SHREC: a SRE Behaviour Knowledge Graph Model for Shell Command Recommendations

TL;DR

SHREC addresses the challenge of preserving SRE operational knowledge and improving shell command efficiency by learning from historical SRE shell data and encoding the resulting relations in a SRE-behaviour knowledge graph. The method combines sequential pattern mining, macro-aggregation, and intent labeling to construct a rich graph that supports real-time command and sequence recommendations via a knowledge-graph based recommender system. Empirical evaluation on real company data shows the approach extracts thousands of frequent sequences, forms macros, and classifies most commands into practical intents, with substantial efficiency gains (e.g., up to 43% fewer command lines and 72.5% fewer characters for file-related commands) and millisecond-scale response times. The work demonstrates the practical value of preserving and reusing SRE knowledge to accelerate IT operations and lays groundwork for future natural language interfaces on top of the knowledge graph.

Abstract

In IT system operations, shell commands are common command line tools used by site reliability engineers (SREs) for daily tasks, such as system configuration, package deployment, and performance optimization. The efficiency in their execution has a crucial business impact since shell commands very often aim to execute critical operations, such as the resolution of system faults. However, many shell commands involve long parameters that make them hard to remember and type. Additionally, the experience and knowledge of SREs using these commands are almost always not preserved. In this work, we propose SHREC, a SRE behaviour knowledge graph model for shell command recommendations. We model the SRE shell behaviour knowledge as a knowledge graph and propose a strategy to directly extract such a knowledge from SRE historical shell operations. The knowledge graph is then used to provide shell command recommendations in real-time to improve the SRE operation efficiency. Our empirical study based on real shell commands executed in our company demonstrates that SHREC can improve the SRE operation efficiency, allowing to share and re-utilize the SRE knowledge.

Figures (8)

• Figure 1: Example of errors found in real shell data before the execution of the correct command (highlighted in yellow).
• Figure 2: Example of command (left) and sequence (right) recommendations provided by ShRec.
• Figure 3: ShRec overview.
• Figure 4: Schema of the SRE behaviour knowledge graph.
• Figure 5: Example of command recommendation (up) and sequence recommendation (down).