Part 5: Finding latency in financial transactions, where every microsecond counts
Live system test
Now that we’ve covered pre-deployment testing and full system testing, let’s look at two techniques that have proven useful in measuring live system performance:
- Injection of low-bandwidth transactions
While it is important to minimize impact to a running system, short duration and bandwidth tests can be used in a number of ways. The latency of metropolitan and wide area networks can be measured with “ping” packets, or more extensively-tested with live system protocols using advanced tools such as Ixia’s IxChariot. IxChariot uses small software or hardware agents in multiple locations to send and receive network traffic, while reporting KPIs.
Within the data center the networking infrastructure’s latency can be tested with tools similar to IxChariot, or more advanced network test tools such as Ixia’s IxNetwork. KPIs related to latency can be obtained, although capacity measurements are not possible.
In some cases, special test accounts may enable full application testing. For example, in trading applications a fake broker could execute trades for a fake stock.
Such low-bandwidth tests are often run on a recurring basis, varying from once every second to several minutes. The values obtained can be plotted over time for a day or longer periods.
Monitoring involves the placement of high-speed network taps at key locations in the system. These taps are connected to intelligent concentrators/filters, such as those made by Anue Systems, and then forwarded to sophisticated analysis tools. High-speed, high-capacity devices record all or filtered network traffic. Depending on the applications monitored, some instantaneous measurements may be available. For example, some monitoring equipment used in trading applications can match up FIX transaction messages to provide instantaneous latency measurements. More often data post-analysis is required to provide performance metrics.
This is the last of my blog series on "Finding latency in financial transactions, where every microsecond counts”. Latency is an important performance indicator in most networked applications and is the KEY performance indicator in high-frequency security exchange applications. There are many factors, however, that contribute to latency inside of and between data centers. There are test tools such as Ixia’s to help you discover the sources of latency and squeeze every microsecond possible out of exchange-based transactions.