Latency: What you don't know can hurt your website's performance
Here's a latency reality check: Most site owners assume their pages experience latency of 20-30ms, but recent analysis of 3 million unique users indicates that the number could be at least four times worse.
Not sure what latency is?
In web performance circles, "latency" is the amount of time it takes for the host server to receive and process a request for a page object. The amount of latency depends largely on how far away the user is from the server.
To put this in real-world terms, say you visit a web page and that page contains 100 objects — things like images, CSS files, etc. Your browser has to make 100 individual requests to the site’s host server(s) in order to retrieve those objects. Each of those requests experiences at least 20-30ms of latency. This adds up to 2 or 3 seconds, which is pretty significant when you consider it as just one factor that can slow your pages down. (To understand latency further, check out this latency primer written by Strangeloop president Joshua Bixby.)
Early findings show that desktop latency ranges from 65ms to 145ms.
Last month, we conducted a survey to identify typical latency for mobile users versus desktop users. The results were surprising. While we expected mobile latency to be high (last fall, some ad hoc research led to the realization that latency can hit 350ms on 3G), we also expected latency for desktop users to be relatively low — and this was not the case.
Our findings, which were recently picked up by GigaOM, included:
1. Desktop latency was worse than expected.
Median desktop latency ranged from 65ms to 145ms. Most site owners tend to estimate their latency numbers in the 20-30ms range. If you do this, these findings should give you pause.
2. Median mobile latency was between 26% to 96% poorer than desktop.
There has been a spate of reports lately citing the fact that mobile users are using devices over their wifi connections at home. As a result, some site owners are relaxing their concerns over mobile performance. However, median latency of 190ms is a serious performance issue.
3. The CDN you pick matters.
Further to the above, the CDN you choose makes a big difference. Each of the sites we measured is on a different CDN, and desktop latency was almost doubled from one site to another.
4. Outliers for mobile had double the latency of desktop outliers.
Individually, outliers aren’t hugely significant, but in our study, the tail of mobile outliers represents a large number of people who are experiencing painful latency – up to 990ms. That’s almost a full second for every page resource.
5. Mobile traffic accounted for about 10% of total traffic.
As an interesting aside, we found this number held across all three sites. Note that these were mobile users who were visiting the full site, not an m.site.
For a more detailed account of our findings, read this post by Strangeloop president Joshua Bixby: Latency reality check: Early findings show that desktop latency ranges from 65-145ms
How Strangeloop tackles latency
- Consolidate page objects into bundles. Fewer bundles means fewer trips to the server, so the total latency hit is greatly reduced. For example, a page that starts with 63 objects could see those objects consolidated into 9 resource requests.
- Leverage the browser cache. Our solutions allow the cache to do a more efficient job of storing files and serving them again where relevant, so that the browser doesn’t have to make repeat calls to the server.
- Allow more page requests to happen concurrently. We leverage Google's SPDY protocol, which extends what the browser can do by adding a session layer atop of SSL that allows for multiple concurrent streams over a single connection.
Questions about latency and web performance?
We have the answers. Take a moment to book your phone meeting with one of our Performance Experts.