US 12,250,268 B2
Orchestrated node removal to reduce cluster capacity in a clustered file system
Ryan Libby, Seattle, WA (US); Raymond Ramsden, Seattle, WA (US); Jahanvi Bishnoi, Seattle, WA (US); and Steven Soumpholphakdy, Chicago, IL (US)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Apr. 20, 2023, as Appl. No. 18/304,051.
Prior Publication US 2024/0357006 A1, Oct. 24, 2024
Int. Cl. H04L 67/1031 (2022.01); H04L 41/0897 (2022.01); H04L 67/1008 (2022.01); H04L 67/1012 (2022.01)
CPC H04L 67/1031 (2013.01) [H04L 41/0897 (2022.05); H04L 67/1008 (2013.01); H04L 67/1012 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
at least one processor; and
at least one memory that stores executable instructions that, when executed by the at least one processor, facilitate performance of operations, the operations comprising:
receiving a user request to adjust a node group of node groups of a data protected storage node cluster, wherein the node group comprises a pool of nodes of the data protected storage node cluster that have a same configuration, and wherein the user request specifies a node identifier of the node group, and an amount of storage space to remove from a total amount of raw storage space distributed across the pool of nodes of the node group; and
in response to the user request, adjusting the node group, comprising:
determining, based on the amount of storage space to remove and raw storage space per node of the node group, a quantity of nodes from the node group to remove;
determining whether removing the quantity of nodes leaves an unsupported quantity of nodes in the node group for protection of data in the node group in response to failure of a node in the node group;
in response to determining that removing the quantity of nodes does not leave the unsupported quantity of nodes in the node group, selecting, based on a defined criterion, one or more nodes to remove from the node group equal to the quantity of nodes, the selecting resulting in one or more selected nodes, and resulting in one or more other nodes of the node group other than the one or more selected nodes being one or more non-selected nodes;
redistributing data of the one or more selected nodes of the node group to the one or more non-selected nodes of the data protected storage node cluster, wherein the redistributing data of the one or more selected nodes, comprises:
for each virtual machine, of the data protected storage node cluster, associated with the one or more selected nodes:
 initiating a fail operation for the virtual machine, and
 removing, from the data protected storage node cluster, logical node numbers corresponding to nodes associated with the virtual machine;
moving data stored on the one or more selected nodes to at least one of the one or more non-selected nodes, and
redirecting data write operations to the one or more selected nodes to the at least one of the one or more non-selected nodes; and
deallocating resources corresponding to the one or more selected nodes of the node group.