Method for forming virtual network storage

• US 7,174,360 B2
• Filed: 09/05/2002
• Issued: 02/06/2007
• Est. Priority Date: 07/23/2002
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Fujiwara, Shinji, Uemura, Tetsuya
• Primary Examiner(s): Nguyen; Van H.
• Application Number:
  US10/234,235
• Publication Number:
  US 20040019655A1
• Time in Patent Office: 1,615 Days
• Field of Search: 709214-217, 709201-203, 709/226, 709/225, 709/213, 711/6, 711/113, 711/114, 711/162, 711/148, 707/102, 707/200, 707/103.R
• US Class Current: 709/201
• CPC Class Codes: H04L 12/4641 Virtual LANs, VLANs, e.g. virtual private networks [VPN] LAN interconnection over a bridge based backbone H04L12/462; encapsulation techniques H04L12/4633; routing of packets H04L45/00; packet switches H04L49/00; virtual private networks for security H04L63/0272
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/288 Distributed intermediate devices, i.e. intermediate devices for interaction with other intermediate devices on the same level
• CPC Class Codes: H04L 67/564 Enhancement of application control based on intercepted application data
• CPC Class Codes: H04L 67/566 Grouping or aggregating service requests, e.g. for unified processing
• CPC Class Codes: H04L 67/59 Providing operational support to end devices by off-loading in the network or by emulation, e.g. when they are unavailable

Abstract

Disclosed is a method for forming a virtual network storage using general network storages and through the processing by a network storage accessing protocol without using any dedicated network storages, concentrated management servers, or distributed directories. The virtual network storage, when receiving a READDIR request from a client, transfers the received READDIR request to each network storage, and receives READDIR responses from the network storages. The virtual network storage then combines the READDIR responses from the network storages and sends the result to the client. This solves the problem caused by increasing the number of network storages wherein a centralized management server becomes a bottleneck that would hinder the improvement of the system scalability, as well as the problem of using dedicated network storages that disables the employment of existing network storages for forming a virtual network storage.

Claims

1. A method of a virtualization controller coupled to a client and a plurality of network storages, and forming a virtual network storage by using said plurality of network storages so that accesses to said plurality of network storages are done just like accesses to one network storage, said method comprising the steps of:

receiving a file list request from said client to said virtualization controller, said file list request being used to request a file list from a virtual directory of said virtual network storage;

transferring first and second file list requests corresponding to said received file list request to each of first and second network storages after converting a source address and a target address of said received file list request for access to each of directories of said first and second network storages, said directories corresponding to said virtual directory, said converted source address being an address of said virtualization controller, said converted target address being an address of said first or second network storage;

receiving a first file list from said first network storage in response to said transferred first file list request;

receiving a second file list from said second network storage in response to said transferred second file list request, said second file list being different from said first file list;

combining both said first and second file lists into a combined file list;

sending said combined file list from said virtualization controller to said client;

receiving a request generated by said client according to said combined file list sent to said client;

determining a network storage to which said received request is to be transferred according to said combined file list received from said network storage;

transferring said request to said determined network storage;

receiving a response from said network storage in response to said transferred request; and

transferring said received response to said client.

2. The method according to claim 1, wherein said method further includes the step of:

encoding an access identifier set in a response from said network storage with use of information specific to said network storage.

3. The method according to claim 1, wherein said method further includes the step of:

storing at least said network storage identification information and said access identifier set in said network storage response in a buffer area.

4. The method according to claim 1 further comprising the step of:

managing the consistency among entry information of said plurality of network storages.

5. The method according to claim 4, wherein said method further includes the steps of:

detecting whether or not an error-occurred network storage is recovered from said error;

checking the consistency between the entry information of said error-occurred network storage and the entry information of said plurality of network storage operating normally so as to manage said consistency among said entry information; and

changing the identifier of entry information in said error-occurred network storage when a consistency error occurs.

6. The method according to claim 4, wherein said method further includes the steps of:

detecting whether or not an error-occurred network storage is recovered from said error;

checking the consistency between the entry information of said error-occurred network storage and the entry information of said plurality of network storage operating normally so as to manage the consistency among said entry information;

generating an inconsistency management entry in said error-occurred network storage when an inconsistency error occurs therein; and

moving said inconsistency-occurred entry to said inconsistency management entry.

7. The method according to claim 4, wherein said method further includes the step of:

registering information of a new network storage; and

wherein said method, upon managing the consistency among said entry information, further includes the steps of;

checking the consistency between the entry information of each of said plurality of network storages included in said virtual network storage and the entry information of said new network storage; and

changing the identifier of said inconsistency-occurred entry information in said new network storage when an inconsistency occurs therein.

8. The method according to claim 4, wherein said method further includes the step of:

registering information of a new network storage; and

wherein said method, upon managing the consistency among said entry information, further includes the steps of;

checking the consistency between the entry information of each of said plurality of network storages included in said virtual network storage and the entry information of said new network storage;

generating an inconsistency management entry in said new network storage when an inconsistency occurs therein; and

moving said inconsistency-occurred entry to said inconsistency management entry.

9. The method according to claim 1 further comprising the steps of:

generating a virtual entry that denotes specific one of said plurality of network storages included in said virtual network storage;

determining whether or not a request from a client is addressed to said virtual entry; and

transferring said request from said client to said specific network storage when said client request is addressed to said virtual entry.

10. The method according to claim 1, wherein said method further comprises the step of:

balancing the load of accesses to said plurality of network storages.

11. The method according to claim 10, wherein said method, upon balancing said load, further includes the steps of:

monitoring the load of each of said plurality of network storages;

selecting one of said plurality of network storages, which has the lowest load; and

transferring a new data write request received from a client to said selected network storage.

