公开(公告)号：US5551027A

公开(公告)日：1996-08-27

申请号：US526723

申请日：1995-09-11

申请人： David M. Choy ,  Chandrasekaran Mohan

发明人： David M. Choy ,  Chandrasekaran Mohan

IPC分类号： G06F12/00 ,  G06F9/355 ,  G06F17/30

CPC分类号： G06F17/30321 ,  G06F9/355 ,  Y10S707/99952

摘要： A multi-tiered indexing method is disclosed for a partitioned table in a parallel or distributed database system. A Local Index is created and maintained for each partition of the table and a Coarse Global Index is created and maintained. The Coarse Global Index identifies the indexed partition(s) by partition identifiers (PIDs) and associates the individual Index Key Values with their target partitions so that an access request with a highly partition-selective search predicate on the Index Key can be quickly and easily directed to the target partition(s) for processing. An index maintenance locking protocol is also disclosed which handles the insertion and deletion of index entries and assures the consistency between the Local Index entries and the Coarse Global Index entries during concurrent index accesses by different transactions. The locking protocol minimizes locking only to those cases involving an inserted or deleted key and to the key following and possibly the key preceding the inserted or deleted key to allow high concurrency between simultaneous Readers, Inserters, and Deleters. This method enhances the efficiency of complex query evaluation and index maintenance and attains a high throughput for transaction processing.

摘要翻译： 公开了一种用于并行或分布式数据库系统中的分区表的多层索引方法。 为表的每个分区创建并维护本地索引，并创建和维护粗糙全局索引。 粗糙全局索引通过分区标识符（PID）标识索引分区，并将各个索引关键值与其目标分区相关联，以便在索引键上具有高度分区选择性搜索谓词的访问请求可以快速轻松 定向到目标分区进行处理。 还公开了索引维护锁定协议，其处理索引条目的插入和删除，并且在不同事务的并发索引访问期间确保本地索引条目和粗全局索引条目之间的一致性。 锁定协议最大限度地将锁定仅限于涉及插入或删除的密钥的情况以及插入或删除的密钥之后的密钥以及可能的同时读取器，插入器和删除器之间的高并发性的密钥。 该方法提高了复杂查询评估和索引维护的效率，实现了交易处理的高吞吐量。

公开(公告)号：US10949415B2

公开(公告)日：2021-03-16

申请号：US13077574

申请日：2011-03-31

申请人： Ru Fang ,  Bin He ,  Hui-I Hsiao ,  Chandrasekaran Mohan ,  Yun Wang

发明人： Ru Fang ,  Bin He ,  Hui-I Hsiao ,  Chandrasekaran Mohan ,  Yun Wang

IPC分类号： G06F16/23

摘要： A computer program product, including: a computer readable storage device to store a computer readable program, wherein the computer readable program, when executed by a processor within a computer, causes the computer to perform operations for logging. The operations include: receiving a transaction including data and a log record corresponding to the data; writing the data to a data storage device; and writing the log record to a log space on a persistent memory device coupled to the data storage device.

公开(公告)号：US09742860B2

公开(公告)日：2017-08-22

申请号：US13406758

申请日：2012-02-28

申请人： Ru Fang ,  Bin He ,  Hui-I Hsiao ,  Chandrasekaran Mohan ,  Rene Mueller

发明人： Ru Fang ,  Bin He ,  Hui-I Hsiao ,  Chandrasekaran Mohan ,  Rene Mueller

IPC分类号： H04L29/08

CPC分类号： H04L67/2842

摘要： Described herein are techniques for supporting bi-temporal data in a key value cache system. An embodiment provides bi-temporal data as the basic functionality of a key value cache system. An embodiment provides a redesign of the core data structures of a key value cache system, adds bi-temporal data storage in the key value hashing structure, and provides a temporality-aware memory space manager. Embodiments can achieve the same performance as current key value cache systems for regular queries (that is, the queries that only access the current versions of data) while supporting bi-temporal data.

公开(公告)号：US09471622B2

公开(公告)日：2016-10-18

申请号：US13460013

申请日：2012-04-30

申请人： Ru Fang ,  Bin He ,  Hui-I Hsiao ,  Chandrasekaran Mohan

发明人： Ru Fang ,  Bin He ,  Hui-I Hsiao ,  Chandrasekaran Mohan

IPC分类号： G06F12/00 ,  G06F13/00 ,  G06F13/28 ,  G06F17/30

CPC分类号： G06F17/30377

摘要： Embodiments of a system are described. In one embodiment, the system is a device for performing operations and supporting transactions. The device is configured to receive a transaction comprising a command and data. The device writes the data to a transaction manager on a persistent memory device. The transaction manager also maintains a status of the transaction and reference to entries within memory that are manipulated by the transaction. The device also creates an in-memory log of the transaction in a first hash directory. The device then commits a copy of the first hash directory to a second hash directory maintained on a persistent memory device.

