Skip to main content

Web Performance 101: The Bandwidth Myth

Web Performance and the impact of SPDY, HTTP/2 and QUIC
Jean Tunis

As websites continue to advance, the underlying protocols that they run on top of must change in order to meet the demands of user expected page load times. This blog is the first in a series on APMdigest where I will discuss web application performance and how new protocols like SPDY, HTTP/2, and QUIC will hopefully improve it so we can have happy website users.

Web Performance 101

The performance of your website is obviously very important. When visitors comes to your company website, they won't stick around very long if it's slow. If those visitors are users of your web application, they may not be for long if they encounter a consistently slow performing app.

Google and other companies have done studies showing that users begin to think of leaving a site if they see nothing within 1 second. Much of this is from a book written by Jakob Nielsen in 1993 called Usability Engineering. Since that time, 1-second response times have been the benchmark of a fast performing website. It still is today, and is not likely change over time.

As performance degrades to over 1 second, users start to think about going elsewhere. If there are other legitimate competitors, you're probably lost that visitor to them already. At 10 seconds of page loading, most users are long gone, even with no competitors. Most will not suffer through waiting that long for a webpage to load.

It's clear to see that a slow website will affect your company's bottom line, particularly if you do most or all of your business online. A slow site leads to higher bounce rate when the visitor hits the Back button before seeing the goodness of your products or services. A slow site also leads to lower conversions because visitors won't buy what you're selling because they may equate the slow site to a poor product or service.

So we want to make our websites and web applications fast. But how can we go about doing that?

First let me tell you about a myth ...

The Bandwidth Myth

According to CDN provider Akamai's State of the Internet report published for Q3 2015, the global average connection speed for the Internet was measured at 5.1Mbps. The top 10 countries are well above that figure with a minimum speed of 14Mbps. Average peaks are measured at 32.2Mbps.

5.1Mbps may seem small for those who live in areas with much higher available speeds for businesses and residents. For others, this may be blazing fast. It's all local.

But anyone who has worked in performance engineering or similar fields knows that bandwidth capacity or speed isn't the only parameter that determine good web performance. In fact, it's very insignificant, especially nowadays with big bandwidth speeds possible, as evidenced by Akamai's report.

Many Internet service providers, however, don't advertise them that way.

They talk up bandwidth, while barely mentioning some other more important parameters: network latency, server response time, application design, etc. Bandwidth speed is not nearly as much as important as how low a latency there is between where the web server is located, and where visitors are coming from.

So how do we go about looking on the other parameters? Let's first look at what happens when make a web request.

Anatomy of a Web Page Request

A web page request involves many steps.

We have:

■ DNS requests

■ Opening up TCP connections

■ Authenticating with TLS

■ The HTTP request itself to get web page data

■ Processing of the request on the server

■ The download of the requested content

There can be many substeps in between, but that's it at a high level. So it is very important to optimize the above steps to ensure that they are occurring as fast as possible, and improve web performance.

But how can you do that?

Glad you asked. Read Web Performance 101 - 4 Recommendations to Improve Web Performance for some common recommendations to optimize the steps of a web page request.

Hot Topics

The Latest

In MEAN TIME TO INSIGHT Episode 24, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network observability tool sprawl ... 

In cloud-native systems, scaling is often as simple as moving a slider. For on-premise databases, the stakes are different. Over-provisioning hardware is expensive. Under-provisioning leads to performance bottlenecks that are difficult to fix once the equipment is in the rack ...

When most people think about cybersecurity, they picture firewalls, encryption, and access controls — technical tools designed to protect systems and data. But beneath the technology lies a deeper set of principles about trust, decision-making, and resilience ... The best leaders don't eliminate risk. They manage it intelligently. And in many ways, cybersecurity offers a surprisingly useful playbook for doing exactly that ...

