公开(公告)号：US08489812B2

公开(公告)日：2013-07-16

申请号：US12915153

申请日：2010-10-29

申请人： Kavita Chavda ,  David P. Goodman ,  Sandeep Gopisetty ,  Larry S. McGimsey ,  James E. Olson ,  Aameek Singh

发明人： Kavita Chavda ,  David P. Goodman ,  Sandeep Gopisetty ,  Larry S. McGimsey ,  James E. Olson ,  Aameek Singh

IPC分类号： G06F12/00

CPC分类号： G06F3/0689 ,  G06F3/0605 ,  G06F3/0619 ,  G06F3/0665 ,  G06F3/067

摘要： An approach for automatic storage planning and provisioning within a clustered computing environment is provided. Planning input for a set of storage area network volume controllers (SVCs) will be received within the clustered computing environment, the planning input indicating a potential load on the SVCs and its associated components. Analytical models (e.g., from vendors) can be also used that allow for a load to be accurately estimated on the storage components. Configuration data for a set of storage components (i.e., the set of SVCs, a set of managed disk (Mdisk) groups associated with the set of SVCs, and a set of backend storage systems) will also be collected. Based on this configuration data, the set of storage components will be filtered to identify candidate storage components capable of addressing the potential load. Then, performance data for the candidate storage components will be analyzed to identify an SVC and an Mdisk group to address the potential load.

摘要翻译： 提供了一种在集群计算环境中自动存储规划和配置的方法。 将在集群计算环境内接收一组存储区域网络卷控制器（SVC）的规划输入，规划输入指示SVC及其相关组件的潜在负载。 还可以使用分析模型（例如，来自供应商），允许在存储组件上准确地估计负载。 还将收集用于一组存储组件（即，一组SVC，与该组SVC相关联的一组受管理磁盘（Mdisk）组）和一组后端存储系统的配置数据。 基于该配置数据，将对该组存储组件进行滤波以识别能够寻址潜在负载的候选存储组件。 然后，将分析候选存储组件的性能数据，以识别SVC和Mdisk组以解决潜在负载。

公开(公告)号：US08489809B2

公开(公告)日：2013-07-16

申请号：US12831455

申请日：2010-07-07

申请人： Kavita Chavda ,  David P. Goodman ,  Sandeep Gopisetty ,  Seshashayee S. Murthy ,  Aameek Singh

发明人： Kavita Chavda ,  David P. Goodman ,  Sandeep Gopisetty ,  Seshashayee S. Murthy ,  Aameek Singh

IPC分类号： G06F21/00

CPC分类号： H04L67/1097 ,  G06F3/0607 ,  G06F3/0631 ,  G06F3/0664 ,  G06F3/067

摘要： Embodiments of the present invention provide an approach for intelligent storage planning and planning within a clustered computing environment (e.g., a cloud computing environment). Specifically, embodiments of the present invention will first determine/identify a set of storage area network volume controllers (SVCs) that is accessible from a host that has submitted a request for access to storage. Thereafter, a set of managed disk (mdisk) groups (i.e., corresponding to the set of SVCs) that are candidates for satisfying the request will be determined. This set of mdisk groups will then be filtered based on available space therein, a set of user/requester preferences, and optionally, a set of performance characteristics. Then, a particular mdisk group will be selected from the set of mdisk groups based on the filtering.

摘要翻译： 本发明的实施例提供了一种用于集群计算环境（例如，云计算环境）内的智能存储规划和规划的方法。 具体地，本发明的实施例将首先确定/识别可从已经提交了访问存储请求的主机可访问的一组存储区域网络卷控制器（SVC）。 此后，将确定作为满足该请求的候选的一组被管理盘（mdisk）组（即，对应于一组SVC）。 然后，这组mdisk组将根据其中的可用空间，一组用户/请求者首选项以及可选的一组性能特征进行过滤。 然后，将根据过滤从一组mdisk组中选择一个特定的mdisk组。

