By Chris Sharp, Jon Lin, and Chris Hunsaker (Part 4 of a 5-part series)
In an earlier post, we outlined how Equinix tests internet application performance. Today, let’s share the results with you.
When compared to a typical deployment, roundtrip time, traceroutes, and availability were all materially better in the multi-carrier, multi-node solution. In addition, predictability was improved across all three factors.
Roundtrip time was reduced 17% globally, in
- Asia-Pacific (APAC) by a striking 29% (65ms)
- Canada by 24% (25ms)
- Latin America (LATAM) by 14% (22ms)
- U.S. by 11% (11ms)
- Europe Middle East/Africa (EMEA) by 7% (9ms).
Using modeling done in other research, with a 20ms improvement representing a 7 – 15% drop in page load times, we can extrapolate the dramatic improvements in performance possible.
Traceroutes depict how many different routers a packet must traverse on its way to the final destination. A more direct route means fewer points in the path for congestion, failure, or variability.
By leveraging direct access to multiple carriers in one Equinix facility, the number of hops to the beacon server is dramatically reduced.
Globally network hops decreased by 24%.
- APAC decreased by 31%
- EMEA by 27%
- Canada by 21%
- LATAM by 16%
- U.S. by 7%.
This translates into more direct connectivity from your end users to your servers.
Availability improvements achieved an 81% reduction in downtime globally, translating into a drop from 11 to two hours of downtime in a year.
Typically, availability measurements simply show whether or not your site infrastructure is up and whether or not it is reachable from a single test node.
By using Gomez’s Active Last Mile monitoring, we gain visibility into site availability from the end user’s perspective, factoring in whatever connectivity or availability issues their internet connection might be introducing.
This provides a more holistic view of site availability. By deploying in our optimized fashion, downtime in Hong Kong went from 50 to 0 hours, in UAE from 120 to 0 hours, and in the U.S. from 13 to 0 hours.
For end users, this represents the difference between failing to access your application and the assurance they can access them reliably every time.
By taking the standard deviations from all the source data, we find:
- 77% less variability in connection time
- 28% less variability in traceroute hops
- 23% less variability in availability
Not only is performance improved across the board, but predictability of that performance is also increased dramatically.
Next week, in the final post of this 5-part series, we’ll be sharing key takeways.