Clustered raid assimilation management

摘要

In one embodiment, a node is a member of a cluster having a plurality of nodes, where each node is coupled to one or more storage arrays of solid state drives (SSDs) that serve as main storage. The node executed a storage input/output (I/O) stack having a redundant array of independent disks (RAID) layer that organizes the SSDs within the one or more storage arrays as one or more RAID groups. Configuration information is stored as a cluster database. The configuration information identifies (i) one or more RAID groups associated with an extent store, (ii) SSDs within each RAID group, and (iii) an identification of a node that owns the extent store. The cluster database is stored separate and apart from the main storage.

主权项

1. A system comprising:
a central processing unit (CPU) of a node of a cluster having a plurality of nodes, each node coupled to one or more storage arrays of solid state drives (SSDs) configured to serve as main storage for the nodes of the cluster; a memory coupled to the CPU and configured to store a storage input/output (I/O) stack having a redundant array of independent disks (RAID) layer executable by the CPU, the RAID layer configured to organize the SSDs within the one or more storage arrays as one or more RAID groups; and a service storage device coupled to the CPU and configured to store configuration information as a cluster database, the configuration information identifying (i) the one or more RAID groups associated with an extent store, (ii) the SSDs within each RAID group, and (iii) an identification of a node that owns the extent store, the cluster database maintained separate and apart from the main storage to enable the node to access the configuration information without dependency on the main storage and to enable any node of the cluster to access a list of the SSDs in the extent store to perform assimilation and determine ownership of the extent store.