Priority-Based WAN Cache Object Transfer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wide Area Network (WAN) caching faces bottlenecks due to high network bandwidth consumption in large enterprise environments, particularly in regions with low network bandwidth, as numerous file modifications need to be replicated across sites, leading to inefficiencies in data availability and access.
Innovation Solution
A computer program product and method that determines priorities for cached objects based on measured network bandwidth, allowing higher priority objects to be transferred first during periods of limited bandwidth, using a secondary server to assess object attributes and assign priorities, which are then used by the primary server to manage the transfer of modifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all file modifications are replicated to remote sites immediately, then data availability at remote sites is improved, but network bandwidth consumption increases significantly
Solution Approach 1:
The patent applies local quality by assigning different priorities to different cached objects based on their accessibility and importance at each remote site. Not all modifications are treated equally - the system determines which objects are most important for each specific remote site and prioritizes those for replication, thereby reducing unnecessary bandwidth consumption while maintaining critical data availability.
Solution Approach 2:
The patent changes the parameter of replication priority from uniform to differentiated. By introducing priority levels (high, medium, low) for cached objects based on their accessibility metrics at remote sites, the system dynamically adjusts which modifications are replicated first, optimizing the balance between data availability and bandwidth consumption.
2Productivity
If modifications are replicated without priority ordering, then all cached objects are updated, but network congestion occurs during low bandwidth periods
Solution Approach 1:
The patent introduces dynamics by making the replication process adaptive to network conditions and object priorities. During low bandwidth periods, the system dynamically adjusts replication behavior by focusing first on high-priority objects and deferring low-priority ones, thereby maintaining replication effectiveness without causing network congestion.
Solution Approach 2:
The patent applies preliminary action by pre-determining the priority of cached objects before replication occurs. The system assesses accessibility and importance metrics in advance to establish priority levels, so that when replication needs to occur during constrained bandwidth conditions, the ordering is already predetermined, ensuring critical data is replicated first without waiting for network conditions to improve.
3Speed
If high priority objects are transferred first during low bandwidth periods, then network congestion is minimized, but lower priority objects experience delays
Solution Approach 1:
The patent applies partial action by transferring only the most critical high-priority objects during low bandwidth periods rather than attempting to transfer all objects simultaneously. This selective approach ensures that the most important data is replicated efficiently while accepting that lower-priority objects will experience delays or be transferred during higher bandwidth periods.
Data Source
AI summary
Provided are a computer program product, system, and method for determining priorities for cached objects to order the transfer of modifications of cached objects based on measured network bandwidth. Objects are copied from a primary site to a secondary site to cache at the secondary site. The primary site includes a primary server and primary storage and the secondary site includes a secondary server and a secondary storage. Priorities are received from the secondary server for the objects at the secondary site based on determinations made by the secondary server with respect to the objects cached at the secondary storage. A determination is made of modifications to the objects at the primary storage that are cached at the secondary storage. The received priorities for the objects from the secondary server are used to control a transfer of the determined modifications to the objects to the secondary server.