Hybrid Adaptive Tuning for Tiered Memory Systems

TL;DR

This paper introduces PTMT, a hybrid online-offline framework that automates parameter tuning in memory tiering systems, significantly improving performance across various solutions.

Contribution

The paper presents PTMT, a novel lightweight framework that combines offline performance modeling with online reinforcement learning for adaptive memory tiering parameter tuning.

Findings

PTMT improves performance by up to 30% over default configurations.

PTMT outperforms the state-of-the-art by 32% on average.

The framework effectively adapts to different memory tiering solutions.

Abstract

Memory tiering provides a cost-effective solution to increase memory capacity, utilization, and even bandwidth. Memory tiering relies on system software for memory profiling, detection of frequently accessed pages, and page migration. Such a system software often comes with system parameters. The configurations of those parameters impact application performance. We comprehensively classify system parameters, and characterize the sensitivity of application performance to them using representative memory tiering solutions. Furthermore, we introduce a lightweight and user-friendly framework PTMT, which automates tuning of parameters at runtime for various memory tiering solutions. We identify major challenges for online tuning of memory tiering. PTMT uses a hybrid "offline + online" tuning method: while the offline phase builds a performance database for online queries and reduces runtime overhead, the online phase uses reinforcement learning (customized to memory tiering) to tune. PTMT improves performance by 30%, 26%, 21%, and 14%, on four memory tiering solutions (TPP, UPM, Colloid, and AutoNUMA), compared to using the default configurations. PTMT outperforms the state-of-the-art by 32% on average.