File data multiplexing method and data processing system

• US 5,511,177 A
• Filed: 05/27/1994
• Issued: 04/23/1996
• Est. Priority Date: 11/21/1991
• Status: Expired due to Term

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Takamoto, Yoshifumi, Kakuta, Hitoshi, Kagimasa, Toyohiko
• Primary Examiner(s): Kulik, Paul V.
• Application Number:
  US08/250,427
• Time in Patent Office: 697 Days
• Field of Search: 395/438-441, 395/497.01, 395/497.02, 395/182.04, 395/600, 371/10.1, 371/10.2
• US Class Current: 711/114
• CPC Class Codes: G06F 11/2097 maintaining the standby controller/processing unit updated initialisation or re-synchronisation thereof G06F11/1658 and subgroups
• CPC Class Codes: G06F 16/184 implemented as replicated file system
• CPC Class Codes: G06F 2003/0697 device management, e.g. handlers, drivers, I/O schedulers
• CPC Class Codes: G06F 3/0601 Interfaces specially adapted for storage systems
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: G11C 29/74 using duplex memories, i.e. using dual copies
• CPC Class Codes: Y10S 707/99953 Recoverability

Abstract

In a data processing system to which a large number of disk drive units are connected, data in the whole or part area of a file are multiplexed and distributed into a plurality of disk drive units when the file is opened, and the multiplex data of the file are deleted when the file is closed. Among the multiplex data, data shortest in access time or striped data shortest in transfer time is selected to be accessed. When data multiplexing is applied only to the part area, the data storage capacity of the system can be reduced more remarkably.

Claims

1. A file access control method in a computer system which includes a processor and a plurality of drive units for holding files in rotating disk-type medium, wherein an operating system running on said processor provides an access request to said drive units in response to an access request given by one of plural application programs running on said processor;

comprising steps executed by said operating system, the steps including;

monitoring accesses executed during each of predetermined time intervals to ones of files held in said drive units, said ones of said files being opened files for each of which a file open request has been provided by one of the application programs;

selecting at least one of said opened files, based upon said accesses monitored for one of said time intervals, as a file at least part of which is to be duplicated;

storing duplicated data of at least part of said selected one opened file at another one of said drive units;

reading out first data belonging to said part of said one opened file from either one of said one drive unit and said another drive unit, in response to a file read request provided by one of application programs for said first data after the storing of said duplicated data; and

writing second data which should belong to said part of said one file into both of said one drive unit and said another drive unit, in response to a file write request provided by said application program for said second data after the storing of said duplicated data.

2. A method according to claim 1, further comprising:

deleting said duplicated data of said part of said one opened file held in said another drive unit, in response to a file close request provided for said one file by said one application program.

3. A method according to claim 1, wherein said selecting step includes the steps of:

detecting whether the accesses executed to said opened files as monitored for each interval satisfies a predetermined condition which allows one of said opened files to be duplicated;

selecting one of said opened files, in response to detecting that said accesses executed to said opened files, as monitored for one of said time intervals, satisfies the predetermined condition with respect to said one of said opened files.

4. A method according to claim 3, wherein said predetermined condition includes a first condition on a frequency of accesses to each opened file during one of the time intervals.

5. A method according to claim 4, wherein said first condition is that the frequency of accesses made to each opened file during one of the time intervals exceeds a predetermined threshold value.

6. A method according to claim 4, wherein said frequency of accesses includes a frequency of accesses for data read and does not include a frequency of accesses for data write.

7. A method according to claim 6, wherein said first condition is that the frequency of accesses made to said one opened file for data read during one of the time intervals exceeds a predetermined threshold value.

8. A method according to claim 4, wherein said predetermined condition further includes a second condition on average length of data accessed by accesses executed either for data read or data write during one of said time intervals to each opened file.

9. A method according to claim 8, wherein said second condition is that the average length of data accessed by said accesses exceeds a predetermined threshold.

10. A method according to claim 1, wherein the storing step includes storing whole data of one opened file into said another drive unit.

11. A method according to claim 1, wherein the storing step includes storing a number of parts of said one opened file respectively into plural ones of said drive units other than said one drive unit.

12. A method according to claim 1, further comprising the steps of:

monitoring a total amount of free area within each of the drive units;

detecting, in response to an allocation request of a new file provided by one of said application programs, whether there is in one of said drive units a free space large enough to be allocated to said new file, based upon the total amount of free space monitored for said one drive unit; and

deleting one duplicated data stored in said one drive unit by said storing step, so as to make an area occupied by said duplicated area be a free space, if it has been detected that there is no such large free space in said one drive unit.

13. A method according to claim 1, further comprising:

monitoring a total number of files already opened among files held in each drive unit;

comparing drive units other than said one drive unit with each other, regarding the monitored number of files already opened, among files held in each of said other drive unit; and

selecting, based upon a result of the comparing, one of said other drive units which holds a less number of files already opened than others of said other drive units, as said another drive unit.

