Resilience to memory errors with firmware assistance
    1.
    发明授权
    Resilience to memory errors with firmware assistance 失效
    通过固件帮助恢复内存错误

    公开(公告)号:US07895477B2

    公开(公告)日:2011-02-22

    申请号:US12132135

    申请日:2008-06-03

    IPC分类号: G06F11/00

    摘要: Embodiments of the invention provide an interrupt handler configured to distinguish between critical and non-critical unrecoverable memory errors, yielding different actions for each. Doing so may allow a system to recover from certain memory errors without having to terminate a running process. In addition, when an operating system critical task experiences an unrecoverable error, such a task may be acting on behalf of a non-critical process (e.g., when swapping out a virtual memory page). When this occurs, an interrupt handler may respond to a memory error with the same response that would result had the process itself performed the memory operation. Further, firmware may be configured to perform diagnostics to identify potential memory errors and alert the operating system before a memory region state change occurs, such that the memory error would become critical.

    摘要翻译: 本发明的实施例提供了一种中断处理器,其被配置为区分关键和非关键不可恢复的存储器错误,为每个存储器错误产生不同的动作。 这样做可能允许系统从某些内存错误中恢复,而不必终止正在运行的进程。 此外,当操作系统关键任务遇到不可恢复的错误时,这样的任务可以代表非关键过程(例如,当交换出虚拟存储器页面时)起作用。 当这种情况发生时,中断处理程序可以响应存储器错误,具有相同的响应,这将导致进程本身执行存储器操作。 此外,固件可以被配置为执行诊断以识别潜在的存储器错误并且在发生存储器区域状态改变之前警告操作系统,使得存储器错误将变得至关重要。

    Clearing Interrupts Raised While Performing Operating System Critical Tasks
    2.
    发明申请
    Clearing Interrupts Raised While Performing Operating System Critical Tasks 失效
    在执行操作系统关键任务时清除中断

    公开(公告)号:US20090300434A1

    公开(公告)日:2009-12-03

    申请号:US12132124

    申请日:2008-06-03

    IPC分类号: G06F11/00

    摘要: Embodiments of the invention provide an interrupt handler configured to distinguish between critical and non-critical unrecoverable memory errors, yielding different actions for each. Doing so may allow a system to recover from certain memory errors without having to terminate a running process. In addition, when an operating system critical task experiences an unrecoverable error, such a task may be acting on behalf of a non-critical process (e.g., when swapping out a virtual memory page). When this occurs, an interrupt handler may respond to a memory error with the same response that would result had the process itself performed the memory operation. Further, firmware may be configured to perform diagnostics to identify potential memory errors and alert the operating system before a memory region state change occurs, such that the memory error would become critical.

    摘要翻译: 本发明的实施例提供了一种中断处理器,其被配置为区分关键和非关键不可恢复的存储器错误,为每个存储器错误产生不同的动作。 这样做可能允许系统从某些内存错误中恢复,而不必终止正在运行的进程。 此外,当操作系统关键任务遇到不可恢复的错误时,这样的任务可以代表非关键过程(例如,当交换出虚拟存储器页面时)起作用。 当这种情况发生时,中断处理程序可以响应存储器错误,具有相同的响应,这将导致进程本身执行存储器操作。 此外,固件可以被配置为执行诊断以识别潜在的存储器错误并且在发生存储器区域状态改变之前警告操作系统,使得存储器错误将变得至关重要。

    Resilience to Memory Errors with Firmware Assistance
    3.
    发明申请
    Resilience to Memory Errors with Firmware Assistance 失效
    使用固件协助恢复内存错误

    公开(公告)号:US20090300425A1

    公开(公告)日:2009-12-03

    申请号:US12132135

    申请日:2008-06-03

    IPC分类号: G06F11/00

    摘要: Embodiments of the invention provide an interrupt handler configured to distinguish between critical and non-critical unrecoverable memory errors, yielding different actions for each. Doing so may allow a system to recover from certain memory errors without having to terminate a running process. In addition, when an operating system critical task experiences an unrecoverable error, such a task may be acting on behalf of a non-critical process (e.g., when swapping out a virtual memory page). When this occurs, an interrupt handler may respond to a memory error with the same response that would result had the process itself performed the memory operation. Further, firmware may be configured to perform diagnostics to identify potential memory errors and alert the operating system before a memory region state change occurs, such that the memory error would become critical.

