Elastic replication of virtual machines
AssigneeDatrium, Inc.
InventorsBoris Weissman, Sazzala Reddy
Life of this patent
Estimating the term…
Abstract
Techniques for replicating virtual machine data is provided. A plurality of compute nodes running on a primary cluster determine the amount of virtual machine data cached within each compute node. Based on the amount of virtual machine data for a particular virtual machine, a particular compute node is assigned to replicate the data to a secondary cluster. The amount of particular virtual machine data copied to the secondary cluster is based on updated virtual machine data that belongs to a particular state of the virtual machine. The destination of the particular virtual machine data is based on available cache space and prior replication statistics for target compute nodes on the secondary cluster.
Claims22
A method for replicating virtual machine data from a primary cluster to a secondary cluster, comprising:
- for each compute node of a plurality of compute nodes running within the primary cluster, determining an amount of virtual machine data, for a particular virtual machine, that is stored on the compute node;
- selecting a particular compute node, from the plurality of compute nodes, to replicate the virtual machine data of the particular virtual machine, based, at least in part, on the amount of virtual machine data of the particular virtual machine that is stored on the particular compute node;
- and
- causing the particular compute node to copy the virtual machine data corresponding to the particular virtual machine to the secondary cluster.
A method comprising:
- determining whether to use a first replication technique or a second replication technique to replicate virtual machine data of a particular virtual machine from a primary cluster to a secondary cluster based, at least in part, on:
- a hit rate associated with the particular virtual machine;
- and
- a fragmentation level associated with data, for the particular virtual machine, stored on one or more data nodes in the primary cluster;
- responsive to determining to use the first replication technique, causing a compute node in the primary cluster to replicate the virtual machine data of the particular virtual machine;
- and
- responsive to determining to use the second replication technique, replicating the virtual machine data by causing the one or more of data nodes to perform one or more bulk copies of data from disks managed by the one or more data nodes.
A non-transitory computer-readable medium that stores instructions for replicating virtual machine data from a primary cluster to a secondary cluster which, when executed by one or more processors, cause performance of:
- for each compute node of a plurality of compute nodes running within the primary cluster, determining an amount of virtual machine data, for a particular virtual machine, that is stored on the compute node;
- selecting a particular compute node, from the plurality of compute nodes, to replicate the virtual machine data of the particular virtual machine, based, at least in part, on the amount of virtual machine data of the particular virtual machine that is cached on the particular compute node;
- and
- causing the particular compute node to copy the virtual machine data corresponding to the particular virtual machine to the secondary cluster.
A non-transitory computer-readable medium that stores instructions for replicating virtual machine data from a primary cluster to a secondary cluster which, when executed by one or more processors, cause performance of:
- determining whether to use a first replication technique or a second replication technique to replicate virtual machine data of a particular virtual machine from a primary cluster to a secondary cluster based, at least in part, on:
- a hit rate associated with the particular virtual machine;
- and
- a fragmentation level associated with data, for the particular virtual machine, stored on one or more data nodes in the primary cluster;
- responsive to determining to use the first replication technique, causing a compute node in the primary cluster to replicate the virtual machine data of the particular virtual machine;
- and
- responsive to determining to use the second replication technique, replicating the virtual machine data by causing the one or more of data nodes to perform one or more bulk copies of data from disks managed by the one or more data nodes.
Dependencies are inferred from the claim text.