system Throughput (TPS), user concurrency, performance test concepts and formulas
The throughput of a system (load capacity) is closely related to the request for CPU consumption, external interfaces, IO, etc.
The lower the CPU consumption of a single request, the more the external interface, the faster the ID response, the greater the throughput of the system, and vice versa.
System throughput has 3 concepts: QPS, concurrency number, response time
Throughput: Number of visits per second,
Concurrent number: The system can process the number of requests simultaneously,
Response time: The time from the request to the response experience.
From the above can be drawn:
QPS (TPS) = concurrency number/response time
The performance of a system is determined by the QPS (TPS) and concurrency, in each system, the two values, there is a relative limit value, they either reached its limit value,
Represents the system's performance of the neck bottle, the system's throughput will not go, if the pressure is large, the system throughput will be reduced, because the system is overloaded with work,
Context switching, memory consumption, and so on, caused the performance of the computer to degrade.
The main factors that determine system response time are CPU operation, IO response speed, external interface response speed and so on.
System Throughput Evaluation:
When we do system design, we need to consider the impact of CPU, IO, External system response factors, as well as the preliminary estimation of system performance.
And usually, we face the demand, we are in addition to the QPS, concurrency, there is a day PV
By observing the system's access logs, it was found that, in the case of a large number of users, the same time period in each time period of access traffic is almost the same.
Like every morning on weekdays. As long as we can get the daily flow chart and the QPS we can calculate the daily traffic.
System throughput (TPS), user concurrency, performance test concepts and formulas