公开(公告)号：US08019962B2

公开(公告)日：2011-09-13

申请号：US11735809

申请日：2007-04-16

申请人： William Joseph Armstrong ,  Michael J. Corrigan ,  Stuart Zachary Jacobs ,  David Anthony Larson ,  Naresh Nayar ,  Wade Byron Ouren

发明人： William Joseph Armstrong ,  Michael J. Corrigan ,  Stuart Zachary Jacobs ,  David Anthony Larson ,  Naresh Nayar ,  Wade Byron Ouren

IPC分类号： G06F12/00

CPC分类号： G06F12/10 ,  G06F9/4856 ,  G06F9/5077 ,  G06F12/08 ,  G06F12/1036 ,  G06F12/109

摘要： An apparatus, program product and method for tracking the state of a migrating logical partition. Embodiments may use the state to determine the readiness and/or appropriateness of a page of the logical partition for transferring. The state may include a value or other data used to track changes affecting the page or the relative ease and/or appropriateness of migrating the page. A page manager table with entries corresponding to the state of each page of the logical partition may be used to track the state while the logical partition continues to run during a migration.

摘要翻译： 用于跟踪迁移逻辑分区的状态的装置，程序产品和方法。 实施例可以使用该状态来确定用于传送的逻辑分区的页面的准备和/或适当性。 状态可以包括用于跟踪影响页面的变化的值或其他数据，或迁移页面的相对容易度和/或适当性。 可以使用具有与逻辑分区的每个页面的状态对应的条目的页面管理器表来跟踪状态，同时逻辑分区在迁移期间继续运行。

公开(公告)号：US20080256321A1

公开(公告)日：2008-10-16

申请号：US11735809

申请日：2007-04-16

申请人： William Joseph Armstrong ,  Michael J. Corrigan ,  Stuart Zachary Jacobs ,  David Anthony Larson ,  Naresh Nayar ,  Wade Byron Ouren

发明人： William Joseph Armstrong ,  Michael J. Corrigan ,  Stuart Zachary Jacobs ,  David Anthony Larson ,  Naresh Nayar ,  Wade Byron Ouren

IPC分类号： G06F12/00

CPC分类号： G06F12/10 ,  G06F9/4856 ,  G06F9/5077 ,  G06F12/08 ,  G06F12/1036 ,  G06F12/109

摘要： An apparatus, program product and method for tracking the state of a migrating logical partition. Embodiments may use the state to determine the readiness and/or appropriateness of a page of the logical partition for transferring. The state may include a value or other data used to track changes affecting the page or the relative ease and/or appropriateness of migrating the page. A page manager table with entries corresponding to the state of each page of the logical partition may be used to track the state while the logical partition continues to run during a migration.

摘要翻译： 用于跟踪迁移逻辑分区的状态的装置，程序产品和方法。 实施例可以使用该状态来确定用于传送的逻辑分区的页面的准备和/或适当性。 状态可以包括用于跟踪影响页面的变化的值或其他数据，或迁移页面的相对容易度和/或适当性。 可以使用具有与逻辑分区的每个页面的状态对应的条目的页面管理器表来跟踪状态，同时逻辑分区在迁移期间继续运行。

公开(公告)号：US07281075B2

公开(公告)日：2007-10-09

申请号：US10422513

申请日：2003-04-24

申请人： William Joseph Armstrong ,  David Anthony Larson ,  Naresh Nayar

发明人： William Joseph Armstrong ,  David Anthony Larson ,  Naresh Nayar

IPC分类号： G06F13/24

CPC分类号： G06F9/45533 ,  G06F13/24

摘要： A method, system, and article of manufacture for processing virtual interrupts in a logically partitioned system are provided. An intelligent virtual global interrupt queue (virtual GIQ) that may be associated with a plurality of virtual processors running in a logical partition may be utilized. Upon receiving a virtual interrupt, the virtual GIQ may examine the operating states of the associated virtual processors. In an effort to ensure the virtual interrupt is processed as quickly as possible, the virtual GIQ may present the virtual interrupt to one of the associated virtual processors determined to be in an operating state best suited for processing the virtual interrupt.

