Managing the write performance of an asymmetric memory system

A system comprising a non-volatile random-access memory (NVRAM) based storage subsystem, the NVRAM-based storage subsystem comprising at least one NVRAM device in communication with a host computing device, the NVRAM-based storage subsystem is configured to perform the operations of:

• receiving, at a device driver on the host computing device, a plurality of write requests each requesting to write a respective unit of data to the NVRAM-based storage subsystem;
• categorizing the plurality of write requests into subgroups of write requests by determining whether a particular write request is latency-sensitive or throughput-sensitive and by identifying an application process or thread that has issued the particular write request such that each write request is categorized into only one subgroup of write requests and a first set of application processes or threads identified as having issued the latency-sensitive subgroup of write requests are smaller in number of application processes and threads than a second set of application processes or threads identified as having issued the through-put sensitive subgroup of write requests;
• identifying a target location on at least one NVRAM device of the NVRAM-based storage subsystem to service a particular subgroup of write requests according to the categorization, the NVRAM-based storage subsystem in communication with an intermediate volatile storage;
• and
• servicing the particular subgroup of write requests by writing the corresponding units of data to the identified target location on the at least one NVRAM device of the NVRAM-based storage subsystem.

A non-transitory computer readable medium, comprising software instructions, which software instructions when executed causes a non-volatile random-access memory (NVRAM) based storage subsystem, which NVRAM based storage subsystem comprising at least one NVRAM device in communication with a host computing device, to perform the operations of:

• receiving, at a device driver on the host computing device, a plurality of write requests each requesting to write a respective unit of data to the NVRAM-based storage subsystem;
• categorizing the plurality of write requests into subgroups of write requests by automatically determining whether a particular write request is latency-sensitive or throughput-sensitive and by automatically identifying an application process or thread that has issued the particular write request such that each write request is categorized into only one subgroup of write requests and a first set of application processes or threads identified as having issued the latency-sensitive subgroup of write requests are smaller in number of application processes and threads than a second set of application processes or threads identified as having issued the through-put sensitive subgroup of write requests;
• identifying a target location on at least one NVRAM device of the NVRAM-based storage subsystem to service a particular subgroup of write requests according to the categorization, the NVRAM-based storage subsystem in communication with an intermediate volatile storage;
• and
• servicing the particular subgroup of write requests by writing the corresponding units of data to the identified target location on the at least one NVRAM device of the NVRAM-based storage subsystem.