摘要翻译： 描述系统的实施例。 在一个实施例中，系统是用于执行操作和支持事务的设备。 该设备被配置为接收包括命令和数据的事务。 设备将数据写入持久存储设备上的事务管理器。 事务管理器还维护事务的状态以及由事务处理的内存中的条目的引用。 该设备还在第一个散列目录中创建事务的内存中日志。 然后，该设备将第一散列目录的副本提交到在持久存储器设备上维护的第二散列目录。

公开(公告)号：US20140059284A1

公开(公告)日：2014-02-27

申请号：US13594098

申请日：2012-08-24

申请人： Ru Fang ,  Bin He ,  Hui-I Hsiao ,  Chandrasekaran Mohan

发明人： Ru Fang ,  Bin He ,  Hui-I Hsiao ,  Chandrasekaran Mohan

IPC分类号： G06F12/02

CPC分类号： G06F3/0608 ,  G06F3/0644 ,  G06F3/0656 ,  G06F3/0679 ,  G06F12/02 ,  G06F12/0646

摘要： Embodiments of the present invention provide a system, method and computer program products for memory space management for storage class memory. One embodiment comprises a method for information storage in an information technology environment. The method comprises storing data in a storage class memory (SCM) space, and storing storage management metadata corresponding to said data, in the SCM in a first data structure. The method further includes buffering storage management metadata corresponding to said data, in a main memory in a second data structure.

摘要翻译： 本发明的实施例提供了一种用于存储类存储器的存储器空间管理的系统，方法和计算机程序产品。 一个实施例包括在信息技术环境中信息存储的方法。 该方法包括在第一数据结构中将数据存储在存储类存储器（SCM）空间中，并且将对应于所述数据的存储管理元数据存储在SCM中。 该方法还包括在第二数据结构的主存储器中缓冲对应于所述数据的存储管理元数据。

公开(公告)号：US20120254120A1

公开(公告)日：2012-10-04

申请号：US13077574

申请日：2011-03-31

申请人： Ru Fang ,  Bin He ,  Hui-I Hsiao ,  Chandrasekaran Mohan ,  Yun Wang

发明人： Ru Fang ,  Bin He ,  Hui-I Hsiao ,  Chandrasekaran Mohan ,  Yun Wang

IPC分类号： G06F7/00

CPC分类号： G06F16/2379

摘要： A computer program product, including: a computer readable storage device to store a computer readable program, wherein the computer readable program, when executed by a processor within a computer, causes the computer to perform operations for logging. The operations include: receiving a transaction including data and a log record corresponding to the data; writing the data to a data storage device; and writing the log record to a log space on a persistent memory device coupled to the data storage device.

摘要翻译： 一种计算机程序产品，包括：用于存储计算机可读程序的计算机可读存储设备，其中所述计算机可读程序在由计算机内的处理器执行时使所述计算机执行记录操作。 操作包括：接收包含数据的事务和对应于该数据的日志记录; 将数据写入数据存储设备; 以及将所述日志记录写入耦合到所述数据存储设备的持久存储器设备上的日志空间。

公开(公告)号：US06874104B1

公开(公告)日：2005-03-29

申请号：US09330865

申请日：1999-06-11

申请人： Jeffrey William Josten ,  Chandrasekaran Mohan ,  Inderpal Singh Narang

发明人： Jeffrey William Josten ,  Chandrasekaran Mohan ,  Inderpal Singh Narang

IPC分类号： G06F11/00 ,  G06F17/30

CPC分类号： G06F17/30348 ,  Y10S707/99938 ,  Y10S707/99945 ,  Y10S707/99953

摘要： A method, apparatus, article of manufacture, and data structure for use in providing transaction control for a computer-implemented database management system. The database management system manages one or more databases. A transaction processing system provides transaction control for one or more of the databases managed by the database management system, wherein the transaction processing system assigns a recoverable, unique sequence number whenever a request is made by an application.

摘要翻译： 一种用于为计算机实现的数据库管理系统提供事务控制的方法，装置，制造和数据结构。 数据库管理系统管理一个或多个数据库。 事务处理系统为由数据库管理系统管理的数据库中的一个或多个数据库提供事务控制，其中事务处理系统每当应用程序作出请求时分配可恢复的唯一序列号。

公开(公告)号：US06581205B1

公开(公告)日：2003-06-17

申请号：US09464556

申请日：1999-12-16

申请人： Roberta Jo Cochrane ,  Ting Yu Leung ,  Chandrasekaran Mohan ,  Mir Hamid Pirahesh ,  Richard Sefton Sidle

发明人： Roberta Jo Cochrane ,  Ting Yu Leung ,  Chandrasekaran Mohan ,  Mir Hamid Pirahesh ,  Richard Sefton Sidle

IPC分类号： G06F945

CPC分类号： G06F17/30383 ,  Y10S707/99933

摘要： A method, apparatus, and article of manufacture for maintaining a materialized view derived from at least one base table in a database stored on a computer. An update is performed to the base table in a transaction. Thereafter, the materialized view is accessed to identify affected records therein using at least one mechanism, such as an isolation level or update- and exclusive-locks, to guarantee consistency while avoiding deadlocks with other transactions that modify at least one base table of the materialized view and to improve concurrency with other transactions that are accessing the materialized view when the modification to the base table is applied to the materialized view.