    摘要翻译: 本发明的实施例提供了一种中断处理器,其被配置为区分关键和非关键不可恢复的存储器错误,为每个存储器错误产生不同的动作。 这样做可能允许系统从某些内存错误中恢复,而不必终止正在运行的进程。 此外,当操作系统关键任务遇到不可恢复的错误时,这样的任务可以代表非关键过程(例如,当交换出虚拟存储器页面时)起作用。 当这种情况发生时,中断处理程序可以响应存储器错误,具有相同的响应,这将导致进程本身执行存储器操作。 此外,固件可以被配置为执行诊断以识别潜在的存储器错误并且在发生存储器区域状态改变之前警告操作系统,使得存储器错误将变得至关重要。

    Memory Metadata Used to Handle Memory Errors Without Process Termination
    4.
    发明申请
    Memory Metadata Used to Handle Memory Errors Without Process Termination 失效
    用于处理无过程终止的内存错误的内存元数据

    公开(公告)号:US20090300290A1

    公开(公告)日:2009-12-03

    申请号:US12132112

    申请日:2008-06-03

    IPC分类号: G06F12/12

    摘要: Embodiments of the invention provide an interrupt handler configured to distinguish between critical and non-critical unrecoverable memory errors, yielding different actions for each. Doing so may allow a system to recover from certain memory errors without having to terminate a running process. In addition, when an operating system critical task experiences an unrecoverable error, such a task may be acting on behalf of a non-critical process (e.g., when swapping out a virtual memory page). When this occurs, an interrupt handler may respond to a memory error with the same response that would result had the process itself performed the memory operation. Further, firmware may be configured to perform diagnostics to identify potential memory errors and alert the operating system before a memory region state change occurs, such that the memory error would become critical.

    摘要翻译: 本发明的实施例提供了一种中断处理器,其被配置为区分关键和非关键不可恢复的存储器错误,为每个存储器错误产生不同的动作。 这样做可能允许系统从某些内存错误中恢复,而不必终止正在运行的进程。 此外,当操作系统关键任务遇到不可恢复的错误时,这样的任务可以代表非关键过程(例如,当交换出虚拟存储器页面时)起作用。 当这种情况发生时,中断处理程序可以响应存储器错误,具有相同的响应,这将导致进程本身执行存储器操作。 此外,固件可以被配置为执行诊断以识别潜在的存储器错误并且在发生存储器区域状态改变之前警告操作系统,使得存储器错误将变得至关重要。

    Memory metadata used to handle memory errors without process termination
    5.
    发明授权
    Memory metadata used to handle memory errors without process termination 失效
    用于处理内存错误而不进行过程终止的内存元数据

    公开(公告)号:US08195981B2

    公开(公告)日:2012-06-05

    申请号:US12132112

    申请日:2008-06-03

    IPC分类号: G06F11/00

    摘要: Embodiments of the invention provide an interrupt handler configured to distinguish between critical and non-critical unrecoverable memory errors, yielding different actions for each. Doing so may allow a system to recover from certain memory errors without having to terminate a running process. In addition, when an operating system critical task experiences an unrecoverable error, such a task may be acting on behalf of a non-critical process (e.g., when swapping out a virtual memory page). When this occurs, an interrupt handler may respond to a memory error with the same response that would result had the process itself performed the memory operation. Further, firmware may be configured to perform diagnostics to identify potential memory errors and alert the operating system before a memory region state change occurs, such that the memory error would become critical.

    摘要翻译: 本发明的实施例提供了一种中断处理器,其被配置为区分关键和非关键不可恢复的存储器错误,为每个存储器错误产生不同的动作。 这样做可能允许系统从某些内存错误中恢复,而不必终止正在运行的进程。 此外,当操作系统关键任务遇到不可恢复的错误时,这样的任务可以代表非关键过程(例如,当交换出虚拟存储器页面时)起作用。 当这种情况发生时,中断处理程序可以响应存储器错误,具有相同的响应,这将导致进程本身执行存储器操作。 此外,固件可以被配置为执行诊断以识别潜在的存储器错误并且在发生存储器区域状态改变之前警告操作系统,使得存储器错误将变得至关重要。

    Clearing interrupts raised while performing operating system critical tasks
    6.
    发明授权
    Clearing interrupts raised while performing operating system critical tasks 失效
    在执行操作系统关键任务时清除中断

    公开(公告)号:US07953914B2

    公开(公告)日:2011-05-31

    申请号:US12132124

    申请日:2008-06-03

    IPC分类号: G06F13/24 G11C29/00

    摘要: Embodiments of the invention provide an interrupt handler configured to distinguish between critical and non-critical unrecoverable memory errors, yielding different actions for each. Doing so may allow a system to recover from certain memory errors without having to terminate a running process. In addition, when an operating system critical task experiences an unrecoverable error, such a task may be acting on behalf of a non-critical process (e.g., when swapping out a virtual memory page). When this occurs, an interrupt handler may respond to a memory error with the same response that would result had the process itself performed the memory operation. Further, firmware may be configured to perform diagnostics to identify potential memory errors and alert the operating system before a memory region state change occurs, such that the memory error would become critical.

    摘要翻译: 本发明的实施例提供了一种中断处理器,其被配置为区分关键和非关键不可恢复的存储器错误,为每个存储器错误产生不同的动作。 这样做可能允许系统从某些内存错误中恢复,而不必终止正在运行的进程。 此外,当操作系统关键任务遇到不可恢复的错误时,这样的任务可以代表非关键过程(例如,当交换出虚拟存储器页面时)起作用。 当这种情况发生时,中断处理程序可以响应存储器错误,具有相同的响应,这将导致进程本身执行存储器操作。 此外,固件可以被配置为执行诊断以识别潜在的存储器错误并且在发生存储器区域状态改变之前警告操作系统,使得存储器错误将变得至关重要。