Multi-monitoring task multi-target efficient IP end performance monitoring and scheduling method and system

Abstract

The invention discloses a multi-monitoring task multi-target efficient IP end performance monitoring and scheduling method and system. According to the efficient multi-monitoring-task multi-target IPend performance monitoring and scheduling method based on the measurement service in the linux operating system environment, the automatic periodic measurement of multi-monitoring task multi-target equipment can be achieved on a single monitoring host, and the problems of measurement time consumption, resource consumption, network intrusion and measurement errors can be solved.

Description

technical field [0001] The invention belongs to the technical field of network operation and maintenance, and in particular relates to a method and system for multi-monitoring tasks, multi-objectives and high-efficiency IP terminal performance monitoring and dispatching. Background technique [0002] In the operation and maintenance of IP networks, it is usually necessary to deploy some monitoring systems to periodically obtain IP-side performance data such as delay, packet loss, and delay jitter of multiple targets for graphical presentation or statistical analysis. These monitoring systems need to deploy monitoring software on a monitoring host (or probe). In order to realize the flexibility of monitoring function development and deployment, the user monitoring requirements generation interface function and monitoring realization function are usually divided into two different components, respectively. Use the same or different development platforms to develop and then int...

AI Technical Summary

Problems solved by technology

[0011] 1) Using a multi-threading scheme, each task thread corresponds to a monitoring task. If each task creates a sub-thread, it will increase the complexity of the program and increase the resource occupancy rate

[0012] 2) Each task thread is responsible for realizing multiple target monitoring, and each round of measurement takes a long time and is not efficient

[0013] 3) When the number of threads increases to a certain value (such as the number of threads > 50), the terminal performance error will be large

[0014] 4) Multi-threaded parallel sending of packets will increase the intrusion on the network

[0021] 1) Each task corresponds to a task process. When the number of processes increases (such as the number of processes > 50), it will cause a large error in the end performance data obtained by each task

[0022] 2) Multiple processes send packets in parallel, which will increase the intrusion on the network

Images