Mixed sequence flow identification method and device, and data pre-reading method and device

By identifying and grouping read commands, combining the compliant counter and non-regular counter, the mixed sequence stream is identified and data pre-read, which solves the problem of long response time of solid-state drives when processing mixed sequence streams, and significantly improves the performance of storage devices.

CN119645302APending Publication Date: 2025-03-18MEMBLAZE TECH BEIJING
1 Cites 0 Cited by

Patent Information

Application Number
CN202411693425.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-25
Publication Date
2025-03-18

AI Technical Summary

Technical Problem

In high-performance computing and distributed storage systems, solid-state drives need to process a large number of mixed sequential streams to read data streams, and the prior art is difficult to effectively identify and optimize such data streams, resulting in a long response time for read commands.

Method used

By grouping the received read commands, the direction and step size of each group of read commands is determined, and the mixed sequential stream is identified using compliance counters and non-regular counters. If identified, data pre-reading is performed, and the data is stored in the read pre-buffer so that subsequent read commands respond directly from the buffer.

Benefits of technology

It significantly shortens the response time of read commands, improves the overall performance of the storage device, and reduces the number of read operations on NAND flash memory, thereby improving system performance.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of storage, in particular to a method based on mixed sequence flow, comprising: grouping received read commands, each group comprising a plurality of read commands; for each group of read commands, determining the direction and step length of each group of read commands; if the direction of the current group of read commands is the same as the direction of the previous group of read commands and the step length of the current group of read commands is not greater than the size of the pre-read buffer area, progressively increasing the numerical value of the compliance counter; and if the value of the compliance counter is greater than or equal to the compliance threshold value, completing self-training, and identifying that the mixed sequence read data stream exists. The response time of the read command can be prolonged, and the overall performance of the storage system is improved.
Need to check novelty before this filing date? Find Prior Art