Balance scheduling center, method, system and device of distributed tasks

Abstract

The invention discloses a balance scheduling center, method, system and device of distributed tasks. The method comprises the steps that according to a function or type, multiple task groups are created, and a corresponding scheduling strategy is distributed for each task group; multiple scheduling plans are formulated for each task group, and each scheduling plan corresponds to an executable taskset; the execution amount of current tasks of each task group is monitored, and according to configuration parameters, the scheduling amount of each scheduling plan is calculated and obtained; according to the execution amount of the current tasks of each task group, the task issuing amount of each task main unit is calculated according to configuration parameters; according to the issuing amountof each task main unit, an executable task is issued for the corresponding task main unit. The scheduling center comprises a configuration module, a task scheduling module, a task issuing module anda task cache and monitoring module. According to the balance scheduling center, the task execution efficiency and use rate of the task main unit are effectively improved, and the load of the task mainunit is balanced.

Description

Technical field [0001] The present invention relates to the field of data transmission technology, and in particular to a balanced scheduling center, method, system and device for distributed tasks. Background technique [0002] With the development of computer and network information technology, in some enterprise-level systems, a large number of tasks are distributed on different task hosts to complete. How to schedule these tasks and allocate them to the corresponding task hosts reasonably has become an important technical problem. [0003] Currently, task scheduling and execution are mainly divided into the following two types: [0004] Serial single-node task scheduling, that is, the scheduling and execution of tasks completed by a single machine. The characteristics are: simple to implement and easy to maintain. The disadvantage is: but when there are a large number of tasks that need to be scheduled and executed, the single machine pressure is so great that it is impossible...

AI Technical Summary

Problems solved by technology

The disadvantage is: but when there are a large number of tasks that need to be scheduled and executed, the pressure on the single machine is so high that it is impossible to guarantee the completion of the tasks

[0014] However, the technical solutions in the prior art only use the scheduling framework and cannot monitor the execution of tasks, so the support for distributed multi-machine execution is not ideal, and it is easy to cause a backlog of some host tasks and unbalanced load

Images