摘要:
In a file server for suppressing power consumption of a storage apparatus, when a file sharing program receives a file access from a client, the program references a mapping table. The program addresses the access to the target file in the volume of a RAID group where the target file is stored. A coupling-request reception program memorizes a coupling time for each user into a coupling history table. A grouping program applies a grouping to users whose coupling time-zones are similar. A data transfer program transfers, into the same RAID group, data of the files associated with the grouped users, thereby collecting the data into the same RAID group. Thus, the time-zone when no access is made to the RAID group (i.e., non-coupling time-zone) can be made longer. Accordingly, a spin-up/down request program makes a spin-down request to the RAID group in the non-coupling time-zone.
摘要:
Decrease in the write speed is prevented even when overwriting the entire file. When a NAS apparatus receives a file size change request from a computer as an access request source for changing the size of a file, the NAS apparatus creates a new file related to the file in a file system with a processing performance that is higher than a file system containing the file as an entity of that file, associates the new file and the foregoing file, deletes the file on the condition that the new file and the file has been associated, and executes data write processing of writing data into the new file on the condition of subsequently receiving a data write request from the access request source for writing data into the file.
摘要:
In order to provide HSM that can effectively use the storage capacity of an upper Tier in an HSM system, a lower Tier of the HSM system detects a group of files having the same data content from a plurality of files stored in the lower Tier, and keeps at least one of the real data of the group of files having the same data content while deleting the rest of the data. The upper Tier receives the process result from the lower Tier. Then, in response to a read request from the host computer that specifies a file included in the group of files and transferred to the upper Tier from the lower Tier, the upper Tier identifies the at least one of the data that is kept and corresponding to the specified file, and responds to the host computer.
摘要:
When receiving a file access from the client, the file access program refers to the mapping table, and processes an access to files of on volumes of RAID groups. The file server analyzes the file access states, and groups the files depending on the access time period, defines the file migration pattern based on the grouping, migrates the files, and then carries out a power management operation like a spin-down/-up operation on the RAID groups based on the migration pattern.
摘要:
There is provided a file management method of a hierarchy management file system capable of preventing an access performance from dropping when a user accesses to a file. According to the method, a server creates file systems in high-speed and low-speed volumes and a file-sharing server virtually integrates those file systems into one system as a pseudo file system. Then, the server moves a file to be moved to the file system created in the low-speed volume in advance, not when an access is made to the file. When a user accesses to the file after that, the user directly accesses to destination without requiring to copy the file, so that the accessing performance may be prevented from dropping.
摘要:
A computer apparatus which integrates at least two or more services of user management domains has a processor, a memory and an interface. The processor receives an access request, specifies an access source domain, specifies an access target domain, and judges whether the specified access source domain matches the specified access target domain. If the access source domain is different from the access target domain, the processor extracts a user ID of the specified access source domain from the received access request, and refers to ID conversion information indicating correspondence of user IDs between the user management domains whose services are integrated to convert the extracted user ID of the access source domain into a user ID of the specified access target domain. Thus, loads of configuration at the time of service integration are reduced.