公开(公告)号：US07237242B2

公开(公告)日：2007-06-26

申请号：US10334768

申请日：2002-12-31

申请人： Christopher James Blythe ,  Gennaro A. Cuomo ,  Erik A. Daughtrey ,  Matt R. Hogstrom

发明人： Christopher James Blythe ,  Gennaro A. Cuomo ,  Erik A. Daughtrey ,  Matt R. Hogstrom

IPC分类号： G06F9/46

CPC分类号： G06F9/505 ,  G06F2209/5018

摘要： Thread pools in a multithreaded server are programmatically adjusted, based on observed statistics from the server's inbound workload. In a multithreaded server environment, response time to end users is improved while increasing the efficiency of software execution and resource usage. Execution time and wait/queued time are tracked, for various types of requests being serviced by a server. Multiple logical pools of threads are used to service these requests, and inbound requests are directed to a selected one of these pools such that requests of similar execution-time requirements are serviced by the threads in that pool. The number and size of thread pools may be adjusted programmatically, and the distribution calculation (i.e., determining which inbound requests should be assigned to which pools) is a programmatic determination. In preferred embodiments, only one of these variables is adjusted at a time, and the results are monitored to determine whether the effect was positive or negative. The disclosed techniques also apply to tracking and classifying requests by method name (and, optionally, parameters).

摘要翻译： 基于服务器入站工作负载的观察统计信息，可编程调整多线程服务器中的线程池。 在多线程服务器环境中，提高了终端用户的响应时间，同时提高了软件执行和资源使用的效率。 跟踪服务器处理各种类型的请求的执行时间和等待/排队时间。 线程的多个逻辑池用于服务这些请求，并且入站请求被定向到这些池中的一个选定的一个，使得类似执行时间要求的请求由该池中的线程提供服务。 线程池的数量和大小可以以编程方式进行调整，并且分布计算（即，确定哪些入站请求应被分配给哪个池）是编程确定。 在优选实施例中，一次仅调整这些变量中的一个，并且监视结果以确定效果是正还是负。 所公开的技术也适用于通过方法名称（和可选地，参数）跟踪和分类请求。

公开(公告)号：US07207043B2

公开(公告)日：2007-04-17

申请号：US10334262

申请日：2002-12-31

申请人： Christopher James Blythe ,  Gennaro A. Cuomo ,  Erik A. Daughtrey ,  Matt R. Hogstrom

发明人： Christopher James Blythe ,  Gennaro A. Cuomo ,  Erik A. Daughtrey ,  Matt R. Hogstrom

IPC分类号： G06F9/46 ,  G06F15/16 ,  G06F15/173 ,  G06F17/00

CPC分类号： G06F9/505 ,  G06F2209/5018 ,  G06Q30/0283 ,  G06Q50/06

摘要： Workload is programmatically distributed across a set of execution resources. In a multithreaded server environment, response time to end users is improved while increasing the efficiency of software execution and resource usage. Execution time and wait/queued time are tracked, for various types of requests being serviced by a server. Multiple logical pools of threads are used to service these requests, and inbound requests are directed to a selected one of these pools such that requests of similar execution-time requirements are serviced by the threads in that pool. The number and size of thread pools may be adjusted programmatically, and the distribution calculation (i.e., determining which inbound requests should be assigned to which pools) is a programmatic determination. In preferred embodiments, only one of these variables is adjusted at a time, and the results are monitored to determine whether the effect was positive or negative. The disclosed techniques also apply to tracking and classifying requests by method name (and, optionally, parameters).

摘要翻译： 工作负载以编程方式分布在一组执行资源中。 在多线程服务器环境中，提高了终端用户的响应时间，同时提高了软件执行和资源使用的效率。 跟踪服务器处理各种类型的请求的执行时间和等待/排队时间。 线程的多个逻辑池用于服务这些请求，并且入站请求被定向到这些池中的一个选定的一个，使得类似执行时间要求的请求由该池中的线程提供服务。 线程池的数量和大小可以以编程方式进行调整，并且分布计算（即，确定哪些入站请求应被分配给哪个池）是编程确定。 在优选实施例中，一次仅调整这些变量中的一个，并且监视结果以确定效果是正还是负。 所公开的技术也适用于通过方法名称（和可选地，参数）跟踪和分类请求。

公开(公告)号：US20090210873A1

公开(公告)日：2009-08-20

申请号：US12032351

申请日：2008-02-15

申请人： Gennaro A. Cuomo ,  Matt R. Hogstrom ,  Sai G. Rathnam ,  Matthew J. Sheard ,  Brian L. White Eagle

