InfiniFS: An Efficient Metadata Service for Large-Scale Distributed Filesystems

Modern datacenters prefer one single filesystem instance that spans the entire datacenter and supports billions of files. The maintenance of filesystem metadata in such scenarios faces unique challenges, including load balancing while preserving locality, long path resolution, and near-root hotspots.

To solve these challenges, we propose INFINIFS, an efficient metadata service for extremely large-scale distributed filesystems. It includes three key techniques. First, INFINIFS decouples the access and content metadata of directories, so that the directory tree can be partitioned with both metadata locality and load balancing. Second, INFINIFS designs the speculative path resolution to traverse the path in parallel, which substantially reduces the latency of metadata operations. Third, INFINIFS introduces the optimistic access metadata cache on the client-side, to alleviate the near-root hotspot problem, which effectively improves the throughput of metadata operations. The extensive evaluation shows that INFINIFS outperforms state-of-the-art distributed filesystem metadata services in both latency and throughput, and provides stable performance for extremely large-scale directory trees with up to 100 billion files.