Azul Systems (Azul) has announced that it has partnered with Hazelcast to ensure explicit Service Level Agreement (SLA) assurance for Java-based in-memory computing applications. By combining Zing plus Hazelcast Enterprise, Java-based businesses are now able to deliver consistent in-memory application performance without the risk of performance-robbing Java runtime artifacts.
Key Highlights:
- Azul Zing plus Hazelcast Enterprise provide 40% overall performance improvement
- With Zing, max latency is reduced by 28X over Oracle’s HotSpot JVM
- Hazelcast’s ideal use cases include caching, ecommerce, payments processing, and
financial servicesA recent benchmark showed that the Zing/Hazelcast combination had a maximum latency of 8 milliseconds at the 99.99th (four nines) percentile. The same workload using the Oracle HotSpot JVM had a maximum latency of 225 milliseconds, an improvement of over 28X when using Zing. Across the entire latency profile range, average transactions were 40% faster with Zing. In all cases the configuration was identical, using 2-node clusters and both 1 and 2 GB JVM heaps.
SLAs can be formal or informal, depending upon the business requirements. Lower peak latencies and predictable performance are key to driving revenues and reducing exposure in business-critical applications. Here’s how the Zing/ Hazelcast combo is delivering value and SLA compliance in three important use cases:
- Ecommerce: As everyone who has completed a web-based shopping transaction knows, slow websites are bad for business, especially during the holiday shopping season when demand is at its peak. 200 milliseconds per online transaction is ideal – in most cases 2 seconds is tolerable, and within 5-10 seconds of a screen freeze the customer vanishes. Online buyers won’t wait – they will abandon the session or the shipping cart and move on to a provider with a better user experience and a faster site. An ecommerce sight can use Hazelcast with Zing to meet their SLA targets and ensure that
customer inquiries and transactions happen quickly – every time, even under high, unpredictable loads of the holiday season.
- Payments processing: Credit card companies face a balancing act between their need to ensure that a transaction is valid and the very brief time available to make a go/no go decision. Their merchant clients and end consumers won’t tolerate long wait times – and if credit card validation takes too long and payment is approved, the payment processor bears the fraud risk. By adding the Zing runtime to their Hazelcast-based risk platform, payment processors can meet their SLA targets while reducing their fraud exposure.
- Financial services: Low latency is a requirement within capital markets, where the proliferation of algorithmic trading requires firms to react to market events faster than the competition to increase profitability of trades. For example, when executing arbitrage strategies the opportunity to “arb” the market may only present itself for a few milliseconds before parity is achieved. Hazelcast combined with Zing slashes latency and
shaves precious milliseconds of latency, capturing revenue and profits otherwise unattainable.
“Businesses are constantly faced with balancing the need to develop and deliver innovative new capabilities and features for their revenue generating platforms with development costs and time-to-market requirements,' said Scott Sellers, Azul Systems president and CEO. 'Java remains the world’s most popular and productive language for the enterprise, however the constant tuning and tweaking needed to try and achieve consistent performance is expensive and often times futile. Azul Zing, combined with in-memory datagrids like Hazelcast Enterprise, deliver rock-solid consistent performance that scales to meet the demanding requirements of today’s high growth businesses.”