GAIA: Glass-Aware I/O Middleware

As cloud-scale services and data-centric applications continue to generate massive volumes of data, the need for ultra-durable, energy-efficient, and cost-effective archival storage becomes increasingly urgent. Quartz glass has recently emerged as a promising archival medium, offering multi-century durability, radiation and thermal resistance, and support for three-dimensional data encoding using femtosecond laser writing. However, the hybrid mechanical-optical architecture of glass storage - requiring mechanical movement along the X and Y axes and optical focal tuning along the Z axis - introduces unique performance bottlenecks during data access, which conventional I/O scheduling strategies are not equipped to handle.In this work, we present GAIA, a Glass-Aware I/O middlewAre designed to optimize data access in quartz glass storage systems. GAIA features three coordinated strategies: (1) Zigzag Data Placement, which aligns data with the mechanical stage's natural motion to minimize direction-switching latency; (2) Z-Axis First Placement, which prioritizes low-latency optical traversal along the depth dimension; and (3) Shortest Moving Time First (SMTF) scheduling, which selects I/O operations based on predicted movement time rather than geometric distance. Through trace-driven simulations using enterprise-scale workloads and various glass sizes, GAIA reduces data read latency by up to 82% compared to traditional baseline schedulers. These results demonstrate the critical importance of middleware-level co-design in unlocking the performance potential of next-generation glass-based storage systems.