Future work: Learning configurations using ML

[SankBad]

Modern Operating incorporates thousands of configurations that can be set by users.
There are at least two broad categories that can directly affect applications’ performances and can largely benefit from ML approaches.

1. There are many timing-related configurations in Linux, such as the frequency of interrupting a CPU core (for thread
   scheduling), the frequency of invoking background swapping (for memory paging), the frequency of flushing buffer cache
   (for storage), and the sampling rate of CPU clock frequency (for energy and performance). Setting these timing-related
   configurations is hard since there are various tradeoffs associated with them. For example, frequent CPU interruption
   offers the opportunity to improve CPU utilization (with more aggressive thread scheduling) but can cause performance overhead (by preempting and context switching threads), which in turn, reduces effective CPU utilization.
2. There are many configurations on various types of sizes, such as the buffer cache size (for storage caching), disk
   prefetching amount (for storage access), and swap prefetching amount (for memory paging). Setting these size-related configurations is hard, especially when there are tradeoffs among different sizes. For example, a larger buffer cache improves
   the performance of the storage system but reduces available memory for user applications.

Many of the above two types of configurations can considerably affect application performance and other important
metrics like energy cost. However, the practice of setting them has long been one that involves heavy engineering and human efforts: with heuristics, by trial and error, or with offline
experiments. Moreover, once set, they are seldom changed. ML is a better fit for setting these OS configurations. A
good ML model trained with past workloads and OS/hardware environments can potentially outperform human-set configurations. The model can continue to dynamically generate new configurations to adapt to the workload and environment changes. We can use reinforcement learning for learning OS configurations.

Source:

1. https://cseweb.ucsd.edu/~yiying/LearnedOS-OSR19.pdf
2. https://github.com/containers-ai/federatorai-operator
3. https://arxiv.org/pdf/2005.14410.pdf