Parallel Node Backup for Cluster Shared Volumes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing backup solutions for Cluster Shared Volumes (CSV) only utilize the first node in the Preferred Server Order List (PSOL) for backup operations, leaving other nodes idle, even when multiple nodes are available, resulting in inefficient use of resources and prolonged backup windows.
Innovation Solution
Implementing a parallel backup process that utilizes all available nodes in the PSOL to perform backups simultaneously, with a master/monitoring process coordinating the effort by dividing the workload among participating nodes, allowing for simultaneous access and backup of CSV volumes across multiple nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If only the first node in the PSOL is used to back up the CSV volume, then the backup process is simple to manage, but the backup window is prolonged and throughput is reduced
Solution Approach 1:
The patent divides the CSV volume into multiple segments or portions, assigning each segment to a different node in the PSOL for parallel backup operations. This segmentation enables multiple nodes to work simultaneously on different parts of the same volume, increasing overall backup throughput while maintaining manageable complexity through structured division of labor
Solution Approach 2:
The patent merges the backup capabilities of multiple nodes by coordinating them to work together on the same CSV volume. Instead of having nodes work sequentially or independently, the system combines their resources and capabilities into a unified parallel backup operation, achieving higher throughput while using a master/monitor process to manage the coordination
2Loss of time
If multiple nodes are used to back up the CSV volume in parallel, then the backup window is reduced and throughput is enhanced, but the coordination complexity increases
Solution Approach 1:
The patent establishes a master/monitor process beforehand that is responsible for coordinating the parallel backup operations. This preliminary setup of coordination infrastructure allows multiple nodes to be efficiently managed during the backup process, reducing the actual backup window while the coordination complexity is handled by the pre-established master process rather than ad-hoc management
Solution Approach 2:
The master/monitor process acts as an intermediary between the multiple backup nodes and the backup management system. It mediates the coordination by receiving backup requests, distributing work to appropriate nodes, monitoring their progress, and consolidating results, thereby enabling parallel operations without requiring direct complex interactions between all nodes
3Productivity
If all nodes in the PSOL are utilized for backup operations, then resource utilization is maximized and efficiency is improved, but the system requires more complex management
Solution Approach 1:
The master/monitor process is designed with multi-functionality, handling multiple tasks including node selection, workload distribution, progress monitoring, and result consolidation. This universal coordinator simplifies the management interface while enabling all nodes in the PSOL to be utilized effectively, maintaining ease of operation through a single point of control rather than requiring complex management of each node individually
Data Source
AI summary
Techniques to back up a cluster shared volume (CSV) are disclosed. In various embodiments, a snapshot of the cluster shared volume is stored persistently on the cluster shared volume itself. A task to back up a corresponding assigned portion of the snapshot is assigned to each of one or more cluster servers available to participate in backing up the cluster shared volume. The cluster servers have shared access to the snapshot as stored on the cluster shared volume, and each is configured to perform the task assigned to it in parallel with any other cluster servers assigned to back up other portions of the same cluster shared volume snapshot. The respective assigned tasks are monitored to completion.