# Liquid Cloud Storage

## TL;DR

Liquid cloud storage systems distribute data redundantly across many unreliable nodes, using advanced coding and repair strategies to optimize durability, overhead, bandwidth, and performance.

## Contribution

This paper introduces a liquid storage architecture that combines large coding, lazy repair, and flow organization to optimize multiple storage metrics.

## Key findings

- Liquid systems can achieve flexible, near-optimal trade-offs among durability, overhead, and repair bandwidth.
- The proposed design enables scalable and reliable object storage across large, unreliable networks.
- The system's strategies improve efficiency and resilience compared to traditional storage methods.

## Abstract

A liquid system provides durable object storage based on spreading redundantly generated data across a network of hundreds to thousands of potentially unreliable storage nodes. A liquid system uses a combination of a large code, lazy repair, and a flow storage organization. We show that a liquid system can be operated to enable flexible and essentially optimal combinations of storage durability, storage overhead, repair bandwidth usage, and access performance.