-
公开(公告)号：US07895352B2
公开(公告)日：2011-02-22
申请号：US12021873
申请日：2008-01-29
申请人： Igor I. Ageyev , Gary Anna , Thomas W. Bish , Kimberly A. Bortz , Gregory T. Kishi , Joseph M. Swingler
发明人： Igor I. Ageyev , Gary Anna , Thomas W. Bish , Kimberly A. Bortz , Gregory T. Kishi , Joseph M. Swingler
IPC分类号： G06F15/16
CPC分类号： G06F15/16
摘要： A method for throttling host throughput in a computer storage subsystem is provided. The host throughput is compared to a throughput limit for a predetermined time period. If the host throughput exceeds the throughput limit during the predetermined time period, an input/output (I/O) delay is set equal to the remainder of the predetermined time period, and the delay is implemented for an associated storage device of the computer storage subsystem.
摘要翻译： 提供了一种用于在计算机存储子系统中抑制主机吞吐量的方法。 将主机吞吐量与预定时间段的吞吐量限制进行比较。 如果在预定时间段内主机吞吐量超过吞吐量限制，则将输入/输出（I / O）延迟设置为等于预定时间段的剩余时间，并且对于计算机存储器的相关联的存储设备实施延迟 子系统。
-
12.发明授权公开(公告)号：US07853681B2
公开(公告)日：2010-12-14
申请号：US12165019
申请日：2008-06-30
IPC分类号： G06F15/173
CPC分类号： G06F3/0659 , G06F3/0613 , G06F3/0653 , G06F3/0656 , G06F3/0686
摘要： A method for controlling the throughput in a communications channel between a host and its storage subsystem is disclosed. A determination is made whether or not a total throughput value is greater than a predetermined maximum throughput value. If the total throughput value is greater than the predetermined maximum throughput value, a delay is applied to the communications channel. If the total throughput value is not greater than the predetermined maximum throughput value, another determination is made whether or not one time period has completed. If one time period has completed, a total throughput value and an exponential moving average (EMA) throughput value of the communications channel is retrieved, a new EMA throughput value is generated based on the total throughput value and the EMA throughput value, and adjusting the total throughput value based on whether or not the new throughput value is greater than a predetermined maximum throughput value.
摘要翻译： 公开了一种用于控制主机与其存储子系统之间的通信信道中的吞吐量的方法。 确定总吞吐量值是否大于预定的最大吞吐量值。 如果总吞吐量值大于预定的最大吞吐量值，则延迟被施加到通信信道。 如果总吞吐量值不大于预定的最大吞吐量值，则另外确定一个时间段是否已经完成。 如果一个时间段完成，则检索通信信道的总吞吐量值和指数移动平均（EMA）吞吐量值，基于总吞吐量值和EMA吞吐量值生成新的EMA吞吐量值，并且调整 总吞吐量值基于新的吞吐量值是否大于预定的最大吞吐量值。
-
公开(公告)号：US20080154904A1
公开(公告)日：2008-06-26
申请号：US11613564
申请日：2006-12-20
申请人： Thomas W. Bish , Joseph M. Swingler
发明人： Thomas W. Bish , Joseph M. Swingler
IPC分类号： G06F17/30
CPC分类号： G06F3/0659 , G06F3/061 , G06F3/065 , G06F3/067 , G06F11/1662
摘要： A composite storage server employs a plurality of distributed storage sites including a mount site, a source copy site and one ore more copy target sites for executing a storage of volume data within the composite storage server. In operation, a deferred copy target site receives a communication of a source copy complete message from the mount site, the source copy complete message being indicative of the source copy site having a complete copy of the volume data, and detects a transition by the mount site of the host job from an active status to an inactive status subsequent to the communication of the source copy complete message from the mount site. Based on the inactive status of the host job, the deferred copy target site pulls the volume data from a peer distributed storage site having a complete copy of the volume data.
摘要翻译： 复合存储服务器使用多个分布式存储站点，包括安装站点，源复制站点和一个以上复制目标站点，用于执行复合存储服务器内的卷数据的存储。 在操作中，延迟复制目标站点从装载站点接收源复制完成消息的通信，源复制完成消息指示源拷贝站点具有卷数据的完整副本，并且检测由安装 主站作业的站点从源安装站点的源代码完成消息通信之后的活动状态到非活动状态。 基于主机作业的不活动状态，延迟复制目标站点从具有卷数据的完整副本的对等分布式存储站点拉取卷数据。
-
公开(公告)号：US08037361B2
公开(公告)日：2011-10-11
申请号：US12612077
申请日：2009-11-04
申请人： Thomas W. Bish , Joseph M. Swingler
发明人： Thomas W. Bish , Joseph M. Swingler
IPC分类号： G06F11/00
CPC分类号： G06F11/004 , G06F11/2056 , Y10S707/99955
摘要： Various method, system, and computer program product embodiments for implementing selective write-protect by a processor in a data storage system within a plurality of redundant storage systems for disaster recovery testing are provided. In one such embodiment, a write-protect state is initiated within at least one of the plurality of redundant storage systems. An available plurality of categories, including at least one write-protect exclusion category, is configured within a management interface of the data storage system, such that during the disaster recovery testing a storage volume categorized in the write-protect exclusion category is excluded from write protection.
