Server performance indicators (QPS/TPS/RT)

table of Contents

1. PV

PV (page view) page traffic is one of the most commonly used indicators for evaluating website traffic.

2. QPS

QPS (Queries per second) query rate per second is a measure of how much traffic a specific query server handles in a specified time, and is often used as one of the standards to measure the performance of the server.

  • Principle: 80% of daily visits are concentrated in 20% of the time, and this 20% is called the peak time.

  • Formula: (Total PV * 80%) / (Seconds per day * 20%) = Requests per second (QPS) at peak time

  • Number of machines: QPS of peak time / QPS of a single machine = number of machines required (QPS of a machine is related to its CPU, memory, IO, etc.)

With 300w PV per day on a single machine, how much QPS does this machine need?

( 3000000 * 0.8 ) / (86400 * 0.2 ) = 139 (QPS)。

Generally need to reach 139QPS, because it is the peak value. (2 million pv only has 100 peak qps)

3. TPS

TPS (Transactions per second) The number of transactions processed by the server per second.

A thing refers to the process in which a client sends a request to the server and the server responds. The client starts timing when sending the request, and ends even after receiving the server's response, so as to calculate the time used and the number of things completed.

Generally, the performance of the evaluation system is measured by the number of technical transactions completed per second, and the overall processing capacity of the system depends on the TPS value of the module with the lowest processing capacity.

4. RT

RT (response time) response time refers to the time it takes for the system to respond to a request (a request takes time).

5. LOAD

Linux Load (system load) refers to how many active_tasks the computer has in a certain period of time, that is, the length of the task execution queue of the computer and the queue calculated by the CPU.

Commands such as Top/uptime will display the average load of 1 minute, 5 minutes, and 15 minutes by default.

Specifically, the average load refers to the average value of the number of tasks running in the CPU (R state), waiting for the CPU to run, and in uninterruptible sleep (D state) in a specific period of time. Understand Linux system load

  • When the CPU is completely idle, the average load is 0;
  • When the CPU workload is saturated, the average load is 1

6. UV

Unique visitor The number of visitors (de-duplication).

Guess you like

Origin blog.csdn.net/Dkangel/article/details/108410877