Using rdma for fast system recovery in virtualized environments

A recovery system for recovery in a virtualized computing environment operating on a physical computer system, using remote direct memory access, wherein a virtual computer system maintains a record of a state of the virtual computer system at each of a series of checkpoints, the recovery system comprising:

• one or more processing units configured for:
• setting up a virtual address space for a communication connection between the virtual computer system and the standby computer system, and mapping local buffers to the virtual space;
• and
• when defined error conditions occur on the virtual computer system, initializing a system recovery procedure for using said virtual address space for pushing the record of the state of the virtual computer system at one of the checkpoints onto the standby computer system using remote direct memory access, including re-initializing an input/output system of the physical computer system.

An article of manufacture comprising:

• at least one tangible computer readable hardware device having computer readable program code logic tangibly embodied therein to provide recovery in a virtualized computing environment operating on a physical computer system, using remote direct memory access, wherein a virtual computer system maintains a record of a state of the virtual computer system at each of a series of checkpoints, the computer readable program code logic, when executing on a computer:
• setting up a virtual address space for a communication connection between the virtual computer system and the standby computer system, and mapping local buffers to the virtual space;
• and
• when defined error conditions occur on the virtual computer system, initializing a system recovery procedure for using said virtual address space for pushing the record of the state of the virtual computer system at one of the checkpoints onto the standby computer system using remote direct memory access, including re-initializing an input/output system of the physical computer system.