Parallel processing method and system for server service requests based on limitation of number of threads

Abstract

The present invention provides a server service request parallel processing method based on thread number limiting and a system thereof. According to the server service request parallel processing method and the system, a control solution for classifying service requests according to different processing time lengths, and the upper limit of the number of the threads which are called by the server for parallelly processing each kind of service requests, thereby preventing monopoly occupation of server thread by the service request with long processing time length, ensuring partial threads in the server is used for parallelly processing the service request with short processing time length, so that distribution balance for the threads for processing the service request of the server is improved, thereby improving service request processing executing efficiency and user service efficiency of the integral body of the server. Simultaneously the possibility of long-time monopoly occupation for server system resource caused by parallel processing for a large amount of service requests with complicated operation and long processing time length by the server is reduced, thereby improving system resource distribution performance of the server.

Description

technical field [0001] The present invention relates to the field of computer communication network technology and server technology, in particular to a method and system for parallel processing of server service requests based on thread number limitation. Background technique [0002] A server refers to a high-performance computer that provides external business services to a management resource in a computer communication network. There are many types of servers, such as data servers, file servers, web servers, streaming media servers, search servers, etc., they listen to business requests from computer clients or mobile communication clients in the computer communication network, and respond to and process the business requests , and then provide various business services for computer clients or mobile communication clients, enriching network applications. Servers in computer communication networks are faced with a huge number of business requests that need to be process...

AI Technical Summary

Problems solved by technology

[0004] However, due to the limitation of the processing performance and system resources of the server system, the total number of threads that the server can use to perform parallel processing of business requests is limited, and the business requests received by the server are highly random, so the server adopts this simple method. In the multi-threaded concurrent processing mode, it is likely that such a situation often occurs: in a certain period of time, the top queues in the single request queue are all business requests with a long processing time, so that almost all of the servers that can be used to perform parallel processing of business requests Threads are called to execute these business requests with a long processing time

The occurrence of this situation will mainly bring about two adverse effects: ①. If the business request with a short processing time can be processed first, and then the business request with a long processing time can be processed, not only will the service request with a short processing time The corresponding users can quickly obtain the request processing results. For the users corresponding to the long-processing business requests, the waiting time for obtaining the request processing results has not greatly exceeded expectations, so that different users can obtain better business services. Experience; however, since all the threads of the server that can be used to perform parallel processing of business requests are "monopoly occupied" by business requests with a long processing time, business requests with a short processing time must also be queued up to wait for a thread to complete the business request processing It can only be processed after it is released. Although it does not affect the user experience of business services corresponding to long processing time business requests, it greatly increases the waiting time for users corresponding to short processing time business requests to obtain request processing results. And its waiting time is much longer than expected, so it is likely to seriously affect the business service experience of these users; and, if the processing time of a business request with a long processing time is several times that of a business request with a short processing time, it means that this happens In the process, although the business service experience of users corresponding to a certain number of long processing time business requests is ensured, it is at the cost of greatly reducing the business service experience of users corresponding to the number of short processing time business requests. , so on the whole, it actually reduces the server's business request processing execution efficiency and user service efficiency

②. The longer the processing time of a business request, it usually means that the corresponding processing operation of the business request is more complicated, and the more server system resources need to be occupied; if all the threads of the server that can be used to execute parallel processing of business requests are called to execute Processing business requests with a long time means that a large amount of system resources of the server will be occupied by these parallel processing threads for executing business requests for a long time, and may even cause "several problems" to server system resources during this long period of time. "monopoly occupation", which makes the server's operation efficiency of other tasks suddenly reduced or even terminated, resulting in serious consequences such as network service interruption, server system task crash, etc.

Images