公开(公告)号：US20120036292A1

公开(公告)日：2012-02-09

申请号：US12851634

申请日：2010-08-06

申请人： Vaijayanthimala K. Anand ,  Ronen Grosman ,  Michael E. Lyons ,  Bret R. Olszewski

发明人： Vaijayanthimala K. Anand ,  Ronen Grosman ,  Michael E. Lyons ,  Bret R. Olszewski

IPC分类号： G06F13/22 ,  G06F13/24

CPC分类号： G06F13/22 ,  G06F13/24

摘要： A software thread is dispatched for causing the system to poll a device for determining whether a condition has occurred. Subsequently, the software thread is undispatched and, in response thereto, an interrupt is enabled on the device, so that the device is enabled to generate the interrupt in response to an occurrence of the condition, and so that the system ceases polling the device for determining whether the condition has occurred. Eventually, the software thread is redispatched and, in response thereto, the interrupt is disabled on the device, so that the system resumes polling the device for determining whether the condition has occurred.

摘要翻译： 调度软件线程使系统轮询设备以确定是否已经发生条件。 随后，软件线程未分配，并且响应于此，在设备上启用中断，使得设备能够响应于条件的发生而产生中断，并且使得系统停止轮询设备 确定病情是否发生。 最终，软件线程被重新分配，并且响应于此，设备上的中断被禁用，使得系统恢复轮询该设备以确定该条件是否已经发生。

公开(公告)号：US20090204959A1

公开(公告)日：2009-08-13

申请号：US12027525

申请日：2008-02-07

申请人： Vaijayanthimala K. Anand ,  Peter J. Heyrman ,  Bret R. Olszewski

发明人： Vaijayanthimala K. Anand ,  Peter J. Heyrman ,  Bret R. Olszewski

IPC分类号： G06F9/455

CPC分类号： G06F9/5027 ,  G06F9/45558 ,  G06F9/5077 ,  G06F12/109 ,  G06F2009/45583 ,  G06F2212/656

摘要： The present invention provides a computer implemented method, data processing system, and computer program product for mapping and dispatching virtual processors in a data processing system having at least a first partition and a second partition. The data processing system runs a first partition on a virtual processor during a first timeslice. The data processing system identifies an at least one physical page used by the first partition and the second partition. The data processing system maps the at least one physical page to the first partition and the second partition. The data processing system determines a fitness value based on the mapping. The data processing system dispatches the Virtual processor to the second partition on a second timeslice based on the fitness value, wherein the second timeslice immediately succeeds after the first timeslice, whereby the at least one physical page remains in cache during at least the first timeslice and the second timeslice.

摘要翻译： 本发明提供了一种用于在具有至少第一分区和第二分区的数据处理系统中映射和分派虚拟处理器的计算机实现方法，数据处理系统和计算机程序产品。 数据处理系统在第一时间片段期间在虚拟处理器上运行第一分区。 数据处理系统识别由第一分区和第二分区使用的至少一个物理页面。 数据处理系统将至少一个物理页面映射到第一分区和第二分区。 数据处理系统基于映射确定适应度值。 所述数据处理系统基于所述适合度值将所述虚拟处理器分配到所述第二分区，其中所述第二时间片在所述第一时间片之后立即成功，由此所述至少一个物理页在至少所述第一时间片内保持在高速缓存中，以及 第二个时间片

公开(公告)号：US20090119474A1

公开(公告)日：2009-05-07

申请号：US11936456

申请日：2007-11-07

申请人： Vaijayanthimala K. Anand ,  Bret R. Olszewski ,  Mysore Sathyanarayana Srinivas

发明人： Vaijayanthimala K. Anand ,  Bret R. Olszewski ,  Mysore Sathyanarayana Srinivas

IPC分类号： G06F13/00

CPC分类号： G06F12/1009 ,  G06F2212/401

摘要： Illustrated embodiments provide a computer implemented method and data processing system for redispatching a partition by tracking a set of memory pages, belonging to the dispatched partition. In one illustrative embodiment the computer implemented method comprises finding an effective page address to real page address mapping for a page address miss to create a found real page address and page size combination, responsive to determining the page address miss in a page addressing buffer, and saving the found real page address and page size combination as an entry in set of entries in an array. Further in the computer implemented method, creating a preserved array from the array, responsive to determining the dispatched partition to be an undispatched partition. The computer implemented method further, analyzing each entry of the preserved array for a compressed page, responsive to determining the undispatched partition is now redispatched, and invoking a partition management firmware function to decompress the compressed page, prior to the partition being redispatched, responsive to determining a compressed page.

