Server Interrupt Control via CPLD Segmentation for Power Failure Protection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high-density design of storage/server hardware results in significant power consumption, which exceeds the capacity of limited Battery Backup Units (BBUs), leading to data loss during power failures.
Innovation Solution
A server interrupt operation execution method that categorizes components into three types: a first component not participating in power failure operations, a second component participating but not initially coupled, and a third component actively participating. The method generates specific interrupt information and uses a logic programming device CPLD to control these components to perform targeted interrupt operations during power failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If high-density design is adopted to increase storage capacity, then the storage capacity is improved, but the power consumption increases beyond BBU support capability
Solution Approach 1:
The patent segments components into three categories (first, second, and third components) based on their coupling relationship with power failure operations. This segmentation allows differential power management where third components (critically coupled) receive priority power supply while first components (not coupled) are powered down, resolving the contradiction between maintaining storage capacity and reducing overall power consumption.
Solution Approach 2:
The patent applies local quality by providing different power supply strategies to different components based on their specific coupling characteristics. Third components that are critically coupled with power failure operations receive steady-state power reduction, while first components that are not coupled receive transient power reduction, optimizing power distribution locally rather than applying a uniform approach system-wide.
2Reliability
If BBU power supply is used during power failure, then data protection is enabled, but the limited BBU capacity cannot support high power consumption of dense hardware
Solution Approach 1:
The patent implements preliminary action by detecting power failure conditions and generating interrupt information before complete power loss occurs. This allows the system to proactively initiate power reduction operations on non-critical components, ensuring data protection operations can proceed with limited BBU energy capacity rather than attempting to support full system power consumption.
Solution Approach 2:
The patent applies partial action by selectively maintaining power supply only to third components that are critically coupled with power failure operations, while reducing or eliminating power to first and second components. This partial power maintenance ensures sufficient energy capacity for data protection while avoiding the excessive energy consumption that would deplete BBU reserves.
3Reliability
If interrupt operations are performed on all components during power failure, then comprehensive protection is achieved, but system complexity and operational difficulty increase
Solution Approach 1:
The patent reduces control complexity by segmenting components into three distinct categories based on their coupling relationship with power failure operations. This segmentation enables simplified control logic where each category receives a predetermined power management strategy, avoiding the need for complex individualized control of each component while still achieving comprehensive protection for critical operations.
Data Source
AI summary
A server interruption operation execution method and apparatus. The method comprises: when it is determined that the mains power supply stops supplying power, generating first power failure interruption information for a first component and second power failure interruption information for a second component and a third component; sending the first power failure interrupt information to the first component to control the first component to execute a first interrupt operation; sending the second power failure interrupt information to the second component to control the second component to execute a second interrupt operation; and sending the second power failure interrupt information to the third component to control the third component to execute a third interrupt operation. Therefore, when a server executes a power failure operation, interrupt operations are performed on different types of components in a targeted manner, thereby effectively improving the efficiency of power failure protection.