System and method for handling cross-platform system call with shared page cache in hybrid system

A computer program product, comprising a computer usable storage device having a computer readable program code embodied therein, said computer readable program code containing instructions that when executed by at least one processor of a hybrid system implement a method for handling a page fault while executing a cross-platform system call with a shared page cache in the hybrid system, the method comprising:

• said at least one processor receiving, by a first kernel running in a first computer system of the hybrid system, a request for a faulted page associated with raw data from a second kernel running in a second computer system of the hybrid system, wherein the raw data is referred to by a parameter of the cross-platform system call, wherein the cross-platform system call is invoked from a user application running on the first computer system, wherein the cross-platform system call provides a kernel service to the user application upon being remotely executed on the second computer system of the hybrid system, wherein the first kernel has a first copy of the shared page cache for pages of the first computer system that are shared with the second kernel of the second computer system, wherein the second kernel has a second copy of the shared page cache for pages of the second computer system that are shared with the first kernel of the first computer system, wherein a first validity flag representing the faulted page indicates whether the faulted page is available to the first computer system in the first copy of the shared page cache, wherein a second validity flag representing the faulted page indicates whether the faulted page is available the second computer system in the second copy of the shared page cache, and wherein the faulted page cannot be concurrently available to the first computer system and the second computer system in the first copy and the second copy, respectively, of the shared page cache, and wherein the first kernel is coupled to the second kernel by use of a direct data path device for high-speed communication;
• and
• in response to the request for the faulted page:
• (i) said at least one processor updating the first validity flag to denote that the faulted page is unavailable to the first computer system in the first copy of the shared page cache and (ii) said at least one processor transmitting the faulted page to the second kernel for insertion of the faulted page in the second copy of the shared page cache and for updating the second validity flag to denote that the faulted page is available to the second computer system in the second copy of the shared page cache.

A computing system comprising at least one processor and a computer readable memory unit coupled to the at least one processor, said memory unit containing instructions that when executed by the at least one processor implement a method for handling a page fault while executing a cross-platform system call with a shared page cache in a the hybrid system, said method comprising:

• said at least one processor receiving, by a first kernel running in a first computer system of the hybrid system, a request for a faulted page associated with raw data from a second kernel running in a second computer system of the hybrid system, wherein the raw data is referred to by a parameter of the cross-platform system call, wherein the cross-platform system call is invoked from a user application running on the first computer system, wherein the cross-platform system call provides a kernel service to the user application upon being remotely executed on the second computer system of the hybrid system, wherein the first kernel has a first copy of the shared page cache for pages of the first computer system that are shared with the second kernel of the second computer system, wherein the second kernel has a second copy of the shared page cache for pages of the second computer system that are shared with the first kernel of the first computer system, wherein a first validity flag representing the faulted page indicates whether the faulted page is available to the first computer system in the first copy of the shared page cache, wherein a second validity flag representing the faulted page indicates whether the faulted page is available the second computer system in the second copy of the shared page cache, and wherein the faulted page cannot be concurrently available to the first computer system and the second computer system in the first copy and the second copy, respectively, of the shared page cache, and wherein the first kernel is coupled to the second kernel by use of a direct data path device for high-speed communication;
• and
• in response to the request for the faulted page:
• (i) said at least one processor updating the first validity flag to denote that the faulted page is unavailable to the first computer system in the first copy of the shared page cache and (ii) said at least one processor transmitting the faulted page to the second kernel for insertion of the faulted page in the second copy of the shared page cache and for updating the second validity flag to denote that the faulted page is available to the second computer system in the second copy of the shared page cache.