公开(公告)号：US08935500B1

公开(公告)日：2015-01-13

申请号：US13293516

申请日：2011-11-10

申请人： Ajay Gulati ,  Irfan Ahmad ,  Carl A. Waldspurger ,  Chethan Kumar

发明人： Ajay Gulati ,  Irfan Ahmad ,  Carl A. Waldspurger ,  Chethan Kumar

IPC分类号： G06F12/00

CPC分类号： G06F11/3485 ,  G06F3/0613 ,  G06F3/0647 ,  G06F3/067 ,  G06F11/3433 ,  G06F11/3452 ,  G06F2201/815 ,  G06F2206/1012

摘要： Distributed storage resources having multiple storage units are managed based on data collected from online monitoring of workloads on the storage units and performance characteristics of the storage units. The collected data is sampled at discrete time intervals over a time period of interest, such as a congested time period. Normalized load metrics are computed for each storage unit based on time-correlated sums of the workloads running on the storage unit over the time period of interest and the performance characteristic of the storage unit. Workloads that are migration candidates and storage units that are migration destinations are determined from a representative value of the computed normalized load metrics, which may be the 90th percentile value or a weighted sum of two or more different percentile values.

摘要翻译： 基于从存储单元上的工作负载的在线监视和存储单元的性能特征收集的数据来管理具有多个存储单元的分布式存储资源。 收集的数据在感兴趣的时间段（例如拥塞的时间段）以离散的时间间隔被采样。 基于在感兴趣的时间段上存储单元上运行的工作负载和存储单元的性能特性的时间相关的和来计算每个存储单元的归一化负载度量。 作为迁移目的地的迁移候选和存储单元的工作负载是根据计算的归一化负载度量的代表值确定的，其可以是第90百分位值或两个或多个不同百分位数值的加权和。

公开(公告)号：US20110072208A1

公开(公告)日：2011-03-24

申请号：US12566435

申请日：2009-09-24

申请人： Ajay GULATI ,  Irfan AHMAD ,  Chethan KUMAR

发明人： Ajay GULATI ,  Irfan AHMAD ,  Chethan KUMAR

IPC分类号： G06F12/00 ,  G06F12/16

CPC分类号： G06F11/3485 ,  G06F3/0613 ,  G06F3/0647 ,  G06F3/067 ,  G06F11/3433 ,  G06F11/3447 ,  G06F2201/815 ,  G06F2206/1012

摘要： Distributed storage resources are managed based on data collected from online monitoring of workloads on the storage resources and performance characteristics of the storage resources. Load metrics are calculated from the collected data and used to identify workloads that are migration candidates and storage units that are migration destinations, so that load balancing across the distributed storage resources can be achieved.

摘要翻译： 分布式存储资源根据从存储资源的工作负载和存储资源的性能特征的在线监控收集的数据进行管理。 负载指标由收集的数据计算，用于识别作为迁移目的地的迁移候选和存储单元的工作负载，从而可以实现跨分布式存储资源的负载平衡。

公开(公告)号：US08914598B2

公开(公告)日：2014-12-16

申请号：US12566435

申请日：2009-09-24

申请人： Ajay Gulati ,  Irfan Ahmad ,  Chethan Kumar

发明人： Ajay Gulati ,  Irfan Ahmad ,  Chethan Kumar

IPC分类号： G06F12/00

CPC分类号： G06F11/3485 ,  G06F3/0613 ,  G06F3/0647 ,  G06F3/067 ,  G06F11/3433 ,  G06F11/3447 ,  G06F2201/815 ,  G06F2206/1012

摘要： Distributed storage resources are managed based on data collected from online monitoring of workloads on the storage resources and performance characteristics of the storage resources. Load metrics are calculated from the collected data and used to identify workloads that are migration candidates and storage units that are migration destinations, so that load balancing across the distributed storage resources can be achieved.

摘要翻译： 分布式存储资源根据从存储资源的工作负载和存储资源的性能特征的在线监控收集的数据进行管理。 负载指标由收集的数据计算，用于识别作为迁移目的地的迁移候选和存储单元的工作负载，从而可以实现跨分布式存储资源的负载平衡。

公开(公告)号：US20060036387A1

公开(公告)日：2006-02-16

申请号：US10710873

申请日：2004-08-10

申请人： Chethan Kumar ,  Ravishanker PASUPULETI

发明人： Chethan Kumar ,  Ravishanker PASUPULETI

IPC分类号： G01D18/00

CPC分类号： G01R31/3191 ,  G01R31/31727 ,  G01R31/31937

摘要： A software controlled mechanism causing a test equipment to place the edges of test signals accurately. The mechanism determines expected time of occurrence of an edge of a signal in relation to a tester cycle time. The mechanism sends commands to the test equipment to receive back the signal (of interest) in multiple cycles and provides the time points corresponding to the edge in the multiple cycles. The software controlled mechanism computes an error based on the time points and the expected time, and adjusts the timing of the edges of the signal according to the error. Such computation and adjustment are performed until the error is within an acceptable range.

摘要翻译： 一种软件控制机制，使测试设备准确地放置测试信号的边缘。 该机制确定相对于测试器循环时间的信号边缘的预期发生时间。 该机制向测试设备发送命令以接收多个周期的信号（感兴趣的），并提供与多个周期中的边缘相对应的时间点。 软件控制机构根据时间点和预期时间计算误差，根据误差调整信号边沿的时序。 执行这样的计算和调整，直到错误在可接受的范围内。