公开(公告)号：US08478845B2

公开(公告)日：2013-07-02

申请号：US12857005

申请日：2010-08-16

申请人： Sandip Agarwala ,  Richard J. Ayala ,  Kavita Chavda ,  Sandeep Gopisetty

发明人： Sandip Agarwala ,  Richard J. Ayala ,  Kavita Chavda ,  Sandeep Gopisetty

IPC分类号： G06F15/177 ,  G06F15/167 ,  G06F15/173

CPC分类号： G06F15/177 ,  G06F3/0605 ,  G06F3/0629 ,  G06F3/067 ,  G06F9/5061 ,  H04L41/5054 ,  H04L67/1097

摘要： Embodiments discussed in this disclosure provide an integrated provisioning framework that automates the process of provisioning storage resources, end-to-end, for an enterprise storage cloud environment. Such embodiments configure and orchestrate the deployment of a user's workload and, at the same time, provide optimization across a multitude of storage cloud resources. Along these lines, input is received in the form of workload requirements and configuration information for available system resources. Based on the input, a set (at least one) of storage cloud configuration plans is developed that satisfy the workload requirements. A set of scripts is then generated that orchestrate the deployment and configuration of different software and hardware components based on the plans.

摘要翻译： 在本公开中讨论的实施例提供了一种集成供应框架，其自动化为企业存储云环境提供端到端的存储资源的过程。 这样的实施例配置和协调用户工作负载的部署，并且同时在多个存储云资源上提供优化。 沿着这些方式，以可用系统资源的工作负载需求和配置信息的形式接收输入。 基于输入，开发满足工作负载要求的一组（至少一个）存储云配置计划。 然后生成一组脚本，根据计划编排不同软件和硬件组件的部署和配置。

公开(公告)号：US08407501B2

公开(公告)日：2013-03-26

申请号：US13073081

申请日：2011-03-28

申请人： Sandip Agarwala ,  Eric K. Butler ,  Sandeep Gopisetty ,  Kavita Chavda

发明人： Sandip Agarwala ,  Eric K. Butler ,  Sandeep Gopisetty ,  Kavita Chavda

IPC分类号： G06F1/26

CPC分类号： H04L47/70 ,  G06F3/0625 ,  G06F3/0635 ,  G06F3/067 ,  Y02D10/154

摘要： Embodiments of the present invention provide an approach to provision storage resources (e.g., across an enterprise storage system (ESS) such as a general parallel file system (GPFS) or the like) for different workloads in an energy efficient manner. The system evaluates different energy profiles/workloads' energy consumption characteristics of storage devices to determine an allocation plan that reduces the energy cost (e.g., results in the lowest cost/energy consumption for handling a storage workload). In a typical embodiment, energy consumption characteristics for handling a particular storage workload will be determined. Thereafter, a type of storage device capable of handling the workload will be determined. Then, an allocation plan that results in the most efficient energy consumption for handling the workload will be developed. In general, the allocation plan is based upon the energy consumption characteristics and an energy efficiency algorithm. The energy efficiency algorithm serves to identify storage device(s) that can handle the workload in such a way as to reduce total energy consumption and, accordingly, costs. Along these lines, the energy efficiency algorithm may also consider other factors such as capacity and load of storage devices and service level agreement (SLA) terms in addition to energy costs (e.g., over times of day and/or days of week). In any event, at least one storage device can then be selected for handling the storage workload according to the allocation plan.

摘要翻译： 本发明的实施例提供了一种以能量效率方式为不同工作负载提供存储资源（例如，跨企业存储系统（ESS），诸如通用并行文件系统（GPFS）等）的方法。 该系统评估存储设备的不同能量简档/工作负载的能量消耗特征，以确定降低能量成本的分配计划（例如，导致用于处理存储工作负载的最低成本/能量消耗）。 在典型的实施例中，将确定用于处理特定存储工作负载的能量消耗特性。 此后，可以确定能够处理工作量的一种存储装置。 然后，将开发出一种能够最有效地处理工作负载能耗的分配计划。 一般来说，分配方案是基于能量消耗特性和能量效率算法。 能源效率算法用于识别能够处理工作负载的存储设备，以减少总能量消耗，并因此降低成本。 除此之外，能源效率算法还可以考虑其他因素，例如存储设备的容量和负载以及服务水平协议（SLA）术语以及能量成本（例如，超过一天和/或几周的时间）。 在任何情况下，可以根据分配计划选择至少一个存储设备来处理存储工作负载。

