How do we choose the bandwidth of the server when we are building a video station? The measurement method of audio and video transmission on the Internet is mainly to calculate the load of video data according to the data rate obtained from the compression ratio of image decomposer. In order to make it easier for more customers and friends to understand, the analysis process below Micronet will convert kilobytes by bits per second to answer your questions.
Before we know the detailed data, Micronet believes that we should first understand the following issues:
1. Usually, the bandwidth traffic of an online audience watching facial expression videos is about 30K-40K.
2. The bandwidth conversion method is that 128 K communication requires 1 M network bandwidth. The amount of downloads available for home bandwidth is generally as follows:
3. Similarly, the bandwidth requirement of the server for the load is also calculated based on the maximum concurrent traffic it can carry. Parallel traffic is the traffic value of simultaneously accessing resources. If FMS technology is used, in order to meet the requirements of parallel traffic, it is necessary to accumulate parallel traffic. For example, 100 people access a video resource at the same time, you can calculate:
100*30 K=3000 K
3000 K/128 K/M=23.4 M (bandwidth is about 20 M)
If the number of people watching videos on the website reaches 100, a bandwidth of at least 20 M is required;
If the number of people watching videos on the website reaches 1000, a bandwidth of at least 200 M is required;
At present, the general cost of 100 M bandwidth configuration for domestic regular server suppliers is about 100000 yuan/year. In this way, it can be calculated that if there are up to 100 users on the site, the server bandwidth cost will be at least 200000/year, and if there are 1000 users, it will be at least 1 million/year. Admittedly, the prices of computer rooms vary from region to region, from line to line, and from operator to operator.
The above estimates are both theoretical values and full load calculations. In actual operation, the server will not only consider full load and theoretical full load. Most of them use two-level server bandwidth resources on the basis of modification to ensure safe operation.
The above is the analysis of the neutrino network How do we choose the bandwidth of the server when building a video station. Huawei Cloud, a micro network agent, is an excellent cloud computing service provider with perfect industry solutions and excellent cloud computing technology. The self-developed pure SSD architecture ECS breaks the industry record with 50000 IOPS random read/write speed and 800 Mb/s throughput as performance indicators. The ECS elastic cloud server uses hardware devices with a pure SSD architecture. In just a few minutes, you can easily obtain and enable the cloud to meet your computing needs. Expanding the flexibility of resource use also saves you computing costs, simplifies IT operations, and enables you to pay more attention to core business innovation.
