NAS Cluster FSDB Distributed Metadata Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data storage systems face limitations in failover options and scalability, particularly with conventional virtual data movers (VDMs) relying on centralized databases, which can lead to performance bottlenecks and inadequate handling of double-fault scenarios, and storage processors becoming bottlenecks as non-volatile storage devices improve in speed.
Innovation Solution
Implementing a network-attached storage (NAS) cluster with multiple physical computing machines, each equipped with a file system database (FSDB) that allows NAS servers to be self-contained and move independently, reducing reliance on centralized databases and enabling flexible failover and load balancing, as well as tracking and accessing snapshots across machines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If conventional VDMs rely on centralized databases, then system management is simplified, but performance bottlenecks occur and scalability is limited
Solution Approach 1:
The patent segments the centralized database functionality into distributed FSDBs (File System Databases) located on each NAS server. Each FSDB manages its own file system metadata locally, eliminating the single-point bottleneck of centralized database access while maintaining simplified management through standardized interfaces.
Solution Approach 2:
The patent implements local quality by placing FSDBs on individual NAS servers rather than relying on centralized database access. Each NAS server has its own local database instance that manages file system metadata, enabling independent operation and eliminating performance bottlenecks associated with centralized database access.
2Reliability
If multiple SPs are used for redundancy, then system reliability improves, but failover options remain limited
Solution Approach 1:
The patent implements dynamic failover capabilities where any NAS server in the cluster can take over operations for a failed server. The system dynamically reassigns workloads and updates routing tables to redirect traffic to available servers, providing flexible failover options beyond fixed hot-spare configurations.
Solution Approach 2:
The patent creates a universal failover mechanism where any NAS server can serve as a backup for any other NAS server in the cluster. The standardized FSDB interface and cluster-wide routing enable any server to assume the role of a failed server, providing multi-functional redundancy rather than dedicated hot-spares.
3Productivity
If storage processors become more numerous, then parallel processing capacity increases, but system complexity and coordination overhead increase
Solution Approach 1:
The patent implements self-service through autonomous NAS servers that independently manage their own FSDBs and file system operations. Each server makes local decisions about data management without requiring constant coordination with central controllers, enabling parallel processing while minimizing coordination overhead through standardized peer-to-peer communication protocols.
Data Source
AI summary
A technique for managing data storage provides multiple physical computing machines and block storage arranged in a NAS (network attached storage) cluster. The physical computing machines run NAS servers, with each NAS server including an FSDB (file system database) that identifies a set of file systems that belong to the NAS server. LUNs (Logical UNits) in the block storage provide backing store for the set of file systems of each NAS server. In response to a request to move operation of a NAS server from a first physical computing machine to a second physical computing machine, the second physical computing machine accesses the FSDB of the NAS server, identifies the set of file systems that belong to that NAS server, and acts to provide host access to the identified set of file systems.