Financial services companies rely on their networks to provide their customers with seamless market data and enable high-speed financial transactions. These networks require extremely low latency—much lower than most enterprise—and must be kept secure. This puts a lot of pressure on the IT teams supporting these networks to maintain these low latencies. At the same time, trends such as digital transformation, the automation of processes like loan applications, the shift from desktop to mobile, the modernization of applications, and the personalization of services have made it much more difficult to maintain these levels of performance and security. This has created several unique pain points for financial services IT teams. Let’s explain why these have occurred, go through some of the most common ones, and discuss how a strong network observability strategy can help mitigate them.
Changes in the process, changes in networks
The rapid growth of high-frequency trading in financial markets around the globe places new demands on IT operations teams to ensure high performance, extreme accuracy and robust security. At the same time, more and more customers are using financial services such as trading via mobile devices, making traffic patterns more unpredictable and more difficult for IT to manage. It’s inefficient and expensive to centralize applications in a single data center, but moving them to the cloud means IT can’t easily capture traffic to and from those applications. If an application is performing poorly for a user, IT won’t know until the user complains and will then scramble to troubleshoot without package data. IT is now walking a tightrope, balancing the increasing expectations placed on it with the growing complexity of its networks.
Time is money when it comes to financial trading. It comes down to fractions of a second and individual network packets. High-risk trades rely on fast trade execution and timely market data. Investors and investment managers strive to maximize profits, even on small price movements. IT needs to be able to measure network latency at an extremely granular level—down to the millisecond—to identify when it’s exceeding acceptable limits and to find and fix the problem. IT must ensure that its monitoring hardware (e.g., packet switches) can handle packets at speeds of 40 Gbps or more (this is not possible without dedicated hardware support) and that it is able to control latency and jitter in the millisecond range measure, time-stamp and analyze .
Feature performance matters in a mobile-first world—poor performance means angry customers. But when some service components are moved to the cloud (or perhaps in multi-cloud environments), the latency of the entire service increases significantly compared to anything residing in the data center (where latency between network components is minimal). The application and DevOps teams need to align new mobile services and ensure that the customer gets the same performance despite any backend changes. To do this, however, they need a network observability solution to measure the latency between each service component. It’s always a best practice if they test this before the feature goes live and then continue to monitor for issues once it’s in production. The stakes are high – even low latency is enough to lose customers.
Network Operations (NetOps) teams must monitor KPI metrics (such as steady-state traffic, round-trip timing, bursts/microbursts, latency, and jitter) to effectively balance infrastructure performance, costs, and ROI. They need to be able to measure the overall health of their network, track performance metrics across multiple clouds and on-premises with low latency, and maintain a holistic view of all operations and executions across the trading cycle, from order to execution. This approach to network operations, which focuses on getting a comprehensive view of the overall health of the network, is often referred to as “network observability.” This allows IT to know when it may need to rebalance loads and when to add new WAN links. Many pre-cloud network monitoring tools and strategies focus on measuring the performance of individual devices or links and fail to provide this overall view.
Financial trading services are attractive targets for cybercriminals and must maintain strong network security. While that task falls to the security team, they need the NetOps team to give them access to packet data from all parts of the network so they can traverse the firewall or feed network detection and response tools. These tools look for signatures of malware or suspicious network behavior. When IT has detailed visibility into all parts of the network, they can often spot signs of an attack (such as unusually high traffic on certain ports that are commonly used for malware) and report the issue to the security team for further investigation.
Addressing all of these issues (maintaining security, tracking user experience, fixing issues before they impact those users, and maintaining extremely low latency) requires that the network be observable for IT – it must have access to all network data have (including packets and data flow). data) from all parts of the network, including cloud and SaaS applications. Most importantly, they need this capability — it gives them the data they need to identify and fix all of these problems.
Many IT vendors are now offering more predictive capabilities that proactively uncover problems (either via dashboards or automated with Big Data/AI/ML analytics) and suggest solutions that can help ease the burden on IT professionals. This new approach, which focuses on understanding the network holistically, is called “Network Observability” and has great potential to help financial services companies meet the demanding demands of their network and keep the services that depend on it running smoothly .