-
公开(公告)号：US08024498B2
公开(公告)日：2011-09-20
申请号：US12335307
申请日：2008-12-15
CPC分类号： G06F9/546 , G06F2209/548
摘要： Disclosed is a computer implemented method and apparatus for queuing I/O requests to a pending queue. The I/O device driver sets a maximum ordered queue length for an I/O device driver coupled to a storage device then receives an I/O request from an application. The I/O device driver determines whether the pending queue is sorted and responds to a determination that the pending queue is sorted, determining if queued I/O requests exceed the maximum ordered queue length. Responding to a determination that the pending queue exceeds the maximum ordered queue length, the I/O device driver adds the I/O request based on a high pointer, and points the high pointer to the I/O request.
摘要翻译： 公开了一种用于将I / O请求排队到等待队列的计算机实现的方法和装置。 I / O设备驱动程序设置耦合到存储设备的I / O设备驱动程序的最大有序队列长度，然后从应用程序接收I / O请求。 I / O设备驱动程序确定待处理队列是否被排序，并响应确定等待队列被排序的确定，确定排队的I / O请求是否超过最大有序队列长度。 响应于挂起队列超过最大有序队列长度的确定，I / O设备驱动程序根据高指针添加I / O请求，并将高指针指向I / O请求。
-
公开(公告)号：US07783663B2
公开(公告)日：2010-08-24
申请号：US12029202
申请日：2008-02-11
CPC分类号： G06F3/0635 , G06F3/0613 , G06F3/067 , G06F2206/1012 , H04L67/1002 , H04L67/1008 , H04L67/101 , H04L67/1097 , Y10S707/99942 , Y10S707/99943 , Y10S707/99948
摘要： A mechanism is provided for balancing I/O among available paths connected to a device. The mechanism partitions paths so a device can use all or only a subset of available paths to a device, depending on the load of I/O for other devices that are sharing the paths. The partitioning of paths is dynamic, readjusting as I/O loads change for the devices.
摘要翻译： 提供了一种用于在连接到设备的可用路径之间平衡I / O的机制。 该机制分割路径，因此设备可以使用设备可用路径的全部或仅一部分子集，具体取决于共享路径的其他设备的I / O负载。 路径的分割是动态的，随着设备的I / O负载变化而重新调整。
-
3.发明授权Load balancing to support tape and disk subsystems on shared fibre channel adapters 有权负载平衡以支持共享光纤通道适配器上的磁带和磁盘子系统公开(公告)号：US07058758B2
公开(公告)日：2006-06-06
申请号：US10687260
申请日：2003-10-16
IPC分类号： G06F12/00
CPC分类号： G06F3/0635 , G06F3/0613 , G06F3/0685 , G06F11/3433 , G06F11/3485 , G06F2206/1012
摘要： A mechanism is provided for monitoring I/O activity of each device and the total I/O activity for each adapter. When there is low I/O activity for the tape subsystem, the I/O for the disk subsystems may be spread across all available adapters and paths. When I/O activity for the tape subsystem increases, the I/O activity for the disk subsystems may be reduced on the adapter processing the tape I/O, but will continue across all other adapters. If the tape subsystem begins to report errors due to I/O starvation, the disk I/O activity may be adjusted until the errors stop.
摘要翻译： 提供了一种机制，用于监视每个设备的I / O活动以及每个适配器的总I / O活动。 当磁带子系统的I / O活动较低时，磁盘子系统的I / O可能会扩展到所有可用的适配器和路径上。 当磁带子系统的I / O活动增加时，可能会在处理磁带I / O的适配器上减少磁盘子系统的I / O活动，但会在所有其他适配器上继续运行。 如果磁带子系统由于I / O不足而开始报告错误，则可能会调整磁盘I / O活动，直到错误停止为止。
-
公开(公告)号：US08271706B2
公开(公告)日：2012-09-18
申请号：US12125633
申请日：2008-05-22
CPC分类号： G06F3/0635 , G06F3/0617 , G06F3/067 , G06F3/0689 , G06F11/2092
摘要： The present invention provides a computer implemented method and apparatus to revising logical unit ownership in a host. A host receives an error message from a storage subsystem having at least two storage controllers and at least one logical unit coupled to at least one of the storage controllers. The host suspends I/O from the host to the storage subsystem. The host transmits a verification of logical unit ownership query to the storage subsystem. The host determines that ownership between a host and a logical unit on the at least one of the storage controllers has changed from a mapping table of the host. Responsive to a determination that ownership has changed, the host updates ownership in a mapping table of the host to reflect the ownership between the host and the logical unit. The host resumes I/O from the host to the storage subsystem, wherein the host routinely exchanges I/O with the storage subsystem.