公开(公告)号：US20120254640A1

公开(公告)日：2012-10-04

申请号：US13073081

申请日：2011-03-28

申请人： Sandip Agarwala ,  Eric K. Butler ,  Sandeep Gopisetty ,  Kavita Chavda

发明人： Sandip Agarwala ,  Eric K. Butler ,  Sandeep Gopisetty ,  Kavita Chavda

IPC分类号： G06F12/02 ,  G06F1/32

CPC分类号： H04L47/70 ,  G06F3/0625 ,  G06F3/0635 ,  G06F3/067 ,  Y02D10/154

摘要： Embodiments of the present invention provide an approach to provision storage resources (e.g., across an enterprise storage system (ESS) such as a general parallel file system (GPFS) or the like) for different workloads in an energy efficient manner. The system evaluates different energy profiles/workloads' energy consumption characteristics of storage devices to determine an allocation plan that reduces the energy cost (e.g., results in the lowest cost/energy consumption for handling a storage workload). In a typical embodiment, energy consumption characteristics for handling a particular storage workload will be determined. Thereafter, a type of storage device capable of handling the workload will be determined. Then, an allocation plan that results in the most efficient energy consumption for handling the workload will be developed. In general, the allocation plan is based upon the energy consumption characteristics and an energy efficiency algorithm. The energy efficiency algorithm serves to identify storage device(s) that can handle the workload in such a way as to reduce total energy consumption and, accordingly, costs. Along these lines, the energy efficiency algorithm may also consider other factors such as capacity and load of storage devices and service level agreement (SLA) terms in addition to energy costs (e.g., over times of day and/or days of week). In any event, at least one storage device can then be selected for handling the storage workload according to the allocation plan.

摘要翻译： 本发明的实施例提供了一种以能量效率方式为不同工作负载提供存储资源（例如，跨企业存储系统（ESS），诸如通用并行文件系统（GPFS）等）的方法。 该系统评估存储设备的不同能量简档/工作负载的能量消耗特征，以确定降低能量成本的分配计划（例如，导致用于处理存储工作负载的最低成本/能量消耗）。 在典型的实施例中，将确定用于处理特定存储工作负载的能量消耗特性。 此后，可以确定能够处理工作量的一种存储装置。 然后，将开发出一种能够最有效地处理工作负载能耗的分配计划。 一般来说，分配方案是基于能量消耗特性和能量效率算法。 能源效率算法用于识别能够处理工作负载的存储设备，以减少总能量消耗，并因此降低成本。 除此之外，能源效率算法还可以考虑其他因素，例如存储设备的容量和负载以及服务水平协议（SLA）术语以及能量成本（例如，超过一天和/或几周的时间）。 在任何情况下，可以根据分配计划选择至少一个存储设备来处理存储工作负载。

公开(公告)号：US20120042033A1

公开(公告)日：2012-02-16

申请号：US12856019

申请日：2010-08-13

申请人： Richard J. Ayala, JR. ,  Eric K. Butler ,  Kavita Chavda ,  Mihail C. Constantinescu ,  Reshu Jain ,  Prasenjit Sarkar ,  Aameek Singh

发明人： Richard J. Ayala, JR. ,  Eric K. Butler ,  Kavita Chavda ,  Mihail C. Constantinescu ,  Reshu Jain ,  Prasenjit Sarkar ,  Aameek Singh

IPC分类号： G06F15/167 ,  G06F15/173

CPC分类号： G06F9/4856

摘要： Embodiments of the present invention provide an approach for migrating virtual machines across network (e.g., WAN) separated data centers (e.g., storage clouds). Specifically, under embodiments of the present invention, a first storage system associated with a first data center is synchronized with a second storage system associated with a second data center via a storage system link. Then, a minimal state of a virtual machine is migrated from a first computer in the first data center to a second computer in the second data center via a WAN link. Using the minimal state, the virtual machine is stored in the second computer. Thereafter, the storage system link is terminated. In addition, as updated pages are received in memory of the first computer, they are migrated to the second computer via the WAN link. Once this migration is complete, the WAN link can be terminated. Therefore, embodiments of the present invention provide at least two forms of synchronization: computational synchronization and storage synchronization.

