公开(公告)号：US20070240162A1

公开(公告)日：2007-10-11

申请号：US11763726

申请日：2007-06-15

申请人： David Coleman ,  Steven Froehlich ,  Joseph Hellerstein ,  Lawrence Hsiung ,  Edwin Lassettre ,  Todd Mummert ,  Mukund Raghavachari ,  Lance Russell ,  Maheswaran Surendra ,  Noshir Wadia ,  Peng Ye

发明人： David Coleman ,  Steven Froehlich ,  Joseph Hellerstein ,  Lawrence Hsiung ,  Edwin Lassettre ,  Todd Mummert ,  Mukund Raghavachari ,  Lance Russell ,  Maheswaran Surendra ,  Noshir Wadia ,  Peng Ye

IPC分类号： G06F9/00

CPC分类号： G06F11/008

摘要： Automated or autonomic techniques for managing deployment of one or more resources in a computing environment based on varying workload levels. The automated techniques may comprise predicting a future workload level based on data associated with the computing environment. Then, an estimation is performed to determine whether a current resource deployment is insufficient, sufficient, or overly sufficient to satisfy the future workload level. Then, one or more actions are caused to be taken when the current resource deployment is estimated to be insufficient or overly sufficient to satisfy the future workload level. Actions may comprise resource provisioning, resource tuning and/or admission control.

摘要翻译： 基于不同的工作负载级别来管理计算环境中的一个或多个资源的部署的自动或自主技术。 自动化技术可以包括基于与计算环境相关联的数据预测未来的工作负载水平。 然后，执行估计以确定当前资源部署是否不充足，足够或过度足以满足未来的工作负载水平。 然后，当估计当前资源部署不足够或过度足以满足未来的工作负载级别时，会采取一个或多个动作。 动作可以包括资源调配，资源调整和/或准入控制。

公开(公告)号：US06745294B1

公开(公告)日：2004-06-01

申请号：US09877539

申请日：2001-06-08

申请人： Kenneth Mark Wilson ,  Fong Pong ,  Lance Russell ,  Tung Nguyen ,  Lu Xu

发明人： Kenneth Mark Wilson ,  Fong Pong ,  Lance Russell ,  Tung Nguyen ,  Lu Xu

IPC分类号： G06F1200

CPC分类号： G06F12/0808 ,  G06F12/0804

摘要： A method is provided for cache flushing in a computer system having a processor, a cache, a synchronization primitive detector, and a cache flush engine. The method includes providing a synchronization primitive from the processor into the computer system; detecting the synchronization primitive in the synchronization primitive detector; providing a trigger signal from the synchronization primitive detector in response to detection of the synchronization primitive; providing cache information from the recall unit into the computer system in response to the trigger signal; and flushing the cache in response to the cache information in the computer system.

摘要翻译： 提供了一种用于具有处理器，高速缓存，同步原语检测器和高速缓存冲洗引擎的计算机系统中的高速缓存冲洗的方法。 该方法包括从处理器向计算机系统提供同步原语; 检测同步原语检测器中的同步原语; 响应于同步原语的检测，提供来自同步原语检测器的触发信号; 响应于所述触发信号，从所述调用单元向计算机系统提供高速缓存信息; 并响应于计算机系统中的缓存信息来刷新高速缓存。

公开(公告)号：US08689046B2

公开(公告)日：2014-04-01

申请号：US12940604

申请日：2010-11-05

申请人： David J. Craft ,  Lance Russell

发明人： David J. Craft ,  Lance Russell

IPC分类号： G06F11/00

CPC分类号： G06F11/2097 ,  G06F11/1469 ,  G06F11/1471 ,  G06F11/1474 ,  G06F11/1662 ,  G06F11/2038 ,  G06F11/2048

摘要： Accurate recovery of a primary server at a recovery server is accomplished with reduced network overhead by maintaining at the recovery server checkpoints taken over time of the primary server and an intention log of logical transactions pending and complete by the primary server. The recovery server is brought to the operational state of the primary server as of failure at the primary server by recovering the most recent checkpoint and then executing the transactions indicated by the intention log as received but not complete as of the time that the checkpoint was taken.

摘要翻译： 恢复服务器上的主服务器的准确恢复是通过在主服务器的时间段内维护恢复服务器检查点和由主服务器等待和完成的逻辑事务的意图日志来减少网络开销而实现的。 通过恢复最近的检查点，然后执行由意图日志指示的事务，但是到达检查点的时间未完成，恢复服务器由于主服务器故障而处于主服务器的操作状态。 。

公开(公告)号：US20070027999A1

公开(公告)日：2007-02-01

申请号：US11193841

申请日：2005-07-29

申请人： James Allen ,  Matthew Kalos ,  Thomas Mathews ,  Lance Russell

发明人： James Allen ,  Matthew Kalos ,  Thomas Mathews ,  Lance Russell

IPC分类号： G06F15/173

CPC分类号： G06F11/0775 ,  G06F11/0727 ,  G06F11/0784 ,  H04L41/069

摘要： A system for coordinating error tracking, level setting and reporting among the various layers/components of a distributed storage system. Each component of the distributed system includes a trigger generation and response (TGR) utility, which generates an error tracking trigger (ETT), comprising: (1) an action that the initiator wants the stack's error tracking mechanisms to take; (2) a message that the initiator wants the stack to immediately post in its logs; and (3) a route/direction that the trigger is to be transmitted through the stack. The ETT is transmitted one layer at a time through the stack, and each intervening layer of the stack is equipped with a utility to examine the ETT and take the appropriate action(s), designated by the trigger. An error log is maintained by each layer of the stack and used to record information about the error and enable user determination of the source, timing and cause of errors.