摘要翻译： 本发明提供了一种用于修改主机中的逻辑单元所有权的计算机实现的方法和装置。 主机从具有至少两个存储控制器的存储子系统接收错误消息，以及耦合到至少一个存储控制器的至少一个逻辑单元。 主机将I / O从主机挂起到存储子系统。 主机向存储子系统发送逻辑单元所有权查询的验证。 所述主机确定所述至少一个所述存储控制器上的主机与逻辑单元之间的所有权已经从所述主机的映射表改变。 响应于所有权已经改变的确定，主机更新主机映射表中的所有权，以反映主机和逻辑单元之间的所有权。 主机从主机恢复到存储子系统的I / O，其中主机定期与存储子系统交换I / O。
-
公开(公告)号：US20120143892A1
公开(公告)日：2012-06-07
申请号：US12957980
申请日：2010-12-01
申请人： ERIC P. FRIED , Rajeev Mishra , Lance W. Russell , Chris A. Schwendiman , Stephen M. Tee , Stephen J. Tovcimak
发明人： ERIC P. FRIED , Rajeev Mishra , Lance W. Russell , Chris A. Schwendiman , Stephen M. Tee , Stephen J. Tovcimak
IPC分类号： G06F17/30
CPC分类号： G06F9/4411 , G06F17/30109 , G06F17/30197
摘要： A unique device name is assigned to each of a plurality of shared storage devices in a cluster configuration database defining membership of nodes in a cluster. A particular node among the nodes defined by the cluster configuration database as a member of the cluster searches the cluster configuration database for a device identifier matching a device identifier of a shared storage device hosted by the particular node. In response to finding a matching device identifier in the cluster configuration database, the particular node renames, in a local configuration maintained at the particular node, a storage device associated with the matching device identifier with the unique name assigned to that storage device in the cluster configuration database.
摘要翻译： 在定义集群中节点的成员资格的集群配置数据库中的每一个共享存储设备中分配唯一的设备名称。 由集群配置数据库定义的作为集群成员的节点中的特定节点在集群配置数据库中搜索与特定节点托管的共享存储设备的设备标识符匹配的设备标识符。 响应于在集群配置数据库中找到匹配的设备标识符，特定节点在维护在特定节点的本地配置中重命名与匹配设备标识符相关联的存储设备，其中分配给该集群中的该存储设备的唯一名称 配置数据库。
-
公开(公告)号：US08086896B2
公开(公告)日：2011-12-27
申请号：US12647664
申请日：2009-12-28
申请人： James P. Allen , Kiran K. Anumalasetty , Sudhir Maddali , Bhyrav M. Mutnury , James A. Pafumi , Sanket Rathi , Stephen M. Tee
发明人： James P. Allen , Kiran K. Anumalasetty , Sudhir Maddali , Bhyrav M. Mutnury , James A. Pafumi , Sanket Rathi , Stephen M. Tee
IPC分类号： G06F11/00
CPC分类号： G06F12/10 , G06F11/1443
摘要： In virtualized environments, storage may be managed dynamically due to the changing data storage requirements. In such environments, logical storage unit identifiers (LUN IDs) may be modified as a result of deleting an existing mapping between physical storage and a virtualization server and recreating the mapping. This can result in I/O request failure. Techniques for resolving errors resulting from LUN ID modifications can be time-intensive and labor-intensive and can disrupt a communication path between a host device and the physical storage. Functionality can be implemented to dynamically identify the LUN ID modifications, determine valid LUN IDs, and retransmit failed I/O requests. This can help minimize I/O request failures due to LUN ID modifications without disrupting the communication path between the host device and the physical storage.
摘要翻译： 在虚拟化环境中，存储可能由于数据存储需求的变化而动态管理。 在这种环境中，可以通过删除物理存储和虚拟化服务器之间的现有映射并重新创建映射来修改逻辑存储单元标识符（LUN ID）。 这可能导致I / O请求失败。 用于解决由LUN ID修改产生的错误的技术可能是耗时且费力的，并且可能会中断主机设备和物理存储之间的通信路径。 可以实现功能来动态识别LUN ID修改，确定有效的LUN ID，并重新发送失败的I / O请求。 这可以帮助最小化由于LUN ID修改而导致的I / O请求失败，而不会中断主机设备和物理存储之间的通信路径。
-
公开(公告)号：US20100180086A1
公开(公告)日：2010-07-15
申请号：US12353492
申请日：2009-01-14
CPC分类号： G06F3/0656 , G06F3/0617 , G06F3/0676
摘要： A method, system, and computer usable program product for an improved data storage device driver are provided in the illustrative embodiments. For managing an elevator queue, several requests are stored in the elevator queue. A determination is made whether the elevator queue is sorted. A number of requests in the elevator queue is determined if the elevator queue is unsorted. The unsorted elevator queue is monitored. Reaching a threshold condition in the unsorted elevator queue is detected. Sorting of the unsorted elevator queue is initiated. The requests may be I/O requests for a data storage device. The elevator queue may be sorted according to an ascending or descending order of data block addresses in the requests. The monitoring may monitor a remaining number of unsorted requests in the elevator queue as requests are removed from the elevator queue. The threshold condition may be associated with a threshold value.
