Method for designating communication paths in a network

• US 7,499,413 B2
• Filed: 01/26/2005
• Issued: 03/03/2009
• Est. Priority Date: 02/28/2001
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Harvey, Nicholas J. A., Vu, Van H., Vesztergombi, Katalin, Lovasz, Laszlo, Lees, William B., Parham, Jeffrey B., Brown, Mark R.
• Primary Examiner(s): Duong; Frank
• Application Number:
  US11/043,607
• Publication Number:
  US 20050256879A1
• Time in Patent Office: 1,497 Days
• Field of Search: None
• US Class Current: 370/256
• CPC Class Codes: H04L 45/04 Interdomain routing, e.g. hierarchical routing
• CPC Class Codes: H04L 45/14 Routing performance; Theoretical aspects
• CPC Class Codes: H04L 45/46 Cluster building

Abstract

A method for designating communication paths in a computer network is provided, in which communication paths are designated for the transmission of data throughout a network. The network may have both recipient computers, which are the intended recipients of the data, and intermediary computers, which are not the intended recipients, but merely relay the data. Each intermediary computer is grouped with the “closest” recipient computer (i.e. the recipient computer with whom it is “least expensive” to communicate). Communication paths between the resulting groups are then identified. A representation of the network is then created. The representation replaces the intermediary computers with the inter-group communication paths, so that the inter-group communication paths appear to pass directly through the locations occupied by the intermediary computers. The created representation is then further processed so that the “least expensive” communication paths may be designated.

Claims

1. One or more computer storage media containing executable instructions that, when executed, implement the following steps:

creating one or more communication groups from a plurality of servers sharing a distributed database, wherein the plurality of servers has one or more replicating servers and at least two intermediate servers, each communication group being created by grouping each a first intermediate server with at least a second intermediate server and a replicating server, wherein the intermediate servers are grouped with the replicating server with which it is optimal for the intermediate servers to communicate;

identifying one or more inter-group communication paths, each inter-group communication path connecting two or more groups;

creating a replication topology representation having a plurality of primary communication paths in which the intermediate servers are replaced with the inter-group communication paths; and

determining optimal communication paths using the replication topology representation.

2. The one or more computer storage media of claim 1, wherein the grouping of intermediate servers with a replicating server further comprises:

for each intermediate server, determining which replicating server of one or more replicating servers has a fastest intra-group communication path to each intermediate server and grouping the intermediate servers with the replicating server providing the fastest intra-group communication path to the intermediate servers.

3. The one or more computer storage media of claim 1, wherein the grouping of intermediate servers with a replicating server further comprises:

for each intermediate server, determining which replicating server of one or more replicating servers has a shortest intra-group path, in terms of physical distance, to each intermediate server and grouping the intermediate servers with the replicating server providing the shortest intra-group path to the intermediate servers.

4. The one or more computer storage media of claim 1, wherein the grouping of intermediate servers with a replicating server further comprises:

for each intermediate server, determining which replicating server of one or more replicating servers has a least expensive, in terms of monetary cost, intra-group communication path to each intermediate server and grouping the intermediate server with the replicating server providing the least expensive intra-group communication path to the intermediate servers.

5. The one or more computer storge media of claim 1, wherein the grouping of intermediate servers with a replicating server further comprises:

for each intermediate server, determining which replicating server of one or more replicating servers has an intra-group communication path with the largest bandwidth to each intermediate server and grouping the intermediate servers with the replicating server providing for the intra-group communication path with the largest bandwidth to the intermediate servers.

6. One or more computer storage media containing executable instructions that, when executed, implement the following steps:

creating a replication topology for a network having replicating computers and intermediary computers, wherein the replicating computers share a common data store and replicate changes to the data store to other replicating computers, by grouping each intermediary computer with the replicating computer with which it is least expensive to communicate, thereby creating one or more shortest-path trees;

determining the total cost of sending replicated changes between pairs of replicating computers via their respective shortest-path trees;

creating a replication path cost map having only replicating computers, wherein each of the pairs of replicating computers is represented as communicating by one or more direct links having a cost equal to the determined total cost;

designating the least expensive, non-redundant paths on the cost map as paths over which the replicating computers can transmit replicated changes to one another;

grouping the computers holding one or more writeable copies of a partition with each other without any intervening computers holding only one or more read-only copies of a partition;

linking the computers holding only one or more read-only copies of a partition with the computers holding one or more writeable copies of a partition; and

grouping the computers holding only one or more read-only copies of a partition to replicate from one or more other computers holding only one or more read-only copies of a partition if required by the replication topology for the network.

7. The one or more computer storage media of claim 6, wherein the replicated changes are disseminated to all of the replicating computers, and wherein the intermediary computers do not incorporate the changes.

8. The one or more computer storage media of claim 6, wherein the network includes one or more bridges, the method further comprising repeating the creating a replication topology, determining, creating a replication cost map, and designating steps for each of the one or more bridges.

9. The one or more computer storage media of claim 6, wherein the network uses one or more schedules, the method further comprising repeating the creating a replication topology, determining, creating a replication cost map, and designating steps for each of the one or more schedules.