公开(公告)号：US5974462A

公开(公告)日：1999-10-26

申请号：US828440

申请日：1997-03-28

申请人： Jeffrey D. Aman ,  John E. Arwe ,  David A. Booz ,  David V. Bostjancic ,  Gregory M. Dritschler ,  Catherine K. Eilert ,  Peter B. Yocom

发明人： Jeffrey D. Aman ,  John E. Arwe ,  David A. Booz ,  David V. Bostjancic ,  Gregory M. Dritschler ,  Catherine K. Eilert ,  Peter B. Yocom

IPC分类号： H04L29/06 ,  H04L29/08 ,  G06F13/33 ,  G06F15/17

CPC分类号： H04L67/1008 ,  H04L67/1002 ,  H04L67/1031

摘要： A method and apparatus for controlling the number of servers in an information handling system in which incoming work requests belonging to a first service class are placed in a queue for processing by one or more servers. The system also has units of work assigned to a second service class that acts as a donor of system resources. In accordance with the invention, a performance measure is defined for the first service class as well as for the second service class. Before adding servers to the first service class, there is determined not only the positive effect on the performance measure for the first service class, but also the negative effect on the performance measure for the second service class. Servers are added to the first service class only if the positive effect on the performance measure for the first service class outweighs the negative effect on the performance measure for the second service class.

摘要翻译： 一种用于控制信息处理系统中的服务器数量的方法和装置，其中属于第一服务类的传入工作请求被放置在队列中以供一个或多个服务器处理。 该系统还具有分配给作为系统资源的捐赠者的第二服务类的工作单元。 根据本发明，为第一服务类以及第二服务类定义性能测量。 在将服务器添加到第一个服务类之前，不仅确定了对第一个服务类的性能测量的积极影响，而且还确定了对第二个服务类的性能测量的负面影响。 仅当对第一个服务类的性能测量的积极影响超过对第二个服务类的性能测量的负面影响时，才会将服务器添加到第一个服务类。

公开(公告)号：US06230183B1

公开(公告)日：2001-05-08

申请号：US09038573

申请日：1998-03-11

申请人： Peter B. Yocom ,  Catherine K. Eilert ,  John E. Arwe

发明人： Peter B. Yocom ,  Catherine K. Eilert ,  John E. Arwe

IPC分类号： G06F1300

CPC分类号： G06F9/5061 ,  G06F9/5083 ,  G06F2209/505

摘要： A method and apparatus for controlling the number of servers in a multisystem cluster. Incoming work requests are organized into service classes, each of which has a queue serviced by servers across the cluster. Each service class has defined for it a local performance index for each particular system of the cluster and a multisystem performance index for the cluster as a whole. Each system selects one service class as a donor class for donating system resources and another service class as a receiver class for receiving system resources, based upon how well the service classes are meeting their goals. Each system then determines the resource bottleneck causing the receiver class to miss its goals. If the resource bottleneck is the number of servers, each system determines whether and how many servers should be added to the receiver class, based upon whether the positive effect of adding such servers on the performance index for the receiver class outweighs the negative effect of adding such servers on the performance measure for the donor class. If a system determines that servers should be added to the receiver class, it then determines the system in the cluster to which the servers should be added, based upon the effect on other work on that system. To make this latter determination, each system first determines whether another system has enough idle capacity and, if so, lets that system add servers. If no system has sufficient idle capacity, each system then determines whether the local donor class will miss its goals if servers are started locally. It not, the servers are started on the local system. Otherwise, each system determines where the donor class will be hurt the least and acts accordingly. To ensure the availability of a server capable of processing each of the work requests in the queue, each system determines whether there is a work request in the queue with an affinity only to a subset of the cluster that does not have servers for the queue and, if so, starts a server for the queue on a system in the subset to which the work request has an affinity.

公开(公告)号：US06393455B1

公开(公告)日：2002-05-21

申请号：US08827528

申请日：1997-03-28

申请人： Catherine K. Eilert ,  Peter B. Yocom ,  Gary M. King ,  Jeffrey D. Aman

发明人： Catherine K. Eilert ,  Peter B. Yocom ,  Gary M. King ,  Jeffrey D. Aman

IPC分类号： G06F900

CPC分类号： G06F9/5061 ,  G06F9/5083

摘要： A technique is disclosed for managing a workload distributed across multiple data processing systems to enhance shared resource access to meet a common performance standard. The technique includes on at least one system, measuring performance of the work units on the system to create local performance data, and on at least some of the systems sending the local performance data to at least one other system of the multiple data processing systems. The method further includes on at least one of the systems, receiving the performance data from the sending systems to create remote performance data, and adjusting at least one control parameter for accessing shared resources in response to the local and remote performance data to modify the performance of the work units distributed across the data processing systems to achieve the common performance standard. A dynamic resource clustering process is also employed to enhance the shared resource management.

