Direct access to de-duplicated data units in memory-based file systems

A non-transitory, machine readable medium having stored thereon instructions comprising machine executable code which when executed by a machine, causes the machine to:

• map a first data unit of a file to a memory address of a process at a memory of a computing device;
• detect a page fault by a memory-based file system retained in memory with the data unit, in response to receiving a first store instruction for the first data unit, wherein the page fault is triggered when there is no entry corresponding to the first data unit at a page data structure, indicating that the first data unit has not been accessed prior to the first store instruction;
• execute a copy on write operation by the file system by allocating a second data unit for copying data from the first data unit to the second data unit, when the first data unit is a de-duplicated data unit determined by the file system after detecting the page fault;
• and
• update the page data structure by adding an entry corresponding to the second data unit, indicating the second data unit is write enabled;
• wherein the entry enables direct access by the process to the second data unit from the memory, for an instruction received after the first store instruction, bypassing use of a page cache of the file system.

A system, comprising:

• a memory containing machine readable medium comprising machine executable code having stored thereon instructions;
• and a processor coupled to the memory, the processor configured to execute the machine executable code to:
• map a first data unit of a file to a memory address of a process at a memory of a computing device;
• detect a page fault by a memory-based file system retained in memory with the data unit, in response to receiving a first store instruction for the first data unit, wherein the page fault is triggered when there is no entry corresponding to the first data unit at a page data structure, indicating that the first data unit has not been accessed prior to the first store instruction;
• execute a copy on write operation by the file system by allocating a second data unit for copying data from the first data unit to the second data unit, when the first data unit is a de-duplicated data unit determined by the file system after detecting the page fault;
• and
• update the page data structure by adding an entry corresponding to the second data unit, indicating the second data unit is write enabled;
• wherein the entry enables direct access by the process to the second data unit from the memory, for an instruction received after the first store instruction, bypassing use of a page cache of the file system.