摘要翻译： 提供了用于实现用于灾难恢复测试的多个冗余存储系统内的数据存储系统中的处理器进行选择性写保护的各种方法，系统和计算机程序产品实施例。 在一个这样的实施例中，在多个冗余存储系统中的至少一个内启动写保护状态。 包括至少一个写保护排除类别的可用多个类别被配置在数据存储系统的管理接口内，使得在灾难恢复测试期间，将分类在写保护排除类别中的存储卷从写入中排除 保护。
-
公开(公告)号：US08019723B2
公开(公告)日：2011-09-13
申请号：US11613564
申请日：2006-12-20
申请人： Thomas W. Bish , Joseph M. Swingler
发明人： Thomas W. Bish , Joseph M. Swingler
CPC分类号： G06F3/0659 , G06F3/061 , G06F3/065 , G06F3/067 , G06F11/1662
摘要： A composite storage server employs a plurality of distributed storage sites including a mount site, a source copy site and one ore more copy target sites for executing a storage of volume data within the composite storage server. In operation, a deferred copy target site receives a communication of a source copy complete message from the mount site, the source copy complete message being indicative of the source copy site having a complete copy of the volume data, and detects a transition by the mount site of the host job from an active status to an inactive status subsequent to the communication of the source copy complete message from the mount site. Based on the inactive status of the host job, the deferred copy target site pulls the volume data from a peer distributed storage site having a complete copy of the volume data.
摘要翻译： 复合存储服务器使用多个分布式存储站点，包括安装站点，源复制站点和一个以上复制目标站点，用于执行复合存储服务器内的卷数据的存储。 在操作中，延迟复制目标站点从装载站点接收源复制完成消息的通信，源复制完成消息指示源拷贝站点具有卷数据的完整副本，并且检测由安装 主站作业的站点从源安装站点的源代码完成消息通信之后的活动状态到非活动状态。 基于主机作业的不活动状态，延迟复制目标站点从具有卷数据的完整副本的对等分布式存储站点拉取卷数据。
-
16.发明申请公开(公告)号：US20090327469A1
公开(公告)日：2009-12-31
申请号：US12165019
申请日：2008-06-30
IPC分类号： G06F15/16
CPC分类号： G06F3/0659 , G06F3/0613 , G06F3/0653 , G06F3/0656 , G06F3/0686
摘要： A method for controlling the throughput in a communications channel between a host and its storage subsystem is disclosed. A determination is made whether or not a total throughput value is greater than a predetermined maximum throughput value. If the total throughput value is greater than the predetermined maximum throughput value, a delay is applied to the communications channel. If the total throughput value is not greater than the predetermined maximum throughput value, another determination is made whether or not one time period has completed. If one time period has completed, a total throughput value and an exponential moving average (EMA) throughput value of the communications channel is retrieved, a new EMA throughput value is generated based on the total throughput value and the EMA throughput value, and adjusting the total throughput value based on whether or not the new throughput value is greater than a predetermined maximum throughput value.
摘要翻译： 公开了一种用于控制主机与其存储子系统之间的通信信道中的吞吐量的方法。 确定总吞吐量值是否大于预定的最大吞吐量值。 如果总吞吐量值大于预定的最大吞吐量值，则延迟被施加到通信信道。 如果总吞吐量值不大于预定的最大吞吐量值，则另外确定一个时间段是否已经完成。 如果一个时间段完成，则检索通信信道的总吞吐量值和指数移动平均（EMA）吞吐量值，基于总吞吐量值和EMA吞吐量值生成新的EMA吞吐量值，并且调整 总吞吐量值基于新的吞吐量值是否大于预定的最大吞吐量值。
-
公开(公告)号：US20100174762A1
公开(公告)日：2010-07-08
申请号：US12349975
申请日：2009-01-07
IPC分类号： G06F12/00
CPC分类号： G06F12/0253 , G06F3/0619 , G06F3/0656 , G06F3/0665 , G06F3/0689 , G06F9/5016 , G06F9/5033 , G06F2209/5011 , G06F2212/702
摘要： An apparatus, system, and method are disclosed for maintaining a context stack. A monitor module monitors a stack size after each monitor interval for a stack of a plurality of contexts. Each context defines communications between a process and a data set and comprises a pathway for communicating with the data set and a process identifier. A stack module deallocates a context that satisfies a stack policy from the stack if the stack size is within a buffer threshold of a maximum threshold.