摘要翻译： 公开了一种用于管理分布在多个数据处理系统上的工作负载以增强共享资源访问以满足公共性能标准的技术。 该技术包括至少一个系统，测量系统上的工作单元的性能以创建本地性能数据，以及在至少一些将本地性能数据发送到多个数据处理系统的至少一个其他系统的系统中。 该方法还包括在至少一个系统中，从发送系统接收性能数据以创建远程性能数据，以及响应于本地和远程性能数据调整用于访问共享资源的至少一个控制参数以修改性能 的工作单位分布在数据处理系统中实现共同的性能标准。 动态资源聚类过程也用于增强共享资源管理。

公开(公告)号：US5473773A

公开(公告)日：1995-12-05

申请号：US222755

申请日：1994-04-04

申请人： Jeffrey D. Aman ,  Catherine K. Eilert ,  Gary M. King ,  Bernard R. Pierce ,  Peter B. Yocom

发明人： Jeffrey D. Aman ,  Catherine K. Eilert ,  Gary M. King ,  Bernard R. Pierce ,  Peter B. Yocom

IPC分类号： G06F9/48 ,  G06F9/46 ,  G06F9/50 ,  G06F15/00

CPC分类号： G06F9/5083

摘要： A workload manager creates goal control data, defining two or more classes of system work units, in response to specification of goals of two or more goal types for the classes, and specification of importance values for each of the goal types. A system resource manager causes the goals to be met by periodically sampling work unit status; calculating a performance index for each class; selecting a receiver class to receive improved service based on the relative performance indexes and goal importance; a system bottleneck impacting achievement of goal by the receiver class is identified; and one or more system control data elements are identified and adjusted to cause the goal to be met for the receiver class.

摘要翻译： 响应于类的两个或多个目标类型的目标的规范以及每个目标类型的重要性值的规范，工作负载管理器创建目标控制数据，定义两个或多个系统工作单元类。 系统资源管理器通过定期抽样工作单位状态来实现目标; 计算每个班级的表现指数; 选择接收者类，根据相对性能指标和目标重要性接收改进的服务; 确定影响接收者类目标实现的系统瓶颈; 并且识别和调整一个或多个系统控制数据元素以使接收器类别满足目标。

公开(公告)号：US06760910B2

公开(公告)日：2004-07-06

申请号：US09905236

申请日：2001-07-13

申请人： Catherine K. Eilert ,  Peter B. Yocom ,  Gary M. King ,  Jeffrey D. Aman

发明人： Catherine K. Eilert ,  Peter B. Yocom ,  Gary M. King ,  Jeffrey D. Aman

IPC分类号： G06F900

CPC分类号： G06F9/5061 ,  G06F9/5083

摘要： A technique is disclosed for managing a workload distributed across multiple data processing systems to enhance shared resource access to meet a common performance standard. The technique includes on at least one system, measuring performance of the work units on the system to create local performance data, and on at least some of the systems sending the local performance data to at least one other system of the multiple data processing systems. The method further includes on at least one of the systems, receiving the performance data from the sending systems to create remote performance data, and adjusting at least one control parameter for accessing shared resources in response to the local and remote performance data to modify the performance of the work units distributed across the data processing systems to achieve the common performance standard. A dynamic resource clustering process is also employed to enhance the shared resource management.

摘要翻译： 公开了一种用于管理分布在多个数据处理系统上的工作负载以增强共享资源访问以满足公共性能标准的技术。 该技术包括至少一个系统，测量系统上的工作单元的性能以创建本地性能数据，以及在至少一些将本地性能数据发送到多个数据处理系统的至少一个其他系统的系统中。 该方法还包括在至少一个系统中，从发送系统接收性能数据以创建远程性能数据，以及响应于本地和远程性能数据调整用于访问共享资源的至少一个控制参数以修改性能 的工作单位分布在数据处理系统中实现共同的性能标准。 动态资源聚类过程也用于增强共享资源管理。

公开(公告)号：US06587938B1

公开(公告)日：2003-07-01

申请号：US09407212

申请日：1999-09-28

申请人： Catherine K. Eilert ,  Jeffrey P. Kubala ,  Jeffrey M. Nick ,  Peter B. Yocom

发明人： Catherine K. Eilert ,  Jeffrey P. Kubala ,  Jeffrey M. Nick ,  Peter B. Yocom

IPC分类号： G06F1516

CPC分类号： G06F9/5061 ,  G06F9/5083

摘要： Central processing unit (CPU) resources are managed within a computing environment. When the allocation of CPU resources to a partition of the computing environment is to be adjusted, the allocation is adjusted dynamically. This dynamic adjustment is across at least two partitions of the computing environment. The adjusting includes modifying processor weights associated with the partitions.

