Reducing network traffic when replicating memory data across hosts
AssigneeAmazon Technologies, Inc.
InventorsBrijesh Singh, Eden Grail Adogla, II
Life of this patent
Estimating the term…
Abstract
Technologies are described herein for reducing network traffic when replicating memory data across hosts. The memory data stored in a main memory of the host computer is replicated to a main memory of a second host computer. Memory data from the local data storage of the second host computer that is a duplicate of memory data from the main memory is identified. Instead of sending the memory data from the main memory that is duplicated, the duplicated memory is copied from the local storage to the main memory of the second host computer.
Claims20
A non-transitory computer-readable storage medium having computer-executable instructions stored thereon that, when executed by a computer, cause the computer to:
- receive a request to facilitate a migration of a first virtual machine from a first computer, the first virtual machine associated with first memory data stored in a first memory of the first computer;
- identify one or more duplicate portions of the first memory data stored in a local storage of a second computer selected from a group of one or more potential destination computer systems based at least in part on an amount of duplicate portions of the first memory data stored in local storage of the second computer;
- and
- cause to copy the one or more duplicate portions of the first memory data only from the local storage of the second computer to a second memory of the second computer.
A system, comprising:
- one or more computers configured to:
- receive a request to facilitate replication of first memory data from a source computer;
- access memory identification data that identifies second memory data stored by one or more of a local data storage device or a main memory associated with one or more potential destination computers, the memory identification data indicating contents of memory pages on one or more of the local data storage device or the main memory;
- identify, using the memory identification data, one or more duplicate portions of the first memory data stored by the one or more of the potential destination computers;
- select, based at least in part on the memory identification data identifying one or more duplicate portions of first memory data, a destination computer;
- and
- cause the destination computer and the source computer to use the identified one or more duplicate portions to replicate the first memory data in a destination memory of the destination computer.
A computer-implemented method, comprising:
- receiving a request to replicate first memory data stored by a source computer;
- accessing memory identification data that identifies second memory data stored by one or more of a local data storage device or a main memory associated with one or more potential destination computers, the memory identification data indicating contents of memory pages on one or more of the local data storage device or the main memory;
- identifying, using the memory identification data, one or more duplicate portions of the first memory data stored by the one or more of the potential destination computers;
- selecting, based at least in part on the memory identification data identifying one or more duplicate portions of first memory data, a destination computer;
- and
- causing the destination computer and the source computer to use the identified one or more duplicate portions to replicate the first memory data in the destination computer.
Dependencies are inferred from the claim text.