BoostIO

Overview

In the decoupled storage and compute architecture, BoostIO uses memory and drive resources on the compute side to build a distributed multi-tier cache. The write cache uses RDMA high-speed communication, cache affinity, data replication, and linear layout characteristics to improve service write performance and data reliability. The read cache pre-loads hotspot data to cache drives through data prefetch and leverages the LRU and cold/hot data identification algorithms to improve the read cache hit rate, thereby improving the read performance.

Technical Principles

Figure 1 BoostIO framework

Expected Results

This feature can be used in AI foundation model applications to increase the large block read-write performance by more than 300% in checkpoint (CKPT) and dataset loading scenarios.