摘要翻译： 用于协调分布式存储系统的各个层/组件之间的错误跟踪，级别设置和报告的系统。 分布式系统的每个组件包括产生错误跟踪触发器（ETT）的触发器生成和响应（TGR）实用程序，其包括：（1）启动器希望堆栈的错误跟踪机制采取的动作; （2）发起者希望堆栈在其日志中立即发布的消息; 和（3）触发器将通过堆栈传输的路由/方向。 ETT通过堆叠一次传输一层，堆叠的每个中间层配备有一个实用程序来检查ETT并采取由触发器指定的适当的动作。 错误日志由堆栈的每一层维护，用于记录有关错误的信息，并使用户可以确定错误的来源，时间和原因。

公开(公告)号：US06360231B1

公开(公告)日：2002-03-19

申请号：US09258608

申请日：1999-02-26

申请人： Fong Pong ,  Lance Russell ,  Tung Nguyen

发明人： Fong Pong ,  Lance Russell ,  Tung Nguyen

IPC分类号： G06F1730

CPC分类号： G06F12/0815 ,  Y10S707/99952

摘要： A cache coherent distributed shared memory multi-processor computer system is provided which supports transactional memory semantics. A cache flushing engine and temporary buffer allow selective forced write-backs of dirty cache lines to the home memory. A flush can be performed from the updated cache to the temporary buffer and then to the home memory after confirmation of receipt or from the updated cache to the home memory directly with the temporary buffer holding the old data until confirmation that the home memory contains the update.

摘要翻译： 提供了一种支持事务性存储器语义的高速缓存一致分布式共享存储器多处理器计算机系统。 高速缓存刷新引擎和临时缓冲区允许有选择地将脏缓存行强制回写到家庭存储器。 可以在保存了旧数据的临时缓冲器之后，从更新的缓存到临时缓冲区执行刷新，然后在确认接收之后到家庭存储器或从更新的高速缓存直接到家庭存储器，直到确认家庭存储器包含更新 。

公开(公告)号：US20080098184A1

公开(公告)日：2008-04-24

申请号：US11955505

申请日：2007-12-13

申请人： Matthew Huras ,  Thomas Mathews ,  Lance Russell

发明人： Matthew Huras ,  Thomas Mathews ,  Lance Russell

IPC分类号： G06F13/00

CPC分类号： G06F17/30067

摘要： A method, apparatus, and computer program product for storage pools with write atomicity. An abstraction manager enforces write atomicity and disallows options which are inconsistent with write atomicity. The abstraction manager constructs through a physical device interface a logical continuous view of a storage pool in a manner consistent with write atomicity. Applications collect information specific to write atomicity from the abstraction manager through an application interface.

摘要翻译： 一种具有写入原子性的存储池的方法，装置和计算机程序产品。 抽象管理器强制写入原子性，并禁止与写入原子性不一致的选项。 抽象管理器通过物理设备接口以与写入原子性一致的方式构建存储池的逻辑连续视图。 应用程序通过应用程序接口从抽象管理器收集特定于写入原子性的信息。

公开(公告)号：US20060235990A1

公开(公告)日：2006-10-19

申请号：US11109089

申请日：2005-04-19

申请人： James Allen ,  Matthew Kalos ,  Thomas Mathews ,  George Penokie ,  Lance Russell ,  Gail Spear

发明人： James Allen ,  Matthew Kalos ,  Thomas Mathews ,  George Penokie ,  Lance Russell ,  Gail Spear

IPC分类号： G06F3/00 ,  G06F15/16

CPC分类号： H04L67/1097

摘要： A method, apparatus, and computer instructions for controlling data flow. A control message is formed for the data flow in response to an event while the data flow is occurring. The control message includes a data type, an action, and a duration. The control message is sent to a receiver data processing system, wherein the receiver data processing system modifies the data flow to the data processing system using the control message.