Many organizations assumed their infrastructure strategy was settled. It had been implemented, optimized and built into long-term plans. Recent changes in technology and vendor consolidation are forcing a second look. Cloud outages and licensing changes have exposed how much dependency exists on a small number of platforms. As a result, organizations are reevaluating whether those decisions still hold up under current conditions ...

Edge AI is strategically embedded in core IT and infrastructure spending across industries, according to the 2026 Edge AI Survey from ZEDEDA. The research shows that 83% of C-suite and IT executive respondents say edge AI is important to their core business strategy ...

As AI adoption accelerates, operational complexity — not model intelligence — is becoming the primary barrier to reliable AI at scale, according to the State of AI Engineering 2026 from Datadog ... The report highlights a compounding complexity challenge as AI systems scale ... Around 5% of AI model requests fail in production, with nearly 60% of those failures caused by capacity limits ...

For years, production operations teams have treated alert fatigue as a quality-of-life problem: something that makes on-call rotations miserable but isn't considered a direct contributor to outages. That framing doesn't capture how these systems fail, and we now have data to show why. More importantly, it's now clear alert fatigue is a symptom of a deeper issue: production systems have outgrown the current operational approaches ...

I was on a customer call last fall when an enterprise architect said something I haven't been able to shake. Her team had just spent four months trying to swap one AI vendor for another. The original plan said three weeks. "We didn't switch vendors," she told me. "We rebuilt half our integrations and discovered what we'd actually been depending on." Most enterprise leaders don't expect that to be the experience ...

Ask any senior SRE or platform engineer what keeps them up at night, and the answer probably isn't the monitoring tool — it's the data feeding it. The proliferation of APM, observability, and AIOps platforms has created a telemetry sprawl problem that most teams manage reactively rather than architect proactively. Metrics are going to one platform. Traces routed somewhere else. Logs duplicated across multiple backends because nobody wants to be caught without them when something breaks. Every redundant stream costs money ...

80% of respondents agree that the IT role is shifting from operators to orchestrators, according to the 2026 IT Trends Report: The Human Side of Autonomous IT from SolarWinds ...

Web Performance 101: The Bandwidth Myth

Web Performance and the impact of SPDY, HTTP/2 and QUIC
Jean Tunis

As websites continue to advance, the underlying protocols that they run on top of must change in order to meet the demands of user expected page load times. This blog is the first in a series on APMdigest where I will discuss web application performance and how new protocols like SPDY, HTTP/2, and QUIC will hopefully improve it so we can have happy website users.

Web Performance 101

The performance of your website is obviously very important. When visitors comes to your company website, they won't stick around very long if it's slow. If those visitors are users of your web application, they may not be for long if they encounter a consistently slow performing app.

Google and other companies have done studies showing that users begin to think of leaving a site if they see nothing within 1 second. Much of this is from a book written by Jakob Nielsen in 1993 called Usability Engineering. Since that time, 1-second response times have been the benchmark of a fast performing website. It still is today, and is not likely change over time.

As performance degrades to over 1 second, users start to think about going elsewhere. If there are other legitimate competitors, you're probably lost that visitor to them already. At 10 seconds of page loading, most users are long gone, even with no competitors. Most will not suffer through waiting that long for a webpage to load.

It's clear to see that a slow website will affect your company's bottom line, particularly if you do most or all of your business online. A slow site leads to higher bounce rate when the visitor hits the Back button before seeing the goodness of your products or services. A slow site also leads to lower conversions because visitors won't buy what you're selling because they may equate the slow site to a poor product or service.

So we want to make our websites and web applications fast. But how can we go about doing that?

First let me tell you about a myth ...

The Bandwidth Myth

According to CDN provider Akamai's State of the Internet report published for Q3 2015, the global average connection speed for the Internet was measured at 5.1Mbps. The top 10 countries are well above that figure with a minimum speed of 14Mbps. Average peaks are measured at 32.2Mbps.

5.1Mbps may seem small for those who live in areas with much higher available speeds for businesses and residents. For others, this may be blazing fast. It's all local.

