A method for implementing scalable storage index structure in cloud environment
An index structure and extended storage technology, applied in the field of cloud storage, can solve problems such as lack of real-time performance, storage index structure does not support range query, etc., to reduce memory overhead, improve query speed, and improve real-time performance.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0031] figure 1 It is a schematic diagram of the two-layer structure of the scalable storage index in the present invention.
[0032] In this example, if figure 1 As shown, the process of establishing a two-tier structure of a master-slave scalable storage index is:
[0033] The entire storage index structure is divided into upper and lower layers. The lower layer consists of multiple local indexes. Each local index is managed by a local index server. The index data is stored in the local index nodes of the lower layer, while the global index of the upper layer acts A positioning and guiding role, managed by the global index server.
[0034] When the storage index is established, the data set to be indexed is first divided into data subsets containing the same amount of data according to the principle of averaging. The number of divided data subsets is equal to that of the local index server in the lower layer. Then, the divided data subsets are in one-to-one correspondence...
example
[0058] 1. The construction process of the scalable storage index structure
[0059] Current Internet applications usually use cloud storage systems to store massive business data, and these cloud storage systems generally use Distributed Hash Table (DHT for short) to provide access access. DHT is a typical example of the key-value model. When data is saved to DHT, the corresponding hash value is first calculated for its key, and then mapped to the corresponding location in the logical space according to the hash value. Because of the discreteness of the hash function, the storage of data is randomly distributed, so the way of storing data in DHT cannot well support range queries. The present invention proposes a secondary index built on the upper layer of the cloud storage system, and its construction process is as follows: Figure 6 shown.
[0060] 1. The storage index structure divides the storage space of the cloud storage system, and sets the spatial scope of each local ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More