Performance test model_inflection point model learning

Curve inflection point model of performance test model-pressure curve analysis diagram
Reference file: http://www.51testing.com/index.php?action-viewnews-itemid-3719703-php-1

Need to master:
(1) Understand and summarize the inflection point model
(2) the function of the inflection point model

The performance test inflection point curve model is a curve change law that is closely related to server resources, the number of users or other performance indicators (throughput, response time, etc.) as the number of concurrent tests increases.

Indicators:
resource utilization,
throughput (transactions per second)
concurrent number,
response time
area:
light load: light pressure area;
heavy load: heavy pressure area;
buckle load: inflection point area;

Response time: As the number of concurrent users increases, in the [light pressure zone and heavy pressure zone], the response time is basically stable, with a small increase. In the [inflection point area]: a sharp increase. The point in the third zone is the inflection point.
Throughput: As the number of concurrent users increases, in the [light stress zone and heavy stress zone], for a good system, the increase in the number of concurrent users, the increase in requests, the increase in throughput, and the processing peak.
In the [inflection point area]: resource utilization: a straight line, indicating saturation.

When the system load is equal to the optimal number of concurrent users, the overall system efficiency is the highest, no resources are wasted, and users do not need to wait; when the system load is between the optimal number of concurrent users and the maximum number of concurrent users, the system can continue Work, but the user’s waiting time is prolonged, and satisfaction begins to decrease, and if the load continues, some users will eventually become unbearable and give up; and when the system load is greater than the maximum number of concurrent users, it will be destined to cause some users to be unable to Endure the long response time and give up.

Model function:
Function 1: Borrow the performance test model to analyze possible performance problems;
Function 2: Test the curve consciously during the performance test process to obtain the best number of concurrent users, the maximum number of concurrent users, etc.
Function 3: When there are no specific requirements during the performance test, this model can be used for reference;

Guess you like

Origin blog.csdn.net/weixin_43533308/article/details/105352599