摘要翻译： 提供了一种用于处理逻辑分区系统中的虚拟中断的方法，系统和制品。 可以利用可以与在逻辑分区中运行的多个虚拟处理器相关联的智能虚拟全局中断队列（虚拟GIQ）。 在接收到虚拟中断时，虚拟GIQ可以检查相关联的虚拟处理器的操作状态。 为了确保尽可能快地处理虚拟中断，虚拟GIQ可以将虚拟中断呈现给被确定为处于最适合于处理虚拟中断的操作状态的相关虚拟处理器之一。

公开(公告)号：US07882326B2

公开(公告)日：2011-02-01

申请号：US11690174

申请日：2007-03-23

申请人： William Joseph Armstrong ,  David Anthony Larson ,  Naresh Nayar

发明人： William Joseph Armstrong ,  David Anthony Larson ,  Naresh Nayar

IPC分类号： G06F12/00 ,  G06F21/00 ,  G06F13/00 ,  G06F13/28 ,  G06F9/455

CPC分类号： G06F9/4856 ,  G06F9/45558 ,  G06F9/5077 ,  G06F2009/4557

摘要： A partition migration mechanism migrates a logical partition executing an operating system and resumes the logical partition before all resources in the logical partition have been migrated. When a partition is being migrated, a call checkpoint mechanism creates checkpoints of the state of the operating system when the partition manager is called. Before performing the call to the partition manager, a check is made to determine if all resources required by the call are available. If so, the partition manager call is executed. If all resources required by the call are not available, a resource fault is indicated, which causes the operating system state from the last checkpoint to be restored and a corresponding virtual CPU to be preempted until the resource that caused the fault becomes available. Exceptions that do not require the missing resource may be performed while the virtual CPU awaits the resource to become available.

摘要翻译： 在迁移逻辑分区中的所有资源之前，分区迁移机制将迁移执行操作系统的逻辑分区并恢复逻辑分区。 当分区正在迁移时，调用检查点机制会在调用分区管理器时创建操作系统状态的检查点。 在执行对分区管理器的呼叫之前，进行检查以确定呼叫所需的所有资源是否可用。 如果是这样，则执行分区管理器调用。 如果呼叫所需的所有资源都不可用，则会指示资源故障，从而导致最后一个检查点的操作系统状态恢复，相应的虚拟CPU将被抢占，直到导致故障的资源变为可用。 可以在虚拟CPU等待资源变为可用时执行不需要缺少资源的异常。

公开(公告)号：US07546406B2

公开(公告)日：2009-06-09

申请号：US11781085

申请日：2007-07-20

申请人： William Joseph Armstrong ,  David Anthony Larson ,  Naresh Nayar

发明人： William Joseph Armstrong ,  David Anthony Larson ,  Naresh Nayar

IPC分类号： G06F13/24

CPC分类号： G06F9/45533 ,  G06F13/24

摘要： A method, system, and article of manufacture for processing virtual interrupts in a logically partitioned system are provided. An intelligent virtual global interrupt queue (virtual GIQ) that may be associated with a plurality of virtual processors running in a logical partition may be utilized. Upon receiving a virtual interrupt, the virtual GIQ may examine the operating states of the associated virtual processors. In an effort to ensure the virtual interrupt is processed as quickly as possible, the virtual GIQ may present the virtual interrupt to one of the associated virtual processors determined to be in an operating state best suited for processing the virtual interrupt.

摘要翻译： 提供了一种用于处理逻辑分区系统中的虚拟中断的方法，系统和制品。 可以利用可以与在逻辑分区中运行的多个虚拟处理器相关联的智能虚拟全局中断队列（虚拟GIQ）。 在接收到虚拟中断时，虚拟GIQ可以检查相关联的虚拟处理器的操作状态。 为了确保尽可能快地处理虚拟中断，虚拟GIQ可以将虚拟中断呈现给被确定为处于最适合于处理虚拟中断的操作状态的相关虚拟处理器之一。

公开(公告)号：US20080256530A1

公开(公告)日：2008-10-16

申请号：US11735770

申请日：2007-04-16

申请人： William Joseph Armstrong ,  Robert J. Battista ,  David Anthony Larson ,  Naresh Nayar ,  Jonathan Ross Van Niewaal

发明人： William Joseph Armstrong ,  Robert J. Battista ,  David Anthony Larson ,  Naresh Nayar ,  Jonathan Ross Van Niewaal

IPC分类号： G06F9/445

CPC分类号： G06F9/45533 ,  G06F9/5077

摘要： An apparatus, program product and method for facilitating logical partition migrations between computers by determining if the firmware of the computers is compatible. A hypervisor of a source logical partition may transfer a token and compatibility table indicative of firmware running on the source computer. A hypervisor on the system of the target logical partition may compare the firmware indicated by the token with a token and/or compatibility table listing firmware versions compatible with the target computer. Conversely, a token of the target computer may be compared to a compatibility table associated with firmware that is compatible with the source computer. In either instance, a match may result in the migration of the logical partition. Alternatively, an absence of a match may result in the migration being prohibited.

