Storage Workload Modelling by Hidden Markov Models: Application to FLASH Memory

TL;DR

This paper introduces a Hidden Markov Model-based workload analysis technique for Flash memory, enabling efficient trace generation and performance estimation, validated against real industrial data and applicable to performance modeling.

Contribution

It presents a novel HMM-based approach for modeling storage workloads from traces, facilitating trace generation and performance analysis for Flash memory systems.

Findings

HMM accurately captures workload autocorrelation and statistics.

HMM-based models enable effective performance estimation.

Validated with industrial workload data.

Abstract

A workload analysis technique is presented that processes data from operation type traces and creates a Hidden Markov Model (HMM) to represent the workload that generated those traces. The HMM can be used to create representative traces for performance models, such as simulators, avoiding the need to repeatedly acquire suitable traces. It can also be used to estimate directly the transition probabilities and rates of a Markov modulated arrival process, for use as input to an analytical performance model of Flash memory. The HMMs obtained from industrial workloads are validated by comparing their autocorrelation functions and other statistics with those of the corresponding monitored time series. Further, the performance model applications are illustrated by numerical examples.