Dynamic structural management of a distributed caching infrastructure

Patent metadata

Field	Value
Publication number	US-9767031-B2
Application number	US-98280610-A
Country	US
Kind code	B2
Filing date	Dec 30, 2010
Priority date	Oct 23, 2009
Publication date	Sep 19, 2017
Grant date	Sep 19, 2017

Abstract

Embodiments of the present invention provide a method, system and computer program product for the dynamic structural management of an n-Tier distributed caching infrastructure. In an embodiment of the invention, a method of dynamic structural management of an n-Tier distributed caching infrastructure includes establishing a communicative connection to a plurality of cache servers arranged in respective tier nodes in an n-Tier cache, collecting performance metrics for each of the cache servers in the respective tier nodes of the n-Tier cache, identifying a characteristic of a specific cache resource in a corresponding one of the tier nodes of the n-Tier crossing a threshold, and dynamically structuring a set of cache resources including the specific cache resource to account for the identified characteristic.

First claim

We claim:

1. A data processing system configured with an n-Tier distributed cache, the system comprising:
a plurality of cache resources in respective tier nodes arranged in an n-Tier distributed cache;
an application server with processor and memory configured to host execution of application logic and coupled to the n-Tier distributed cache;
a cache server of a plurality of cache servers with processor and memory providing access to the n-Tier distributed cache;
dynamic distributed cache hierarchy management logic coupled to the n-Tier distributed cache, the dynamic distributed cache hierarchy management logic comprising computer usable program code executable in the memory of the cache server by the processor of the cache server, the computer usable program code when executed establishing a communicative connection to the plurality of the cache servers, collecting performance metrics for each of the cache resources in the respective tier nodes of the n-Tier distributed cache, identifying a characteristic of a specific cache resource in a corresponding one of the tier nodes of the n-Tier distributed cache crossing a pre-determined threshold by identifying a utilization disparity among children cache servers supporting different cache clients in a common set of cache clients and a common parent cache server, and
dynamically structuring a set of the cache resources including the specific cache resource to account for the identified characteristic; and
wherein the identified characteristic is a set of geographically proximate cache devices supporting the different cache clients instead of the utilization disparity amongst the children cache servers in the common set of the cache clients and the common parent cache server.

2. The system of claim 1 , wherein the dynamic structuring of the set of the cache resources is the consolidation of caching support for the different cache clients of the common set of the cache clients in one of the children cache servers demonstrating cache underutilization.

3. The system of claim 1 , wherein the dynamic structuring of the set of the cache resources is the establishment of a partitioned cluster of the geographically proximate cache devices each caching data pertaining to a corresponding unique topic assigned by the cache server of the plurality of cache servers providing access to the n-Tier distributed cache.

4. A computer program product for dynamic structural management of an n-Tier distributed caching infrastructure, the computer program product comprising:
a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code for establishing a communicative connection to a plurality of cache servers arranged in respective tier nodes in an n-Tier distributed cache;
computer readable program code for collecting performance metrics for each of the cache servers in the respective tier nodes of the n-Tier distributed cache; computer readable program code for identifying a characteristic of a specific cache resource in a corresponding one of the tier nodes of the n-Tier distributed cache crossing a predetermined threshold by identifying a utilization disparity amongst children cache servers supporting different cache clients in a common set of cache clients and a common parent cache server; and,
computer readable program code for dynamically structuring a set of cache resources including the specific cache resource to account for the identified characteristic; and
wherein the computer readable program code for identifying the characteristic of the specific cache resource in the corresponding one of the tier nodes of the n-Tier crossing the predetermined threshold, comprises computer readable program code for identifying a set of geographically proximate cache devices supporting one of the children cache servers instead of identifying the utilization disparity amongst the children cache servers in the common set of the cache clients and the common parent cache server.

5. The computer program product of claim 4 , wherein the utilization disparity is an underutilization of one of the children cache servers.

6. The computer program product of claim 5 , wherein the computer readable program code for dynamically structuring the set of the cache resources including the specific cache resource to account for the identified characteristic, comprises computer readable program code for consolidating caching support for the different cache clients of the common set of cache clients in the one of the children cache server demonstrating cache underutilization.

7. The computer program product of claim 4 , wherein the computer readable program code for dynamically structuring the set of the cache resources including the specific cache resource to account for the identified characteristic, comprises computer readable program code for establishing a partitioned cluster of the geographically proximate cache devices, the cache devices individually caching data pertaining to a corresponding unique topic assigned by the respective cache server of the plurality of cache servers arranged in the respective tier nodes in the n-Tier distributed cache.

8. The computer program product of claim 7 , further comprising:
computer readable program code for designating one of the geographically proximate cache devices as a slave device assigned to cache data pertaining to a corresponding assigned unique topic; and,
computer readable program code for designating one of the geographically proximate cache devices as a master device responsible for establishing a routing table of the different unique topics and distributing the routing table to each geographically proximate cache device designated as the slave device.

Assignees

• Antani Snehal S
• Burckart Erik J
• Kelapure Rohit D
• IBM

Inventors

• Antani Snehal S
• Burckart Erik J
• Kelapure Rohit D

Classifications

• G06F2212/264

  Remote server · CPC title

• G06F12/0877 Primary

  Cache access modes · CPC title

• G06F17/30545

  Physics · mapped topic

• G06F17/30457

  Physics · mapped topic

• G06F2212/284

  being distributed · CPC title