File server for performing cache prefetching in cooperation with search AP

• US 7,827,178 B2
• Filed: 01/03/2008
• Issued: 11/02/2010
• Est. Priority Date: 06/08/2007
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Ishii, Yohsuke, Akagawa, Etsutaro
• Primary Examiner(s): LEROUX, ETIENNE PIERRE
• Application Number:
  US11/968,699
• Publication Number:
  US 20080306917A1
• Time in Patent Office: 1,034 Days
• Field of Search: 707/3, 707/10, 707/203, 707/736
• US Class Current: 707/736
• CPC Class Codes: G06F 16/172 Caching, prefetching or hoarding of files

Abstract

Provided is a control computer coupled to a storage apparatus for storing a plurality of information resources and a search computer for receiving a search request containing a search condition and transmitting information resource list information containing at least one piece of information regarding an information resource corresponding to the search condition as a search result, the control computer includes a cache memory for storing at least one of the plurality of information resources, in which the control computer is configured to: receive the information resource list information from the search computer; calculate cache priority for each of the information resources based on the received information resource list information; decide at least one information resource to be stored in the cache memory based on the calculated cache priority; and store the decided at least one information resource in the cache memory.

Claims

1. A control computer coupled to a storage apparatus and a search computer, wherein the storage apparatus stores plurality of information resources, and wherein the search computer receives a search request containing a search condition and transmits information resource list information containing at least one piece of information regarding at least one information resource of the plurality of information resources as a search result, the at least one information resource corresponding to the search condition, the control computer comprising;

a processor;

a cache memory that stores the at least one information resource of the plurality of information resources; and

a cache candidate management table that manages the plurality of information resources being considered as candidates for storage in the cache memory, and that stores an accumulated number and a date for each of the plurality of information resources being considered as candidates for storage in the cache memory,

wherein the accumulated number indicates the number of times the information resource is ranked within a range including a highest search hit rank down to a predetermined lower limit search hit rank,

wherein the date indicates a last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank, and

wherein the processor is operable to;

receive the information resource list information from the search computer,

wherein the information resource list information includes a plurality of search result lists, each search result list including names of the information resources high in relevance to the search condition and a search hit rank corresponding to each of the names, the search hit rank being an indicator of relevance to the search condition;

extract, from each of the plurality of search result lists, the names of information resources having a search hit rank within the range including the highest search hit rank down to the predetermined lower limit search hit rank;

calculate, for each information resource having the search hit rank within the range, the accumulated number that indicates the number of times the information resource is ranked within the range;

create a prioritized list that includes the names of the information resources having the search hit rank within the range, and includes the accumulated number corresponding to each information resource, the names of the information resources being listed in a descending order from a highest accumulated number corresponding to each information resource;

calculate, for each information resource having the search hit rank within the range, a cache priority, at least one factor being used for calculating the cache priority,

wherein when the at least one factor for calculating the cache priority includes using the accumulated number corresponding to each information resource, the cache priority is set to correspond to the descending order from the highest accumulated number corresponding to each information resource, such that a highest cache priority is assigned to the information resource having the largest accumulated number;

decide at least one information resource to be stored in the cache memory based on the calculated cache priority; and

store the decided at least one information resource in the cache memory.

2. The control computer according to claim 1,

wherein the control computer is further coupled to at least one client computer which accesses the information resource, and

wherein the processor is further operable to:

receive the search request from the client computer;

transfer the received search request to the search computer; and

transfer the received information resource list information to the client computer of a transmission source of the received search request.

3. The control computer according to claim 1,

wherein the control computer is further coupled to at least one client computer which accesses the information resource and transmits the search request to the search computer, and

wherein the processor is further operable to receive, from the search computer, the information resource list information transmitted as the search result from the search computer to the client computer.

4. The control computer according to claim 1,

wherein when the at least one factor for calculating the cache priority includes using the date corresponding to the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank, the processor is further operable to:

calculate, for each information resource, a passage of time from the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank to the current date,

wherein the cache priority is set to correspond to the ascending order of the calculated passage of time corresponding to each information resource, such that a highest cache priority is assigned to the information resource having a shortest passage of time.

