Ultra Messaging Is Also High-Throughput, High-Availability, Lower-TCO Messaging

From fuel-efficient cars, to energy-efficient homes and office buildings, to saving time by shaving while reading Twitter on your smart phone and also making sure your kids eat their breakfast, efficiency is on our minds more and more today. And for very good reason.

Efficiency is one of the most sought-after qualities of any product or service, because it means more for your money compared to the competition, and therefore, more overall buyer satisfaction. The product works, it works well, it works when you need it, it doesn’t quit unexpectedly or too soon, and you would buy it again in the future.

And it works the same way in the software market, most especially in the software messaging space, with the rise of algorithmic trading, where the one and only goal is to move data between applications as fast as technology allows. Enter the latest buzzword in high performance computing: ultra-low latency messaging, a space that Informatica Ultra Messaging helped to pioneer.

So what is “latency”, anyway? It may sound exotic and mysterious but it isn’t, really. It’s a measure of delay, more or less: the time for one piece of data to travel from one application to another, through the network (or maybe on the same host). But latency is just one of many types of measurements to evaluate the efficiency of a piece of software. That’s really what performance is all about: maximizing efficiency to do the most work in the shortest amount of time. Today, latency is usually measured in microseconds (1,000,000 of a second) between two servers. Moving a single piece of data in 10 or 20 microseconds requires a very lean, efficient architecture.

And this very same lean, efficient architecture provides great business value no matter how you measure performance, and no matter what kind of applications you run.

Consider an application that requires high throughput, such as sifting through mobile phone logs and then storing this data into a database for data warehousing analytics. Such an application is ideal for Ultra Messaging, because the same efficiency that can move a small piece of data very quickly can also move many millions of these pieces of data very quickly. The application is essentially limited only by the capacity of the network and hardware resources. One user reduced their window for processing this huge amount of data from 4 days to .5 days, a reduction of 87%.

As another example, consider a system that does not require high performance, but runs on older, slower hardware. Because of inefficient messaging software, the system is rapidly running out of capacity. You could buy and implement new hardware and network equipment, of course, but another option is to upgrade the messaging with the efficiency of Ultra Messaging to relieve strain on CPU and network resources and defer hardware upgrades. Likewise, when deploying a new application, consider the impact of more effective use of hardware resources over the lifespan of the hardware. What is the business value of a 50 or 100% throughput increase? What is the business value of deferring hardware upgrades for an extra 2-3 years? For most customers, these are not trivial questions.

And Informatica Ultra Messaging goes even further than that. By using a “nothing in the middle” design which eliminates messaging brokers and daemons, Ultra Messaging removes those single points of failure. This design also moves data at “wire speed” instead of slowing down the data by routing it through extra layers of hardware and software in the network. It is linked into the applications themselves, providing lean, efficient end-to-end communication.

See the following graphics – note in particular the extra overhead and points of failure (circled in red), in the graphic on the right showing server-based and daemon-based designs (click-thru to embiggen):


Nothing in the middle - Ultra Messaging

Nothing in the Middle - Ultra Messaging


Messaging daemons and brokers - legacy messaging

Messaging daemons and servers

The “nothing in the middle” approach provides not just leading performance in both latency and throughput, but these other valuable benefits too: lower total cost of ownership (TCO), and better availability, reliability, scalability, and agility – these topics will be covered in future blog posts.

Post #1 of a three-part series – see Post #2 here: Ultra Messaging: For 24×7 High Availability, Lower TCO, and Robust Reliability. Post #3 to be published next week.

For more, see whitepapers Ultra Messaging Business Benefits and Direct Edge Switches to Ultra Messaging, Improves Performance with Less Hardware. Watch our customer testimonial videos at Ultra Messaging Zero Latency Tour 2009 – Selected Panel Sound Bites.

This entry was posted in Business Impact / Benefits, Financial Services, Operational Efficiency, Ultra Messaging and tagged , , , , , , , , , . Bookmark the permalink.

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>