摘要翻译： 公开了用于维护上下文栈的装置，系统和方法。 监视器模块在多个上下文的堆栈的每个监视间隔之后监视堆栈大小。 每个上下文定义进程和数据集之间的通信，并且包括用于与数据集进行通信的路径和进程标识符。 如果堆栈大小在最大阈值的缓冲区阈值内，堆栈模块会从堆栈中释放满足堆栈策略的上下文。
-
公开(公告)号：US20080250197A1
公开(公告)日：2008-10-09
申请号：US11697004
申请日：2007-04-05
IPC分类号： G06F12/08
CPC分类号： G11B27/329 , G06F12/0866 , G11B20/1201 , G11B2020/1267 , G11B2220/90
摘要： A virtual tape server for executing a method involving a partitioning of a virtual tape volume into a plurality of virtual tape blocks. The virtual tape volume includes a virtual tape volume header having recovery information, each virtual tape block includes a virtual tape block header identifying the virtual tape volume and a block sequence number, and one or more of the virtual tape blocks includes the virtual tape volume header. The method further involves a formatting of a physical tape volume including each virtual tape block.
摘要翻译： 一种虚拟磁带服务器，用于执行涉及将虚拟磁带卷划分成多个虚拟磁带块的方法。 虚拟磁带卷包括具有恢复信息的虚拟磁带卷标头，每个虚拟磁带块包括标识虚拟磁带卷的虚拟磁带块头和块序列号，并且一个或多个虚拟磁带块包括虚拟磁带卷头 。 该方法还涉及包括每个虚拟磁带块的物理磁带卷的格式化。
-
19.发明申请APPARATUS AND METHOD TO MANAGE ONE OR MORE RESERVED VOLUME SERIAL NUMBERS IN A VIRTUAL LIBRARY GRID 失效在虚拟图书馆中管理一个或多个保留的卷数字的装置和方法公开(公告)号：US20080040535A1
公开(公告)日：2008-02-14
申请号：US11464255
申请日：2006-08-14
IPC分类号： G06F13/00
CPC分类号： G06F3/0664 , G06F3/0617 , G06F3/0631 , G06F3/067 , G06F3/0686
摘要： An apparatus and method are disclosed to manage one or more reserved volume serial numbers in a virtual library grid. The method supplies a virtual library grid comprising one or more virtual library clusters, wherein each of said one or more virtual library clusters comprises a management interface node, at least one virtualization node, at least one management node, at least one library manager node, at least one direct access storage device, one or more information storage media, and at least one data storage device to read information from and to write information to the one or more information storage media. The method then reserves in each of the one or more virtual library system clusters one or more volume serial numbers, and establishes a time out period. The method then determines if the time out period has expired. If the time out period has expired, the method unreserves in each of the one or more virtual library clusters the one or more volume serial numbers.
摘要翻译： 公开了一种用于管理虚拟库网格中的一个或多个保留卷序列号的装置和方法。 该方法提供包括一个或多个虚拟库集群的虚拟库网格，其中所述一个或多个虚拟库集群中的每一个包括管理接口节点，至少一个虚拟化节点，至少一个管理节点，至少一个库管理器节点， 至少一个直接访问存储设备，一个或多个信息存储介质以及至少一个数据存储设备，用于从一个或多个信息存储介质读取信息并向其写入信息。 该方法然后在一个或多个虚拟库系统集群中的每一个中保留一个或多个卷序列号，并建立超时期。 然后，该方法确定超时周期是否已过期。 如果超时时间已经过期，则该方法在一个或多个虚拟库集群中的每一个中取消保留一个或多个卷序列号。
-
公开(公告)号：US08667238B2
公开(公告)日：2014-03-04
申请号：US13403805
申请日：2012-02-23
IPC分类号： G06F12/00
CPC分类号： G06F3/0665 , G06F3/061 , G06F3/0653 , G06F3/0682 , G06F3/0686 , G06F12/0873 , G06F12/123 , G06F2212/213 , G06F2212/224
摘要： For selecting an input/output tape volume cache (TVC), a history module maintains access history instances for a plurality of clusters, each cluster comprising a TVC. A request module receives an access request for a logical volume wherein an instance of the logical volume is stored on each of the plurality of clusters and each instance of the logical volume is synchronized with each other instance of the logical volume. An adjustment module weights the access history instances in favor of recent access history instances. A calculation module calculates an affinity of the logical volume instance stored on each cluster of the plurality of clusters. A selection module selects a cluster TVC with a highest logical volume affinity as the TVC for the logical volume.
摘要翻译： 为了选择输入/输出磁带卷高速缓存（TVC），历史模块维护多个集群的访问历史实例，每个集群包括一个TVC。 请求模块接收对逻辑卷的访问请求，其中逻辑卷的实例被存储在多个集群中的每一个上，并且逻辑卷的每个实例与逻辑卷的每个其他实例同步。 调整模块对访问历史实例进行加权，有利于最近的访问历史实例。 计算模块计算存储在多个集群的每个集群上的逻辑卷实例的亲和度。 选择模块选择具有最高逻辑卷亲和力的集群TVC作为逻辑卷的TVC。
-
-
-
-
-
-
-
-
-
搜索结果
40 条记录 (耗时 0.029 秒)
