Efficient buffering for a system having non-volatile memory

Abstract

Systems and methods are disclosed for efficient buffering for a system having non-volatile memory (“NVM”). In some embodiments, a control circuitry of a system can use heuristics to determine whether to perform buffering of one or more write commands received from a file system. In other embodiments, the control circuitry can minimize read energy and buffering overhead by efficiently re-ordering write commands in a queue along page-aligned boundaries of a buffer. In further embodiments, the control circuitry can optimally combine write commands from a buffer with write commands from a queue. After combining the commands, the control circuitry can dispatch the commands in a single transaction.

Description

BACKGROUND OF THE DISCLOSURE[0001]NAND flash memory, as well as other types of non-volatile memories (“NVMs”), are commonly used for mass storage. For example, consumer electronics such as portable media players often include flash memory to store music, videos, and other media.[0002]Because a file system of a device may perform multiple small synchronous input / outputs (“I / Os”), die parallelism cannot be achieved in some cases. This consequently may reduce system bandwidth, and increase the latency for programming the pages of a NVM.[0003]In some scenarios, the latency for programming a NVM can be improved by buffering one or more I / Os prior to programming the I / Os to the NVM. However, in other scenarios, if I / Os can instead be directly programmed to the NVM, indiscriminate buffering of all I / Os received from a file system may actually slow down the programming process.SUMMARY OF THE DISCLOSURE[0004]Systems and methods are disclosed for efficient buffering of a system having non-vol...

AI Technical Summary

Benefits of technology

[0004]Systems and methods are disclosed for efficient buffering of a system having non-volatile memory (“NVM”). The system can select to buffer writes where the buffering will increase system performance, and select to program writes directly to a NVM where the buffering would be a net performance burden. In some embodiments, a system can use heuristics to determine whether to perform buffering of one or more write commands received from a file system. In other embodiments, the system can minimize read energy and buffering overhead by efficiently re-ordering write commands in a queue along page-aligned boundaries of a buffer. In further embodiments, the system can optimally combine write commands from a buffer with write commands from a queue. After combining the commands, the system can dispatch the commands in a single transaction.

Problems solved by technology

The system can select to buffer writes where the buffering will increase system performance, and select to program writes directly to a NVM where the buffering would be a net performance burden.

Images