摘要翻译： 本发明的实施例提供了一种用于跨网络（例如，WAN）分离的数据中心（例如，存储云）迁移虚拟机的方法。 具体地，在本发明的实施例中，与第一数据中心相关联的第一存储系统经由存储系统链路与与第二数据中心相关联的第二存储系统同步。 然后，通过WAN链路将虚拟机的最小状态从第一数据中心的第一计算机迁移到第二数据中心中的第二计算机。 使用最小状态，虚拟机存储在第二台计算机中。 此后，终止存储系统链路。 另外，随着在第一台计算机的存储器中接收到更新的页面，它们将通过WAN链路迁移到第二台计算机。 迁移完成后，可以终止WAN链路。 因此，本发明的实施例提供至少两种形式的同步：计算同步和存储同步。

公开(公告)号：US09582319B2

公开(公告)日：2017-02-28

申请号：US12856019

申请日：2010-08-13

申请人： Richard J. Ayala, Jr. ,  Eric K. Butler ,  Kavita Chavda ,  Mihail C. Constantinescu ,  Reshu Jain ,  Prasenjit Sarkar ,  Aameek Singh

发明人： Richard J. Ayala, Jr. ,  Eric K. Butler ,  Kavita Chavda ,  Mihail C. Constantinescu ,  Reshu Jain ,  Prasenjit Sarkar ,  Aameek Singh

IPC分类号： G06F15/167 ,  G06F9/48

CPC分类号： G06F9/4856

摘要： Embodiments of the present invention provide an approach for migrating virtual machines across network (e.g., WAN) separated data centers (e.g., storage clouds). Specifically, under embodiments of the present invention, a first storage system associated with a first data center is synchronized with a second storage system associated with a second data center via a storage system link. Then, a minimal state of a virtual machine is migrated from a first computer in the first data center to a second computer in the second data center via a WAN link. Using the minimal state, the virtual machine is stored in the second computer. Thereafter, the storage system link is terminated. In addition, as updated pages are received in memory of the first computer, they are migrated to the second computer via the WAN link. Once this migration is complete, the WAN link can be terminated. Therefore, embodiments of the present invention provide at least two forms of synchronization: computational synchronization and storage synchronization.

摘要翻译： 本发明的实施例提供了一种用于跨网络（例如，WAN）分离的数据中心（例如，存储云）迁移虚拟机的方法。 具体地，在本发明的实施例中，与第一数据中心相关联的第一存储系统经由存储系统链路与与第二数据中心相关联的第二存储系统同步。 然后，通过WAN链路将虚拟机的最小状态从第一数据中心的第一计算机迁移到第二数据中心中的第二计算机。 使用最小状态，虚拟机存储在第二台计算机中。 此后，终止存储系统链路。 另外，随着在第一台计算机的存储器中接收到更新的页面，它们将通过WAN链路迁移到第二台计算机。 迁移完成后，可以终止WAN链路。 因此，本发明的实施例提供至少两种同步形式：计算同步和存储同步。

