Azul Systems and GigaSpaces Technologies, a provider of innovative Grid-based solutions for data-intensive, business-critical applications, announced test results showing phenomenal enterprise application performance with a 60 percent reduction in hardware costs using Azul Compute Appliances with the GigaSpaces Enterprise Application Grid (EAG). The test demonstrated the ability of Azul and GigaSpaces to improve transaction processing efficiency across an enterprise service bus (ESB), which is typically at the heart of a service-oriented architecture (SOA). With the combined Azul and GigaSpaces solution, organizations can lower total cost of ownership for their IT infrastructure by increasing throughput, consolidating hardware and reducing costs for real estate, electricity and cooling.

The benchmark test, conducted at the Azul Center for Unbound Compute, simulated a typical financial services SOA workload that correlates a trade order lifecycle from disparate order events. This correlation requires significant computation and generates large amounts of traffic to the database. Performing 100 million computations took 14 hours on six 4-way x86-based servers for a baseline of approximately 120,000 computations per minute. GigaSpaces EAG was then used to create a cached shared object store of 16 million objects, thus moving database requests, which slow down application performance, into the application memory heap. The test compared the baseline to the total throughput achieved using GigaSpaces on the provided servers, then to a configuration of only one server attached to an Azul Compute Appliance.

By leveraging GigaSpaces EAG with the same six 4-way x86-based servers, the application was able to handle more than 1 million computations per minute (up from 120,000 per minute), cutting the 14-hour job down to approximately one hour and 40 minutes.

Taking away 90 percent of the server resources, a single 2-way x86 server was then authorized to tap into an Azul Compute Appliance 1920B, and was able to double the throughput again to more than 2 million computations per minute. With the combination of GigaSpaces and Azul, the 14-hour job was accomplished in just 50 minutes. Furthermore, the Azul approach reduced the total infrastructure acquisition cost by more than 60 percent, from approximately $480,000 to $165,000. Fewer hardware systems and lower management, maintenance, real estate, electricity, and cooling costs would result in significant additional savings.

"This test reflects the power of Azul and GigaSpaces to address the cost and complexity our customers are facing as they scale their mission-critical applications," said Yaron Benvenisti, CEO of GigaSpaces. "Building and scaling these high-throughput, low-latency applications is no easy task and the impressive results of this test demonstrate that our joint solution delivers the dynamic scalability and breakthrough performance our customers need."

As more and more companies move to SOAs, they face a number of critical business issues such as ensuring service availability, maintaining adequate response times at peak periods and minimizing excess capacity. Current servers alone are weak in these areas, especially when running virtual machine-based applications, such as the Java-based applications that are the basis of many SOA deployments. Azul technology is optimized for such workloads and is transparently delivered - as a shared resource -- to enterprise applications running on existing servers.

GigaSpaces EAG lets application developers rapidly build and deploy high-performance, highly-reliable, business-critical applications that run on a distributed set of IT resources. It enables an organization to dynamically distribute data and achieve in-memory levels of performance with significantly less administration and costs than dedicated hardware solutions. The EAG is based on a leading commercial implementation of clustered JavaSpaces that provides a rich set of tightly-integrated application services (such as JMS, Clustering, Caching, JDBC and parallel processing) -- on top of a federated shared memory platform.