A Common Mistake Which Everyone does When it Comes to Measure Performance of Dynamic Content
Monitoring the performance of your traffic is vital.
IT experts frequently rely on the performance measurements of static content, as a strong indication of Edge platform functionality.
They assume that this indication reflects also the performance of the Edge for their dynamic content.
If your online service heavily relies on dynamic traffic, you must take a closer look at it.
Trust me, you might be SURPRISED by the results.
How to Measure your Dynamic Content's Performance
Dynamic and static traffics are SO DIFFERENT by the way they perform.
Dynamic traffic versus static traffic is making a long way and passing more hops and services on the way.
So how and what to measure (take a look at the illustration below).
Dynamic traffic starts its journey at the end-user, goes through the CDN to the origin, and travels back.
Let’s break it down into four parts:
- (A) Time From End user to CDN
- (B) Time inside the CDN platform
- (C) Time From CDN to Data Center
- (D) Time inside the Data Center itself
How to measure each part:
- (A) Measure by performance tests for cacheable content
- (A+B+C+D) Measured by RUM (Real User Monitoring) or dedicated synthetic checks of dynamic traffic.
- (D) By running performance testing on your infrastructure.
- *(B+C) Not trivial to measure (In a second, I will show you how to calculate it)
*
The way from the CDN to the Data Center (B + C), can be tremendously long and complex. It has a critical impact on the overall performance of dynamic traffic. This part needs to get more appropriate attention.
With the simple formula I’ve shared below you can easily measure the performance from CDN to origin (marked as “B+C” in the illustration).
So Why The "B+C" Part is So Critical
End-user request for dynamic content through CDN travels to the nearest CDN’s hop. Then the request travels through the CDN's global network until it reaches its origin.
Every CDN provider has a different algorithm that decided how to route the traffic to the data center. The decision-making process is further impacted by variables such as geo-location, time, network load, and the quality of the internet infrastructure.
It is a bit frustrating to not be able to pave the way for your request in your CDN provider’s network. But it is vital to acknowledge where your weakness in terms of performance.
Conclusion
I recommended running performance tests and collecting the measurements determined above*.
I would recommend analyzing B+C metrics to find opportunities to improve performance and take these metrics into consideration when you choose or evaluate the performance of your edge platform.
* Geo-location, time, network load, and the quality of the internet infrastructure and the content itself have a significant impact on the test result. Make sure you take it under your consideration
Top comments (0)