IO deterministic optimization strategy method for NVMe

Abstract

An NVMe-oriented IO deterministic optimization strategy method can reduce performance jitter and the like of I / O requests by performing optimization based on sets and window division, thereby improving garbage collection efficiency and further prolonging the service life of a solid state disk, and is characterized by comprising the following steps: step A, realizing mutual independence of different sets by performing set division on NVMe storage units, therefore, reading, writing and garbage collection operations can be performed in parallel among different sets; step B, proposing a new I / O request scheduling algorithm for the NVMe after set division, and avoiding conflict between garbage collection and I / O request access; and step C, designing a new cache management algorithm to perceivethe garbage collection operation of the NVMe set, avoiding the possibility of conflict between the garbage collection operation and the I / O request access to the greatest extent, and reducing the performance jitter of the I / O request.

Description

technical field [0001] The present invention relates to computer science and technology, such as an NVMe I / O-oriented deterministic scheduler and cache optimization based on Open Channel SSD, especially an NVMe-oriented IO deterministic optimization strategy method. NVMe (Non-Volatile Memory express) refers to non-volatile storage systems and their standards or protocols. I / O (or IO, Input / Output) refers to input / output. Open Channel SSD (Solid State Drives) refers to open channel solid state drives or solid state drives. Background technique [0002] With the continuous development of storage systems, storage media has taken a huge leap forward due to the birth of NAND flash memory. Its superior random read and write speed and gradually lower unit capacity price are more and more favored by enterprise users. The development of solid-state drives (SSDs) is accompanied by the expansion of the number of bits of flash memory particles and the performance enhancement of flash...

AI Technical Summary

Problems solved by technology

In terms of garbage collection, the existing research improves the efficiency of garbage collection by dynamically determining the threshold of free page ratio, reducing the blocking unit of garbage collection, and establishing an interruptible garbage collection algorithm, but none of them can fully realize the performance of no garbage collection

Due to the relatively independent nature of the host side and the SSD, the host side cannot know when the SSD is in the garbage collection state, so it is still impossible to completely eliminate the tail delay caused by the garbage collection operation.

Images