Shared Data Fabric Client Reset via Status Communication Blocking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In shared data fabric systems, resetting a processing client while status communications are outstanding can lead to unintended consequences such as system failures or degraded performance due to unhandled status requests and processing credits.
Innovation Solution
The system intercepts, blocks, and spoofs status communications to temporarily mark the processing client as offline, allowing it to service requests without affecting other clients, then resets the client while managing processing credits and flow control checks to prevent errors and inefficiencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a processing client is reset during operation in a shared data fabric system, then the processing client can be restarted without system shutdown, but system failures or degraded performance occur due to outstanding status communications
Solution Approach 1:
The system performs preliminary actions before resetting the processing client by intercepting and blocking status communications destined for the client. This prevents outstanding status requests from causing errors during the reset process, allowing the client to be restarted without system failure while maintaining system stability
Solution Approach 2:
The system introduces an intermediary mechanism that intercepts status communications between other processing clients and the target processing client. This intermediary blocks or spoofs status requests during the reset process, preventing communication errors while allowing the reset to proceed, thus resolving the contradiction between reset capability and system reliability
2Productivity
If status communications are allowed to pass during processing client reset, then communication continuity is maintained, but unhandled status requests cause system failures
Solution Approach 1:
The system extracts problematic status communications from the normal communication flow by intercepting them before they reach the resetting processing client. By removing these outstanding status requests from the system, communication continuity is maintained for other clients while preventing the specific failure mode that would occur if these requests were allowed to pass through to the reset client
3Device complexity
If processing credits are not managed during reset, then resource allocation remains simple, but processing credits are lost causing degraded system performance
Solution Approach 1:
The system performs preliminary credit management actions before the processing client reset by identifying and preserving processing credits associated with the client. This preliminary preservation prevents credit loss during reset, maintaining system performance without requiring complex real-time credit management mechanisms during the reset process itself
Data Source
AI summary
A processing system that includes a shared data fabric resets a first client processor while operating a second client processor. The first client processor is instructed to stop making requests to one or more devices of the shared data fabric. Status communications are blocked between the first client processor and a memory controller, the second client processor, or both, such that the first client processor enters a temporary offline state. The first client processor is indicated as being non-coherent. Accordingly, when the processor is reset some errors and efficiency losses due messages sent during or prior to the reset are prevented.