PMCTrack: Delivering performance monitoring counter support to the OS scheduler

Abstract

Hardware performance monitoring counters (PMCs) have proven effective in characterizing application performance. Because PMCs can only be accessed directly at the OS privilege level, kernellevel tools must be developed to enable the end-user and userspace programs to access PMCs. A large body of work has demonstrated that the OS can perform effective runtime optimizations in multicore systems by leveraging performance-counter data. Special attention has been paid to optimizations in the OS scheduler. While existing performance monitoring tools greatly simplify the collection of PMC application data from userspace, they do not provide an architecture-agnostic kernel-level mechanism that is capable of exposing high-level PMC metrics to OS components, such as the scheduler. As a result, the implementation of PMC-based OS scheduling schemes is typically tied to specific processor models. To address this shortcoming we present PMCTrack, a novel tool for the Linux kernel that provides a simple architecture-independent mechanism that makes it possible for the OS scheduler to access per-thread PMC data. Despite being an OSoriented tool, PMCTrack still allows the gathering of monitoring data from userspace, enabling kernel developers to carry out the necessary offline analysis and debugging to assist them during the scheduler design process. In addition, the tool provides both the OS and the user-space PMCTrack components with other insightful metrics available in modern processors and which are not directly exposed as PMCs, such as cache occupancy or energy consumption. This information is also of great value when it comes to analyzing the potential benefits of novel scheduling policies on real systems. In this paper, we analyze different case studies that demonstrate the flexibility, simplicity and powerful features of PMCTrack.