摘要翻译： 说明的实施例提供了一种计算机实现的方法和数据处理系统，用于通过跟踪属于所分派的分区的一组存储器页来重新分配分区。 在一个说明性实施例中，计算机实现的方法包括：响应于确定页面寻址缓冲器中的页面地址未命中，找到用于寻址页面地址的真实页面地址映射以产生找到的真实页面地址和页面大小组合的有效页面地址，以及 将发现的真实页面地址和页面大小组合保存为数组中的条目集中的条目。 此外，在计算机实现的方法中，响应于将分派的分区确定为未分配的分区，从阵列创建保留的数组。 计算机实现的方法还包括：响应于确定未分配的分区现在被重新分配，分析压缩页面的保留数组的每个条目，并且在重新分配分区之前调用分区管理固件功能来解压缩压缩页面，响应于 确定压缩页面。

公开(公告)号：US20080163203A1

公开(公告)日：2008-07-03

申请号：US11617206

申请日：2006-12-28

申请人： Vaijayanthimala K. Anand ,  Peter Joseph Heyrman ,  Bret R. Olszewski

发明人： Vaijayanthimala K. Anand ,  Peter Joseph Heyrman ,  Bret R. Olszewski

IPC分类号： G06F9/455

CPC分类号： G06F9/45533 ,  G06F9/5033 ,  G06F9/5077

摘要： A computer implemented method, data processing system, and computer usable program code are provided for dispatching virtual processors. A determination is made as to whether a physical processor in a set of physical processors is idle, and, if so, a determination is made as to whether an affinity map for the idle physical processor exists. Responsive to an existence of the affinity map, a determination is made as to whether a virtual processor last mapped to the idle physical processor is ready to run using the affinity map and a dispatch algorithm. Responsive to identifying a ready-to-run virtual processor whose affinity map indicates that the idle physical processor is mapped to this virtual processor in its preceding dispatch, the ready-to-run virtual processor is dispatched to the idle physical processor. Thus, memory affinity is maintained between physical and virtual processors when the memory affinity is not expired.

摘要翻译： 提供计算机实现的方法，数据处理系统和计算机可用程序代码来调度虚拟处理器。 确定一组物理处理器中的物理处理器是否空闲，并且如果是，则确定存在空闲物理处理器的亲和度映射是否存在。 响应于亲和力映射的存在，确定最后映射到空闲物理处理器的虚拟处理器是否准备好使用亲和度映射和调度算法运行。 响应于识别其亲和力映射表示空闲物理处理器在其之前的分派中被映射到该虚拟处理器的可运行虚拟处理器，则准备运行的虚拟处理器被调度到空闲物理处理器。 因此，当存储器相关性未过期时，在物理和虚拟处理器之间保持存储器亲和性。

公开(公告)号：US09158668B2

公开(公告)日：2015-10-13

申请号：US13535259

申请日：2012-06-27

申请人： Rohith K. Ashok ,  Agustin Mena, III ,  Thuy B. Nguyen ,  Bret R. Olszewski

发明人： Rohith K. Ashok ,  Agustin Mena, III ,  Thuy B. Nguyen ,  Bret R. Olszewski

IPC分类号： G06F9/46 ,  G06F15/173 ,  G06F12/02 ,  G06F9/50

CPC分类号： G06F12/02 ,  G06F9/5077

摘要： Automated techniques ensure that system central processing unit (“CPU”) power is not a bottleneck when migrating logical partitions from one system to another system or systems (e.g., in the event of a system evacuation). CPU resources needed to fully drive available bandwidth during the migration are computed. CPU resources of the system are then adjusted for the migration, which may comprise scaling down the CPU resources that are guaranteed for the executing partitions and/or adjusting relative partition variable weights to limit the amount of excess capacity that can be allocated to a partition.