摘要翻译： 中央处理单元（CPU）资源在计算环境中进行管理。 当将CPU资源分配给计算环境的分区时，动态调整分配。 这种动态调整在计算环境的至少两个分区上。 调整包括修改与分区相关联的处理器权重。

公开(公告)号：US06622177B1

公开(公告)日：2003-09-16

申请号：US09626519

申请日：2000-07-27

申请人： Catherine K. Eilert ,  Gary M. King ,  Peter B. Yocom ,  Harry M. Yudenfriend

发明人： Catherine K. Eilert ,  Gary M. King ,  Peter B. Yocom ,  Harry M. Yudenfriend

IPC分类号： G06F300

CPC分类号： G06F13/387

摘要： Disclosed is a method and computer program device for dynamically managing the assignment of alias addresses to base addresses referencing an input/output (I/O) device, such as a direct access storage device (DASD). Two distinct methods are disclosed. In one method, alias addresses are assigned based on the performance of the I/O devices. In this method, alias addresses are assigned to highly utilized devices, as indicated by device performance data, in order to maximize the efficient utilization of I/O device resources. In a second method, workload management principles are utilized to assign alias addresses. In this method, a correlation is made between each I/O device and the service classes utilizing each device. As in the first method, performance data is generated for each I/O device. Alias addresses are assigned to I/O devices experiencing queue delays as indicated by their performance data, if the device is associated with a service class that has failed to meet one or more processing goals. These methods may operate on a single host, or in a multi-host environment. The methods may be operated individually, or concurrently. Methods are disclosed to manage contention between concurrently operating assignment methods, and between multiple hosts concurrently operating one or more assignment methods.

摘要翻译： 公开了一种用于动态管理参考诸如直接存取存储设备（DASD）的输入/输出（I / O）设备的基地址的别名地址分配的方法和计算机程序设备。 公开了两种不同的方法。 在一种方法中，根据I / O设备的性能分配别名地址。 在这种方法中，别名地址被分配给高度利用的设备，如设备性能数据所示，以便最大化I / O设备资源的有效利用。 在第二种方法中，使用工作负载管理原则来分配别名地址。 在这种方法中，每个I / O设备和使用每个设备的服务类别之间进行相关。 与第一种方法一样，为每个I / O设备生成性能数据。 如果设备与不符合一个或多个处理目标的服务类相关联，则别名地址被分配给遇到队列延迟的I / O设备，如性能数据所示。 这些方法可以在单个主机或多主机环境中运行。 这些方法可以单独操作或同时操作。 公开了用于管理并发操作分配方法之间的争用以及同时操作一个或多个分配方法的多个主机之间的争用的方法。

公开(公告)号：US07844709B2

公开(公告)日：2010-11-30

申请号：US11533558

申请日：2006-09-20

申请人： Jeffrey D. Aman ,  Yuk L. Chan ,  Yuksel Gunal ,  Hiren R. Shah ,  Mathew S. Thoennes ,  Peter B. Yocom

发明人： Jeffrey D. Aman ,  Yuk L. Chan ,  Yuksel Gunal ,  Hiren R. Shah ,  Mathew S. Thoennes ,  Peter B. Yocom

IPC分类号： G06F15/173

CPC分类号： G06F9/5077 ,  G06F9/5027

摘要： A method and apparatus for managing CPU resources of a logically partitioned computing environment without shared memory access. A logical partition needing additional resources sends a message requesting such resources to a central domain manager, which sends messages to other partitions in the same group requesting that they assess their ability to donate resources to the requesting partition. Upon receiving such assessment request, each logical partition assesses its ability to donate resources to the requesting partition and responds accordingly to the domain manager. If at least one partition responds that it can donate resources to the requesting partition, the domain manager sends a message to a selected donor partition requesting that it reconfigure itself to donate resources to the requesting partition. Upon receiving a notification from the donor partition that it has successfully reconfigured itself, the domain manager notifies the requesting partition, which reconfigures itself to accept the donated resources.

