Data processing method and device

Abstract

The embodiment of the invention discloses a data processing method and device, and the method comprises the steps that a scheduler detection module obtains an operation index of a resource scheduler in a distributed system, and the scheduler detection module is coupled with the resource scheduler; and it is determined that the resource scheduler is abnormal under the condition that the operation index exceeds a preset range. Through the method provided by the embodiment of the invention, whether the resource scheduler is abnormal or not can be determined according to the real-time operation index of the resource scheduler under the condition of not influencing the normal operation of the resource scheduler. In this way, an accurate and reliable detection result can be obtained, the detection result can be rapidly obtained, and the exception handling efficiency of the resource manager is improved.

Description

technical field [0001] The present application relates to the technical field of software development, in particular to a data processing method and device. Background technique [0002] The resource scheduler is an important role in a distributed system and is used to manage all resource nodes in the entire distributed system. The resource manager can acquire resources of each resource node, and perform resource scheduling according to a resource scheduling request (such as a CPU request, a memory request) sent by a user. In practical applications, the resource scheduler is often a single-point role. It not only needs to manage thousands of resource nodes running on physical nodes, but also needs to undertake tens of thousands of resource scheduling requests per second, and needs to respond to the Resource scheduling request, query resource availability at the frequency of second level. Therefore, once the resource scheduler is unavailable, the entire distributed system c...

AI Technical Summary

Problems solved by technology

Therefore, once the resource scheduler is unavailable, the entire distributed system cannot make resource requests, which may cause serious consequences for distributed systems

[0003] Even if it is found that the resource scheduler cannot provide services normally, when the problem needs to be found, it can only be found and handled manually

The process of manual processing is more difficult, not only because the working principle of the resource scheduler is more complicated, and there are many work indicators at runtime, but also, manual processing takes a lot of time, and it is impossible to find out which work indicators have problems in a short time

Therefore, in the existing technology, the manual processing process is often only processed based on personal experience, resulting in untimely processing, resulting in unreliable resource request services in distributed systems

Images