MASTER Assignment
Machine Learning for system level tuning of Linux OS - in collaboration with SUSE
Type: Master CS/EEĀ
Period: TBD
Student: (Unassigned)
If you are interested please contact :
Introduction and aim:
This assignment is in collaboration with SUSE [1], who are working on the development of a self-healing and auto-tuning engine for their Linux OS.
System-level tuning is a very complex task, requiring the knowledge and expertise about several, if not all, layers that compose the system itself, and how they interact with each other. Often, it is also required to have knowledge of the implementation of the various OS layers.
An important aspect of systems running in production is dealing with failure. In many circumstances, operators use telemetry, live charts, alerts, etc. which could help them identifying the offending machine(s) and (re)act to fix any potential issues. However, one question comes to mind: wouldn't it be awesome if the machine could auto-tune itself and provide a self-healing capability to the user? That is what this project aims to achieve.
Assignment:
The assignment concerns the improvement of Phoebe [2] via Machine Learning, and is focused on:
- Optimizing current detection and analysis of failures
- Developing new machine learning solution to optimize the auto-tuning functionality
- Support with data engineering enhancements
Programming languages are C and Python.