Real-Time Processing in Modern Technology


In 1968, Robert Miller published his seminal paper Response time in man-computer conversational transactions outlining the responsiveness of computer mainframes. Miller concluded that a consistent 2-second response would be ideal, a value that has since been adopted as a performance target for many web-based applications. However, with technological advancements and increased focus on real-time data processing, many of today's applications require near-instantaneous responsiveness. The question then arises - is even 100ms fast enough? The answer largely depends on the context.

How Fast Can a Human Process Input?

As humans, we are gifted with the ability to perceive and experience the continuous passage of time. However, our brain architecture limits our sensory perception, preventing us from reacting to our perceptions within a certain short timeframe. This timeframe is commonly referred to as Reaction Time.

Human Reaction Time

On average, human reaction time is approximately a quarter of a second (250 milliseconds). This can be tested using various online tests. However, it's worth noting that some individuals, such as fighter pilots, Formula One drivers, and championship video game players, demonstrate superior reaction times, falling within the 100 – 120ms range.

Real-Time Latency: From Eye to Brain

Reaction time is a complex subject, encompassing several different components of mental processing. To truly understand the speed of real-time for the human brain, we need to focus on the Sensory Perception phase. This is where our senses receive incoming data from the external world, whether visual or auditory.

For instance, the time taken for an image of a tiger to travel from your retina, down your optic nerve, and into the visual cortex is incredibly fast. Recent studies have shown that humans can interpret visual cues seen for as little as 13 ms (around 1 in 75 frames per second).

As our brain receives the incoming data stream, an asynchronous process acknowledges and admits the input into our consciousness. Once aware of the incoming data stream, another part of the brain applies context to the stream, enabling us to decide how to react. All of this happens at lightning speed.

While human reaction time involves more than just mental processing, two key takeaways here are:

  1. Humans can process incoming visual stimuli at a rate as fast as 13 ms. Receiving a data stream faster than this will only underscore the limits of our perception.

  2. Increasing latency above 13 ms negatively impacts human performance for a given task. While initially imperceptible, added latency continues to degrade a human’s processing ability until it reaches around 75 to 100 ms. At this point, input becomes noticeably slow, and users must adapt by anticipating input rather than simply reacting to it. In a duel, for example, a 100 ms lag can be a game-changer, especially if it is random and cannot be anticipated.

Implications for Real-Time Application Developers

Real-time applications have varying tolerances to data stream latency. Applications with particularly demanding targets include gaming, e-commerce & retail, and live audience engagement. These types of applications require real-time human perception and interaction. Given the resources required to build and maintain a real-time data stream network to support these types of applications, many developers opt to rely on an existing platform such as PubNub and focus more on the application itself.


While role-playing, turn-based, and strategy games typically do not need to rely on real-time movements or actions (or tolerate latencies of up to 500ms or more), in most online games, such as Massively Multiplayer Online Games (MMOGs), real-time is a requirement.

As online gaming matures, players flock to games with more immersive and lifelike experiences. To satisfy this demand, developers now need to produce games with very realistic environments that have very strict data stream latency requirements. A delay of even 100 ms reduces player performance in Twitch games by a measurable amount. It becomes noticeably difficult to track targets effectively and forces players into predicting movements.

Given these parameters, a successful MMOG architecture must consider network performance as a fundamental requirement to ensure Quality of Experience for gamers. This architecture needs to be capable of delivering thousands of simultaneous data streams with latencies as low as 50 ms or better and scale for players in different geographic regions on different networks and devices.

eCommerce & Retail

With any auction, every second counts. Success depends on making all bidders feel there is a seamless, reliable, real-time engaging experience for everyone. Having the right end-to-end platform for delivering real-time capabilities like real-time notifications, alerts, and updates is an imperative part of the user experience.

A reliable and scalable platform solution is the key to online auction success:

Live Audience Engagement

The benchmark of a successful virtual event is gauged by the level of audience engagement with the performers and also with each other. Even though virtual events have been a part of our daily lives for a few years now, it doesn't necessarily mean that all event organizers or platforms offer the necessary features to facilitate engaging, interactive events. In the era of real-time data processing, it is essential to keep audience engagement high with features that encourage interactivity.

Embrace the Future with PubNub and Real-Time Data Processing

The PubNub platform helps developers build, deliver, and manage real-time interactivity for web apps, mobile apps, and IoT devices. Whether businesses need in-app or in-game chat, live audience engagement, multi-user collaboration, or any other form of real-time functionality, we help bring it to life with our suite of purpose-built real-time APIs, SDKs, Solution Kits, integrations, and analytics. The foundation of our platform is the industry’s largest and most scalable real-time edge messaging network. With over 15 points-of-presence worldwide supporting 800 million monthly active users, and 99.999% reliability, you’ll never have to worry about outages, concurrency limits, or any latency issues caused by traffic spikes.

Read more about PubNub in our blogs or follow our in-depth how-to guides, tutorials, and demos to learn how to implement PubNub in your application.