# SSDFS: Towards LFS Flash-Friendly File System without GC operation

## TL;DR

SSDFS is a novel flash-friendly file system designed to reduce write amplification and garbage collection overhead, thereby extending SSD lifespan and ensuring predictable performance without relying on traditional garbage collection.

## Contribution

It introduces new mechanisms like logical segments, diff-on-write, and hybrid B-trees to effectively manage write amplification and GC overhead in SSDs.

## Key findings

- Reduces write amplification effectively
- Decreases garbage collection overhead
- Prolongs SSD lifespan

## Abstract

Solid state drives have a number of interesting characteristics. However, there are numerous file system and storage design issues for SSDs that impact the performance and device endurance. Many flash-oriented and flash-friendly file systems introduce significant write amplification issue and GC overhead that results in shorter SSD lifetime and necessity to use the NAND flash overprovisioning. SSDFS file system introduces several authentic concepts and mechanisms: logical segment, logical extent, segment's PEBs pool, Main/Diff/Journal areas in the PEB's log, Diff-On-Write approach, PEBs migration scheme, hot/warm data self-migration, segment bitmap, hybrid b-tree, shared dictionary b-tree, shared extents b-tree. Combination of all suggested concepts are able: (1) manage write amplification in smart way, (2) decrease GC overhead, (3) prolong SSD lifetime, and (4) provide predictable file system's performance.