, scripting for automatic compute pool management, automated disaster recovery handling, and automatic retrieval of resource usage for billing and chargeback purposes.

Azul REALTime Performance Monitor: The new Azul REALTime Performance Monitor provides deep performance analysis of applications running on the Azul virtual machine and helps existing industry-leading performance monitoring and analysis tools to reach further into the details of application performance than ever before. Developed as a runtime tool with minimum impact on application performance, detailed actionable information about threads, I/O, garbage collection, object allocations, etc is revealed, enabling application developers and deployment engineers in addressing problems with application scalability and response times and allows them to make adjustments in real time.

About Azul Systems

Azul Systems Inc, has pioneered the industry's first network attached processing solution, designed to deliver massive amounts of compute capacity as a shared network service to transaction-intensive applications and services. Without application level modifications, binary compatibility requirements or operating system dependencies, this transparent new compute model significantly increases utilization across existing infrastructure, enables unprecedented application scalability and predictably ensures high levels of service with up to 50% less cost than traditional computing models. More information on Azul Systems can be found at www.azulsystems.com.

Legal Notices

Azul Systems and Azul are registered trademarks, and the Azul arch logo is a trademark of Azul Systems, Inc. in the United States and other countries. Java and all Java based trademarks and logos are trademarks or registered trademarks of Sun Microsystems, Inc. in the United States and other countries. Other marks are the property of their respective owners and are used here only for identification purposes.

Source: Azul Systems

CONTACT: Karen Reynolds of Azul Systems, Inc., +1-650-230-6581, or karen@azulsystems.com; or Elyce Ventura of Eastwick Communications,
+1-650-480-4054, or elyce@eastwick.com, for Azul Systems, Inc.

Web site: www.azulsystems.com/

All Topics