5. The control computer according to claim 1,

wherein when the at least one factor for calculating the cache priority includes using the accumulated number corresponding to each information resource, and using the date corresponding to the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank, the processor is further operable to:

calculate, for each information resource, a passage of time from the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank to the current date,

wherein the cache priority is set to correspond to the descending order from the highest accumulated number corresponding to each information resource, such that a highest cache priority is assigned to the information resource having the largest accumulated number, and is set to correspond to the ascending order of the calculated passage of time corresponding to each information resource, such that a highest cache priority is assigned to the information resource having a shortest passage of time.

6. The control computer according to claim 1, further comprising:

a file system providing data stored in the storage apparatus as files,

wherein the information resource comprises the file provided by the file system or a directory containing at least one file.

14. The access control method according to claim 3,

wherein the control computer is coupled to at least one client computer which accesses the information resource, and

wherein the access control method further comprises the steps of:

receiving the search request from the client computer;

transferring the received search request to the search computer; and

transferring the received information resource list information to the client computer of a transmission source of the received search request.

16. The control computer according to claim 5, wherein the cache priority is calculated using the equation:

P=f(a)/g(B),

wherein P indicates the cache priority, A indicates the accumulated number, and B indicates the passage of time from the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank to the current date.

7. A computer system, comprising:

a control computer coupled to a storage apparatus that stores a plurality of information resources; and

a search computer coupled to the control computer;

wherein the search computer is operable to;

receive a search request containing a search condition;

search at least one information resource corresponding to the search condition; and

transmit information resource list information containing at least one piece of information regarding the searched at least one information resource of the plurality of information resources as a search result,

wherein the control computer comprises a processor, a cache memory that stores the at least one information resource of the plurality of information resources, and a cache candidate management table that manages the plurality of information resources being considered as candidates for storage in the cache memory, and that stores an accumulated number and a date for each of the plurality of information resources being considered as candidates for storage in the cache memory,

wherein the accumulated number indicates the number of times the information resource is ranked within a range including a highest search hit rank down to a predetermined lower limit search hit rank,

wherein the date indicates a last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank,

wherein the processor is operable to;

receive the information resource list information from the search computer,

wherein the information resource list information includes a plurality of search result lists, each search result list including names of the information resources high in relevance to the search condition and a search hit rank corresponding to each of the names, the search hit rank being an indicator of relevance to the search condition;

extract, from each of the plurality of search result lists, the names of information resources having a search hit rank within the range including the highest search hit rank down to the predetermined lower limit search hit rank;

calculate, for each information resource having the search hit rank within the range, the accumulated number that indicates the number of times the information resource is ranked within the range;

create a prioritized list that includes the names of the information resources having the search hit rank within the range, and includes the accumulated number corresponding to each information resource, the names of the information resources being listed in a descending order from a highest accumulated number corresponding to each information resource;

calculate, for each information resource having the search hit rank within the range, a cache priority, at least one factor being used for calculating the cache priority,

wherein when the at least one factor for calculating the cache priority includes using the accumulated number corresponding to each information resource, the cache priority is set to correspond to the descending order from the highest accumulated number corresponding to each information resource, such that a highest cache priority is assigned to the information resource having the largest accumulated number;

decide at least one information resource to be stored in the cache memory based on the calculated cache priority; and

store decided at least one information resource in the cache memory.

8. The computer system according to claim 7,

wherein the control computer is further coupled to at least one client computer which accesses the information resource, and

wherein the processor is further operable to:

receive the search request from the client computer;

transfer the received search request to the search computer; and

transfer the received information resource list information to the client computer of a transmission source of the received search request.

9. The computer system according to claim 7,

wherein the control computer and the search computer are coupled to at least one client computer which accesses the information resource, and

wherein the search computer is further operable to:

receive the search request from the client computer; and

transmit the information resource list information containing the at least one piece of information regarding the searched information resource to the client computer and the control computer.

10. The computer system according to claim 7,

wherein when the at least one factor for calculating the cache priority includes using the date corresponding to the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank, the processor is further operable to:

calculate, for each information resource, a passage of time from the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank to the current date,

wherein the cache priority is set to correspond to the ascending order of the calculated passage of time corresponding to each information resource, such that a highest cache priority is assigned to the information resource having a shortest passage of time.