14. A file access control method in a computer system which includes a processor and a plurality of drive units for holding files in rotating disk-type medium, wherein an operating system running on said processor provides an access request to said drive units in response to an access request given by one of plural application programs running on said processor;

comprising steps executed by said operating system, the steps including;

selecting, as a file at least part of which is to be duplicated, at least one of opened files among said files held in said drive units, said opened files being files for each of which a file open request has been provided by one of the application programs;

monitoring a total number of opened files among files held in each drive unit;

comparing drive units other than one drive unit which holds said selected opened file with each other, regarding the monitored number of already opened files, among files held in each of said other drive unit;

selecting, based upon a result of the comparing, one of said other drive units which holds a less number of files already opened than others of said other drive units, as said another drive unit;

storing duplicated data of at least part of said selected one opened file at another one of said drive units;

reading out first data belonging to said part of said one opened file from either one of said one drive unit and said another drive unit, in response to a file read request provided by one of application programs for said first data after the storing of said duplicated data; and

writing second data which should belong to said part of said one file into both of said one drive unit and said another drive unit, in response to a file write request provided by said application program for said second data after the storing of said duplicated data.

15. A method according to claim 14, further comprising:

monitoring accesses executed during each of predetermined time intervals to said opened files;

wherein said selecting of said one opened file is executed based upon a result of said monitoring executed at one of said intervals.

16. A file access control method in a computer system which includes a processor and a plurality of drive units for holding files in rotating disk-type medium, wherein an operating system running on said processor provides an access request to said drive units in response to an access request given by one of plural application programs running on said processor;

comprising steps executed by said operating system, the steps including;

storing duplicated data of at least part of one of said files held in said drive units at another one of said drive units, in response to a file open request provided for said one file by one of said application programs to said operating system;

reading out first data belonging to said part of said one opened file from either one of said one drive unit and said another drive unit, in response to a file read request provided subsequently by said one application program for said first data;

writing second data which should belong to said part of said one opened file into both of said one drive unit and said another drive unit, in response to a file write request provided subsequently by said one application program for said second data; and

deleting said duplicated data of said predetermined part of said one file held in said another drive unit, in response to a file close request provided for said one file by said one application program.

17. A method according to claim 16, wherein the storing step includes storing whole data of one file already opened into said another drive unit.

18. A method according to claim 16, wherein the storing step includes storing a number of parts of said one opened file respectively into plural ones of said drive units other than said one drive unit.

19. A method according to claim 16, further comprising:

monitoring a total number of files already opened among files held in each drive unit;

comparing drive units other than said one drive unit with each other, regarding the monitored number of files already opened, among files held in each of said other drive unit; and

selecting, based upon a result of the comparing, one of said other drive units which holds a less number of files already opened than others of said other drive units, as said another drive unit.

20. A method according to claim 16, further comprising the steps of:

monitoring a total amount of free area within each of the drive units;

detecting, in response to an allocation request of a new file provided by one of said application programs, whether there is in one of said drive units a free space large enough to be allocated to said new file, based upon the total amount of free space monitored for said one drive unit; and

deleting one duplicated data stored in said one drive unit by said storing step, so as to make an data occupied by said duplicated area be a free space, if it has been detected that there is no such a large free area in said one drive unit.

21. A file access control method in a computer system which includes a processor and a plurality of drive units for holding files in rotating disk-type medium, wherein an operating system running on said processor provides an access request to said drive units in response to an access request given by one of plural application programs running on said processor;

comprising steps executed by said operating system, the steps including;

selecting, as a file at least part of which is to be duplicated, at least one opened file held in one of said drive units, said one opened file being selected from opened files among said files held in said drive units, said opened files being files for each of which a file open request has been provided by one of the application programs;

reading out data belonging to said one opened file from said one drive unit, in response to a file read request subsequently provided by said one application program for said data after the selecting;

transferring said read out data to a buffer area provided within a main storage provided in said computer system as read out data requested by said file read request;

transferring said transferred data from said buffer area into another of said drive units other than said one drive unit, as duplicated data of said part of said one opened file;

reading out first data belonging to said part of said one opened file from either one of said one drive unit and said another drive unit, in response to a file read request provided by one of application programs for said first data after the storing of said duplicated data; and

writing second data which should belong to said part of said one file into both of said one drive unit and said another drive unit, in response to a file write request provided by said application program for said second data after the storing of said duplicated data.

22. A method according to claim 21, further comprising:

monitoring accesses executed during each of predetermined time intervals to said opened files;

wherein said selecting of said one opened file is executed based upon said accesses monitored for one of said time intervals.

23. A method according to claim 21, further comprising the steps of:

monitoring a total number of opened files among files held in each drive unit;

comparing drive units other than one drive unit which holds said selected opened file with each other, regarding the monitored number of files already opened files, among files held in each of said other drive unit; and

selecting, based upon a result of the comparing, one of said other drive units which holds a less number of files already opened than others of said other drive units, as said another drive unit.

24. A method according to claim 21, further comprising:

deleting said duplicated data of said part of said one opened file held in said another drive unit, in response to a file close request provided for said one file by said one application program.