SMORE: A Cold Data Object Store for SMR Drives (Extended Version)

TL;DR

SMORE is an object storage system optimized for shingled magnetic recording drives, enabling efficient storage and retrieval of large, infrequently changed data objects with high throughput and quick crash recovery.

Contribution

It introduces a log-structured, zone-aware storage architecture with an index on flash, tailored for SMR drives, ensuring reliable, efficient large object storage with crash resilience.

Findings

Achieves full disk bandwidth for large object ingestion and reading.

Maintains a write amplification below 2.0 at 80% occupancy.

Recovers from crashes in less than a minute with hourly index snapshots.

Abstract

Shingled magnetic recording (SMR) increases the capacity of magnetic hard drives, but it requires that each zone of a disk be written sequentially and erased in bulk. This makes SMR a good fit for workloads dominated by large data objects with limited churn. To explore this possibility, we have developed SMORE, an object storage system designed to reliably and efficiently store large, seldom-changing data objects on an array of host-managed or host-aware SMR disks. SMORE uses a log-structured approach to accommodate the constraint that all writes to an SMR drive must be sequential within large shingled zones. It stripes data across zones on separate disks, using erasure coding to protect against drive failure. A separate garbage collection thread reclaims space by migrating live data out of the emptiest zones so that they can be trimmed and reused. An index stored on flash and backed up to the SMR drives maps object identifiers to on-disk locations. SMORE interleaves log records with object data within SMR zones to enable index recovery after a system crash (or failure of the flash device) without any additional logging mechanism. SMORE achieves full disk bandwidth when ingesting data---with a variety of object sizes---and when reading large objects. Read performance declines for smaller object sizes where inter- object seek time dominates. With a worst-case pattern of random deletions, SMORE has a write amplification (not counting RAID parity) of less than 2.0 at 80% occupancy. By taking an index snapshot every two hours, SMORE recovers from crashes in less than a minute. More frequent snapshots allow faster recovery.