SUPR
Data Migration Management in Multi-Tiered Storage System
Dnr:

NAISS 2025/22-805

Type:

NAISS Small Compute

Principal Investigator:

Tianru Zhang

Affiliation:

Uppsala universitet

Start Date:

2025-06-04

End Date:

2026-01-01

Primary Classification:

10201: Computer Sciences

Webpage:

Allocation

Abstract

With the development of storage technologies, a wide variety of storage devices with different performance characteristics and cost profiles have emerged. Consequently, modern data systems are increasingly adopting multi-tiered storage solutions, where faster (but typically smaller) devices are placed in higher tiers, while lower tiers comprise slower, higher-capacity devices. A primary challenge in such systems is data placement--determining how data should be dynamically stored and migrated across different storage tiers to optimize overall performance. Effective data migration policies should be lightweight and adaptive to workload variations while considering storage device characteristics, notably the read/write asymmetry and parallelism of modern SATA/PCI SSDs and NVMs. In this project we will explore the performance of different data migration policies via a three-tier storage system built by FEMU SSD emulators.