Destination Transaction Accelerator Pre-Acknowledgement Throttling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In network communication systems, pre-acknowledgement of transactions can lead to data loss when the server-side transaction accelerator or LAN connection is inadequate, causing bottlenecks and potential data loss due to premature acknowledgement of writes before they are fully processed.
Innovation Solution
A system with a destination-side transaction accelerator that includes a queue for managing writes, memory for storing status, and logic to adjust pre-acknowledgement rules based on the destination-side queue status, ensuring that pre-acknowledgements are only sent when the server can process them, thereby preventing data loss and optimizing server resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If pre-acknowledgement of writes is implemented at the source-side transaction accelerator, then performance is improved by allowing asynchronous writes to complete faster, but data loss occurs when the server or LAN connection degrades
Solution Approach 1:
The destination-side transaction accelerator monitors the status of the destination queue and sends feedback signals to the source-side transaction accelerator. When the destination queue is full or degrading, the feedback mechanism causes the source-side accelerator to stop or slow down pre-acknowledging writes, preventing data loss while maintaining high performance during normal operation
Solution Approach 2:
The system dynamically adjusts the rate of pre-acknowledgement based on real-time conditions at the destination. The destination-side accelerator modifies its behavior according to queue status, and this dynamic adjustment is communicated back to the source-side accelerator, creating a adaptive system that balances performance and reliability
2Productivity
If pre-acknowledgements are sent at a high rate to maximize performance, then productivity increases, but the server may be overwhelmed causing connection termination
Solution Approach 1:
The destination-side transaction accelerator continuously monitors server load and queue status, providing feedback to the source-side accelerator. When the server is approaching capacity or the queue is filling up, the feedback mechanism reduces the pre-acknowledgement rate, preventing server overload while maintaining high throughput during normal conditions
Solution Approach 2:
The system performs preliminary monitoring of destination queue status before sending pre-acknowledgements. By checking the state of the destination queue in advance, the source-side accelerator can adjust its pre-acknowledgement behavior proactively, preventing server overload before it occurs
Data Source
AI summary
In a system where transactions are accelerated with asynchronous writes that require acknowledgements, with pre-acknowledging writes at a source of the writes, a destination-side transaction accelerator includes a queue for queue writes to a destination, at least some of the writes being pre-acknowledged by a source-side transaction accelerator prior to the write completing at the destination, a memory for storing a status of a destination-side queue and possibly other determinants, and logic for signaling to the source-side transaction accelerator with instructions to alter pre-acknowledgement rules to hold off on and pursue pre-acknowledgements based on the destination-side queue status. The rules can take into account adjusting the flow of pre-acknowledged requests or pre-acknowledgements at the sender-side transaction accelerator based at least on the computed logical length.