专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09298733B1 Storing files in a parallel computing system based on user or application specification 有权
标题翻译：基于用户或应用程序规范将文件存储在并行计算系统中
公开(公告)号：US09298733B1
公开(公告)日：2016-03-29
申请号：US13536289
申请日：2012-06-28
申请人： Sorin Faibish , John M. Bent , Jeffrey M. Nick , Gary Grider , Aaron Torres
发明人： Sorin Faibish , John M. Bent , Jeffrey M. Nick , Gary Grider , Aaron Torres
IPC分类号： G06F17/30
CPC分类号： G06F17/302 , G06F17/30224
摘要： Techniques are provided for storing files in a parallel computing system based on a user-specification. A plurality of files generated by a distributed application in a parallel computing system are stored by obtaining a specification from the distributed application indicating how the plurality of files should be stored; and storing one or more of the plurality of files in one or more storage nodes of a multi-tier storage system based on the specification. The plurality of files comprise a plurality of complete files and/or a plurality of sub-files. The specification can optionally be processed by a daemon executing on one or more nodes in a multi-tier storage system. The specification indicates how the plurality of files should be stored, for example, identifying one or more storage nodes where the plurality of files should be stored.
摘要翻译：提供了基于用户规范在并行计算系统中存储文件的技术。由并行计算系统中的分布式应用生成的多个文件通过从分布式应用获得指定如何存储多个文件的规范来存储; 以及基于所述规范，将所述多个文件中的一个或多个存储在多层存储系统的一个或多个存储节点中。多个文件包括多个完整文件和/或多个子文件。该规范可以可选地由在多层存储系统中的一个或多个节点上执行的守护进程来处理。该规范指示如何存储多个文件，例如，识别应该存储多个文件的一个或多个存储节点。

2. 发明授权

US08805951B1 Virtual machines and cloud storage caching for cloud computing applications 有权
标题翻译：云计算应用的虚拟机和云存储缓存
公开(公告)号：US08805951B1
公开(公告)日：2014-08-12
申请号：US13022946
申请日：2011-02-08
申请人： Sorin Faibish , Jeffrey M. Nick
发明人： Sorin Faibish , Jeffrey M. Nick
IPC分类号： G06F15/167
CPC分类号： G06F9/5072 , G06F21/6218 , H04L63/04
摘要： An application is included in a virtual machine sent to a cloud computing server. The cloud computing server has a remote access layer that fetches data blocks of the private dataset of the application from private data storage as the data blocks are requested by the application, so that the application in the public cloud begins execution without waiting for the entire application dataset to be transferred to the public cloud, and the data blocks are transferred from the private dataset to the public cloud only when the data blocks are accessed by the application. The application's private data is kept in the public cloud only when it is currently being used. If there are security concerns, the application's private data is transferred over the public network in an encrypted form and stored in the public cloud in an encrypted form.
摘要翻译：应用程序包含在发送到云计算服务器的虚拟机中。云计算服务器具有一个远程访问层，当应用程序请求数据块时，从专用数据存储中取出应用程序的私有数据集的数据块，从而公共云中的应用程序开始执行，而无需等待整个应用程序数据集转移到公共云中，只有当应用程序访问数据块时，数据块才会从私有数据集传输到公共云。应用程序的私有数据仅在当前正在使用时才会保留在公共云中。如果存在安全问题，应用程序的私有数据将以加密形式通过公共网络传输，并以加密形式存储在公共云中。