发明人： Gennaro A. Cuomo ,  Matt R. Hogstrom ,  Sai G. Rathnam ,  Matthew J. Sheard ,  Brian L. White Eagle

IPC分类号： G06F9/455

CPC分类号： G06F9/5077

摘要： Embodiments of the present invention provide a method, system and computer program product for virtualization of application lifecycles. In an embodiment of the invention, a virtualization data processing system can be provided. The system can include a hypervisor configured for execution in a host computing platform, a VM image managed by the hypervisor, and a configuration applied to the VM image. The configuration can specify a set of resources in the host computing platform accessible by applications executing in the VM image. Finally, the system can include re-tasking logic coupled to the hypervisor. The logic can include program code enabled to select a new role for the VM image, to determine a new configuration for the new role, and to apply the new configuration to the VM image.

摘要翻译： 本发明的实施例提供了一种用于应用生命周期的虚拟化的方法，系统和计算机程序产品。 在本发明的实施例中，可以提供虚拟化数据处理系统。 该系统可以包括配置为在主机计算平台中执行的管理程序，由管理程序管理的VM映像以及应用于VM映像的配置。 该配置可以指定在VM映像中执行的应用程序可访问的主机计算平台中的一组资源。 最后，系统可以包括耦合到管理程序的重新任务逻辑。 该逻辑可以包括启用以为VM映像选择新角色的程序代码，以确定新角色的新配置，以及将新配置应用于VM映像。

公开(公告)号：US09047160B2

公开(公告)日：2015-06-02

申请号：US13036588

申请日：2011-02-28

申请人： Asaf Adi ,  William C. Arnold ,  Daniel C. Berg ,  Tamar Eilam ,  Dinakaran Joseph ,  Michael H. Kalantar ,  Alexander Kofman ,  Alexander V. Konstantinou ,  Tova Roth ,  Edward C. Snible ,  Harm Sluiman ,  Ruth E. Willenborg ,  Matt R. Hogstrom ,  Jose I. Ortiz

发明人： Asaf Adi ,  William C. Arnold ,  Daniel C. Berg ,  Tamar Eilam ,  Dinakaran Joseph ,  Michael H. Kalantar ,  Alexander Kofman ,  Alexander V. Konstantinou ,  Tova Roth ,  Edward C. Snible ,  Harm Sluiman ,  Ruth E. Willenborg ,  Matt R. Hogstrom ,  Jose I. Ortiz

IPC分类号： G06F9/445

CPC分类号： G06F8/63

摘要： A virtual image is created by receiving a selection of at least one composable software bundle. The at least one composable software bundle includes a first set of metadata and a first set of artifacts comprising a first set of executable instructions associated with a first set of operations. A virtual image asset is selected and received. The virtual image asset includes one or more virtual image disks, a second set of metadata, and a second set of artifacts including a second set of executable instructions associated with a second set of operations. A new virtual image asset is created based on the at least one composable software bundle and the virtual image asset. The new virtual image asset includes a third set of metadata that is based on the first set of metadata and the second set of metadata.

摘要翻译： 通过接收至少一个可组合软件包的选择来创建虚拟图像。 所述至少一个可组合软件包包括第一组元数据和第一组伪像，其包括与第一组操作相关联的第一组可执行指令。 选择并接收虚拟图像资源。 虚拟图像资产包括一个或多个虚拟图像盘，第二组元数据和第二组伪像，其包括与第二组操作相关联的第二组可执行指令。 基于至少一个可组合软件包和虚拟图像资产创建新的虚拟图像资产。 新的虚拟图像资产包括基于第一组元数据和第二组元数据的第三组元数据。

公开(公告)号：US08782640B2

公开(公告)日：2014-07-15

申请号：US13435034

申请日：2012-03-30

申请人： Rohith Ashok ,  Matt R. Hogstrom ,  Jose Ortiz ,  Ruth E. Willenborg

发明人： Rohith Ashok ,  Matt R. Hogstrom ,  Jose Ortiz ,  Ruth E. Willenborg

IPC分类号： G06F9/455

CPC分类号： G06F9/45533 ,  G06F8/63 ,  G06F9/45558 ,  G06F2009/4557

摘要： At least one master overloaded virtual image is deployed, by a virtual image configuration device, to a hypervisor cloud that includes a group of servers, each of the group of servers configured based upon a hypervisor platform to support at least one virtual machine. A service solution is instantiated as a group of virtual machines associated with at least one of the group of servers, based upon at least one master overloaded virtual image, where the service solution includes a platform agnostic pattern independent of the hypervisor platform. Startup is initiated for each of the instantiated group of virtual machines.