摘要翻译： 自动化技术确保系统中央处理单元（“CPU”）在将逻辑分区从一个系统迁移到另一个系统或系统时（例如，在系统撤离的情况下）不是瓶颈。 计算在迁移期间完全驱动可用带宽所需的CPU资源。 然后调整系统的CPU资源以用于迁移，其可以包括缩小对于执行分区保证的CPU资源和/或调整相对分区变量权重以限制可以分配给分区的多余容量的量。

公开(公告)号：US20120278809A1

公开(公告)日：2012-11-01

申请号：US13544958

申请日：2012-07-09

申请人： Larry B. Brenner ,  Dirk Michel ,  Bret R. Olszewski

发明人： Larry B. Brenner ,  Dirk Michel ,  Bret R. Olszewski

IPC分类号： G06F9/46

CPC分类号： G06F9/5033 ,  G06F9/4856 ,  G06F9/5088

摘要： The present invention provides a computer implemented method and apparatus to assign software threads to a common virtual processor of a data processing system having multiple virtual processors. A data processing system detects cooperation between a first thread and a second thread with respect to a lock associated with a resource of the data processing system. Responsive to detecting cooperation, the data processing system assigns the first thread to the common virtual processor. The data processing system moves the second thread to the common virtual processor, whereby a sleep time associated with the lock experienced by the first thread and the second thread is reduced below a sleep time experienced prior to the detecting cooperation step.

摘要翻译： 本发明提供了一种计算机实现的方法和装置，用于将软件线程分配给具有多个虚拟处理器的数据处理系统的公共虚拟处理器。 数据处理系统相对于与数据处理系统的资源相关联的锁检测第一线程和第二线程之间的协作。 响应于检测合作，数据处理系统将第一线程分配给公共虚拟处理器。 所述数据处理系统将所述第二线程移动到所述公共虚拟处理器，由此与所述第一线程和所述第二线程所经历的锁相关联的休眠时间减少到在所述检测合作步骤之前经历的睡眠时间以下。

公开(公告)号：US20120246652A1

公开(公告)日：2012-09-27

申请号：US13069338

申请日：2011-03-22

申请人： Bernard A. King-Smith ,  Bret R. Olszewski ,  Stephen Rees ,  Basu Vaidyanathan

发明人： Bernard A. King-Smith ,  Bret R. Olszewski ,  Stephen Rees ,  Basu Vaidyanathan

IPC分类号： G06F9/48

CPC分类号： G06F1/3228 ,  G06F1/3296 ,  G06F9/4843 ,  Y02B70/1441 ,  Y02D10/24

摘要： Various systems, processes, and products may be used to manage a processor. In particular implementations, managing a processor may include the ability to determine whether a thread is pausing for a short period of time and place a wait event for the thread in a queue based on a short thread pause occurring. Managing a processor may also include the ability to activate a delay thread that determines whether a wait time associated with the pause has expired and remove the wait event from the queue based on the wait time having expired.

摘要翻译： 可以使用各种系统，过程和产品来管理处理器。 在特定实现中，管理处理器可以包括确定线程是否在短时间段内暂停并且基于发生的短线程暂停将线程的等待事件置于队列中的能力。 管理处理器还可以包括激活延迟线程的能力，该延迟线程确定与暂停相关联的等待时间是否已经到期，并且基于等待时间已经到期从队列中移除等待事件。

公开(公告)号：US20130290666A1

公开(公告)日：2013-10-31

申请号：US13927193

申请日：2013-06-26

申请人： Mathew Accapadi ,  Grover C. Davidson, II ,  Dirk Michel ,  Bret R. Olszewski

发明人： Mathew Accapadi ,  Grover C. Davidson, II ,  Dirk Michel ,  Bret R. Olszewski

IPC分类号： G06F12/02

CPC分类号： G06F12/023 ,  G06F12/0253

摘要： Management of a UNIX-style storage pools is enhanced by specially managing one or more memory management inodes associated with pinned and allocated pages of data storage by providing indirect access to the pinned and allocated pages by one or more user processes via a handle, while preventing direct access of the pinned and allocated pages by the user processes without use of the handles; scanning periodically hardware status bits in the inodes to determine which of the pinned and allocated pages have been recently accessed within a pre-determined period of time; requesting via a callback communication to each user process to determine which of the least-recently accessed pinned and allocated pages can be either deallocated or defragmented and compacted; and responsive to receiving one or more page indicators of pages unpinned by the user processes, compacting or deallocating one or more pages corresponding to the page indicators.