3. 发明授权

US07035852B2 Implementing a message queuing interface (MQI) indexed queue support that adds a key to the index on put commit 失效
标题翻译：实现消息队列接口（MQI）索引队列支持，它将put提供的索引添加一个密钥
公开(公告)号：US07035852B2
公开(公告)日：2006-04-25
申请号：US09909538
申请日：2001-07-20
申请人： Paul Hopewell , Paul Kettley , Jeffrey M. Nick , Peter Siddall , James H. Warnes
发明人： Paul Hopewell , Paul Kettley , Jeffrey M. Nick , Peter Siddall , James H. Warnes
IPC分类号： G06F17/30
CPC分类号： G06F9/546 , G06F2209/547 , G06F2209/548 , Y10S707/99938
摘要： Provided are a method, computer program product and system for providing indexed queue support for efficient retrieval of messages from a queue. An index key for expediting message retrieval is assigned to a message when the operation of placing the message on a queue is committed. The index key assigned at commit time comprises an attribute (such as a message ID or correlation ID) specified by the sending application program, which placed the message on the queue. This deferred assignment of an index key until commit time means that the index key can be used to search for messages having the particular attribute without any possibility of identifying messages for retrieval before the messages have been committed. This maintains transactional requirements of a transaction-oriented messaging system which requires a message to only be made available for retrieval by receiver application programs after the sender application's put operation has committed.
摘要翻译：提供了一种用于提供索引队列支持以从队列中有效检索消息的方法，计算机程序产品和系统。当消息放置在队列上的操作被提交时，用于加速消息检索的索引键被分配给消息。在提交时分配的索引关键字包括由发送应用程序指定的属性（诸如消息ID或相关ID），该消息将消息放置在队列上。索引键的延迟分配直到提交时间意味着可以使用索引关键字来搜索具有特定属性的消息，而无需在消息提交之前识别用于检索的消息。这维护面向事务的消息系统的事务性要求，该消息系统要求消息仅在发送者应用程序的投入操作已经提交之后被接收方应用程序提供。

4. 发明授权

US06944787B2 System-managed duplexing of coupling facility structures 有权
标题翻译：耦合设施结构的系统管理双工
公开(公告)号：US06944787B2
公开(公告)日：2005-09-13
申请号：US09968242
申请日：2001-10-01
申请人： Ruth A. Allen , Mark A. Brooks , David A. Elko , Michael J. Jordan , Georgette L. Kurdt , Catherine M. Moxey , William C. Neiman , Jeffrey M. Nick , Kelly B. Pushong , David H. Surman
发明人： Ruth A. Allen , Mark A. Brooks , David A. Elko , Michael J. Jordan , Georgette L. Kurdt , Catherine M. Moxey , William C. Neiman , Jeffrey M. Nick , Kelly B. Pushong , David H. Surman
IPC分类号： G06F11/00 , G06F11/16 , G06F11/20 , G06F15/173 , H04B1/74 , H04L1/22
CPC分类号： G06F11/2087
摘要： System-managed duplexing of coupling facility structures. A plurality of instances of coupling facility structures are maintained in a plurality of coupling facilities. Duplexing processing associated with the plurality of instances is managed by one or more operating systems, making many of the steps associated with duplexing transparent to the exploiters of the coupling facility structures. System-managed duplexing provides high availability for coupling facility structure data via a robust recovery mechanism (i.e., duplexing failover).
摘要翻译：耦合设施结构的系统管理双工。耦合设施结构的多个实例被保持在多个耦合设施中。与多个实例相关联的双工处理由一个或多个操作系统管理，使得与双工相关联的许多步骤与耦合设施结构的剥削者是透明的。系统管理的双工功能通过鲁棒的恢复机制（即双工故障切换）提供高可用性来耦合设施结构数据。

5. 发明授权

US06681241B1 Resource contention monitoring employing time-ordered entries in a blocking queue and waiting queue 有权
标题翻译：资源争用监控采用阻塞队列和等待队列中的时间顺序条目
公开(公告)号：US06681241B1
公开(公告)日：2004-01-20
申请号：US09373402
申请日：1999-08-12
申请人： Scott A. Fagen , Jeffrey M. Nick
发明人： Scott A. Fagen , Jeffrey M. Nick
IPC分类号： G06F900
CPC分类号： G06F9/52
摘要： Resource contention monitoring and analysis are provided for a single system or multi-system environment. Resource contention is tracked at a task level when contention occurs by listing each owner of a resource in a blocker list and each waiter for the resource in a waiter list. Each list is ordered oldest to newest so each instance of contention is added to the end of the respective list. The resource request and contention lists are cross-linked to provide easy coordination between the resource queues and the contention lists. Techniques for analyzing contention using the lists, including deadlock analysis, are described.
摘要翻译：为单个系统或多系统环境提供资源争用监控和分析。通过列出阻止程序列表中的资源的每个所有者和服务员列表中的资源的每个服务器，在任务级别跟踪资源争用。每个列表按最旧到最新的顺序排列，因此每个争用的实例被添加到相应列表的末尾。资源请求和争用列表是交互的，以便在资源队列和争用列表之间提供简单的协调。描述了使用列表分析争用的技术，包括死锁分析。

