New data and developments at Webpagetest

In his latest blog post, Strangeloop president Joshua Bixby discusses new research and tools pertaining to the performance monitoring service Webpagetest:

This week, Pat Meenan ran a series of tests to determine what impact, if any, video capture has on Webpagetest’s ability to measure performance consistently. This was after a recent conversation with Tony Perkins, when Tony found that video capture skewed test results during an experimental Micro instance. Pat ran 100 tests each of www.aol.com, www.amazon.com and www.yahoo.com, with and without video capture. He posted his findings (along with some very nice graphs) on his blog.

On a related note, earlier this week Tony released the latest version of the monitoring script he’s been working on for the past few months. This script — now dubbed WPT Monitor 0.2.0 — is designed to sit in front of a private instance of Webpagetest and automatically test multiple landing pages at set intervals in perpetuity, and then aggregate the results. At any given time, the script lets you generate an easy-to-read chart that shows overall performance for one day or for any time span you specify. The script is available for download and discussion here on Webpagetest.

For more information, read Joshua's post at Web Performance Today.

Setting up your own page test systems? Beware of your CPU and memory limitations.

From the blog of Strangeloop president Joshua Bixby:

I’ve been working on a number of interesting research projects lately. As part of my research, I have been conducting thousands of page tests with and without video (a Webpagetest beta feature). Following a conversation with Patrick Meenan late last week — in which he warned that capturing a video might have a significant impact on the overall test results, thus making test results taken in conjunction with a video uncomparable to test results for the same URL without the video — I became concerned about the validity of my research.

On Friday, I had a casual conversation with my friend Tony Perkins. Tony has his own private Webpagetest infrastructure and has been experimenting with different memory and CPU sizes. Over the weekend, he decided to test the impact that including video has on the gathering of performance numbers. Using an experimental instance, he ran just over 100 tests on the same script, with and without video capture.

Patrick’s warning was confirmed: There was a significant difference between the tests.

To find out what the performance culprit was and practical tips for mitigating it, read the rest of this post at Joshua's blog Web Performance Today.

Almost half of the top 1000 retail sites don’t follow two easy performance best practices. Does yours?

Keep-alives and compression are two of the easiest, lowest-hanging fruit on the performance optimization tree, yet almost half of the leading retail websites aren't taking advantage of these best practices simultaneously. In his latest blog post, Strangeloop president Joshua Bixby explains how to identify and fix this problem on your site:

Don’t underrate these two simple measures. They can have a huge impact on page speed. In a session where I first de-optimized, then re-optimized, the Velocity website, the first fixes I implemented were keep-alives and text compression. With just these two fixes, the site experienced major improvements in these areas:

• Start render: 52% faster
• Document complete: 40% faster
• Fully loaded: 31% faster

These two steps alone are not enough, but they’re definitely must-haves before you reach for the fruit on the higher branches.

Read the full post, which includes how-tos, on Joshua's blog, Web Performance Today.

A (somewhat) brief history of the performance landscape

In his latest blog post, Strangeloop president Joshua Bixby tackles the history of web performance, from 1995 to the present:

After creating this timeline, Joshua goes on to say:

As you can see, in addition to showing solution providers, this timeline also shows when new browsers appeared on the market, as well as the appearance of widely embraced performance tools and reference materials. This is a brain dump, but I tried to capture they key elements that I think of when it comes to front-end performance. This historical bird's eye view corroborates my delivery-to-transformation theory of performance evolution:

- The early web was all about the basics: seeing content (i.e. browsers) and getting to modems (Gzip and other server side tricks).

- The exuberance of the late '90s was made possible by huge investments in basic infrastructure and foundational datacenter technology. In our world, the key developments were the first load balancers (F5/Netscaler), the introduction of Akamai, and the development of measurement tools such as Gomez and Keynote, which set the standard for web performance measurement.

- The late '90s was a hotbed for innovation and produced the first interesting cloud play for dynamic content (Netli) and the first real transformation play (Pivia, which was subsequently bought by Swan Labs and then swallowed by F5; this 10-year-old technology is now branded as the F5 Web Accelerator).

