Hardware’s unique advantages highlighted in Solace V5.0
As a more or less happy iPhone 3G user, I will confess that I had the live event playing in my browser when Sir Jobs was unveiling the sexy new features coming in the iPhone4. It’s an exciting day when something that you’ve come to rely on gets a new set of capabilities, and I invested some time thinking about whether a HD Video, multi-tasking or video conferencing would be useful to me. For Solace customers, today is just like that launch day as we released V5.0 of our Solace message router firmware. The only difference between the two is our launch doesn’t have live blogs, video streams, fanboys or CNN coverage. But I bet our demo would have worked.
A bit of history will help to put V5 in context. In our V3 release, the majority of features were aimed at creating hardware versions of features previously available in software products. There is a core set of capabilities that you just must have to be in the game, and our innovation then was focused on making existing messaging features faster or easier to deploy and manage. In V4 about half of the features introduced were rounding out legacy messaging capabilities, and the other half was introducing new capabilities.
AQMP surfing a wave of positive progress
Earlier this week I attended the second annual AMQP Face-to-Face conference at the beautiful Scripps campus at the University of California San Diego. Even a somewhat dreary day in San Diego, which they call June Gloom, is better than a nice day back home in Ottawa, and I was inspired by the many surfer dudes and dudettes who braved the cool weather to venture into the waves. I kept my feet on dry land and the lifeguards no doubt appreciated that.
The first day of the event was open to the public, and over 50 attendees came to see what’s happened with AMQP over the past year. The agenda for the day included technical tutorials on the AMQP1.0 wireline specification, some sharing of user experiences, and a discussion of plans for 2010.
2010 World Cup: Bet on Solace and NovaSparks
Over the past two to three years financial services firms have gone from viewing hardware appliances as a curiosity to viewing them as a necessity. There are three key reasons that hardware has caught on:
- Performance — for high-volume, highly repetitive tasks, special-purpose chips such as FPGAs, network processors and GPU’s have consistently been shown to outperform software running on general purpose CPUs. For many use cases, especially relating to market data and trading, performance alone is enough of a justification to choose hardware.
- Simplicity — the turnkey nature of many appliances such as messaging middleware, ticker plants, monitoring tools and security enforcement is appealing to many firms. They are so much easier and less costly to procure, deploy and configure that firms can focus on what they do best instead of getting bogged down with implementation details.
- Low TCO — appliances can often do the work of many equivalent servers running software, which significantly reduces the overall cost of operating an application or infrastructure.
AMQP v1.0 to be unveiled in San Diego
When you think San Diego, what do you think of? The beautiful waterfront, the San Diego Zoo, Legoland, and of course, interoperable messaging protocols.
Next week the 2nd annual AMQP “face to face” meeting will again be held in San Diego, California. As with last year, the first day will be open to the public (Jun 8), and the next two days (Jun 9, 10) will be for members only.
If you haven’t been paying attention, AMQP V1.0 is firming up . Last week the protocol was voted to “recommended” status which means no more changes (only provable defect fixes are allowed). The biggest change that comes with the V1.0 release is that future releases must maintain backwards compatibility, which significantly reduces the risk of building applications or products using AMQP.
I’ll post another update after the meetings with some detail from the official V1.0 announcement.
Rewind: Solace and Liquidnet keynote
At the recent Ultra-High Performance Technologies in Financial Services event, our CEO Craig Betts and Liquidnet’s Chief Architect Brett Kotch shared the keynote slot to kick off the conference.
Craig talked about how the technology pioneered as low latency solutions in financial services often leads to a better world when applied to challenges like homeland security, smart grids and transportation scheduling.
Brett talked about hedgehogs, S-curves and space time relativity. Yes, really! Brett’s session was definitely the most imaginative and thought provoking presentation at the conference.
If you missed the session or the event you can view their slides below (just click on the title page images) and listen to the audio here. Craig’s presentation starts about five minutes into the audio file, and Brett’s section begins right around the 18:00 mark.
Trading infrastructure that’s joined at the hip
Today we unveiled some interesting work we’ve been doing with Redline Trading to show the consolidation of their InRush ticker plant with the Solace message distribution layer for a wide range of market data delivery use cases.
Redline’s solution is a hybrid of software and hardware that is typically installed within a server to accelerate the various functions performed within a ticker plant. These includes everything you’d expect from a ticker plant: feed handling, order and price book functionality, even last value cache. Redline is fast, too — all of this takes place in an average of 8 microseconds for up to 10 million market data updates per second, with the kind of consistency you expect from a hardware-accelerated solution.
Our appliance picks up where a feed handler leaves off, reliably moving market data from feed to application whether that application is on the same machine, over a network or across the world.
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.
Hardware trading: The machines are taking over…
With each day that passes it becomes more obvious that hardware is replacing software in the critical path of high performance trading. It doesn’t take a genius to see what’s happening, as the evidence is everywhere:
- Feed handlers: All of the recent entrants into the feed handler market are using custom hardware.
- Messaging middleware: Appliances from companies like Solace are winning a larger footprint for market data delivery and back-office order routing.
- Algo engines: Leading algo trading engines are heavily leveraging FPGAs and GPUs to do ultra-fast simulations that accelerate trading decisions.
- TCP offload engines: TOEs are taking the place of software TCP stacks on servers.
- Trading apps: We’ve even seen a flurry of requests from high performance trading firms looking to execute pre-trade risk checking directly in network processors inline with the hardware messaging bus.
We’re bringing sexy (to the) back (office)
For the last few decades, from the early days of Gordon Gekko and Liar’s Poker to today’s focus on hedge funds and high frequency trading, the sex appeal has clearly centered around the front office. The press loves to write about it and we love to read about it. Every trade is like the proverbial iceberg, though — the trading decision is what everyone sees, but the majority of work happens in the murky waters below the surface where the considerably less sexy mid-and-back-office operations occur.
Last week Greg MacSweeney wrote a good article in Wall Street and Technology highlighting the back office as a new battleground for efficiency. After years of chasing zero latency for the front-office, the back office is comparatively archaic and badly in need of updating.
Working on basic sharing skills
In a blog post this week, Lori MacVittie talks about, among other things, the reluctance of different groups towards sharing infrastructure. From her post:
Some pieces of infrastructure – particularly those that are part of the network – are so critical (and so very underappreciated) – that they simply cannot be exposed to the kind of risk that comes from “sharing” resources in any model.
I can’t say her never ever kind of experience matches with what we have seen with hardware middleware. When it comes to sharing, our customers fall into two main camps:
- Those that re-buy gear for each major business unit because of concerns over traffic from one interfering with another. This is how they have always deployed software, and they’re not ready to do it differently in hardware. It has more to do with CYA than technology, which is consistent with Lori’s point.
- Those that are blending market data for many asset classes (across departments), and/or a combination of market data, order routing and risk management in the same infrastructure. Generally the motivation is reducing costs, but it can also reduce risks when the shared environment is both faster and more stable than the standalone software it replaces.