Distributed memory checkpointing using storage class memory systems

An article of manufacture comprising a processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code is executable by one or more processors to implement a process comprising:

• running an application on a plurality of server nodes in a server cluster, wherein each server node includes system memory which comprises volatile system memory and non-volatile system memory;
• maintaining a current application state of the application in the system memory of the plurality of server nodes;
• performing a checkpoint operation to generate a distributed checkpoint image of the current application state of the application;
• storing the distributed checkpoint image in the non-volatile system memory of the plurality of server nodes;
• generating fault-tolerant parity data for the distributed checkpoint image;
• and
• storing the fault-tolerant parity data for the distributed checkpoint image in the non-volatile system memory of one or more of the plurality of server nodes.

A system, comprising:

• a server cluster comprising a plurality of server nodes, wherein each server node includes system memory which comprises volatile system memory and non-volatile system memory;
• and
• a distributed memory checkpointing system hosted by the plurality of server nodes in the server cluster, wherein the distributed memory checkpointing system executes a process comprising:
• performing a checkpoint operation to generate a distributed checkpoint image of a current application state of an application running on the plurality of server nodes of the server cluster, wherein the current application state is maintained in the system memory of one more server nodes in the server cluster;
• storing the distributed checkpoint image in the non-volatile system memory of the plurality of server nodes;
• generating fault-tolerant parity data for the distributed checkpoint image;
• and
• storing the fault-tolerant parity data for the distributed checkpoint image in the non-volatile system memory of one or more of the plurality of server nodes.