摘要翻译： 一种用于通过确定计算机的固件是否兼容来促进计算机之间的逻辑分区迁移的装置，程序产品和方法。 源逻辑分区的管理程序可以传送指示在源计算机上运行的固件的令牌和兼容性表。 目标逻辑分区系统上的管理程序可以将令牌所指示的固件与列出与目标计算机兼容的固件版本的令牌和/或兼容性表进行比较。 相反，可以将目标计算机的令牌与与源计算机兼容的固件相关联的兼容性表进行比较。 在任一情况下，匹配可能导致逻辑分区的迁移。 或者，缺少匹配可能导致迁移被禁止。

公开(公告)号：US20080235482A1

公开(公告)日：2008-09-25

申请号：US11690174

申请日：2007-03-23

申请人： William Joseph Armstrong ,  David Anthony Larson ,  Naresh Nayar

发明人： William Joseph Armstrong ,  David Anthony Larson ,  Naresh Nayar

IPC分类号： G06F12/00

CPC分类号： G06F9/4856 ,  G06F9/45558 ,  G06F9/5077 ,  G06F2009/4557

摘要： A partition migration mechanism migrates a logical partition executing an operating system and resumes the logical partition before all resources in the logical partition have been migrated. When a partition is being migrated, a call checkpoint mechanism creates checkpoints of the state of the operating system when the partition manager is called. Before performing the call to the partition manager, a check is made to determine if all resources required by the call are available. If so, the partition manager call is executed. If all resources required by the call are not available, a resource fault is indicated, which causes the operating system state from the last checkpoint to be restored and a corresponding virtual CPU to be preempted until the resource that caused the fault becomes available. Exceptions that do not require the missing resource may be performed while the virtual CPU awaits the resource to become available.

摘要翻译： 在迁移逻辑分区中的所有资源之前，分区迁移机制将迁移执行操作系统的逻辑分区并恢复逻辑分区。 当分区正在迁移时，调用检查点机制会在调用分区管理器时创建操作系统状态的检查点。 在执行对分区管理器的呼叫之前，进行检查以确定呼叫所需的所有资源是否可用。 如果是这样，则执行分区管理器调用。 如果呼叫所需的所有资源都不可用，则会指示资源故障，从而导致最后一个检查点的操作系统状态恢复，相应的虚拟CPU将被抢占，直到导致故障的资源变为可用。 可以在虚拟CPU等待资源变为可用时执行不需要缺少资源的异常。

公开(公告)号：US08140822B2

公开(公告)日：2012-03-20

申请号：US11735830

申请日：2007-04-16

申请人： Stuart Zachary Jacobs ,  David Anthony Larson ,  Naresh Nayar ,  Jonathan Ross Van Niewaal ,  Kenneth Charles Vossen

发明人： Stuart Zachary Jacobs ,  David Anthony Larson ,  Naresh Nayar ,  Jonathan Ross Van Niewaal ,  Kenneth Charles Vossen

IPC分类号： G06F12/00

CPC分类号： G06F12/1009 ,  G06F9/4856 ,  G06F9/5077 ,  G06F2212/1032

摘要： Maintaining data integrity for a logical partition by enabling nonintrusive switching of page tables used during a migration of the logical partition from a source computer system to a target computer system. A first page table stores a plurality of page entries made within a logically partitioned environment. A second page table stores one or more page entries generated during the migration. After migration, the processor page table pointer is switched to point to the first page table. A page entry in the second page table corresponding to a page entry made to the first page table by the logical partition may be invalidated in response to a page table hypervisor call made by the logical partition. In parallel, a plurality of entries generated during the migration of the logical partition in the second page table may be read through and invalidated.

