Method, system, and computer program product for creating and managing memory affinity in logically partitioned data processing systems
    1.
    发明授权
    Method, system, and computer program product for creating and managing memory affinity in logically partitioned data processing systems 失效
    方法,系统和计算机程序产品,用于在逻辑分区的数据处理系统中创建和管理存储器亲和度

    公开(公告)号:US06912625B2

    公开(公告)日:2005-06-28

    申请号:US10339774

    申请日:2003-01-09

    IPC分类号: G06F9/50 G06F12/00

    CPC分类号: G06F9/5016

    摘要: A method, system, and product are described for creating and managing affinity between memory and processors in logical partitions in a data processing system. The data processing system includes multiple processors. A memory affinity data structure is established. The memory affinity data structure identifies ones of the processors that have a close affinity with each one of multiple regions of the system memory. A memory affinity parameter is established and is utilized to determine whether memory affinity is required for each one of the logical partitions. In response to a determination that memory affinity is required for one of the logical partitions, the memory affinity data structure is utilized by a partition manager for the logical partition to allocate an optimal amount of memory that has a close affinity to ones of the processors that are assigned to the logical partition.

    摘要翻译: 描述了一种方法,系统和产品,用于在数据处理系统中的逻辑分区中创建和管理存储器和处理器之间的亲和性。 数据处理系统包括多个处理器。 建立了记忆关联数据结构。 存储器相关性数据结构识别与系统存储器的多个区域中的每一个具有密切关系的那些处理器。 建立存储器相关性参数并且用于确定每个逻辑分区是否需要存储器亲和性。 响应于确定对于逻辑分区之一需要存储器相关性,存储器相关性数据结构由分区管理器用于逻辑分区以分配与处理器之一具有密切关联的最佳量的存储器 被分配给逻辑分区。

    Method to Detect a Deadlock Condition by Monitoring Firmware Inactivity During the System IPL Process
    3.
    发明申请
    Method to Detect a Deadlock Condition by Monitoring Firmware Inactivity During the System IPL Process 失效
    通过监控系统IPL过程中的固件不活动性来检测死锁条件的方法

    公开(公告)号:US20090300644A1

    公开(公告)日:2009-12-03

    申请号:US12129893

    申请日:2008-05-30

    IPC分类号: G06F9/46

    摘要: A method for managing deadlock in a data processing system during an IPL process includes monitoring the usage of locks in the Hardware Object Model (HOM) of the data processing system. The process further includes detecting a deadlock condition in response to an indication of the IPL process in the data processing system entering a hung state when at least one lock is in use. The process further includes handling the deadlock condition by performing one or more of the following: recording error information for the deadlock condition, and terminating the IPL process.

    摘要翻译: 一种用于在IPL处理期间管理数据处理系统中的死锁的方法包括监视数据处理系统的硬件对象模型(HOM)中的锁的使用。 该过程还包括响应于在使用至少一个锁时数据处理系统进入挂起状态的IPL处理的指示来检测死锁状况。 该过程还包括通过执行以下一个或多个来处理死锁状况:记录死锁状况的错误信息,并终止IPL处理。

    Method and apparatus for verifying hardware implementation of a processor architecture in a logically partitioned data processing system
    5.
    发明授权
    Method and apparatus for verifying hardware implementation of a processor architecture in a logically partitioned data processing system 失效
    用于验证逻辑分区数据处理系统中的处理器架构的硬件实现的方法和装置

    公开(公告)号:US06883116B2

    公开(公告)日:2005-04-19

    申请号:US09965000

    申请日:2001-09-27

    CPC分类号: G06F11/2236 G06F11/263

    摘要: A method, apparatus, and computer instructions for testing hardware in a data processing system having multiple partitions. A monitor process in a first partition assigned to a first processor is initialized. A random code generation process in a second partition associated with a second processor is initialized. The random code generation process generates instructions and executes the instructions to test the second processor. The monitor process monitors the random code generation process and resets the second processor if the random code generation process fails.

    摘要翻译: 一种用于在具有多个分区的数据处理系统中测试硬件的方法,装置和计算机指令。 初始化分配给第一处理器的第一分区中的监视器进程。 初始化与第二处理器相关联的第二分区中的随机代码生成处理。 随机码产生过程产生指令并执行指令以测试第二处理器。 监视进程监视随机码产生过程,如果随机码生成过程失败,则重置第二处理器。

    Method and apparatus to implement logical partitioning of PCI I/O slots

    公开(公告)号:US06665759B2

    公开(公告)日:2003-12-16

    申请号:US09798294

    申请日:2001-03-01

    IPC分类号: G06F1214

    CPC分类号: G06F13/28

    摘要: A method, system, and computer program product for enforcing logical partitioning of input/output slots within a data processing system is provided. In one embodiment, the system includes a hypervisor and at least one DMA address checking component. The hypervisor receives non-direct-memory-access requests for access to input/output slots and prohibits devices within one logical partition from accessing the input/output slots assigned to a different logical partition. The DMA address checking component receives direct-memory-access requests and prohibits requests for addresses not within the same logical partition as the requesting device from being completed. Requests with addresses corresponding to the same logical partition as the requesting device are placed on the primary PCI bus by the DMA address checking component for delivery to the system memory.