12. The method according to claim 10, wherein said method, when balancing said load, further includes the steps of:

monitoring concentration of accesses to each of said plurality of network storages;

monitoring concentration of accesses to a specific entry of each of said plurality of network storages;

specifying a tolerance limit of access concentration to a specific network storage;

identifying each network storage exceeding said tolerance limit according to the result of access concentration monitoring performed for each of said network storages;

identifying an entry on which accesses are concentrated in said network storage that exceeds said tolerance limit; and

moving said entry on which said accesses are concentrated to one of said plurality of network storages, which does not exceed said tolerance limit.

13. The method according to claim 10, wherein said method, when balancing said load, further includes the steps of:

monitoring the load of each of said plurality of network storages;

specifying a tolerance limit of the load deviation among said plurality of network storages;

identifying each of said plurality of network storages, which exceeds said tolerance limit;

identifying an entry that causes a factor for exceeding said tolerance limit among those of said plurality of network storages that exceed said tolerance limit; and

moving said factor entry to any of said plurality of network storages, which does not exceed said tolerance limit.

14. The method according to claim 1 further comprising the step of:

storing information required to operate said virtual network storage in each of said plurality of network storages united into said virtual network storage.

15. The method according to claim 1, further comprising the steps of:

registering the identifier of each of said plurality of network storages;

registering information for accessing each of said plurality of network storages; and

registering information for managing said plurality of network storages.

16. The method according to claim 1, wherein said file list request is a READDIR request.

17. The method according to claim 1, wherein said file list request is used to request a plurality of file handlers of a plurality of files.

18. A method of a virtualization controller coupled to a client and a plurality of network storages, and forming a virtual network storage by using said plurality of network storages so that accesses to said plurality of network storages are done just like accesses to one network storage, said. method. comprising the steps of:

receiving a file list request from said client to said virtualization controller, said file list request being used to request a file list from a virtual directory of said virtual network storage;

transferring file list requests corresponding to said received file list request to each of said plurality of network storages after converting a source address and a target address of said received file list request for access to each of directories of said plurality of network storages, said directories corresponding to said virtual directory, said converted source address being an address of said virtualization controller, said converted target address being an address of said plurality of network storages;

receiving file lists from said plurality of network storages in response to said transferred file list requests, said file lists being different from one other,

determining whether or not each of said received file lists is successful;

combining only successful file lists as determined in said determining step into a combined file list;

sending said combined file list from said virtualization controller to said client;

receiving a request generated by said client according to said combined file list sent to said client;

determining a network storage to which said received request is to be transferred according to said combined file list received from said network storage;

transferring said request to said determined network storage;

receiving a response from said network storage in response to said transferred request; and

transferring said received response to said client.

19. The method according to claim 18, wherein said method further includes the step of:

encoding an access identifier set in a response from said network storage with use of information specific to said network storage.

20. The method according to claim 18, wherein said method further includes the step of:

storing at least said network storage identification information and said access identifier set in said network storage response in a buffer area.

21. A method of a virtualization controller coupled to a client and a plurality of network storages, and forming a virtual network storage by using said plurality of network storages so that accesses to said plurality of network storages are done just like accesses to one network storage, said method comprising the steps of:

receiving a file list request from said client to said virtualization controller, said file list request being used to request a file list from a virtual directory of said virtual network storage;

transferring file list requests corresponding to said received file list request to each of said plurality of network storages after converting a source address and a target address of said received file list request for access to each of directories of said plurality of network storages, said directories corresponding to said virtual directory, said converted source address being an address of said virtualization controller, said converted target address being an address of said plurality of network storages;

receiving file lists from said plurality of network storages in response to said transferred file list requests, said file lists being different from one other;

determining whether or not each of said received file lists is successful;

combining successful file lists selected from among successful responses into a combined successful file list;

sending said combined successful file list as determined in said determining step from said virtualization controller to said client;

receiving a request generated by said client according to said combined successful file list sent to said client;

determining a network storage to which said received request is to be

transferred according to said combined successful file list received from said network storage;

transferring said request to said determined network storage;

receiving a response from said network storage in response to said transferred request, and

transferring said received response to said client.

22. The method according to claim 21, wherein said method further includes the step of:

encoding an access identifier set in a response from said network storage with use of information specific to said network storage.

23. The method according to claim 21, wherein said method further includes the step of:

storing at least said network storage identification information and said access identifier set in said network storage response in a buffer area.

24. A method of a virtualization controller coupled to a client and, a plurality of network storages, and forming a virtual network storage by using said plurality of network storages so that accesses to said plurality of network storages are done just lake accesses to one network storage, said method comprising the steps of:

detecting an operation state of each of a plurality of network storages;

generating an entry that includes error information for each detected error;

receiving a file list request from a client to said virtualization controller, said file list request being used to request a file list from a virtual directory of said virtual network storage;

transferring file list requests corresponding to said received file list request to each of said plurality of network storages after converting a source address end a target address of said received file list request for access to each of directories of said plurality of network storages, said directories corresponding to said virtual directory, said converted source address being an address of said virtualization controller, said converted target address being an address of said plurality of network storages;

receiving file lists from said plurality of network storages in response to said transferred file list requests, said file lists being different from one other;

generating a combined file list in response to said file list request by combining the file lists from network storages operating normally among said plurality of network storages anal the entry information that includes said generated error information;

sending said generated combined file list from said virtualization controller to said client;

receiving a request generated by said client according to said combined file list sent to said client;

determining a network storage to which said received request is to be transferred according to said combined file list received from said network storage;

transferring said request to said determined network storage;

receiving a response from said network storage in response to said transferred request; and

transferring said received response to said client.