GB/T 44216-2024Information technology—Big data—Techinical requirements for integrated batch and streaming computing (English PDF)

3.1 batch processing

Decompose a large job into multiple tasks and assign them to multiple nodes for processing respectively, and then summarize the results of the decomposed multiple tasks.

To obtain the calculation framework for the final analysis results.

3.2 stream processing

For large-scale computing scenarios with high-speed concurrency and high timeliness requirements, it can be used for real-time, high-speed, instantaneous and other characteristics.

A computing framework for real-time processing of streaming data.

3.3 integrated batch and streaming computing

A computing framework that can support both batch processing and stream processing.

3.4 Scatter-gather map-reduce

The required computation is divided and distributed across multiple nodes, and the overall result is the processing of large data sets composed of the results of each node. form.

Example. MapReduce (a computing model that includes two computing processes, Map and Reduce) uses a disperse-gather processing approach.

3.5 Tenant

One or more cloud service users with shared access to a set of physical and virtual resources.

3.6 multi-tenancy

The allocation of physical or virtual resources ensures that multiple tenants and their computing and data are isolated and inaccessible from each other.