System and method for virtualizing network storages into a single file system view

• US 7,606,871 B2
• Filed: 01/03/2003
• Issued: 10/20/2009
• Est. Priority Date: 05/24/2002
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Higuchi, Tatsuo, Okitsu, Jun, Kawamoto, Shinichi, Yasuda, Yoshiko, Ebata, Atsushi
• Primary Examiner(s): Chankong; Dohm
• Application Number:
  US10/335,853
• Publication Number:
  US 20030220985A1
• Time in Patent Office: 2,482 Days
• Field of Search: 709201-203, 709223-226, 707/10, 707/100, 707201-205
• US Class Current: 709/217
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• CPC Class Codes: G06F 3/0643 Management of files
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

A virtualizing file system view method for virtualizing one or more network storage devices into a virtualized file system view network storage system wherein destination network storage information of stored files is compactly held regardless of the number of files, and files are separated into one or more file groups and the file groups managed in destination network storage units. Until now, managing network storage unit information in individual files was necessary however the virtualizing file system view method reduces the management information that must be held and efficiently utilizes network storage capacity without holding destination network storage information in individual files. The cost of rewriting information is also lowered during structural changes such as adding or deleting network storage units since storage destination network information can be rewritten in file groups.

Claims

1. A method for virtualizing a plurality of network storages connected to a network into a virtualized network storage system which can be accessed from a client as a single network storage, the method comprising steps of:

predetermining a group map function which correlates a file to only one file group based on a hash function of a file identifier of the file by using a file inode number I as a search key and a hash value given by the hash function G=Hash (I) which constitutes a file group identifier G;

performing said group map function for at least said file;

creating a file group allocation table which records mutual correlation between each of a plurality of file groups and a destination network storage to store files belonging to a corresponding one of the file groups according to said group map function;

storing each of the grouped files into said destination network storage, respectively;

when a new network storage to become a new destination network storage is being added to said virtualized network storage system, issuing an available remaining capacity acquisition request to each existing destination network storage;

identifying a destination network storage which has a smallest available remaining capacity among the existing destination network storages;

moving files belonging to only one of file groups maintained in the identified destination network storage to said new network storage; and

repeating the steps of issuing, identifying and moving until a difference between an available remaining capacity of said new network storage and said smallest available remaining capacity becomes lower than a threshold.

2. A method for virtualizing a plurality of network storages connected to a network into a virtualized network storage system which can be accessed from a client as a single network storage, the method comprising steps of:

predetermining a group map function which correlates a file to only one file group based on a hash function of a file identifier of the file by using a file inode number I as a search key and a hash value given by the hash function G=Hash (I) which constitutes a file group identifier G;

performing said group map function for at least said file;

creating a file group allocation table which records mutual correlation between each of a plurality of file groups and a destination network storage to store files belonging to a corresponding one of the file groups according to said group map function;

storing each of the grouped files into said destination network storage, respectively;

periodically issuing an available remaining capacity acquisition request to each destination network storage;

when the available remaining capacity of a first destination network storage in said virtualized network storage system drops below a first threshold value, selecting only one file group from among file groups stored in said first destination network storage and said file group as a file group to be moved;

selecting a second destination network storage other than said first destination network storage as a movement destination network storage;

moving files of the selected file group to the second destination network storage;

updating an old mutual correlation between the selected file group and the first destination network storage into a new correlation between the selected file group and the second destination network storage in said file group allocation table; and

repeating the steps of selecting, moving and updating until the remaining available capacity of the first destination network storage exceeds a second threshold value.

3. A method according to claim 2, wherein said second destination network storage has the largest remaining available capacity in said virtualized network storage system.

4. A method according to claim 2, wherein the second threshold value is bigger than the first threshold value.

5. A method for virtualizing a plurality of network storages connected to a network into a virtualized network storage system which can be accessed from a client as a single network storage, the method comprising steps of:

predetermining a group map function which correlates a file to only one file group based on a hash function of a file identifier of the file by using a file inode number I as a search key and a hash value given by the hash function G=Hash (I) which constitutes a file group identifier G;

performing said group map function for at least said file;

creating a file group allocation table which records mutual correlation between each of a plurality of file groups and a destination network storage to store files belonging to a corresponding one of the file groups according to said group map function;

storing each of the grouped files into said destination network storage, respectively;

periodically issuing an available remaining capacity acquisition request to each destination network storage;

when a differential between a maximum available remaining capacity among respective available remaining capacities in respective destination network storages and a minimum available remaining capacity in a first destination network storage of said virtualized network storage system exceeds a first threshold value, selecting only one file group from among file groups stored in said first destination network storage;

selecting a second destination network storage other than said first destination network storage as a movement destination network storage;

moving files of the selected file group to the second destination network storage;

updating an old mutual correlation between the selected file group and the first destination network storage into a new correlation between the selected file group and the second destination network storage in said file group allocation table; and

repeating the steps of selecting, moving and updating until the differential of the remaining available capacities of said first destination network storage drops below a second threshold value.

6. A method according to claim 5, wherein said second destination network storage has the largest remaining available capacity in said virtualized network storage system.

7. A method according to claim 5, wherein the second threshold value is smaller than the first threshold value.