    Method to allow PCI host bridge (PHB) to handle pre-fetch read transactions on the PCI bus which access system memory through translation control entry (TCE) table
    7.
    发明授权
    Method to allow PCI host bridge (PHB) to handle pre-fetch read transactions on the PCI bus which access system memory through translation control entry (TCE) table 失效
    允许PCI主机桥(PHB)处理通过转换控制条目(TCE)表访问系统内存的PCI总线上的预取读事务的方法

    公开(公告)号:US07373479B2

    公开(公告)日:2008-05-13

    申请号:US10809594

    申请日:2004-03-25

    申请人: Van Hoa Lee

    发明人: Van Hoa Lee

    IPC分类号: G06F12/00 G06F13/28

    CPC分类号: G06F12/0292 G06F12/0284

    摘要: A method, system, and computer instructions for providing valid translation entries in the TCE table for all supported DMA addresses to prevent the occurrence of system errors due to prefetching. The mechanism of the present invention reserves a page in system memory. This reserved page is made unavailable to the operating system and may not be utilized by any software in the system. The reserved page is also written with all bytes set to 0xFF. The system firmware then selects a region in system memory for the TCE table. The TCE table is initialized, with all entries within the TCE table initialized to be valid as well as contain the corresponding address of the reserved page. In this manner, all supported DMA page addresses will have valid TCE entries which translate the DMA addresses into the reserved page memory. Thus, prefetched DMA addresses will not encounter invalid DMA address translation, and crash the system.

    摘要翻译: 一种方法,系统和计算机指令,用于在TCE表中为所有支持的DMA地址提供有效的转换条目,以防止由于预取而发生系统错误。 本发明的机制在系统存储器中保留页面。 该保留页面对操作系统不可用,并且可能不被系统中的任何软件使用。 保留页面也写入所有字节设置为0xFF。 系统固件然后在系统存储器中为TCE表选择一个区域。 初始化TCE表,TCE表中的所有条目初始化为有效,并包含保留页面的相应地址。 以这种方式,所有支持的DMA页地址将具有将DMA地址转换为保留页存储器的有效TCE条目。 因此,预取的DMA地址不会遇到无效的DMA地址转换,并且系统崩溃。

    Method and apparatus for managing memory blocks in a logical partitioned data processing system
    8.
    发明授权
    Method and apparatus for managing memory blocks in a logical partitioned data processing system 有权
    用于管理逻辑分区数据处理系统中的存储块的方法和装置

    公开(公告)号:US06941436B2

    公开(公告)日:2005-09-06

    申请号:US10142574

    申请日:2002-05-09

    IPC分类号: G06F9/50 G06F12/02 G06F12/00

    摘要: A method, apparatus, and computer instructions for managing memory blocks. In response to a request to deallocate a memory block from a partition, all processes are prevented from using the memory block. The memory block is isolated from the partition in response to preventing use of the memory block. The memory block is deallocated to form a free memory block.

    摘要翻译: 一种用于管理存储器块的方法,装置和计算机指令。 响应于从分区释放内存块的请求,防止所有进程使用该内存块。 响应于防止使用存储器块,存储器块与分区隔离。 内存块被释放以形成可用的内存块。

    Computer system serialization control method involving unlocking global lock of one partition, after completion of machine check analysis regardless of state of other partition locks
    9.
    发明授权
    Computer system serialization control method involving unlocking global lock of one partition, after completion of machine check analysis regardless of state of other partition locks 失效
    计算机系统串行化控制方法涉及解锁一个分区的全局锁定,完成机器检查分析后无论其他分区锁的状态如何

    公开(公告)号:US06886064B2

    公开(公告)日:2005-04-26

    申请号:US10112477

    申请日:2002-03-28

    IPC分类号: G06F9/46 G06F15/00

    CPC分类号: G06F9/52 Y10S707/99938

    摘要: In a computer system having a logical-partitioned server, each partition of the server is provided with its own separate lock and access corridor, in addition to a global lock. When the locking of a partition lock is followed by the locking of the global lock, the system is serialized. The partition locks are controlled by system firmware on behalf of an OS isolating each partition; however, the global lock is controlled by the system firmware to be unlocked independent of the lock/unlock status of the partition locks. In this manner, the ability or inability of an OS that issued a machine check interrupt to unlock its partition lock after the machine check analysis is complete is irrelevant; once the machine check analysis is complete, the system firmware unlocks the global lock, giving other partitions access to shared system resources to run their own machine checks.

    摘要翻译: 在具有逻辑分区服务器的计算机系统中,除了全局锁之外,服务器的每个分区都具有自己的独立的锁和访问走廊。 当分隔锁的锁定后面是锁定全局锁时,系统将被序列化。 分区锁由系统固件控制,代表隔离每个分区的操作系统; 然而,全局锁由系统固件控制,以解锁,独立于分区锁的锁定/解锁状态。 以这种方式,在机器检查分析完成后,发出机器检查中断来解锁其分区锁定的OS的能力或无效是无关紧要的; 一旦机器检查分析完成,系统固件将解锁全局锁,让其他分区访问共享系统资源来运行自己的机器检查。

    Method and apparatus for initializing a multiprocessor system
    10.
    发明授权
    Method and apparatus for initializing a multiprocessor system 失效
    用于初始化多处理器系统的方法和装置

    公开(公告)号:US5867702A

    公开(公告)日:1999-02-02

    申请号:US787652

    申请日:1997-01-23

    申请人: Van Hoa Lee

    发明人: Van Hoa Lee

    IPC分类号: G06F9/445 G06F9/00

    CPC分类号: G06F15/177 G06F9/4405

    摘要: An apparatus and method for booting a multiprocessor computer system including providing a first portion of boot code to multiple processors for execution, selecting a first processor, the selection based on which of the multiple processors first successfully executes the first portion of the boot code, providing a second portion of the boot code only to the first processor, and the first processor executing the second portion of the boot code to configure the multiprocessor system.

    摘要翻译: 一种用于引导多处理器计算机系统的装置和方法,包括向多个处理器提供引导代码的第一部分用于执行,选择第一处理器,所述选择基于多个处理器中的哪一个首先成功地执行引导代码的第一部分,提供 引导代码的第二部分仅到第一处理器,并且第一处理器执行引导代码的第二部分以配置多处理器系统。