Memory Error Recovery via Page Fault Re-allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory failure recovery methods in information processing apparatuses require special devices and are inefficient when dealing with memory errors in read-only areas, especially in paging-based virtual storage systems, leading to increased overhead and inability to recover errors in writable data areas.
Innovation Solution
A memory failure recovery method that interrupts the process, updates the page table and physical memory management table to disable the affected page frame, and resumes execution, utilizing the page fault mechanism to allocate the virtual page to a different frame, without rewriting the execution program or requiring special devices like a service processor.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional memory failure recovery methods are used with service processors and backup files, then memory errors can be recovered, but device complexity increases and overhead is generated
Solution Approach 1:
The system uses its own page fault mechanism and memory management capabilities to recover from memory errors, eliminating the need for external service processors. When a memory error is detected, the system automatically triggers a page fault, which invokes the operating system's page replacement algorithm to reload the affected page from auxiliary storage, thereby achieving self-service error recovery
Solution Approach 2:
The patent repurposes the existing page fault mechanism, originally designed for virtual memory management, to also serve memory error recovery. This multi-functional use of the page fault mechanism eliminates the need for dedicated error recovery hardware or special processing units
2Reliability
If branch instructions are added to access recovery areas, then memory errors can be recovered, but execution overhead increases
Solution Approach 1:
The system leverages its existing page replacement algorithms and memory management structures to automatically handle error recovery, eliminating the need for manual intervention or special recovery routines that would add execution overhead
3Productivity
If paging-based virtual storage is used, then memory management efficiency is improved, but memory error recovery becomes more difficult
Solution Approach 1:
The patent integrates error recovery functionality into the existing page fault mechanism, allowing the same infrastructure to serve both virtual memory management and error recovery purposes, thereby maintaining efficiency while improving reliability
Solution Approach 2:
The system automatically recovers from memory errors by triggering page faults and using its own page replacement algorithms to reload affected pages, eliminating the need for external recovery mechanisms and maintaining management efficiency
Data Source
AI summary
Upon occurrence of a memory error which is difficult to correct, CPU interrupts a process under execution in response to interrupt signal output from error detection device, and transfers the control to the OS. The OS references attributes of a page stored in a page frame which has suffered the memory error. When read-only is indicated, physical memory management table is updated to set the page frame, which has suffered the error, into a disabled state. Then, page table is updated such that a virtual page stored in the page frame which has suffered the error is not assigned to any page frame, followed by resumption of the execution of the process. After execution of the process is resumed, a page fault process is invoked to store the virtual page which has encountered the memory error in another normal page frame.