System and method for determining target failback and target priority for a distributed file system

• US 7,584,220 B2
• Filed: 02/07/2005
• Issued: 09/01/2009
• Est. Priority Date: 10/01/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Colville, Scott Eric, Bozeman, Patrick, Wickrematillake, Supriya, Pudipeddi, Ravisankar V., Gupta, Mukul, Shankar, Ramesh, Lovinger, Daniel Edward
• Primary Examiner(s): Wong; Don
• Assistant Examiner(s): Nguyen; Kim T
• Application Number:
  US11/053,386
• Publication Number:
  US 20060085428A1
• Time in Patent Office: 1,667 Days
• Field of Search: 707/100, 707/205, 707/200
• US Class Current: 1/1
• CPC Class Codes: G06F 16/13 File access structures, e.g. distributed indices arrangements of input from, or output to, record carriers G06F3/06
• CPC Class Codes: G06F 16/182 Distributed file systems
• CPC Class Codes: Y10S 707/99953 Recoverability

Abstract

A system and method for organizing and sorting targets received in a referral response and for realizing a target fail-back and a target priority policy in a distributed file system is provided. In one embodiment, a sorting method includes receiving a referral response in the form of a list of targets that are sorted into bounded sets. Having a sorted referral response in bounded sets provides a basis for implementing a target fail-back and a target priority policy. The computer system may select a target from a sorted list of targets sorted according to site-cost and/or target priority. Then, the computer system may determine if the set target is associated with a more preferred target when compared to all available targets in the sorted list and if not, switch back to a more preferred target.

Claims

1. In a computer system, a method for locating a file in a network of computers, the method comprising:

requesting, by a client computer, a location of a file located on at least one server computer in a network of server computers;

receiving, by the client computer, a list of a plurality of targets, each of the plurality of targets corresponding to a location in the network of server computers storing the file, wherein the plurality of targets are sorted into bounded sets based on a site-cost of each target such that each bounded set is associated with a same site-cost, wherein the site-cost is associated with at least one parameter of a network that is used in retrieving the file between one of the plurality of targets and the client computer, the plurality of targets within each bounded set being further sorted based on a priority assigned to each target;

selecting, by the client computer, a first target on the list of the plurality of targets for accessing the file, wherein the first target has the lowest site-cost of any available target on the list of the plurality of targets;

for a subsequent access to the file, the client computer determining if a lower site-cost target from the list of the plurality of targets is available that has a lower site-cost than the first target; and

in response to a lower site-cost target being available, the client computer accessing the file using the lower site-cost target.

2. The method of claim 1 wherein the list of targets comprises boundary attributes, including a site-cost between a target and the client computer.

3. The method of claim 1 wherein boundaries of each bounded set are based at least partially on the location of the server computer associated with each target.

4. The method of claim 1 wherein boundaries of each bounded set are based at least partially on a health indication associated with the server computer associated with each target.

5. The method of claim 1, wherein the determining if a lower site-cost target is performed whenever a target fail-back policy pertaining to the lower site-cost target is applied.

6. The method of claim 5, wherein the target fail-back policy is associated with the list of targets.

7. The method of claim 5, wherein the target fail-back policy is associated with a root that may be associated with each individual target in the list of targets.

8. The method of claim 1, further comprising removing at least one target from the list of targets based on an exclusion policy.

9. The method of claim 1, wherein the list of targets is ordered such that targets having a target-priority setting of global high are ordered at the top of a respective bounded set and targets having a target-priority setting of global low are ordered at the bottom of the respective bounded set.

10. A distributed computing system, comprising:

a server computer operably coupled to a network, the server computer operable to;

create a list of a plurality of targets;

sort the list of targets according to a site-cost of each of the plurality of targets, the site-cost associated with at least one parameter of a network that is used in retrieving the file from a server computer corresponding to one of the plurality of targets to the client computer requesting the file;

further sort the list of targets according to a priority assigned to each server computer corresponding to one of the plurality of targets; and

provide the list to a client computer in response to a request for a file;

the client computer coupled to the network, the client computer operable to;

request and retrieve files from other computers coupled to the network,

select a first target on the list of the plurality of targets for accessing the file, wherein the first target has the lowest site-cost of any available target on the list of the plurality of targets,

for a subsequent access to the file, determine if a lower site-cost target from the list of the plurality of targets is available that has a lower site-cost than the first target, and

in response to a lower site-cost target being available, access the file using the lower site-cost target, and

at least one additional server computer storing a requested file thereon that corresponds to at least one of the targets.

11. The distributed computer system of claim 10 wherein the server computer is further operable to sort the list of targets into bounded sets such that each target in a respective bounded set is associated with the same site-cost as other targets in the respective bounded set and such that the bounded sets are sorted according to the site cost associated with each target in the bounded set.

12. The distributed computer system of claim 11 wherein the server computer is further operable to sort each target within each bounded set according to the priority assigned to each server computer.

13. The distributed computer system of claim 12 wherein the client computer is further operable to determine if the lower site-costs target is associated with a more preferred priority when compared to other targets in the list of targets, and access the file using a target having a more preferred priority.

14. In a computer system, a method for locating a file in a network of computers, the method comprising:

receiving a request, from a client computer, for a location of a requested file that is located on at least one server computer in a network of server computers;

determining a plurality of locations in the network of server computers in which the requested file is located;

generating a list of a plurality of targets, each of the plurality of targets corresponding to a location in the network of server computers storing the requested file;

sorting the list of the plurality of targets into bounded sets based on a site-cost of each target such that each bounded set is associated with a same site-cost, wherein the site-cost is associated with at least one parameter of a network that is used in retrieving the file between one of the plurality of targets and the client computer;

further sorting the list of the plurality of targets according to a priority assigned to each server computer corresponding to one of the plurality of targets; and

specifying a target fail-back policy in the list of the plurality of targets, the target fail-back policy indicating whether a lower site-cost target listed on the list of the plurality of targets can be used to access the file after a higher site-cost has been used to access the file; and

providing an indication of the list of the plurality of targets and the target fail-back policy to the client computer.

15. The method of claim 14, wherein the further sorting the list of the plurality of targets according to a priority comprises sorting the list of the plurality of targets such that each target within each bounded set is ordered according to a priority assigned to each server computer corresponding to one of the plurality of targets.

16. The method of claim 15, wherein the further sorting the list of the plurality of targets according to a priority comprises ordering targets having a target-priority setting of global high at the top of a respective bounded set and ordering targets having a target-priority setting of global low at the bottom of the respective bounded set.