Algorithmic location of raid groups and spare capacity for granular expansion

An apparatus, comprising:

• a plurality of non-volatile drives;
• a plurality of interconnected compute nodes that manage access to the drives;
• and
• a drive manager configured to:
• create a minimal drive cluster of protection groups of size G, the minimal drive cluster characterized by (G+1) drives that are each organized into G same-size cells for which the cell at disk X, cell Y is assigned to group (X+Y−1) modulo M, where M is group size (G) plus 1 and one of the groups is reserved as spare capacity for recovering from drive failure;
• expand the minimal drive cluster with N new drives, resulting in an expanded cluster have a total of less than 2*G+1 drives;
• reorder the new drives with the first N drives of the minimal drive cluster by swapping disk indices;
• free cells at N cell indices of the first G-N drives using member transposition;
• and
• create single-cell-index groups in the freed cells.

A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for using a computer system to create and distribute spare capacity, the method comprising:

• creating a minimal drive cluster of protection groups With G members, the minimal drive cluster characterized by (G+1) drives that are each organized into G same-size cells for which the cell at disk X, cell Y is assigned to group (X+Y−1) modulo M, where M is group size (G) plus 1 and one of the groups is reserved as spare capacity for recovering from drive failure;
• expanding the minimal drive cluster with N new drives, resulting in an expanded cluster have a total of less than 2*G+1 drives;
• reordering the new drives with the first N drives of the minimal drive cluster by swapping disk indices;
• freeing cells at N cell indices of the first G-N drives using member transposition;
• and
• creating single-cell-index groups in the freed cells.