Server Request Indicator for Load Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Server computing systems experience performance degradation due to high volumes of requests, leading to slower response times, especially when many requests require intensive processing, affecting all requesters.
Innovation Solution
Implementing a system where requesters check an indicator stored in a shared memory to determine if the server is ready to receive requests, delaying transmissions if the server is busy, thereby protecting server resources and optimizing performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the server computing system receives and processes many requests from many requesters, then the service coverage and request handling capacity are improved, but the response time increases and performance deteriorates
Solution Approach 1:
The patent implements a preliminary action by setting an indicator in a shared memory device before the server is actually busy, based on a prediction or threshold condition. Requesters check this indicator before transmitting requests, allowing them to delay transmissions in advance before the server becomes overloaded. This prevents the accumulation of excessive requests that would otherwise cause performance degradation and long response times.
Solution Approach 2:
The patent employs a feedback mechanism where the server computing system monitors its own performance metrics (such as current request processing capacity and response time). When the server detects that it is approaching a performance threshold, it sets an indicator in the shared memory device to signal requesters to delay their requests. This closed-loop feedback allows the system to dynamically adjust request transmission rates to maintain optimal performance.
2Power
If the server computing system processes intensive requests, then the processing capability is improved, but the performance impact spreads to all requesters
Solution Approach 1:
The patent applies preliminary anti-action by having requesters check the indicator in the shared memory device before submitting requests. When the indicator is set (indicating the server is busy or approaching capacity), requesters delay their transmissions. This preemptive measure prevents excessive request loads from being submitted during intensive processing periods, thereby protecting the server's processing capability and maintaining overall system performance.
3Ease of operation
If requesters transmit requests without checking server readiness, then the request submission simplicity is improved, but the server load increases and causes performance degradation
Solution Approach 1:
The patent introduces an intermediary mechanism - a shared memory device containing an indicator - that sits between the requesters and the server computing system. Requesters check this intermediary indicator to determine whether to delay their requests, rather than directly assessing server readiness. This intermediary simplifies the operation for requesters (they only need to check a simple flag) while effectively controlling the load on the server to maintain performance.
Data Source
AI summary
Some embodiments of the present invention include a method for controlling requests to be transmitted to a server computing system. The method generating, by a first requester, a request to be transmitted to a first server computing system, the first requester being part of a first group of requesters, each of the requesters in the first group of requesters is configured to access an indicator to determine whether the first server computing system is ready to receive its request, the indicator being set or reset at least based on a response received from the first server computing system, the indicator stored in a memory device associated with a second server computing system; and based on the indicator indicating that the first server computing system is not ready, delaying from transmitting, by the first requester, the request to the first server computing system.