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

Method for accelerating access to key value data storage based on log structure merging tree by utilizing double granularity

A data storage and dual-granularity technology, applied in structured data retrieval, database indexing, storage systems, etc., can solve the problem of high search costs, improve throughput, and alleviate cache failure problems

Pending Publication Date: 2020-08-25
TIANJIN UNIVERSITY OF TECHNOLOGY
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such a design makes it necessary to search layer by layer in the merge buffer layer when the read operation does not hit in the buffer, and its search cost is higher than that of the log structure merge tree.

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
  • Method for accelerating access to key value data storage based on log structure merging tree by utilizing double granularity
  • Method for accelerating access to key value data storage based on log structure merging tree by utilizing double granularity
  • Method for accelerating access to key value data storage based on log structure merging tree by utilizing double granularity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The method for using double granularity to accelerate access to key-value data storage based on log-structure merged tree provided by the present invention will be further described below with reference to the accompanying drawings.

[0026] The structure diagram of the log structure merge tree is as follows figure 1 As shown, the log-structure merge tree usually consists of two parts, one is the memory part and the other is the hard disk part. The memory structure is usually organized into an ordered structure in the form of a jump list or a B-tree, called layer 0, which is used to store key-value pairs recently written, updated, or deleted by the system. The size of layer 0 is usually relatively small. When its capacity reaches the set threshold, the key-value pairs stored in layer 0 will be written sequentially to the first layer of the hard disk structure (forming a file , call it a run). This operation is called a flush operation. The hard drive structure is org...

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 a method for accelerating access to key value data storage based on a log structure merging tree by utilizing double granularity, and belongs to the technical field of key value storage. In order to solve the problem of read performance jitter caused by merging operation of a log structure merging tree, a double-granularity cache is provided, the problem of read performancejitter caused by cache failure due to merging operation is relieved, the read performance of a log structure merging tree is improved, and data of different levels in the log structure merging tree are cached into caches of two different granularities. The coarse-grained cache is used for caching data blocks read by a system by taking the data blocks as units, and the fine-grained cache is used for caching recently accessed key value pairs by taking key value pairs as units. The method has the advantages that the two caches with different granularities are combined into the double-granularitycache, and the structural characteristics of the log structure merging tree are fully utilized to accelerate the reading performance of the log structure merging tree.

Description

technical field [0001] The invention belongs to the technical field of computer storage, and relates to a double-granularity caching method based on log structure merge tree key-value storage. The method proposed by the present invention aims at improving the reading performance of the merge tree key-value storage based on the log structure. Background technique [0002] With the rapid development of the Internet, modern society has entered the era of big data, and the amount of data and visits are growing explosively. Effectively storing and accessing these data has become a key concern in the field of mass storage system technology. In this context, non-relational databases represented by NoSQL emerged as the times require. In NoSQL, the key-value storage engine based on log-structure merged tree has become the mainstream storage engine of key-value storage due to its simplicity, scalability and high performance, such as LevelDB, RocksDB, HBase and Cassandra. A log-struc...

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): G06F16/22G06F16/2455G06F12/122G06F12/123
CPCG06F16/2246G06F16/24552G06F12/122G06F12/123
Inventor 徐光平张硕李响薛彦兵王志岗张桦
Owner TIANJIN UNIVERSITY OF TECHNOLOGY