摘要翻译： 至少一个主重载虚拟映像被虚拟映像配置设备部署到包括一组服务器的管理程序云，该组服务器中的每一个基于管理程序平台配置以支持至少一个虚拟机。 基于至少一个主重载虚拟映像，服务解决方案被实例化为与至少一个服务器组中的至少一个相关联的一组虚拟机，其中服务解决方案包括与管理程序平台无关的平台不可知模式。 启动每个虚拟机的实例组。

公开(公告)号：US09092558B2

公开(公告)日：2015-07-28

申请号：US10818072

申请日：2004-04-05

申请人： Robert V. Geiner ,  Matt R. Hogstrom

发明人： Robert V. Geiner ,  Matt R. Hogstrom

IPC分类号： G06F11/34 ,  G06F9/45

CPC分类号： G06F12/0893 ,  G06F8/4442 ,  G06F11/3457 ,  G06F11/3471 ,  G06F11/3476 ,  G06F2201/88 ,  G06F2212/1024 ,  G06F2212/1044 ,  G06F2212/602 ,  G06F2212/6024 ,  G06F2212/6026

摘要： A method, system and apparatus for configuring programmatic objects for cache co-location. The method can include the steps of counting a frequency of access for individual fields in the object in a static analysis, rearranging the fields in the object based upon the counted frequency in the static analysis, and executing the object. Subsequently, a frequency of access for the individual fields in the object further can be counted in a dynamic analysis. Consequently, the fields in the object can be further rearranged based upon the counted frequency in the dynamic analysis to produce an optimal grouping for placement in cache memory. In a preferred aspect of the invention, access types for the individual fields can be identified. Subsequently, the rearranging step and the further rearranging step can be performed based both upon the counted frequency and also upon the access types.

摘要翻译： 一种用于配置用于高速缓存协同定位的编程对象的方法，系统和装置。 该方法可以包括以下步骤：在静态分析中对对象中的各个字段的访问频率进行计数，基于静态分析中计数的频率重新排列对象中的字段，以及执行该对象。 随后，可以在动态分析中进一步计数对象中各个字段的访问频率。 因此，可以基于在动态分析中计数的频率来进一步重新排列对象中的字段，以产生用于放置在高速缓冲存储器中的最佳分组。 在本发明的优选方面，可以识别各个字段的访问类型。 随后，可以基于计数的频率以及访问类型来执行重排步骤和进一步的重新排列步骤。

公开(公告)号：US09021097B2

公开(公告)日：2015-04-28

申请号：US13466224

申请日：2012-05-08

申请人： Rohith K. Ashok ,  Thomas M. Brey ,  Raymond J. Harrington ,  Matt R. Hogstrom ,  Matthew J. Sheard

发明人： Rohith K. Ashok ,  Thomas M. Brey ,  Raymond J. Harrington ,  Matt R. Hogstrom ,  Matthew J. Sheard

IPC分类号： G06F15/173 ,  G06F3/00 ,  G06F9/50 ,  H04L29/08

CPC分类号： G06F9/5072 ,  H04L41/0803 ,  H04L41/5096 ,  H04L67/10

摘要： A method, system and computer program product for managing and deploying physical and virtual environments across multiple hardware platforms. A single unit, referred to herein as a cloud construction block, contains both the hardware and software components used to build a cloud computing environment. By having such a single unit contain both the hardware and software components needed to build a cloud computing environment, the user no longer needs to purchase and integrate different hardware and software components. Furthermore, the cloud construction block contains modular pieces of hardware, such as compute hardware, memory hardware, storage hardware and network hardware, that are integrated with management software configured to manage both the hardware and the cloud computing environment in a seamlessly integrated package. Since there is a single management system, the management software allows the user to manage the modular pieces of hardware via a single user interface.

