Multi-mode database evaluation benchmark system for streaming data and construction method of multi-mode database evaluation benchmark system

Abstract

The invention discloses a streaming data-oriented multimode database evaluation reference system and a construction method thereof. The system comprises an infrastructure layer, a message transmission layer, a workload actuator and an evaluation reference system interface layer, and the components are sequentially arranged from bottom to top. The method comprises the following steps: (1) installing and configuring an Apache CloudStack; (2) virtualizing the infrastructure; (3) in a message transmission layer, based on Kafka, adopting an asynchronous message passing micro-service design mode, and logic of interaction between the Kafka and various multi-mode databases being realized; (4) realizing different request data distribution modes in a working load executor; (5) in a working load executor, realizing load operation of each multimode database for different model data; and (6) in an evaluation reference system interface layer, completing design of an evaluation reference system interface and realizing connection with a background, so that a user can conveniently select a multi-mode database and set and execute related loads, and a visual area is provided for a test result.

Description

technical field [0001] The invention relates to the technical field of software performance evaluation and measurement analysis, in particular to a flow data-oriented multi-mode database evaluation benchmark system and a construction method thereof. Background technique [0002] As the world becomes more instrumented and interconnected, we are witnessing a deluge of data of various structures generated by various hardware or software. These data are divided into three types according to structural classification: structured data, semi-structured data and unstructured data. In the face of large-scale multi-structure data, traditional relational databases have the following problems: (1) they can only provide storage and management of relational data; (2) in the face of large-scale data processing, the efficiency is low, or even impossible; (3 ) Fixed table structure, less flexibility; (4) High concurrent read and write requirements, for traditional relational databases, hard...

AI Technical Summary

Problems solved by technology

In the face of large-scale multi-structure data, traditional relational databases have the following problems: (1) they can only provide storage and management of relational data; (2) in the face of large-scale data processing, the efficiency is low, or even impossible; (3 ) Fixed table structure, less flexibility; (4) High concurrent read and write requirements, for traditional relational databases, hard disk I / O is a big bottleneck

However, they are all data models supported by NoSQL databases or multi-mode databases. For example, YCSB can only test the performance of OrientDB involving document data.

Images