IndexFS: Scaling File System Metadata Performance with Stateless Caching and Bulk Insertion
ACM/IEEE Int'l Conf. for High Performance Computing, Networking, Storage and Analysis (SC'14), November 16-21, 2014, New Orleans, LA. BEST PAPER AWARD!
Kai Ren, Qing Zheng, Swapnil Patil, Garth Gibson
Carnegie Mellon University
Pittsburgh, PA 15213
The growing size of modern storage systems is expected to exceed billions of objects, making metadata scalability critical to overall performance. Many existing distributed file systems only focus on providing highly parallel fast access to file data, and lack a scalable metadata service. In this paper, we introduce a middleware design called IndexFS that adds support to existing file systems such as PVFS, Lustre, and HDFS for scalable high-performance operations on metadata and small files. IndexFS uses a table-based architecture that incrementally partitions the namespace on a per-directory basis, preserving server and disk locality for small directories. An optimized log-structured layout is used to store metadata and small files efficiently. We also propose two client-based stormfree caching techniques: bulk namespace insertion for creation intensive workloads such as N-N checkpointing; and stateless consistent metadata caching for hot spot mitigation. By combining these techniques, we have demonstrated IndexFS scaled to 128 metadata servers. Experiments show our out-of-core metadata throughput out-performing existing solutions such as PVFS, Lustre, and HDFS by 50% to two orders of magnitude.
KEYWORDS: Distributed file systems, file system metadata, stateless caching, bulk insertion, log-structured merge tree
FULL PAPER: pdf