11. The computer system according to claim 7,

wherein when the at least one factor for calculating the cache priority includes using the accumulated number corresponding to each information resource, and using the date corresponding to the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank, the processor is further operable to:

calculate, for each information resource, a passage of time from the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank to the current date,

wherein the cache priority is set to correspond to the descending order from the highest accumulated number corresponding to each information resource, such that a highest cache priority is assigned to the information resource having the largest accumulated number, and is set to correspond to the ascending order of the calculated passage of time corresponding to each information resource, such that a highest cache priority is assigned to the information resource having a shortest passage of time.

12. The computer system according to claim 7,

wherein the control computer further comprises a file system providing data stored in the storage apparatus as files, and

wherein the information resource comprises the file provided by the file system or a directory containing at least one file.

17. The computer system according to claim 11, wherein the cache priority is calculated using the equation:

P=f(a)/g(B),

wherein P indicates the cache priority, A indicates the accumulated number, and B indicates the passage of time from the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank to the current date.

13. An access control method for a control computer, which is coupled to a storage apparatus and a search computer, wherein the storage apparatus stores a plurality of information resources, and wherein the search computer receives a search request containing a search condition and transmits information resource list information containing at least one piece of information regarding at least one information resource of the plurality of information resources as a search result, the at least one information resource corresponding to the search condition, the control computer comprising a processor, a cache memory that stores the at least one information resource of the plurality of information resources, and a cache management table, the method comprising the steps of:

managing, by the cache candidate management table, the plurality of information resources being considered as candidates for storage in the cache memory, and that stores an accumulated number and a date for each of the plurality of information resources being considered as candidates for storage in the cache memory,

wherein the accumulated number indicates the number of times the information resource is ranked within a range including a highest search hit rank down to a predetermined lower limit search hit rank, and

wherein the date indicates a last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank;

receiving the information resource list information from the search computer,

wherein the information resource list information includes a plurality of search result lists, each search result list including names of the information resources high in relevance to the search condition and a search hit rank corresponding to each of the names, the search hit rank being an indicator of relevance to the search condition;

extracting, from each of the plurality of search result lists, the names of information resources having a search hit rank within the range including the highest search hit rank down to the predetermined lower limit search hit rank;

calculating, for each information resource having the search hit rank within the range, the accumulated number that indicates the number of times the information resource is ranked within the range;

creating a prioritized list that includes the names of the information resources having the search hit rank within the range, and includes the accumulated number corresponding to each information resource, the names of the information resources being listed in a descending order from a highest accumulated number corresponding to each information resource;

calculating, for each information resource having the search hit rank within the range, a cache priority, at least one factor being used for calculating the cache priority,

wherein when the at least one factor for calculating the cache priority includes using the accumulated number corresponding to each information resource, the cache priority is set to correspond to the descending order from the highest accumulated number corresponding to each information resource, such that a highest cache priority is assigned to the information resource having the largest accumulated number;

deciding at least one information resource to be stored in the cache memory based on the calculated cache priority; and

storing the decided at least information resource in the cache memory.

15. The access control method according to claim 13,

wherein the control computer is further coupled to at least one client computer which accesses the information resource and transmits the search request to the search computer, and

wherein the step of receiving the information resource list information comprises receiving, from the search computer, the information resource list information transmitted as the search result from the search computer to the client computer.

18. The access control method according to claim 13,

wherein when the at least one factor for calculating the cache priority includes using the accumulated number corresponding to each information resource, and using the date corresponding to the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank, the processor is further operable to:

calculate, for each information resource, a passage of time from the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank to the current date,

wherein the cache priority is set to correspond to the descending order from the highest accumulated number corresponding to each information resource, such that a highest cache priority is assigned to the information resource having the largest accumulated number, and is set to correspond to the ascending order of the calculated passage of time corresponding to each information resource, such that a highest cache priority is assigned to the information resource having a shortest passage of time.

19. The access control method according to claim 18, wherein the cache priority is calculated using the equation:

P=f(a)/g(B),

wherein P indicates the cache priority, A indicates the accumulated number, and B indicates the passage of time from the last date at which the information resource was determined to be ranked in the range including the highest search hit rank down to the predetermined lower limit search hit rank to the current date.