Change Description

The OmniAdvisor parameter tuning feature of Kunpeng BoostKit for Big Data aims to use AI algorithms to intelligently tune the parameters of Spark tasks running in online systems.

Version 2.0.0 is independent of 1.0.0 and 1.1.0. It has the following function updates:

• OmniAdvisor 2.0 samples parameters of spark-submit tasks and recommends optimal configurations through AI iterative tuning, expert rule–based tuning, migration generalization tuning, and operator acceleration, enabling end-to-end parameter tuning for Spark tasks.
• It supports foreground user-unaware tuning and background retesting.
• It supports four tuning algorithms: AI iterative tuning, expert rule–based tuning, migration generalization tuning, and operator acceleration tuning.