公开(公告)号：US09021096B2

公开(公告)日：2015-04-28

申请号：US13356371

申请日：2012-01-23

申请人： Antonio Abbondanzio ,  Rohith K. Ashok ,  Roy F. Brabson ,  Hugh E. Hockett ,  Matt R. Hogstrom ,  Edward M. Howard

发明人： Antonio Abbondanzio ,  Rohith K. Ashok ,  Roy F. Brabson ,  Hugh E. Hockett ,  Matt R. Hogstrom ,  Edward M. Howard

IPC分类号： G06F15/173 ,  G06F9/48 ,  H04L12/24

CPC分类号： G06F9/4856 ,  G06F9/5072 ,  H04L41/00 ,  H04L47/70

摘要： A method, system and computer program product for performing maintenance operations on a cloud computing node. An administrative server receives an indication that a maintenance operation is to be performed on a cloud computing node. The administrative server identifies which virtual machine(s) on the cloud computing node will be affected by the maintenance operation. The administrative server relocates the virtual machine(s) to be affected by the maintenance operation to other suitable cloud computing node(s) prior to the maintenance operation being performed. The administrative server then performs the maintenance operation on the cloud computing node. The virtual machine(s) may be relocated back to the cloud computing node after the maintenance operation is completed in response to a need to rebalance resources in such a manner. In this manner, maintenance operations may be performed on a cloud computing node without requiring to stop all the virtual machines in the node.

公开(公告)号：US20130204918A1

公开(公告)日：2013-08-08

申请号：US13368446

申请日：2012-02-08

申请人： Rohith K. Ashok ,  Michael J. Burr ,  Christine B. Chato ,  Adam R. Geiger ,  Matt R. Hogstrom ,  Michael S. Law ,  Matthew J. Sheard

发明人： Rohith K. Ashok ,  Michael J. Burr ,  Christine B. Chato ,  Adam R. Geiger ,  Matt R. Hogstrom ,  Michael S. Law ,  Matthew J. Sheard

IPC分类号： G06F15/16

CPC分类号： G06F9/5061

摘要： According to one aspect of the present disclosure a method and technique for automatically configuring a set of resources for deployment as a computing environment is disclosed. The method includes: executing a configuration management application, the configuration management application configured to automatically connect to and discover each hardware element forming a networked set of resources; determine whether each discovered hardware element is specified for the computing environment; responsive to determining that each discovered hardware element is specified for the computing environment, determine a configuration setting for each respective discovered hardware element; responsive to determining that the configuration setting of the discovered hardware element conflicts with a desired configuration setting for deployment of the discovered hardware element, automatically configure the discovered hardware element to the desired configuration setting; and automatically load and configure a management interface to enable deployment of the networked set of resources as a computing environment.

摘要翻译： 根据本公开的一个方面，公开了一种用于自动配置用于部署的资源集合作为计算环境的方法和技术。 该方法包括：执行配置管理应用，所述配置管理应用被配置为自动连接并发现形成网络资源集合的每个硬件元素; 确定每个发现的硬件元素是否为计算环境指定; 响应于确定为所述计算环境指定每个发现的硬件元素，确定每个相应发现的硬件元件的配置设置; 响应于确定所发现的硬件元件的配置设置与用于部署所发现的硬件元件的期望的配置设置冲突，将所发现的硬件元件自动配置为所需的配置设置; 并自动加载和配置管理界面，以便将网络资源集合部署为计算环境。

公开(公告)号：US20130179650A1

公开(公告)日：2013-07-11

申请号：US13346412

申请日：2012-01-09

申请人： Matt R. Hogstrom ,  Tiia Salo ,  Nikola Vouk ,  Meeta Yadav

发明人： Matt R. Hogstrom ,  Tiia Salo ,  Nikola Vouk ,  Meeta Yadav

IPC分类号： G06F12/16

CPC分类号： G06F3/065 ,  G06F12/10 ,  G06F12/109 ,  G06F2212/401 ,  Y02D10/13

摘要： When a virtual machine writes to a page that is being shared across VMs, a share value is calculated to determine how different the page would be if the write command were implemented. If the share value is below a predefined threshold (meaning that the page would not be “too different”), then the page is not copied (as it would be in a standard copy-on-write operation). Instead, the difference between the contents of the pages is stored as a self-contained delta. The physical to machine memory map is updated to point to the delta, and the delta contains a pointer to the original page. When the VM needs to access the page that was stored as a delta, the delta and the page are then fetched from memory and the page is reconstructed.

摘要翻译： 当虚拟机写入正在VM上共享的页面时，计算共享值以确定如果实现了写入命令，页面将会有多大差异。 如果共享值低于预定义的阈值（意味着页面不会“太大”），则页面不会被复制（因为它将在标准的写时拷贝操作中）。 相反，页面的内容之间的差异被存储为自包含的增量。 物理机器内存映射被更新为指向增量，增量包含指向原始页面的指针。 当VM需要访问作为增量存储的页面时，然后从存储器中获取增量和页面，并重建页面。