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

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.

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.