A distributed monitoring data acquisition method and system for adaptive scheduling

Abstract

The invention provides an adaptive scheduling distributive monitoring data acquisition method and system. The method and the system comprise a main control end adaptive module, a main control end scheduler, a distributive controlled end acquisition unit and a distributive controlled end self-adjusting module. Specific to the characteristics of an adaptive scheduling mechanism and the characteristic that one main control end is specific to a plurality of controlled ends during distributive monitoring data acquisition, a method based on the main control end adaptive module, the main control end scheduler, the distributive controlled end acquisition unit and the distributive controlled end self-adjusting module is adopted, so that adaptive scheduling of the main control end scheduler is realized. The distributive controlled end acquisition unit is used for making an adjustment according to the scheduling in order to adapt to a current monitoring scale, so that distributive monitoring data acquisition is finished.

Description

technical field [0001] The invention relates to the field of distributed monitoring, in particular to an adaptive scheduling distributed monitoring data collection method and system. Background technique [0002] With the rapid development of the Internet, large-scale data centers have increasingly become the needs of the development of modern society. This brings huge challenges to the difficulty of monitoring and management of data centers. It is very difficult to monitor a data center with tens of thousands of resources, not to mention that under the current development trend, data centers with hundreds of thousands of resources or even millions of resources are Produced gradually. For example, the monitoring of a data center with 100,000 resources cannot be satisfied by the traditional distributed monitoring method. The schematic diagram of the traditional distributed monitoring data collection principle is as follows figure 1 As shown, it is assumed that the resource ...

AI Technical Summary

Problems solved by technology

For example, the monitoring of a data center with 100,000 resources cannot be satisfied by the traditional distributed monitoring method. The schematic diagram of the traditional distributed monitoring data collection principle is as follows figure 1 As shown, it is assumed that the resource configuration (such as CPU processing power, memory size, network bandwidth, etc.) of each distributed controlled terminal is different

Even if the traditional distributed monitoring method can meet the monitoring of thousands of resources, it cannot realize the full and efficient utilization of the resources consumed by monitoring, often causing some distributed controlled end resources to be idle, while other distributed controlled end resources are idle. The exhaustion of resources further affects the real-time performance of monitoring data, that is, the performance of monitoring, so that the entire distributed monitoring data acquisition system cannot really achieve the best results

The above challenges have brought great limitations to the monitoring data collection of large-scale data centers and the resource utilization efficiency consumed by monitoring data collection, which seriously affects the development of large-scale data center monitoring.

Images