Load based file allocation among a plurality of storage devices

• US 8,522,252 B2
• Filed: 08/27/2012
• Issued: 08/27/2013
• Est. Priority Date: 08/29/2007
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Nirvanix Incorporated
• Inventors: Chatley, Scott P., Phan, Thanh T., Gatchell, Troy C.
• Primary Examiner(s): FENNEMA, ROBERT E
• Application Number:
  US13/595,959
• Publication Number:
  US 20120323844A1
• Time in Patent Office: 365 Days
• Field of Search: None
• US Class Current: 718/105
• CPC Class Codes: A61P 17/00 Drugs for dermatological disorders
• CPC Class Codes: G06F 16/185 Hierarchical storage management [HSM] systems, e.g. file migration or policies thereof details of archiving G06F16/11
• CPC Class Codes: G06F 2206/1012 Load balancing
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• 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 67/101 based on network conditions
• CPC Class Codes: H04L 67/1012 based on compliance of requirements or conditions with available server resources
• CPC Class Codes: H04L 67/1021 based on client or server locations
• 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]

Abstract

A method for balancing loads among a plurality of data storage devices, includes: receiving a request from a user device to download a data file; identifying a first set of storage devices containing the requested data file, wherein the first set comprises one or more storage devices; identifying a first storage device from the set that is currently least busy among the storage devices in the first set, and directing the first storage device to serve the request; determining if the first storage device is too busy; and if the first storage device is too busy copying the requested data file to a second storage device which did not previously store the data file, thereby adding the second storage device to the first set of storage devices containing the requested data file.

Claims

1. A method for balancing loads among a plurality of data storage devices, comprising:

receiving a request from a user device to download a data file;

identifying a first set of storage devices containing the requested data file, wherein the first set comprises first and second storage devices each storing a copy of the requested data file;

determining whether one or more redundant copies of the requested file from the first set of storage devices should be deleted based at least in part on a number of current access requests for the file, wherein determining whether one or more redundant copies of the requested file should be deleted comprises;

determining whether a quotient, provided by a total number of current access requests for the file divided by a total number of copies of the files stored in the first set, is lower than a predetermined threshold, wherein if the quotient is lower than the predetermined threshold, the one or more redundant copies are designated to be deleted.

2. The method of claim 1 further comprising determining how many redundant copies to delete based on the formula:

N=CFC−

(T/CAC), where N is the number of redundant copies to delete, CFC is the total number of copies of the requested file stored in the first set, T is a predetermined threshold selected based on a desired average load upon the first set of storage devices, and CAC is the total number of current access requests for the data file.

3. The method of claim 2 further comprising:

designating the N redundant files to be deleted as “

offline”

so they cannot be accessed; and

deleting the N redundant files as a backend process which is transparent to end users who access files from the first set of storage devices.

4. The method of claim 2 wherein the N redundant copies designated for deletion comprise the N most recently stored copies of the data file.

5. A system for balancing loads among a plurality of storage servers within a storage node, comprising:

a node manager server for receiving a request from a user device to download a data file;

a plurality of storage servers contained within a first storage node for storing one or more copies of the data file;

a transfer server coupled to the plurality of storage servers for downloading the data file requested by users;

wherein the node manager server comprises;

a first module for receiving the request from the user device to download the data file;

a second module for identifying a first set of storage servers among the plurality of storage servers in the node containing the requested data file, wherein the first set comprises first and second storage servers each storing a copy of the requested data file;

a third module for determining whether one or more redundant copies of the requested file from the first set of storage servers should be deleted based at least in part on a number of current access requests for the file, wherein fifth module comprises;

a fourth module for determining whether a quotient, provided by a total number of current access requests for the file divided by a total number of copies of the files stored in the first set, is lower than a predetermined threshold, wherein if the quotient is lower than the predetermined threshold, the one or more redundant copies are designated to be deleted.

6. The system of claim 5 further comprising a fifth module for determining how many redundant copies to delete based on the formula:

N=CFC−

(T/CAC), where N is the number of redundant copies to delete, CFC is the total number of copies of the requested file stored in the set, T is a predetermined threshold selected based on a desired average load upon the set of storage devices, and CAC is the total number of current access requests for the data file.

7. The system of claim 6 further comprising:

a sixth module for designating the N redundant files to be deleted as “

offline”

so they cannot be accessed; and

a seventh module for deleting the N redundant files as a backend process which is transparent to the user.

8. The system of claim 6 wherein the N redundant copies designated for deletion comprise the N most recently stored copies of the data file.

9. A non-transitory computer readable medium storing computer executable instructions that when executed perform a process for balancing loads among a plurality of storage servers within a storage node, the instructions comprising:

a first code module for receiving a request from a user device to download a data file;

a second code module for identifying a first set of storage servers among a plurality of storage servers in a first node containing the requested data file, wherein the first set comprises first and second storage servers each storing a copy of the requested data file;

a third code module for determining whether one or more redundant copies of the requested file from the first set of storage servers should be deleted based at least in part on a number of current access requests for the file, wherein fifth code module comprises;

a fourth code module for determining whether a quotient, provided by a total number of current access requests for the file divided by a total number of copies of the files stored in the first set, is lower than a predetermined threshold, wherein if the quotient is lower than the predetermined threshold, the one or more redundant copies are designated to be deleted.

10. The non-transitory computer readable medium of claim 9 further comprising a fifth code module for determining how many redundant copies to delete based on the formula:

N=CFC−

(T/CAC), where N is the number of redundant copies to delete, CFC is the total number of copies of the requested file stored in the first set, T is a predetermined threshold selected based on a desired average load upon the set of storage devices, and CAC is the total number of current access requests for the data file.

11. The non-transitory computer readable medium of claim 10 further comprising:

a sixth code module for designating the N redundant files to be deleted as “

offline”

so they cannot be accessed; and

a seventh code module for deleting the N redundant files as a backend process which is transparent to the user.

12. The non-transitory computer readable medium of claim 10 wherein the N redundant copies designated for deletion comprise the N most recently stored copies of the data file.