But anyone who has worked in performance engineering or similar fields knows that bandwidth capacity or speed isn't the only parameter that determine good web performance. In fact, it's very insignificant, especially nowadays with big bandwidth speeds possible, as evidenced by Akamai's report.

Many Internet service providers, however, don't advertise them that way.

They talk up bandwidth, while barely mentioning some other more important parameters: network latency, server response time, application design, etc. Bandwidth speed is not nearly as much as important as how low a latency there is between where the web server is located, and where visitors are coming from.

So how do we go about looking on the other parameters? Let's first look at what happens when make a web request.

Anatomy of a Web Page Request

A web page request involves many steps.

We have:

■ DNS requests

■ Opening up TCP connections

■ Authenticating with TLS

■ The HTTP request itself to get web page data

■ Processing of the request on the server

■ The download of the requested content

There can be many substeps in between, but that's it at a high level. So it is very important to optimize the above steps to ensure that they are occurring as fast as possible, and improve web performance.

But how can you do that?

Glad you asked. Read Web Performance 101 - 4 Recommendations to Improve Web Performance for some common recommendations to optimize the steps of a web page request.

Hot Topics

The Latest

In MEAN TIME TO INSIGHT Episode 24, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network observability tool sprawl ... 

In cloud-native systems, scaling is often as simple as moving a slider. For on-premise databases, the stakes are different. Over-provisioning hardware is expensive. Under-provisioning leads to performance bottlenecks that are difficult to fix once the equipment is in the rack ...

When most people think about cybersecurity, they picture firewalls, encryption, and access controls — technical tools designed to protect systems and data. But beneath the technology lies a deeper set of principles about trust, decision-making, and resilience ... The best leaders don't eliminate risk. They manage it intelligently. And in many ways, cybersecurity offers a surprisingly useful playbook for doing exactly that ...

Many organizations assumed their infrastructure strategy was settled. It had been implemented, optimized and built into long-term plans. Recent changes in technology and vendor consolidation are forcing a second look. Cloud outages and licensing changes have exposed how much dependency exists on a small number of platforms. As a result, organizations are reevaluating whether those decisions still hold up under current conditions ...

Edge AI is strategically embedded in core IT and infrastructure spending across industries, according to the 2026 Edge AI Survey from ZEDEDA. The research shows that 83% of C-suite and IT executive respondents say edge AI is important to their core business strategy ...

As AI adoption accelerates, operational complexity — not model intelligence — is becoming the primary barrier to reliable AI at scale, according to the State of AI Engineering 2026 from Datadog ... The report highlights a compounding complexity challenge as AI systems scale ... Around 5% of AI model requests fail in production, with nearly 60% of those failures caused by capacity limits ...

For years, production operations teams have treated alert fatigue as a quality-of-life problem: something that makes on-call rotations miserable but isn't considered a direct contributor to outages. That framing doesn't capture how these systems fail, and we now have data to show why. More importantly, it's now clear alert fatigue is a symptom of a deeper issue: production systems have outgrown the current operational approaches ...

I was on a customer call last fall when an enterprise architect said something I haven't been able to shake. Her team had just spent four months trying to swap one AI vendor for another. The original plan said three weeks. "We didn't switch vendors," she told me. "We rebuilt half our integrations and discovered what we'd actually been depending on." Most enterprise leaders don't expect that to be the experience ...

Ask any senior SRE or platform engineer what keeps them up at night, and the answer probably isn't the monitoring tool — it's the data feeding it. The proliferation of APM, observability, and AIOps platforms has created a telemetry sprawl problem that most teams manage reactively rather than architect proactively. Metrics are going to one platform. Traces routed somewhere else. Logs duplicated across multiple backends because nobody wants to be caught without them when something breaks. Every redundant stream costs money ...

80% of respondents agree that the IT role is shifting from operators to orchestrators, according to the 2026 IT Trends Report: The Human Side of Autonomous IT from SolarWinds ...