6. 发明授权

US06438654B1 Castout processing for duplexed cache structures 有权
标题翻译：双工缓存结构的Castout处理
公开(公告)号：US06438654B1
公开(公告)日：2002-08-20
申请号：US09255383
申请日：1999-02-22
申请人： David Arlen Elko , Steven Bruce Jones , Jeffrey W. Josten , Inderpal Singh Narang , Jeffrey M. Nick , Kelly B. Pushong , David Harold Surman , James Zu-Chia Teng
发明人： David Arlen Elko , Steven Bruce Jones , Jeffrey W. Josten , Inderpal Singh Narang , Jeffrey M. Nick , Kelly B. Pushong , David Harold Surman , James Zu-Chia Teng
IPC分类号： G06F1300
CPC分类号： G06F11/1666 , G06F11/1471 , G06F11/20 , G06F12/0804 , G06F12/0866
摘要： Castout processing for duplexed data structures. A selective data item is written from a primary instance of a data structure to at least one storage medium. A determination is made as to whether the selective data item can be deleted from a secondary instance of the data structure. If the selective data item can be deleted, it is deleted from the secondary instance.
摘要翻译：双工数据结构的铸造处理。将选择性数据项从数据结构的主实例写入到至少一个存储介质。确定是否可以从数据结构的次级实例中删除选择性数据项。如果可以删除选择性数据项，则从辅助实例中删除。

7. 发明授权

US06185650B2 High performance locking facility 有权
标题翻译：高性能锁定设施的方法
公开(公告)号：US06185650B2
公开(公告)日：2001-02-06
申请号：US09143328
申请日：1998-08-28
申请人： Mark A. Boonie , Jeffrey M. Nick , Peter G. Sutton , Wendell W. Wilkinson , Phil C. Yeh
发明人： Mark A. Boonie , Jeffrey M. Nick , Peter G. Sutton , Wendell W. Wilkinson , Phil C. Yeh
IPC分类号： G06F1200
CPC分类号： G06F9/52 , Y10S707/99938
摘要： A method of assigning and releasing locks, in a network computing environment having a plurality of central processing units coupled to a high performance locking facility. The method comprises of the steps of first processing multiple requests for locking operations simultaneously and then recording lock names and lock states in entry records of a lock table based on the requests. When a request is being processed, providing high-speed searching to search any particular lock entry in the table and altering and modifying the table accordingly. Finally an appropriate response and the status of the lock state will be generated and sent to other requestors requesting the lock.
摘要翻译：一种在具有耦合到高性能锁定设施的多个中央处理单元的网络计算环境中分配和释放锁的方法。该方法包括以下步骤：首先同时处理多个锁定操作请求，然后根据请求在锁定表的入口记录中记录锁定名称和锁定状态。当处理请求时，提供高速搜索以搜索表中的任何特定锁定条目并相应地改变和修改该表。最后，将生成适当的响应和锁状态的状态，并发送给请求锁的其他请求者。

8. 发明授权

US6088757A Computer program means and device for conducting high performance locking facility in a loosely coupled environment 有权
标题翻译：用于在松散耦合的环境中进行高性能锁定设备的计算机程序装置和装置
公开(公告)号：US6088757A
公开(公告)日：2000-07-11
申请号：US141544
申请日：1998-08-28
申请人： Mark A. Boonie , Jeffrey M. Nick , Peter G. Sutton , Wendell W. Wilkinson , Phil C. Yeh
发明人： Mark A. Boonie , Jeffrey M. Nick , Peter G. Sutton , Wendell W. Wilkinson , Phil C. Yeh
IPC分类号： G06F9/46 , G06F12/14 , G06F13/00
CPC分类号： G06F9/52 , Y10S707/99938
摘要： The present invention provides for a computer program product and device including instructions executable by a digital processing apparatus for conducting a high-performance locking facility. At first multiple requests for locking operations are processed and received simultaneously and their lock names and lock states are recorded in entry records of a lock table based on the requests. Next high-speed searching of any particular lock entry in this table is performed followed. The table can be altered and modified at this time as well accordingly depending upon lock status that is being processed. Finally an appropriate response is generated and the status of the lock state is provided to those requesting the lock.
摘要翻译：本发明提供了一种计算机程序产品和设备，包括可由数字处理设备执行以执行高性能锁定设备的指令。首先，多个锁定操作请求被同时处理和接收，并且它们的锁定名称和锁定状态将根据请求记录在锁定表的条目记录中。然后执行下表中的任何特定锁定条目的高速搜索。此时可以更改和更改表格，因此取决于正在处理的锁定状态。最后，产生适当的响应，并且向请求锁的人提供锁状态的状态。