摘要翻译： 通过在逻辑分区从源计算机系统迁移到目标计算机系统期间使用的页表进行非侵入式切换来维护逻辑分区的数据完整性。 第一页表存储在逻辑分区环境内进行的多个页条目。 第二页表存储迁移期间生成的一个或多个页面条目。 迁移后，处理器页表指针被切换到指向第一页表。 响应于由逻辑分区进行的页表管理程序调用，对应于由逻辑分区对第一页表进行的页条目的第二页表中的页条目可能被无效。 并行地，在第二页表中的逻辑分区的迁移期间生成的多个条目可以被读取并被无效。

公开(公告)号：US20080256327A1

公开(公告)日：2008-10-16

申请号：US11735830

申请日：2007-04-16

申请人： Stuart Zachary Jacobs ,  David Anthony Larson ,  Naresh Nayar ,  Jonathan Ross Van Niewaal ,  Kenneth Charles Vossen

发明人： Stuart Zachary Jacobs ,  David Anthony Larson ,  Naresh Nayar ,  Jonathan Ross Van Niewaal ,  Kenneth Charles Vossen

IPC分类号： G06F12/00

CPC分类号： G06F12/1009 ,  G06F9/4856 ,  G06F9/5077 ,  G06F2212/1032

摘要： An apparatus, program product and method maintains data integrity for a logical partition by enabling nonintrusive switching of page tables used during a migration of the logical partition from a source computer system to a target computer system. A first page table may be configured to store a plurality of page entries made within a logically partitioned environment. A second page table may be used during migration to store one or more page entries generated during the migration. After migration, the processor page table pointer may be transparently switched to point to the first page table. A page entry in the second page table corresponding to a page entry made to the first page table by the logical partition may be invalidated in response to a page table hypervisor call made by the logical partition. In parallel, a plurality of entries generated during the migration of the logical partition in the second page table may be read through and invalidated. This reading through of the entries may be accomplished concurrently with the invalidation of the corresponding page entry in the second page table in response to a page table call made by the logical partition. Moreover, the reading of the entries may be accomplished in intervals and with portions of the plurality of entries.

摘要翻译： 装置，程序产品和方法通过在逻辑分区从源计算机系统迁移到目标计算机系统期间使用的页表的非侵入式切换来维护逻辑分区的数据完整性。 第一页表可以被配置为存储在逻辑分区环境内进行的多个页面条目。 在迁移期间可以使用第二页表来存储迁移期间生成的一个或多个页面条目。 迁移后，处理器页表指针可能被透明地切换到指向第一页表。 响应于由逻辑分区进行的页表管理程序调用，对应于由逻辑分区对第一页表进行的页条目的第二页表中的页条目可能被无效。 并行地，在第二页表中的逻辑分区的迁移期间生成的多个条目可以被读取并被无效。 响应于由逻辑分区进行的页表调用，该条目的读取可以与第二页表中的相应页条目的无效同时完成。 此外，条目的读取可以以间隔和多个条目的一部分来完成。

公开(公告)号：US08209692B2

公开(公告)日：2012-06-26

申请号：US11926967

申请日：2007-10-29

申请人： William Joseph Armstrong ,  Peter Joseph Heyrman ,  Naresh Nayar

发明人： William Joseph Armstrong ,  Peter Joseph Heyrman ,  Naresh Nayar

IPC分类号： G06F9/46

CPC分类号： G06F9/52 ,  G06F9/5016 ,  G06F9/5022 ,  Y10S707/99953 ,  Y10S707/99957

摘要： An apparatus, program product and method support the deallocation of a data structure in a multithreaded computer without requiring the use of computationally expensive semaphores or spin locks. Specifically, access to a data structure is governed by a shared pointer that, when a request is received to deallocate the data structure, is initially set to a value that indicates to any thread that later accesses the pointer that the data structure is not available. In addition, to address any thread that already holds a copy of the shared pointer, and thus is capable of accessing the data structure via the shared pointer after the initiation of the request, all such threads are monitored to determine whether any thread is still using the shared pointer by determining whether any thread is executing program code that is capable of using the shared pointer to access the data structure. Once this condition is met, it is ensured that no thread can potentially access the data structure via the shared pointer, and as such, the data structure may then be deallocated.

摘要翻译： 一种装置，程序产品和方法支持多线程计算机中数据结构的释放，而不需要使用计算上昂贵的信号量或旋转锁。 具体来说，访问数据结构由共享指针控制，当接收到请求以解除分配数据结构时，共享指针最初被设置为指示稍后访问指针的任何线程数据结构不可用的值。 此外，为了解决已经拥有共享指针的副本的任何线程，并且因此能够在请求启动之后通过共享指针访问数据结构，所有这些线程被监视以确定是否有任何线程仍在使用 该共享指针通过确定任何线程是否正在执行能够使用共享指针来访问数据结构的程序代码。 一旦满足此条件，就确保没有线程可以通过共享指针潜在地访问数据结构，因此可以解除分配数据结构。