Method and device for large-scale seismic data storage and rapid positioning

Abstract

The invention provides a method and a device for large-scale seismic data storage and rapid positioning. The storage method includes the steps: designing a first-level hash index structure, and dividing data object storage space into a plurality of data partitions; designing a second-level hash index structure, and dividing the data partitions into a plurality of data block groups; storing data objects in the belonging data partitions and the belonging data block groups. The rapid positioning method includes the steps: determining the belonging data partitions of the data objects according tofirst hash valves of the data objects; determining belonging object storage servers of the data partitions according to hash ranges of the data partitions processed by the object storage servers; determining belonging data block groups of the data objects through second hash valves of the data objects to obtain object position information. According to the method and the device, object storage space of the large-scale seismic data can be elastically expanded, load balancing can be achieved by the aid of low expenses, and the large-scale seismic data are efficiently managed.

Description

technical field [0001] The invention relates to the field of data storage of petroleum seismic exploration data, and more specifically relates to a method and device suitable for large-scale seismic data storage and rapid positioning. Background technique [0002] In the current oil and gas seismic exploration work, due to the popularization and application of vibroseis high-efficiency acquisition technology and the rapid development of high-density 3D seismic exploration, the sampling accuracy of seismic observation is getting higher and higher, and the collected data is getting larger and larger. The amount of collected data grows exponentially, from tens of terabytes to hundreds of terabytes, or even larger. At the same time, the access frequency of seismic data storage is getting higher and higher due to the concurrent application scale of multi-services. Such a huge data volume and application scale put forward new requirements for seismic data storage technology. The...

AI Technical Summary

Problems solved by technology

However, due to the current status of computer cluster file system technology and the limitations of data location information management and maintenance methods, when facing large-scale seismic data storage and read-write applications, multiple storage servers will cause loads with the expansion of data scale and the increase of applications. Unbalanced, the computer cluster file system will adjust the data distribution according to the disk space utilization and access load of the server

When performing load balancing, for a system that manages storage space by recording locations, the migration of a large number of seismic data object files will lead to frequent changes in data location information, and the system overhead and workload of object location information consistency will increase.

Due to the large scale of mapping between the seismic data to be maintained and the object storage server, the total amount of mapping relationship information managed and maintained by the storage server will greatly exceed the system memory capacity of the server, and the efficiency of data storage and the scalability of space are very low.

Images