9. 发明授权

US5613086A Method and system for locking a page of real storage using a virtual address 失效
标题翻译：使用虚拟地址锁定实际存储页面的方法和系统
公开(公告)号：US5613086A
公开(公告)日：1997-03-18
申请号：US567861
申请日：1995-12-06
申请人： Jeffrey A. Frey , David C. Manners , Jeffrey M. Nick
发明人： Jeffrey A. Frey , David C. Manners , Jeffrey M. Nick
IPC分类号： G06F12/08 , G06F12/10 , G06F12/12 , G06F12/14
CPC分类号： G06F12/126 , G06F12/10
摘要： A LOCK PAGE instruction is provided for locking a page of real storage using a virtual address. The LOCK PAGE instruction includes an operation code which specifies the operation to be performed, a first operand which contains the value of the real address obtained during execution of the LOCK PAGE instruction and a second operand which contains the value of the virtual address of the page to be locked during execution of LOCK PAGE. LOCK PAGE enables an address page or a data page to be locked without requiring the entire address space to be locked. A page is locked when a lock control bit in general register 0 is zero, the page is valid in main storage and a lock bit located in a page table entry is zero. In addition to the above, the technique used by an operating system service for reclaiming a page of real storage is altered to intersect with the LOCK PAGE facility.
摘要翻译：提供LOCK PAGE指令，用于使用虚拟地址锁定实际存储的页面。 LOCK PAGE指令包括指定要执行的操作的操作代码，第一操作数，其包含在执行LOCK PAGE指令期间获得的实际地址的值和包含页面的虚拟地址的值的第二操作数在执行LOCK PAGE期间被锁定。锁定页面可以锁定地址页面或数据页面，而不需要锁定整个地址空间。当通用寄存器0中的锁控制位为零时，页面被锁定，该页在主存储器中有效，并且位于页表条目中的锁位为零。除了上述之外，操作系统服务用于回收真实存储页面的技术被改变以与LOCK PAGE设备相交。

10. 发明授权

US5457793A Software cache management of a shared electronic store in a supplex 失效
公开(公告)号：US5457793A
公开(公告)日：1995-10-10
申请号：US860807
申请日：1992-03-30
申请人： David A. Elko , Jeffrey A. Frey , Brian B. Moore , Jeffrey M. Nick , Kevin F. Smith , Michael D. Swanson
发明人： David A. Elko , Jeffrey A. Frey , Brian B. Moore , Jeffrey M. Nick , Kevin F. Smith , Michael D. Swanson
IPC分类号： G06F12/02 , G06F12/08 , G06F12/12 , G06F15/167 , G06F17/30
CPC分类号： G06F12/084 , G06F12/023 , G06F12/0866 , G06F12/123 , Y10S707/968 , Y10S707/99956
摘要： Storage is managed in a shared electronic store (SES) by assigning storage classes (STCs) to each directory entry having a data item stored in SES. The assignments of directory entries and data elements to the respective STCs can be changed at any time by any CPC. Eventually, no free space remains in the SES cache, and then space for new directory entries and data items must be obtained by reclaiming space occupied by directory entries and associated unchanged data items. The reclaiming of SES space is controlled on a STC basis. Any specified STC may reclaim from itself or from another STC using reclaiming software/microcode in SES, which includes a reclaim vector, a reclaim counter, a queue, and reclaiming controls. The vector and counter have respective elements for all possible STCs to controls how a specified STC may reclaim space from any or all target STC. Any enabled target STC reclaims its space according to an LRU algorithm maintained by a queue for the STC. A CPC can issue a command to load different values in target STC elements in the SES vector for a specified STC to control how reclaiming is apportioned for the specified STC. In SES, associated target counter elements are loaded from its vector. Reclaiming is done automatically in SES upon each directory miss in the current target STC having a non-zero counter value, when no free space exists. The counter is decremented for each reclaimed directory entry until its count reaches zero, and then the counter element for the next non-zero target STC is used for reclaiming until it reaches zero. When all STC elements in the counter are zero for the specified STC, the counter elements are reloaded from the vector elements to repeat the reclaiming operation, as long as a repeat factor for the specified STC has not reached zero. The repeat factor is decremented each time the counters are loaded from the vector. When the counters and repeat factor have all reached zero, reclaiming is disabled for the specified STC.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式