Property optimizing method for applying server

Abstract

The present invention relates to performance optimizing method for application server. After receiving the network service request, the network engine creates corresponding task associated with the service target before handing over the task to the task despatcher. If the number m of the work threads in current thread pool is smaller than the upper limit T_M of the thread pool, the despatcher will create one new thread in the pool for processing the task. If m=T_M, the despatcher will queue the task into the task queue. After completing the current task, the work threads in current thread pool will request new task from the task queue. Managing the application threads in the mode of finite thread pool plus infinite task queue can control the number of concurrent threads to reduce thread dispatching and competition overhead, raise utilization of the processor, increase the effective work time of the processor and increase the throughput of application server.

Description

technical field [0001] The invention relates to a performance optimization method of an application server, which belongs to the technical field of computer applications. Background technique [0002] The application server is the high-level operating environment of the application program in the network environment. It provides the application system with component operation management, communication, naming, transaction, security and other service functions, so that application developers can concentrate on the business logic of the target system and simplify the application process. System development and maintenance. The application server itself is a server program, which must have good performance to meet the needs of the application. Performance optimization is usually aimed at the situation where a large number of concurrent client requests arrive at the same time. The goal is to increase throughput and reduce response time as much as possible, so that the applicati...

AI Technical Summary

Problems solved by technology

However, if there is no limit to the use of multi-threading, it may be counterproductive and reduce throughput

This is because when the number of threads increases, on the one hand, creating and destroying threads consumes processor resources; The utilization rate is low, and the effective time actually used to process requests is very small, resulting in an increase in the processing time of a single task and a decrease in total throughput, which urgently needs to be further improved

Images