Dynamic allocation of compute resources at a recovery site
AssigneeNutanix, Inc.
InventorsBINNY SHER GILL, JAN OLDERDISSEN, RAJIV MIRANI, MIAO CUI
Life of this patent
Estimating the term…
Abstract
Examples of systems are described herein which may dynamically allocate compute resources to recovery dusters. Accordingly, a recovery site may utilize fewer compute resources in maintaining recovery clusters for multiple associate clusters, while ensuring that, during use, compute resources are allocated to a particular cluster. This may reduce and/or avoid vulnerabilities arising from a use of shared resources in a virtualized and/or cloud environment.
Claims23
A system comprising:
- an operational cluster located at an operational site, the operational cluster having a first plurality of nodes and a first shared storage pool, the first shared storage pool including local storage of one or more of the first plurality of nodes;
- a recovery cluster, in communication with the operational cluster, and located at a recovery site, the recovery cluster having a second plurality of nodes and a second shared. storage pool, the second shared storage pool including local storage of one or more of the second plurality of nodes;
- wherein each node of the first plurality of nodes and each node of the second plurality of nodes comprises a hypervisor, a user virtual machine, and storage;
- an available resource pool, located at the recovery site, comprising a plurality of unallocated nodes, the plurality of unallocated nodes comprising a plurality of unallocated complete nodes, a plurality of unallocated compute nodes, or combinations thereof;
- and
- a cluster manager, located at the recovery site and in communication with the recovery cluster, configured to, responsive to receipt of an indication of a recovery event from the operational cluster, dynamically add an unallocated compute node of the plurality of unallocated compute nodes to the recovery cluster to support failover.
At least one non-transitory computer readable medium comprising instructions which, when executed, cause a computing system to:
- receive an indication of a recovery event from an operational cluster located at an operational site, the recovery event indicative of a failure at the operational cluster, the operational cluster having a plurality of operational nodes and an operational shared storage, wherein the operational shared storage includes local storage of one or more of the plurality of operational nodes;
- and
- based on receipt of the indication of the recovery event, dynamically add an unallocated compute node of a plurality of unallocated compute nodes to a recovery cluster located at a recovery site, wherein the addition supports failover, and wherein the recovery cluster includes a plurality of recovery nodes and a recovery shared storage, wherein the recovery shared storage includes local storage of one or more of the plurality of recovery nodes.
A method comprising:
- receiving, at a cluster manager located at a recovery site, an indication of a recovery event from an operational cluster located at an operational site;
- and
- dynamically adding, by the cluster manager, an unallocated compute node of a plurality of unallocated compute nodes to a recovery cluster located at the recovery site, wherein the addition of the unallocated compute node supports failover.
Dependencies are inferred from the claim text.