Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for adaptively matching nvme SSD reading speed and fiber interface speed

A technology of adaptive matching and optical fiber interface, which is applied in the direction of instruments, electrical digital data processing, etc., can solve the problem of occupying too much data cache resources, achieve the effect of reducing the demand for cache resources and saving the usage of BlockRam cache resources

Active Publication Date: 2022-01-25
HARBIN INST OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is: in view of the problem that the NVMe SSD reading speed control method occupies more data cache resources in the FPGA, a method for adaptively matching the NVMe SSD reading speed and the optical fiber interface speed is proposed

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for adaptively matching nvme SSD reading speed and fiber interface speed
  • A method for adaptively matching nvme SSD reading speed and fiber interface speed
  • A method for adaptively matching nvme SSD reading speed and fiber interface speed

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0033] Specific implementation mode one: refer to figure 1 Specifically illustrate this embodiment, in this embodiment, a kind of NVMe SSD reading speed and optical fiber interface speed self-adaptive matching method, comprise the following steps: first FPGA receives the data packet of reading data that returns from NVMe SSD, then RxReady signal is pulled low for five clock cycles.

[0034] When an NVMe storage device executes a read command, the speed of the fiber data interface is slower than that of the NVMe SSD. In order to match the speed of the NVMe SSD data read with the speed of the fiber data interface, the data read speed of the NVMe SSD must be reduced .

[0035] A common method is to control the read data speed of NVMe SSD by reducing the size of each NVMe read command and inserting a waiting interval between adjacent read commands. This method is limited by the logical block size (512Byte or 4KByte) of NVMe SSD, and can only control the average speed at which NV...

specific Embodiment approach 2

[0041] Embodiment 2: This embodiment is a further description of the adaptive matching method for NVMe SSD reading speed and fiber interface speed described in Embodiment 1. The difference between this embodiment and Embodiment 1 is that the RxReady The signal is pulled low by the state machine.

specific Embodiment approach 3

[0042] Embodiment 3: This embodiment is a further description of the method for adaptively matching the reading speed of an NVMe SSD and the speed of an optical fiber interface described in Embodiment 2. The difference between this embodiment and Embodiment 2 is the state The state of the machine includes: idle state, parsing packet header state, waiting state and RxReady signal control state.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method for adaptively matching NVMe SSD reading speed and optical fiber interface speed, relating to the field of data storage technology, in order to solve the problem that the NVMe SSD reading speed control method occupies more data cache resources in the FPGA in the prior art, including the following steps : First, the FPGA receives the read data packet returned from the NVMe SSD, and then pulls the RxReady signal low for five clock cycles. The present invention uses the RxReady signal of the AXI-Stream data receiving interface on the PCIe hard core to control the sending speed of the data packet when the NVMe SSD reads data, so that the NVMe SSD data reading speed matches the speed of the optical fiber data interface, without requiring a complete The read command is divided into several subcommands, and sufficient timing margin is reserved for the process of receiving and parsing data packets, which is easy to develop. Moreover, this method can reduce the demand for cache resources in the data reading process. When the logical block size of NVMe SSD is 512Byte and 4KByte, it can save 50% and 92% of the usage of Block Ram cache resources respectively, and can be widely used in data storage technology field.

Description

technical field [0001] The invention relates to the technical field of data storage, in particular to a method for adaptively matching the reading speed of an NVMe SSD and the speed of an optical fiber interface. Background technique [0002] NVMe SSD is a new-generation storage device that has emerged in recent years. With the help of the high transmission speed of the PCIe bus, it can achieve a data reading speed of more than 2GB / s. NVMe SSD is small in size and low in power consumption. Together with FPGA, it can form a miniaturized and portable optical fiber data storage device. The device uses the optical fiber interface to transmit the data in the storage device to the data processing device. This X4 optical fiber interface can reach a total data transmission rate of 12.5Gbps. [0003] When an NVMe storage device executes a read command, the speed of the fiber data interface is slower than that of the NVMe SSD. Therefore, a method must be used to match the read speed ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F13/16
CPCG06F13/16
Inventor 张京超乔立岩孟凡廓朱凯晖刘旺彭喜元
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com