摘要翻译： 一种用于管理逻辑分区计算环境的CPU资源而不进行共享存储器访问的方法和装置。 需要额外资源的逻辑分区将向中央域管理器发送请求这样的资源的消息，该中央域管理器将消息发送到同一组中的其他分区，请求他们评估其向请求分区捐赠资源的能力。 在收到此类评估请求后，每个逻辑分区评估其向请求分区捐赠资源的能力，并相应地响应域管理器。 如果至少一个分区响应它可以向请求分区捐赠资源，则域管理器向选定的供体分区发送一条消息，请求重新配置自己以将资源捐赠给请求分区。 在从捐赠者分区接收到已经成功重新配置的通知之后，域管理器通知请求分区，其重新配置自己以接受所捐赠的资源。

公开(公告)号：US20080215846A1

公开(公告)日：2008-09-04

申请号：US11533558

申请日：2006-09-20

申请人： Jeffrey D. Aman ,  Yuk L. Chan ,  Yuksel Gunal ,  Hiren R. Shar ,  Matthew S. Thoennes ,  Peter B. Yocom

发明人： Jeffrey D. Aman ,  Yuk L. Chan ,  Yuksel Gunal ,  Hiren R. Shar ,  Matthew S. Thoennes ,  Peter B. Yocom

IPC分类号： G06F12/00

CPC分类号： G06F9/5077 ,  G06F9/5027

摘要： A method and apparatus for managing CPU resources of a logically partitioned computing environment without shared memory access. A logical partition needing additional resources sends a message requesting such resources to a central domain manager, which sends messages to other partitions in the same group requesting that they assess their ability to donate resources to the requesting partition. Upon receiving such assessment request, each logical partition assesses its ability to donate resources to the requesting partition and responds accordingly to the domain manager. If at least one partition responds that it can donate resources to the requesting partition, the domain manager sends a message to a selected donor partition requesting that it reconfigure itself to donate resources to the requesting partition. Upon receiving a notification from the donor partition that it has successfully reconfigured itself, the domain manager notifies the requesting partition, which reconfigures itself to accept the donated resources.

摘要翻译： 一种用于管理逻辑分区计算环境的CPU资源而不进行共享存储器访问的方法和装置。 需要额外资源的逻辑分区将向中央域管理器发送请求这样的资源的消息，该中央域管理器将消息发送到同一组中的其他分区，请求他们评估其向请求分区捐赠资源的能力。 在收到此类评估请求后，每个逻辑分区评估其向请求分区捐赠资源的能力，并相应地响应域管理器。 如果至少一个分区响应它可以向请求分区捐赠资源，则域管理器向选定的供体分区发送一条消息，请求重新配置自己以将资源捐赠给请求分区。 在从捐赠者分区接收到已经成功重新配置的通知之后，域管理器通知请求分区，其重新配置自己以接受所捐赠的资源。

公开(公告)号：US07096469B1

公开(公告)日：2006-08-22

申请号：US09677338

申请日：2000-10-02

申请人： Jeffrey P. Kubala ,  Jeffrey M. Nick ,  Peter B. Yocom

发明人： Jeffrey P. Kubala ,  Jeffrey M. Nick ,  Peter B. Yocom

IPC分类号： G06F9/46

CPC分类号： G06F9/5077

摘要： A method and apparatus for enforcing capacity limitations such as those imposed by software license agreements in an information handling system in which a physical machine is divided into a plurality of logical partitions, each of which is allocated a defined portion of processor resources by a logical partition manager. A software license manager specifies a maximum allowed consumption of processor resources by a program executing in one of the logical partitions. A workload manager also executing in the partition measures the actual consumption of processor resources by the logical partition over a specified averaging interval and compares it with the maximum allowed consumption. If the actual consumption exceeds the maximum allowed consumption, the workload manager calculates a capping pattern and interacts with the logical partition manager to cap the actual consumption of processor resources by the partition in accordance with the calculated capping pattern. To provide additional capping flexibility, partitions are assigned phantom weights that the logical partition manager adds to the total partition weight to determine whether the partition has exceeded its allowed share of processor resources for capping purposes. The logical partition thus becomes a “container” for the licensed program with an enforced processing capacity less than that of the entire machine.

摘要翻译： 一种用于执行容量限制的方法和装置，例如在信息处理系统中由软件许可协议强加的容量限制，其中物理机被分成多个逻辑分区，每个逻辑分区通过逻辑分区被分配给定义的处理器资源部分 经理。 软件许可证管理器通过在其中一个逻辑分区中执行的程序指定处理器资源的最大允许消耗。 还在分区中执行的工作负载管理器通过逻辑分区在指定的平均间隔内测量处理器资源的实际消耗，并将其与最大允许消耗进行比较。 如果实际消耗超过允许的最大消耗量，则工作负载管理器计算上限模式，并与逻辑分区管理器进行交互，以根据计算的上限模式来限制分区的处理器资源的实际消耗。 为了提供额外的上限灵活性，分区被分配幻影权重，逻辑分区管理器添加到总分区权重，以确定分区是否超过其允许的处理器资源份额以进行封顶。 因此，逻辑分区成为许可程序的“容器”，其强制处理能力小于整个机器的处理能力。