公开(公告)号：US20140074794A1

公开(公告)日：2014-03-13

申请号：US13610929

申请日：2012-09-12

申请人： Kavita Chavda ,  Nagapramod S. Mandagere ,  Ramani R. Routray ,  Pin Zhou

发明人： Kavita Chavda ,  Nagapramod S. Mandagere ,  Ramani R. Routray ,  Pin Zhou

IPC分类号： G06F17/30

CPC分类号： G06F11/1458 ,  G06F11/1453 ,  G06F11/1469 ,  G06F17/3015 ,  G06F17/30194 ,  G06F17/30958 ,  G06F2201/84

摘要： A computer identifies a plurality of data retrieval requests that may be serviced using a plurality of unique data chunks. The computer services the data retrieval requests by utilizing at least one of the unique data chunks. At least one of the unique data chunks can be utilized for servicing two or more of the data retrieval requests. The computer determines a servicing sequence for the plurality of data retrieval requests such that the two or more of the data retrieval requests that can be serviced utilizing the at least one of the unique data chunks are serviced consecutively. The computer services the plurality of data retrieval requests according to the servicing sequence.

摘要翻译： 计算机识别可以使用多个唯一数据块来服务的多个数据检索请求。 计算机通过利用至少一个唯一数据块来服务数据检索请求。 可以利用至少一个唯一数据块来服务两个或多个数据检索请求。 计算机确定多个数据检索请求的服务顺序，使得可以使用至少一个唯一数据块来服务的两个或多个数据检索请求被连续地服务。 计算机根据服务顺序对多个数据检索请求进行服务。

公开(公告)号：US20130326279A1

公开(公告)日：2013-12-05

申请号：US13482455

申请日：2012-05-29

申请人： Kavita Chavda ,  Nagapramod S. Mandagere ,  Steven Pantridge ,  Ramani R. Routray

发明人： Kavita Chavda ,  Nagapramod S. Mandagere ,  Steven Pantridge ,  Ramani R. Routray

IPC分类号： G06F11/28

CPC分类号： G06Q10/06315 ,  G06F3/0484 ,  G06F11/1458 ,  G06F11/3672 ,  G06F17/30371 ,  G06F2201/82 ,  G06F2201/835

摘要： A solution for validating a set of data protection solutions is provided. A validation scenario can be defined, which can include data corresponding to a set of attributes for the validation scenario. The attributes can include a time frame for the validation scenario. The validation scenario also can include a set of backup images to be validated, each of which is generated using one of the set of data protection solutions. The set of backup images can be identified using the time frame. A set of resource requirements for implementing the validation scenario can be determined based on the set of backup images and the set of attributes for the validation scenario.

公开(公告)号：US08495018B2

公开(公告)日：2013-07-23

申请号：US13168066

申请日：2011-06-24

申请人： Kavita Chavda ,  Nagapramod S. Mandagere ,  Sandeep M. Uttamchandani ,  Pin Zhou

发明人： Kavita Chavda ,  Nagapramod S. Mandagere ,  Sandeep M. Uttamchandani ,  Pin Zhou

IPC分类号： G06F17/00 ,  G06F17/30

CPC分类号： G06F17/30581 ,  G06F17/30017 ,  G06F17/30283 ,  G06F17/30578

摘要： Embodiments of the present invention provide an approach for providing non-disruptive transitioning of application replication configurations and proactive analysis of possible error scenarios. Specifically, under embodiments of the present invention, a common integration model (CIM)-compatible representation of a system replication plan is provided in a computer data structure. Based on the representation, a hierarchical tree data structure having a set of nodes is created. A set of system configuration updates pertaining to the set of nodes are then classified (e.g., based upon the type of configuration update). Once the set of nodes has been classified, the set of nodes may then be analyzed to determine if any nodes of the set are isomorphic. If so, the plan can be modified accordingly. In any event, the replication plan (or modified replication plan) may then be implemented.

摘要翻译： 本发明的实施例提供了一种用于提供应用复制配置的非中断转换和可能的错误情景的主动分析的方法。 具体地，在本发明的实施例中，在计算机数据结构中提供了系统复制计划的公共集成模型（CIM）兼容表示。 基于该表示，创建具有一组节点的分层树数据结构。 然后对与该组节点有关的一组系统配置更新进行分类（例如，基于配置更新的类型）。 一旦节点集合被分类，则可以分析节点集合以确定集合中的任何节点是否是同构的。 如果是这样，可以相应地修改计划。 无论如何，可以实现复制计划（或修改的复制计划）。