Non-disruptive controller replacement in network storage systems

Abstract

A network-based storage system includes multiple storage devices and system controllers. Each storage device in multiple aggregates of storage devices can include ownership portion(s) that are configured to indicate a system controller to which it belongs. First and second system controllers can form an HA pair, and can be in communication with each other, the storage devices, and a separate host server. A first system controller controls an aggregate of storage devices and can facilitate an automated hotswap replacement of a second system controller that controls another aggregate of storage devices with a separate third system controller that subsequently controls the other aggregate of storage devices. The first system controller can take over control of the second aggregate of storage devices during the automated hotswap replacement of the second system controller, and can exchange system identifiers and ownership portion information with the separate third system controller automatically during the hotswap.

Description

technical field [0001] The present disclosure relates generally to network storage systems, and more particularly to the replacement of controllers on network storage systems. Background technique [0002] A storage area network ("SAN") environment typically includes a large number of storage devices that operate using a dual-controller model. In many cases, such storage devices may include at least one disk array, which may be classified as a Redundant Array of Independent Disks ("RAID"). In such a dual-controller model arrangement where the controllers are often referred to as a high-availability (“HA”) pair, a single controller can be assigned to act as the primary controller or “HA” for various storage volumes or arrays. owner" to operate the node. These controllers can also take over storage device volumes from their replacement or partner controllers in the event of a failure or other reason for controller replacement. [0003] Replacing or swapping out a system con...

AI Technical Summary

Problems solved by technology

If any errors occur in this manual ID entry process, the head swap fails and the replacement node must be rebooted entirely

Also, problems can arise when performing return and store operations from the controller concurrently, multi-disk panics can occur when disks are reallocated while they are alive, and support for multiple head swaps is often non-existent

Images