公开(公告)号：US06675262B1

公开(公告)日：2004-01-06

申请号：US09877368

申请日：2001-06-08

申请人： Kenneth Mark Wilson ,  Fong Pong ,  Lance Russell ,  Tung Nguyen ,  Lu Xu

发明人： Kenneth Mark Wilson ,  Fong Pong ,  Lance Russell ,  Tung Nguyen ,  Lu Xu

IPC分类号： G06F1200

CPC分类号： G06F12/0808 ,  G06F12/0804 ,  G06F12/0817 ,  G06F2212/2542

摘要： A cache coherent distributed shared memory multi-processor computer system is provided with a memory controller which includes a recall unit. The recall unit allows selective forced write-backs of dirty cache lines to the home memory. After a request is posted in the recall unit, a recall (“flush”) command is issued which forces the owner cache to write-back the dirty cache line to be flushed. The memory controller will inform the recall unit as each recall operation is completed. The recall unit operation will be interrupted when all flush requests are completed.

摘要翻译： 高速缓存一致分布式共享存储器多处理器计算机系统具有包括调用单元的存储器控​​制器。 调用单元允许将脏的高速缓存行的选择性强制回写到家庭存储器。 在调用单元中发布请求后，会发出召回（“flush”）命令，强制所有者高速缓存写回要清除的脏高速缓存行。 每次召回操作完成后，存储器控制器将通知召回单元。 所有刷新请求完成后，调用单元操作将中断。

公开(公告)号：US20070233897A1

公开(公告)日：2007-10-04

申请号：US11397846

申请日：2006-04-04

申请人： David Craft ,  Vinit Jain ,  Lance Russell ,  Edward Shvartsman

发明人： David Craft ,  Vinit Jain ,  Lance Russell ,  Edward Shvartsman

IPC分类号： G06F15/173

CPC分类号： H04L29/12924 ,  H04L29/12377 ,  H04L45/00 ,  H04L61/2517 ,  H04L61/6063 ,  H04L67/327 ,  H04L69/16 ,  H04L69/162

摘要： In a computer system divided into multiple separate workload partitions, wherein at least one of the partitions contains multiple applications, and a loopback interface is made available to each partition, a method is provided for routing packets from one application to another application. In one embodiment of the invention, each packet to be routed from one application to another application in the same home partition comprises a first packet, and all other packets comprise second packets. The method comprises the steps of assigning the same pre-specified IP address to each of the first packets, and routing each of the first packets from its home partition to a loopback interface at the IP network processing layer. The method further includes marking the first packets to identify the home partition of each first packet, and directing the marked first packets to a mechanism configured to deliver each first packet only to its home partition, in response to the markings. Each second packet is assigned the IP address of its intended destination, and routed thereto over the loopback interface.

摘要翻译： 在划分成多个单独的工作负载分区的计算机系统中，其中至少一个分区包含多个应用，并且使环回接口可用于每个分区，提供了用于将分组从一个应用路由到另一应用的路由的方法。 在本发明的一个实施例中，要从一个应用路由到同一家庭分区中的另一应用的每个分组包括第一分组，并且所有其他分组包括第二分组。 该方法包括以下步骤：将相同的预先指定的IP地址分配给每个第一分组，并将第一分组中的每一个从其归属分区路由到IP网络处理层的环回接口。 该方法还包括标记第一分组以识别每个第一分组的归属分区，以及将标记的第一分组引导到被配置为将每个第一分组仅传送到其归属分区的机制，以响应于标记。 每个第二个分组被分配其预期目的地的IP地址，并通过回送接口被路由到其上。

公开(公告)号：US20070038678A1

公开(公告)日：2007-02-15

申请号：US11198592

申请日：2005-08-05

申请人： James Allen ,  Matthew Huras ,  Thomas Mathews ,  Lance Russell

发明人： James Allen ,  Matthew Huras ,  Thomas Mathews ,  Lance Russell

IPC分类号： G06F17/30

CPC分类号： G06F9/5011

摘要： A method and system for enabling dynamic matching of storage utilization characteristics of a host system application with the characteristics of the available storage pools of an attached distributed storage system, in order to provide an optimal match between the application and selected storage pool. An abstraction manager is provided, enhanced with a storage device configuration utility/module, which performs a series of tasks to (1) obtain/collect the correct configuration information from each connected storage device or storage pools and/or (2) calculate the configuration information when the information is not readily available. The storage device configuration module then normalizes, collates and matches the configuration information to the various applications running on the host system and/or outputs the information to a user/administrator of the host system via a software interface. By using the collected/calculated configuration information, applications are assigned to an optimal storage pool in an intelligent and efficient manner.

摘要翻译： 一种用于使主机系统应用程序的存储利用特性与附加分布式存储系统的可用存储池的特征能够动态匹配的方法和系统，以便提供应用程序和所选存储池之间的最佳匹配。 提供抽象管理器，增强了存储设备配置实用程序/模块，执行一系列任务以（1）从每个连接的存储设备或存储池获取/收集正确的配置信息和/或（2）计算配置 当信息不容易获得时的信息。 然后，存储设备配置模块将配置信息规范化，整理和匹配到主机系统上运行的各种应用和/或经由软件接口将信息输出到主机系统的用户/管理员。 通过使用收集/计算的配置信息，应用程序以智能和有效的方式分配给最佳存储池。