Shulou(Shulou.com)06/02 Report--

Load balancing is based on the existing network structure, which provides a cheap, effective and transparent way to expand the bandwidth of network devices and servers, increase throughput, enhance network data processing capacity, and improve network flexibility and availability. Load balancing (Load Balance) means to distribute the execution among multiple operation units, such as Web server, FTP server, enterprise critical application server and other critical task servers, so as to complete the work task together.

Many tenants access their computers in the cloud through computer networks and use the computing resources inside. Here are three points to note:

There are many tenants.

There are many computers in the cloud.

The number of broadband dedicated lines entering the cloud is limited (usually 1 to 3 optical fibers).

The load is the task, that is, the task that the tenant needs to accomplish in the cloud. How to reasonably assign the tasks to be completed by many tenants to each server in the cloud and deal with them quickly is the problem to be solved by load balancing technology. Instead of sitting idle at home, it is better to start learning immediately. When the opportunity explodes, whether we can grasp it or not depends on whether we are ready and strong enough. So, from now on, Qianfeng 900G+ video tutorials are free! Just leave a message below. I hope it can help you grow up in the "adversity" and start the new year calmly.

The following are common load balancing strategies:

1) make each wake-up server responsible for as many active desktops as possible.

2) make the proportion of computing resources consumed by each server as equal as possible. If all servers are configured the same, then this strategy is to distribute active desktops equally to all servers as much as possible.

3) tenant desktops with the same application software are allocated to the same server as much as possible. Tenants in the same department use similar software, so tenant desktops in the same department are assigned to the same server as much as possible. For example, after-sales service employees generally use customer service software, office software, mail, problem library tools, etc., so the desktops of after-sales service employees are placed on the same computer and used as semi-platform PaaS cloud desktops, thus saving a lot of memory.

4) each time the same tenant logs in, their desktops are allocated to the same server as much as possible. This minimizes the number of desktop roaming, thereby reducing the overhead of network bandwidth.

The load balancer task is accomplished by load balancers. At present, there are not only software-only load balancer products, such as LVS, but also hardware load balancers introduced by manufacturers, such as F5, Shenzhen convincing, barracuda, Radware and so on. The price of F5 load balancer is more than 100000 yuan.

LVS is open source software, has been integrated into the Linux kernel, its superior performance, combined with a general-purpose physical computer, it is possible to build a load balancer comparable to F5. Simple load balancing tasks can also be achieved by directly using DNS polling or iptables.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.