What are the main performance indicators for choosing a server?

1. The configuration standard of the server required by a company of 50 people depends on the form of your company's network to be built, if it is the form of "server workstation", the requirements for the server are not too high, and if it is in the form of "server terminal", the requirements for the server are higher.

If it takes the form of a server workstation, and each client workstation has a well-configured CPU and a hard disk, then the server configuration can be:

CPU: 1 Xeon L2 cache), memory: 1G ECC

Hard disk: 160G, it is recommended to choose Dell server, this grade of server, customized from the Internet, Dell home delivery, only 8000 yuan.

If it is running in the form of a server terminal, there is no disk on the client, and the resources on the server are used, it is recommended to use dual Xeon CPUs, 2G memory, and 320G hard disks. This costs more than 10,000 yuan.

3. The characteristics and principles of small and medium-sized enterprises to choose servers: applicability, must be able to meet the needs of the company. Reliability, the server operation must be stable and reliable, otherwise it will affect the operation of the company.

Forward-looking, we must take into account the development of the situation, the next 5 years will not be eliminated, and can meet the needs of enterprise development, but can not be in pursuit of fashion to buy too high-end servers, which will lead to waste, in a few years, there will be more cost-effective server production. Economy, when considering the cost performance, choose the best and most favorable products.

A normal server is fine, but the system must be server.

Performance metrics are mainly based on the number of CPU cores, memory size, traffic bandwidth, and storage size. In addition, you can also use the cloud helper to manage these services, socks and resource viewing.

The common performance indicators of servers are as follows:

Throughput】 The number of completed transactions in a fixed time interval. Generally, the number of requests that are processed within 1 second, in transaction seconds (TPS).

Response time】The processing time of a transaction. Generally, it refers to the time interval from the time a request is sent, to the server processing and returning, and then to receiving the response data, in milliseconds.

CPU Usage] 1 - CPU idle rate, which indicates that the CPU is used and reflects the utilization of system resources.

CPU, memory, hard disk, bandwidth, shared, or dedicated.

Throughput】 The number of completed transactions in a fixed time interval. Generally, the number of requests that are processed within 1 second, in transaction seconds (TPS).

Average throughput] The average of throughput over a period of time. Failure to reflect transient changes in throughput;

Peak throughput] The maximum amount of throughput over a period of time. It is one of the important indicators used to evaluate the capacity of the system;

Minimum throughput] The minimum amount of throughput over a period of time. If the minimum value is close to 0, it means that the system has a "stuck" phenomenon;

70% throughput concentration interval] The 70% throughput concentration interval is calculated by counting the 15% and 85% throughput boundary values. The more concentrated the interval, the more stable the throughput.