Posts

SDKPerf Download and Docs Now Available

sdkperf-architectureLast week we added a really cool tool called SDKPerf to the developer portal. SDKPerf is primarily a performance testing tool, but it’s really more than that – an extensible framework that can be used to test all kinds of features and functions of Solace message platforms. That means you can use the version that matches your desired API and environment to play around with Solace messaging before you even crack open the API. It’s a great way to familiarize yourself with Solace message routers.

Those of you familiar with SDKPerf know that it is very capable, but tons of flexibility translates to an array of CLI options that can be difficult to get a handle on. To help with that we’ve packaged common options and usage examples into this SDKPerf user guide. We’ve tried to make it easy to pick up and try the tool, but if we haven’t covered something you’d like to know how to do please let us know so we can add it.… Read the rest

Reason 3: Appliances deliver huge performance gains

This is part 3 in a 10 part series: 10 reasons for the growth in middleware appliances. The series summarizes what we’ve learned from our clients about what they value in appliances and why they selected Solace.

So far I’ve talked about saving money and making life easier. The third leg in the stool of commonly recognized advantages of appliances is higher performance. There is no one definition for “kick-ass performance” – it has to be defined in context of some set of rules or objectives. Sprinter Usain Bolt is the fastest man in history over 100 and 200 meters, but at 400 meters the edge goes to Michael Johnston. And neither could hold a candle to Haile Gebrselassie in a marathon. Of course, any of these three elite athletes would be schooled playing one-on-one hoops against LeBron James.

General purpose-ness vs. performance

General purpose computers are remarkably flexible—you can use a high-end server (with the right OS and software) to run a powerful database, perform high-end 3-D modeling or execute real-time trade order management.… Read the rest

Hardware vs. software solutions – the parasite drag analogy

Stephen Hoogasian is a former US Air Force pilot with extensive experience in application of C2 information systems.  He has reviewed the utility of hardware routers such as Solace’s application within the Department of Homeland Security and Department of Defense. Mr. Hoogasian flew aircraft including the U-2 high-altitude reconnaissance aircraft and T-38 jet shown here.

What is the potential benefit of using hardware-based solutions vs. a software solution to solve the problem of routing information? Speed—the maximum speed at which a system can process a given volume of information. That’s where the difference shows dramatically.

As an aviator, I cast the problem set into a vein I was more familiar with—that of aerodynamics. In aviation, induced drag (the drag due to lift generation) tends to be greater at lower speeds because a high angle of attack is required to maintain lift. As speed increases this induced drag becomes much less, but parasitic drag increases because the fluid (air) is flowing faster around protruding objects.… Read the rest

Kernel bypass – revving up linux networking

In Formula One racing, all cars must comply with a defined set of rules (the formula) and find ways to differentiate with a car, driver and support team that all follow the basic guidelines.

The same is true of automated trading systems. The formula is simple: each trading system consumes market data and produces orders. What happens in between is how each firm differentiates themselves. Just like in F1, anything that can be improved is up for evaluation when it comes to achieving fast, consistent performance.

Today we announced a partnership with Solarflare Communications to accelerate linux-based networking of high performance messaging. Let me take a minute to lay out what this partnership does for our customers.

It is well understood that in the software world trading performance is negatively impacted by “context switching”. This is an operating system issue, where the OS needs to manage state as control is passed from “kernel space” where the network drivers reside, to “user space” where the application runs.… Read the rest

Latest financial meme: consistent latency

I can has consistent latency?Let’s face it, if you want to get attention on the Internet, you have to fall in line with the concept of memes. These are the ideas that take on a life of their own, such as the dramatic prairie dog or the VP dropping an F-bomb. Twitter’s version of memes is the concept of trending topics based on frequently tweeted keywords. This lets you see what topics people are talking about at a glance.

If dialog in the low latency finance community had that concept, it appears that “consistent latency” would be moving up the charts. For the majority of 2009, the focus was just on making everything faster. Lower the latency, shave a microsecond here and there, and so on.  This year, it seems that people have figured out that the harder thing to achieve is predictable latency. If you’re going to turn decision making over to algos, you need to be confident that the information that feeds them is current.… Read the rest

MetaBit chooses Solace for FIX-based services

Today, we are pleased to add MetaBit to the ever growing list of financial service providers that have chosen Solace to be their routing and delivery platform of choice. They’re using our hardware as the foundation of their FIX-based DMA and liquidity hubs to efficiently distribute information to customers. Financial service providers have a common set of requirements that map very well to many of the capabilities of hardware:

  • 24/7 reliability to assure service availability
  • Low-latency behavior to provide customers with competitive trade execution times
  • Lots of headroom for growth in service volumes and customers
  • Small data center footprint and minimal incremental operations cost as customer counts increase

Increasingly, customers do not have just a low latency problem, or a queuing problem, or an efficient WAN delivery problem, they have an information delivery problem that is a combination of all three. The prospect of procuring three kinds of software that needs to be made redundant and scaled across separate racks of servers feels so 20 years ago when a single hardware content router can consolidate all of these into one footprint and one API.… Read the rest

Transparency in performance testing = benchmarks that work for buyers

Earlier this week, Solace in partnership with Arista and NetEffect released the test results of a collaboration to drive latency out of high-volume, high-speed market data configurations. These test results generated a lot of attention in the financial services sector not just because of the excellent results but also for the way we reported the benchmark by providing the statistical data customers need to interpret the results in a meaningful way.

Far too many benchmarks cherry pick and publish the good test results and obfuscate the unflattering ones. Worse still are the benchmarks that are designed solely to generate impressive performance results, but bear no resemblance to anything a customer could use. Those benchmarks are a disservice to the industry. They waste the time of the prospect and put the vendor on the defensive as the prospect digs to get the rest of the story, or as they fail to deliver the same results in a proof of concept.… Read the rest