PCI Express Switch Hot-Plug Control for System Continuity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge lies in dynamically securing and managing input/output (I/O) spaces for PCI Express switches during HotPlug operations, as existing methods struggle to prevent system and service disruptions when replacing switches or I/O devices, especially due to the need for power supply management and allocation of continuous I/O regions.
Innovation Solution
A switching control device that monitors access to a host computer, extracts and stores setting information from a primary switch, and sets this information on a secondary switch, allowing seamless switching without rebooting the system when a fault occurs, thereby maintaining continuous operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of repair
If a PCI Express switch is replaced by stopping the power supply, then the switch can be replaced, but system and service disruptions occur
Solution Approach 1:
The patent applies preliminary action by pre-configuring a backup switch with identical settings before the primary switch fails. The backup switch is prepared in advance with all necessary configuration parameters, allowing immediate switchover without power disruption when the primary switch fails.
Solution Approach 2:
The patent introduces an intermediary mechanism through the backup switch that mediates between the primary switch failure and system continuity. The backup switch acts as a mediator that takes over the primary switch's function, enabling replacement without direct impact on system operation.
2Reliability
If HotPlug is used to replace switches, then power supply can be maintained, but I/O space allocation and management become complex
Solution Approach 1:
The patent applies copying by creating a backup switch that is configured with identical settings and parameters as the primary switch. This copy allows the backup to assume the primary's function seamlessly, simplifying the management complexity by having pre-configured duplicates rather than managing complex dynamic allocations.
Solution Approach 2:
The patent segments the switch system into primary and backup components, separating the active function from the standby function. This segmentation allows independent management of each switch while maintaining overall system simplicity, as each segment has well-defined roles and configurations.
3Reliability
If redundancy is provided for switch failure, then system continuity is improved, but device complexity increases
Solution Approach 1:
The patent uses copying to create a backup switch that is an exact replica of the primary switch in terms of configuration and settings. This copying approach improves reliability through redundancy while minimizing complexity by using identical, pre-configured components rather than complex adaptive systems.
Solution Approach 2:
The patent applies parameter changes by switching from the primary switch to the backup switch by changing the active configuration parameters. This simple parameter switching mechanism enables system continuity without requiring complex reconfiguration, as only the active switch identifier needs to change rather than entire system parameters.
Data Source
AI summary
There is provided a switching control device configured to control switching of an access of a host computer communicating with a first switch connected to a first input/output device and a second switch connected to a second input/output device, the switching control device including: a monitor configured to monitor an access of the host computer to the first computer; a memory controller configured to extract setting information to be set in the first switch from the monitored access, the setting information being used to couple the first input/output devices with the host computer, the extracted setting information being stored; a setting controller configured to set the stored setting information into the second switch; and a switching controller configured to switch an access destination of the host computer from the first switch to the second switch, when a fault occurs in the first switch.