Lockify: Understanding Linux Distributed Lock Management Overheads in Shared Storage

This paper presents Lockify, a novel distributed lock manager (DLM) for shared-disk file systems. Our key observation in shared-storage scenarios is that, for file or directory creation, lock acquisition overhead in the Linux kernel DLM increases with the number of clients, even in low-contention scenarios. Lockify minimizes this lock acquisition latency by avoiding unnecessary communication with remote directory nodes through self-owner notifications and asynchronous ownership management. We implement Lockify in the Linux kernel and evaluate its performance on real-world workloads using two representative shared-disk file systems, GFS2 and OCFS2. Our experimental results demonstrate that Lockify improves overall throughput by ∼6.4× compared to the kernel DLM and O2CB, consistently across different numbers of clients.

We confirm that these performance issues occur across different DLM designs (e.g., Linux kernel DLM [1] and O2CB [7]), as DLMs manage lock-owner nodes in a distributed manner.

This paper presents Lockify, a novel distributed lock manager for shared-disk file systems. While looking up the owner node is a fundamental process in DLMs, our key insight is that when creating new files or directories, the node initiating the creation can designate itself as the owner, rather than querying other nodes. Based on this insight, Lockify introduces two novel mechanisms: selfowner notification and asynchronous ownership management. Self-owner notification allows a node that creates files or directories to immediately declare their ownership.