METHOD AND SYSTEM FOR FILE RELOCATION

• US 20090287751A1
• Filed: 05/14/2009
• Published: 11/19/2009
• Est. Priority Date: 05/16/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hasegawa, Tohru, Kamiya, Masanori
• Granted Patent: US 9,256,272 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 1/3221 of disk drive devices
• CPC Class Codes: G06F 16/10 File systems; File servers
• CPC Class Codes: G06F 16/119 Details of migration of file systems migration mechanisms in storage systems G06F3/0647
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G11B 27/105 of operating discs
• CPC Class Codes: H04N 21/84 Generation or processing of descriptive data, e.g. content descriptors systems specially adapted for using meta-information in broadcast systems H04H60/73
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A method and system for file relocation is provided. A file relocation system is connected to multiple storage devices. The system obtains a number of times that each of a number of files stored on the multiple storage devices is requested simultaneously with a concerned file. The relocation system then classifies multiple files into multiple groups, such that groups of files simultaneously are put together into one group. Multiple files classified in to the same group are then relocated to a single storage device. The relocation system then switches a storage device not accessed for a certain period of time into a power-saving mode.

Claims

1. A file relocation method comprising:

reading access request history information of each a plurality of files;

determining a quantity of access requests that each of the plurality of files has been requested simultaneously with a concerned file;

classifying the plurality of files into a plurality of groups, each group comprising a group of files that are simultaneously repeatedly accessed requested with the concerned file;

relocating a group of files into a storage device; and

invoking a power-saving mode in a storage device not accessed for a predetermined time.

2. The method of claim 1 further comprising:

the access request history information including a list of access requests containing identification information of each file accessed, the access requests listed in the order that they are received; and

determining the quantity of simultaneous access requests that each of the plurality of files has been requested to be accessed with the concerned file, wherein access requests within a defined time period surrounding an access request of the concerned filed are regarded as being accessed simultaneously with the concerned file.

3. The method of claim 2 further comprising:

(a) calculating a co-occurrence vector for each file to be relocated, the co-occurrence vector containing an access request frequency component, the access request frequency component comprising the frequency that each file to be relocated was access requested simultaneously with the concerned file;

(b) determining a reference co-occurrence vector, the reference co-occurrence vector containing an access request frequency component of a most requested file of the plurality of files to be relocated;

(c) calculating an inner product of the co-occurrence vector of each file of the plurality of files to be relocated;

(d) classifying files having an inner product equal to or greater than a predetermined value into a group, the group including the most requested file that contains the reference co-occurrence vector; and

(e) acquiring K, where K is the number of storage devices into which files are to be relocated; and

(f) repeating steps b through d for ungrouped files K-1 number of times, on condition that there is a file whose inner product with the reference co-occurrence vector is equal to or greater than the predetermined value in the step.

4. The method of claim 3 further comprising:

excluding files having a low access request frequency component from the plurality of files stored in the plurality of storage devices.

5. The method of claim 4 further comprising:

defining a plurality of time periods by equally dividing a unit observation time, the unit observation time for observing access requests of each file; and

associating each file with one time period where the file was access requested the largest number of times.

6. A file relocation method implemented in a controller that controls input and output of a plurality of storage devices, the method comprising the steps of:

reading history information on access requests for each file of a plurality of files from a memory of the controller;

obtaining an access request frequency for each file of the plurality of files, the access request frequency comprising the frequency that each file was accessed requested simultaneously with a concerned file;

classifying the plurality of files into a plurality of groups of files, each group of files comprising a plurality of files with similar access request frequencies;

relocating a group of files to one of the storage devices;

monitoring access requests of the plurality of storage devices; and

invoking a power-saving mode on a storage device of the plurality of storage devices when the storage device is not accessed for a fixed time.

7. The method of claim 6 further comprising:

the access request history information including a list of access requests containing identification information of each file accessed, the access requests listed in the order that they are received; and

determining the quantity of simultaneous access requests that each of the plurality of files has been requested to be accessed with the concerned file, wherein access requests within a defined time period surrounding an access request of the concerned filed are regarded as being accessed simultaneously with the concerned file.

8. The method of claim 7 further comprising:

(a) calculating a co-occurrence vector for each file to be relocated, the co-occurrence vector containing an access request frequency component, the access request frequency component comprising the frequency that each file to be relocated was access requested simultaneously with the concerned file;

(b) determining a reference co-occurrence vector, the reference co-occurrence vector containing an access request frequency component of a most requested file of the plurality of files to be relocated;

(c) calculating an inner product of the co-occurrence vector of each file of the plurality of files to be relocated;

(d) classifying files having an inner product equal to or greater than a predetermined value into a group, the group including the most requested file that contains the reference co-occurrence vector; and

(e) acquiring K, where K is the number of storage devices into which files are to be relocated; and

(f) repeating steps b through d for ungrouped files K-1 number of times, on condition that there is a file whose inner product with the reference co-occurrence vector is equal to or greater than the predetermined value.

9. The method of claim 8 further comprising:

excluding files having a low access request frequency component from the plurality of files stored in the plurality of storage devices.

10. The method of claim 9 further comprising:

defining a plurality of time periods by equally dividing a unit observation time, the unit observation time for observing access requests of each file; and

associating each file with one time period where the file was access requested the largest number of times.

11. A relocation apparatus coupled to a plurality of storage devices and relocates a plurality of files stored in the plurality of storage devices, the apparatus comprising:

a history information storage for storing history information of access requests to each of the plurality of files;

a counter for obtaining an access request frequency for each file of the plurality of files, the access request frequency comprising the frequency that each file was accessed requested simultaneously with a concerned file;

a classifier for classifying the plurality of files into a plurality of groups of files, each group of files comprising a plurality of files with similar access request frequencies;

a relocating unit for relocating a group of files to one of the storage devices; and

a switching unit for invoking a power-saving mode on a storage device of the plurality of storage devices when the storage device is not accessed for a fixed time.

12. The apparatus of claim 11 further comprising:

the access request history information including a list of access requests containing identification information of each file accessed, the access requests listed in the order that they are received; and

the counter regarding access requests within a defined time period surrounding an access request of the concerned filed are regarded as being accessed simultaneously with the concerned file.

13. The apparatus of claim 12 further comprising:

a co-occurrence vector calculating unit for calculating a co-occurrence vector for each file to be relocated, the co-occurrence vector containing an access request frequency component, the access request frequency component comprising the frequency that each file to be relocated was access requested simultaneously with the concerned file;

;

a co-occurrence vector determining unit for determining a reference co-occurrence vector, the reference co-occurrence vector containing an access request frequency component of a most requested file of the plurality of files to be relocated; and

a judging unit for calculating an inner product of the co-occurrence vector of each of the ungrouped files and the reference co-occurrence vector, and for judging if each of the calculated inner products is equal to or larger than a predetermined number, wherein

the classifier classifies a file determined as having the co-occurrence vector equal to or larger than the predetermined value by the judging unit, into the same group as the file having the reference co-occurrence vector.