Giddyup, JMS!


Think of the lowly workhorse, toiling away while his cousin the thoroughbred races to fame. Much like that workhorse, Java Message Service has been relegated to the less sexy applications in the middle- and back-office (such as routine communications between applications and databases, especially in SOA environments) while the high-profile applications where volume and/or performance are critical (such as low latency market data systems on Wall Street, and event networks in many other industries) are handled with specialized, proprietary messaging solutions.

Many people have JMS pigeon-holed as being just for these relatively simple, low-volume tasks because while it’s very easy to set up, its performance is relatively limited. You can always scale JMS by splitting the workload across dozens or hundreds of servers, but that introduces major architectural complexity, administrative nightmares and high TCO. That simple JMS deployment is no longer so simple.

Solace recently announced a new version of its JMS broker that has the horsepower to support enterprise-scale applications in a purpose-built appliance that’s easy to deploy and has a small footprint in the datacenter. Each Solace message router (just 4 rack units high) supports 100, 000 persistent JMS messages per second, and 11M non-persistent JMS messages per second (for example 5.5M in and 5.5M out, or 3M in and 8M out in a pub/sub configuration). Best of all, each Solace message router can handle high volumes of persistent and non-persistent messages simultaneously. Learn more.

Throughput of 11M messages per second allows JMS to be considered for some of the largest event networks in the world with a single fault-tolerant pair of Solace routers. This will dramatically reduce the effort it takes to architect and operate large JMS networks. This kind of volume is useful when you have a very high powered application, as described above, but also when you need to connect thousands of applications that each have a moderate amount of information to send. At these kinds of volumes, thousands of clients could each consume thousands of messages/second and still have headroom on the router.

It’s time for the workhorse to get some time on the track.