摘要翻译： 在说明性实施例中提供了用于改进的数据存储设备驱动器的方法，系统和计算机可用程序产品。 为了管理电梯队列，几个请求被存储在电梯队列中。 确定电梯队列是否被排序。 如果电梯队列未排序，则确定电梯队列中的多个请求。 监视未排序的电梯队列。 检测未排序的电梯队列中的阈值条件。 启动未排序的电梯队列的排序。 请求可以是用于数据存储设备的I / O请求。 可以根据请求中的数据块地址的升序或降序对电梯队列进行排序。 当请求从电梯队列中移除时，监视可以监视电梯队列中的未排序请求的剩余数量。 阈值条件可以与阈值相关联。
-
公开(公告)号：US07337235B2
公开(公告)日：2008-02-26
申请号：US10976261
申请日：2004-10-28
IPC分类号： G06F15/173
CPC分类号： G06F3/0635 , G06F3/0613 , G06F3/067 , G06F2206/1012 , H04L67/1002 , H04L67/1008 , H04L67/101 , H04L67/1097 , Y10S707/99942 , Y10S707/99943 , Y10S707/99948
摘要： A mechanism is provided for balancing I/O among available paths connected to a device. The mechanism partitions paths so a device can use all or only a subset of available paths to a device, depending on the load of I/O for other devices that are sharing the paths. The partitioning of paths is dynamic, readjusting as I/O loads change for the devices.
摘要翻译： 提供了一种用于在连接到设备的可用路径之间平衡I / O的机制。 该机制分割路径，因此设备可以使用设备可用路径的全部或仅一部分子集，具体取决于共享路径的其他设备的I / O负载。 路径的分割是动态的，随着设备的I / O负载变化而重新调整。
-
公开(公告)号：US09069571B2
公开(公告)日：2015-06-30
申请号：US12957980
申请日：2010-12-01
申请人： Eric P. Fried , Rajeev Mishra , Lance W. Russell , Chris A. Schwendiman , Stephen M. Tee , Stephen J. Tovcimak
发明人： Eric P. Fried , Rajeev Mishra , Lance W. Russell , Chris A. Schwendiman , Stephen M. Tee , Stephen J. Tovcimak
CPC分类号： G06F9/4411 , G06F17/30109 , G06F17/30197
摘要： A unique device name is assigned to each of a plurality of shared storage devices in a cluster configuration database defining membership of nodes in a cluster. A particular node among the nodes defined by the cluster configuration database as a member of the cluster searches the cluster configuration database for a device identifier matching a device identifier of a shared storage device hosted by the particular node. In response to finding a matching device identifier in the cluster configuration database, the particular node renames, in a local configuration maintained at the particular node, a storage device associated with the matching device identifier with the unique name assigned to that storage device in the cluster configuration database.
摘要翻译： 在定义集群中节点的成员资格的集群配置数据库中的每一个共享存储设备中分配唯一的设备名称。 由集群配置数据库定义的作为集群成员的节点中的特定节点在集群配置数据库中搜索与特定节点托管的共享存储设备的设备标识符匹配的设备标识符。 响应于在集群配置数据库中找到匹配的设备标识符，特定节点在维护在特定节点的本地配置中重命名与匹配设备标识符相关联的存储设备，其中分配给该集群中的该存储设备的唯一名称 配置数据库。
-
公开(公告)号：US20100050021A1
公开(公告)日：2010-02-25
申请号：US12197678
申请日：2008-08-25
IPC分类号： G06F11/07
CPC分类号： H04L67/1097 , G06F3/0617 , G06F3/0622 , G06F3/0631 , G06F3/0635 , G06F3/067
摘要： Disclosed is a computer implemented method and apparatus for making ownership changes to a storage subsystem. The host sends the first ownership change command to the storage subsystem then determines whether the storage subsystem responded with an error message. Upon responding to a determination that the storage subsystem responded with the error message, the host determines whether the storage subsystem indicated an error associated with an ownership change. In response to a determination that the storage subsystem indicated an error associated with an ownership change, the host sends a discover ownership message to the storage subsystem. Upon receiving a list of logical unit number associations from the storage subsystem, the host responds to receiving a list of logical unit number associations. The host performs a second ownership command to determine whether the list of logical unit number associations matches an ownership defined in the ownership change command. The host responds to a determination that the list of logical unit number associations matches an ownership defined in the ownership change command by aborting ownership changes.
摘要翻译： 公开了一种用于使存储子系统的所有权改变的计算机实现的方法和装置。 主机向存储子系统发送第一个所有权更改命令，然后确定存储子系统是否响应错误消息。 在响应确定存储子系统使用错误消息进行响应时，主机确定存储子系统是否指示与所有权变更相关联的错误。 响应于确定存储子系统指示与所有权改变相关联的错误，主机向存储子系统发送发现所有权消息。 在从存储子系统接收到逻辑单元号关联的列表时，主机响应于接收到逻辑单元号关联的列表。 主机执行第二个所有权命令来确定逻辑单元编号关联的列表是否与所有权更改命令中定义的所有权匹配。 主机响应于通过中止所有权更改来确定逻辑单元号关联列表与所有权更改命令中定义的所有权相匹配。
-
-
-
-
-
-
-
-
-
搜索结果
21 条记录 (耗时 0.017 秒)
