Unlock instant, AI-driven research and patent intelligence for your innovation.

MBR parallel reading method based on fragmentation

A technology of slicing and data blocks, applied in the input/output process of data processing, instruments, input/output to record carriers, etc., can solve the problems of limited read performance of MBR storage system, and achieve improved read performance and good parallelism Effect

Active Publication Date: 2019-11-08
HUAZHONG UNIV OF SCI & TECH +1
View PDF11 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the defects of the prior art, the purpose of the present invention is to solve the technical problem that the read performance of the MBR storage system in the prior art is limited

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
  • MBR parallel reading method based on fragmentation
  • MBR parallel reading method based on fragmentation
  • MBR parallel reading method based on fragmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0031] The MBR (Minimum-Bandwidth Regenerating Codes) code is constructed based on a complete graph. When storing, each block is stored in two copies, and two copies of the same block are stored on different nodes. Naturally, Good support for parallelism.

[0032] Such as figure 1 As shown in (a), the number of nodes is n=4, and any k=3 nodes can restore the failed node. There are data blocks 0, 1...5 distributed on the four nodes, and each data block is stored on two different nodes, that is to say, each block is stored in the form of a double copy.

[0033] Such as figure 1 As shown in (b), t...

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

The invention discloses an MBR parallel reading method based on fragmentation, and belongs to the field of computer storage. When the MBR storage system writes in, the same data block is sequentiallywritten into two different nodes according to a file stream at the same time, and the method comprises the steps that before a file is requested to be read from the MBR storage system, each data blockin the MBR storage system is divided into two slices with the same size; when a certain file is requested to be read from an MBR storage system, two different nodes where each data block in the fileis located are sequentially searched for; and two different slices of the same data block are read from two different nodes in parallel until the file is read. By fragmenting the data blocks and reading the same data block on the two different nodes, only half of the original data block needs to be read, and the additional data reading amount is not increased, so that the system reads less data while maintaining good parallelism, and the reading performance of the storage system is further improved.

Description

technical field [0001] The invention belongs to the field of computer storage, and more specifically relates to a fragment-based MBR parallel reading method. Background technique [0002] In a distributed storage system, due to the large number of nodes, cheap commercial disks are often used as storage media to reduce costs. However, due to unreliable disk quality and software or program failures, data failure is normal. Therefore, how to quickly restore invalid data when data fails is a hot issue. Common fault-tolerant mechanisms include copy mechanism and erasure code mechanism. [0003] The replica mechanism, also known as the replication mechanism, is the easiest to implement among the fault-tolerant mechanisms and is widely used. It is used in file systems such as HDFS, Ceph, and Swift. GFS, HDFS, and Swift all adopt a three-copy mechanism, that is, each data will be stored in three copies. Taking HDFS as an example, the original file is divided into 64MB or 128MB ...

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 Applications(China)
IPC IPC(8): G06F3/06
CPCG06F3/061G06F3/064G06F3/067
Inventor 胡燏翀徐熙豪张晓阳
Owner HUAZHONG UNIV OF SCI & TECH