An information processing method and electronic device

Abstract

Embodiments of the invention disclose an information processing method and an electronic device. The method comprises the steps of obtaining first query data, and / or, obtaining first load information for representing a load state of a computing device; analyzing the first query data, and obtaining a first parameter for representing a complexity degree of the first query data; and selecting a first computing framework in the computing device according to a preset policy based on the first parameter and / or the first load information, and sending the first query data to the first computing framework in the computing device, wherein the computing device comprises at least two computing frameworks, and the first computing framework is any computing framework in the two computing frameworks.

Description

technical field [0001] The invention relates to information processing technology, in particular to an information processing method and electronic equipment. Background technique [0002] Commonly used computing frameworks such as Impala, MapReduce, Spark, etc., of course, are not limited to the computing frameworks listed above (Impala is a query system; MapReduce is a programming model that can provide parallel computing for large-scale data sets; Spark is a computing engine for large-scale data processing). Usually, multiple computing frameworks are deployed in a cluster and run on top of the cluster resource scheduler. However, data analysts or business personnel are usually not familiar with the principles or characteristics of each computing framework, so they are at a loss in the face of multiple computing frameworks. In the existing technology, users usually need to spend a lot of time and energy to understand the principles or characteristics of each computing fr...

AI Technical Summary

Problems solved by technology

However, data analysts or business personnel are usually not familiar with the principles or characteristics of each computing framework, so they seem at a loss in the face of multiple computing frameworks

In the existing technology, users usually need to spend a lot of time and energy to understand the principles or characteristics of each computing framework, choose a computing framework, or choose a computing framework based on experience or subjective wishes; the former requires a lot of time and energy for users, which is not conducive to In addition, the computing framework selected by the two schemes is not necessarily the optimal computing framework, which may easily lead to the problem of low overall utilization of cluster resources, and, in the case of a large amount of concurrent queries, the user's The response time of the query operation is too long, which is not conducive to the user experience

Images