Harvesting unused resources in a distributed computing system

A method in a system including at least one host server and at least one interface card configured to interface with a network or a storage, wherein the at least one host server comprises a processor having a first instruction set architecture (ISA) and the at least one interface card comprises a processor having a second ISA, the method comprising:

• the at least one host server designating at least one type of resource, associated with the at least one host server for harvesting by compute entities configured for execution using the processor having the second ISA, wherein the host server is configured to execute virtual machines requiring execution by the processor having the first ISA, and wherein the at least one type of resource includes at least one of a host memory and an input/output (I/O) device;
• a first hypervisor associated with the at least one host server sharing control information with a second hypervisor associated with the at least one interface card to enable access to a portion of the host memory and a portion of the I/O device;
• and
• in response to a request for accessing the at least one type of resource by a compute entity, executing on the processor having the second ISA, automatically allowing the compute entity to access the at least one type of resource associated with the at least one host server.

A distributed computing system comprising:

• a host server comprising a processor having a first instruction set architecture (ISA), wherein the host server is configured to service compute entities corresponding to at least one tenant, and wherein each of the compute entities is required to execute using the processor having the first ISA;
• an interlace card, coupled to the host server, comprising a processor having a second ISA;
• and
• a system configured to:
• allow designation of at least one type of resource, associated with the host server for harvesting by compute entities configured for execution using the processor having the second ISA,
• allow sharing of control information between a first hypervisor associated with the host sever and a second hypervisor with the interlace card, and
• in response to a request for accessing the at least one type of resource by a compute entity, executing on the processor having the second ISA, automatically allow the compute entity to access the at least one type of resource associated with the at least one host server.