- 2000-2006 was a tough time for the front-end performance market. We did see some incredible innovation in related markets, such as the branch office acceleration market (i.e. technology that speeds up Outlook and Office between branch offices). The only interesting and key innovator in my eyes was Fineground, which blazed a trail in transformation but sold to Cisco and subsequently was killed.

- With the recovery of the web economy came greater investment in new tools and research. In 2006, I co-founded Strangeloop and we filed our first patent on the technology that formed the basis for the set of solutions now known as Site Optimizer.

- Shortly afterward, O’Reilly published Steve Souders’ book High Performance Web Sites. On its heels came a number of developer resources and diagnostic tools such as Webpagetest, and Browserscope, as well as the Velocity conference, which quickly became an unofficial hub of the performance community.

- In more recent times, our industry has matured with more entrants into the transformation space and legitimization of the core premise with seminal moments like the inclusion of page speed as a key ranking factor in the Google search algorithm.

Read the full post, which includes in-depth discussion of the evolution of performance solutions from a delivery-based model to delivery-plus-transformation, on Joshua's blog, Web Performance Today.

Demystifying web performance automation

From the blog of Strangeloop president Joshua Bixby:

This past Wednesday, I had the great privilege of hanging out with the New York Web Performance Meetup crowd, where I led a session on web performance automation. I wanted to identify what kinds of performance best practices are manually do-able versus which practices lend themselves better to automation. After going over performance-related terminology and concepts — such as waterfall charts, first vs repeat views, and concurrency — we jumped into a hands-on case study: optimizing the Velocity website.

Read the full post, along with the slide deck, at Joshua's blog, Web Performance Today.

Why test with Internet Explorer 7?

In his latest blog entry, Strangeloop president Joshua Bixby explains why he still includes Internet Explorer 7 when he runs batches of performance tests:

I used to test with IE 8, then made the switch to include IE 7 after some consideration of the fact that it’s still the third most popular browser version in the world, and a 15% market share is still pretty significant. Put it this way: If you owned a bricks and mortar shop, would you be happy knowing that 3 out of 20 prospective customers had a hard time opening your door? It made sense to me to identify IE7 as a reasonable baseline for performance.

Read the full post on Web Performance Today.

Three kinds of page test visuals, and the best ways to use them

This is a bird's eye view snapshot of the performance of 20 top holiday ecommerce sites - from Amazon to Zappos. It's just one of three kinds of visuals Strangeloop president Joshua Bixby discusses in his latest blog post.

Joshua conducted page speed tests of the top 20 holiday ecommerce sites - from Amazon to Zappos. The results showed huge differences between the time it took for pages to deliver meaningful content and the time it took for the pages to fully load. He shows how this information can be presented in three different formats, depending on what kind of presentation you're making, and who is receiving it.

Read the full post on Joshua's blog, Web Performance Today.

Strangeloop to accelerate page load times on PETCO.com

"At PETCO, we’re committed to helping pet parents give their pets the quality of life they deserve," says John Lazarchic, PETCO’s VP of E-Commerce. "Providing pet parents with an efficient, convenient and enjoyable user experience when shopping us online is an important part of that commitment. With Strangeloop’s Site Optimizer, we’ve been able to decrease the average page load time on PETCO.com by 5.5 seconds – a phenomenal improvement."

Read the full announcement.

Webinar: Waterfalls 101

Thursday, October 7th at 2 pm EST: Hooman Beheshti, Strangeloop’s VP product, will demystify waterfall charts – what they are, why they’re important, and how to interpret them – in a straightforward, step-by-step, half-hour tutorial. 

A waterfall chart can be one of the most useful ways to present your site’s performance at a glance… but it is often the most misunderstood. If you’ve ever found yourself at a loss to understand some aspect of your site’s waterfall – or struggling to explain a chart to a third party – this session will make it all clear.

In this 30-minute webinar, you’ll learn, in plain language, how each of the following is represented and what they mean: 

• DNS lookup 
• TCP connection 
• Time to first byte vs. start render 
• Content download 
• Document complete vs. fully loaded 

You will also leave this webinar with an understanding of what a “good” waterfall looks like versus a “bad” waterfall.

> Register

> Fall webinar schedule