摘要翻译： 通过专门管理与固定和分配的数据存储页面相关联的一个或多个存储器管理异常节点，通过一个或多个用户进程通过句柄间接访问被固定和分配的页面来增强对UNIX风格存储池的管理，同时防止 用户进程直接访问固定和分配的页面，而不使用手柄; 周期性地扫描inode中的硬件状态位，以确定在预定时间段内最近访问的被固定和分配的页面中的哪一个; 通过对每个用户进程的回调通信来请求，以确定哪个最近访问的固定和分配的页面可以被解除分配或碎片整理和压缩; 并且响应于接收由用户进程解除的页面的一个或多个页面指示符，压缩或取消分配对应于页面指示符的一个或多个页面。

公开(公告)号：US20120311605A1

公开(公告)日：2012-12-06

申请号：US13149492

申请日：2011-05-31

申请人： Bret R. Olszewski ,  Basu Vaidyanathan

发明人： Bret R. Olszewski ,  Basu Vaidyanathan

IPC分类号： G06F9/46

CPC分类号： G06F9/5094 ,  Y02D10/22

摘要： A method maintains, for each processing element in a processor, a count of threads waiting in a data structure for hand-off locks in order to execute on the processing element. The method maintains the processing element in a first power state if the count of threads waiting for hand-off locks is greater than zero. The method puts the processing element in a second power state if the count of threads waiting for hand-off locks is equal to zero and no thread is ready to be processed by the processing element. The method returns the processing element to the first power state if the count of threads becomes greater than zero, or if a thread becomes ready to be processed by the processing element.

摘要翻译： 一种方法为处理器中的每个处理元件维护在数据结构中等待切换锁的线程数，以便在处理元件上执行。 如果等待切换锁的线程数大于零，则该方法将处理元件维持在第一功率状态。 如果等待切换锁的线程数等于零并且没有线程准备好被处理元件处理，则该方法将处理元件置于第二功率状态。 如果线程数大于零，或者线程准备好被处理元件处理，该方法将处理元件返回到第一功率状态。

公开(公告)号：US20120102258A1

公开(公告)日：2012-04-26

申请号：US12910234

申请日：2010-10-22

申请人： David A. Hepkin ,  Peter J. Heyrman ,  Bret R. Olszewski

发明人： David A. Hepkin ,  Peter J. Heyrman ,  Bret R. Olszewski

IPC分类号： G06F12/08

CPC分类号： G06F9/45558 ,  G06F12/0811 ,  G06F12/1027 ,  G06F2009/4557 ,  G06F2009/45583

摘要： A method of dynamically reallocating memory affinity in a virtual machine after migrating the virtual machine from a source computer system to a destination computer system migrates processor states and resources used by the virtual machine from the source computer system to the destination computer system. The method maps memory of the virtual machine to processor nodes of the destination computer system. The method deletes memory mappings in processor hardware, such as translation lookaside buffers and effective-to-real address tables, for the virtual machine on the destination computer system. The method starts the virtual machine on the destination computer system in virtual real memory mode. A hypervisor running on the destination computer system receives a page fault and virtual address of a page for said virtual machine from a processor of the destination computer system and determines if the page is in local memory of the processor. If the hypervisor determines the page to be in the local memory of the processor, the hypervisor returning a physical address mapping for the page to the processor. If the hypervisor determines the page not to be in the local memory of the processor, the hypervisor moves the page to local memory of the processor and returns a physical address mapping for said page to the processor.

摘要翻译： 将虚拟机从源计算机系统迁移到目标计算机系统之后，在将虚拟机迁移到目标计算机系统之后，在虚拟机中动态重新分配存储器亲和性的方法将将虚拟机使用的处理器状态和资源从源计算机系统迁移到目标计算机系统。 该方法将虚拟机的内存映射到目标计算机系统的处理器节点。 该方法会删除目标计算机系统上的虚拟机的处理器硬件中的内存映射，例如翻译后备缓冲区和有效到真实的地址表。 该方法以虚拟实时存储模式启动目标计算机系统上的虚拟机。 在目的地计算机系统上运行的管理程序从目的地计算机系统的处理器接收所述虚拟机的页面错误和虚拟地址，并确定页面是否在处理器的本地存储器中。 如果管理程序将该页面确定在处理器的本地存储器中，则管理程序将页面的物理地址映射返回到处理器。 如果管理程序确定页面不在处理器的本地存储器中，则管理程序将页面移动到处理器的本地存储器，并将所述页面的物理地址映射返回到处理器。