摘要翻译： 一种用于在存储在计算机上的数据库中维护从至少一个基表导出的物化视图的方法，装置和制品。 在事务中对基表执行更新。 此后，访问物化视图以使用至少一种机制（例如隔离级别或更新和排他锁定）来确定其中的受影响的记录，以保证一致性，同时避免与修改实例化的至少一个基表的其他事务的死锁 查看并改进与基础表的修改应用于实例化视图时访问物化视图的其他事务的并发性。

公开(公告)号：US5455942A

公开(公告)日：1995-10-03

申请号：US955076

申请日：1992-10-01

申请人： Chandrasekaran Mohan ,  Inderpal S. Narang ,  James Zu-chia Teng

发明人： Chandrasekaran Mohan ,  Inderpal S. Narang ,  James Zu-chia Teng

IPC分类号： G06F12/00 ,  G06F11/10 ,  G06F12/08 ,  G06F12/16 ,  G06F15/167 ,  G06F11/08

CPC分类号： G06F11/1076 ,  G06F11/1008 ,  G06F12/0866 ,  Y10S707/99953

摘要： Disk check bits refer to bit patterns stored in particular bytes of a page which are used to detect errors in writing the page to storage. Every time a page is obtained from storage, changed from the version retained in storage, and written back to storage, the check bit pattern on the changed page is altered to be different from the bit pattern on the storage page. This is because the changed page overwrites the stored page. The invention provides a method for managing the check bits in a multi-DBMS system employing a high-speed shared electronic store as a store-in cache for all pages obtained from disk storage. When a page is first obtained from disk storage by a DBMS and changed, check bit information for the page is maintained in a directory of the storing cache which indicates what the patterns are for the version of the page in the disk storage. All pages which are modified are stored in the store-in cache and are only returned to disk storage from the cache. Therefore, when a page is to be written to disk storage, the DBMS writing the page to storage processes the check bits on the page itself, changing them as required based on the check bit information stored in the directory for the page.

摘要翻译： 磁盘检查位是指存储在页面的特定字节中的位模式，用于检测将页面写入存储器时的错误。 每次从存储中获取页面时，从存储中保留的版本中更改页面，并将其写回存储器，更改页面上的校验位模式将更改为与存储页面上的位模式不同。 这是因为更改的页面将覆盖存储的页面。 本发明提供一种用于管理采用高速共享电子商店的多DBMS系统中的校验位的方法，作为从磁盘存储器获得的所有页面的存储高速缓存。 当页首首先由DBMS从磁盘存储器中获取并更改时，检查页面的位信息是否保存在存储缓存的目录中，该目录指示磁盘存储器中页面版本的模式。 被修改的所有页面都存储在存储缓存中，只能从高速缓存返回到磁盘存储。 因此，当将页面写入磁盘存储器时，将页面写入存储器的DBMS处理页面本身的校验位，根据存储在页面目录中的校验位信息根据需要进行改变。

公开(公告)号：US07945577B2

公开(公告)日：2011-05-17

申请号：US12123101

申请日：2008-05-19

申请人： Mehmet Altinel ,  Christof Bomhoevd ,  Chandrasekaran Mohan ,  Mir Hamid Pirahesh ,  Berthold Reinwald ,  Saileshwar Krishnamurthy

发明人： Mehmet Altinel ,  Christof Bomhoevd ,  Chandrasekaran Mohan ,  Mir Hamid Pirahesh ,  Berthold Reinwald ,  Saileshwar Krishnamurthy

IPC分类号： G06F17/00

CPC分类号： G06F17/3048 ,  Y10S707/99933

摘要： A local database cache enabling persistent, adaptive caching of either full or partial content of a remote database is provided. Content of tables comprising a local cache database is defined on per-table basis. A table is either: defined declaratively and populated in advance of query execution, or is determined dynamically and asynchronously populated on-demand during query execution. Based on a user input query originally issued against a remote DBMS and referential cache constraints between tables in a local database cache, a Janus query plan, comprising local, remote, and probe query portions is determined. A probe query portion of a Janus query plan is executed to determine whether up-to-date results can be delivered by the execution of a local query portion against a local database cache, or whether it is necessary to retrieve results from a remote database by executing a remote query portion of Janus query plan.

摘要翻译： 提供本地数据库缓存，实现远程数据库的完整或部分内容的持久自适应缓存。 包含本地缓存数据库的表的内容基于每个表进行定义。 表是：在查询执行之前以声明方式和填充方式定义，或者在查询执行期间按需动态和异步地填充表。 基于最初针对远程DBMS发出的用户输入查询和本地数据库高速缓存中的表之间的参考高速缓存约束，确定包括本地，远程和探测查询部分的Janus查询计划。 执行Janus查询计划的探查查询部分以确定是否可以通过对本地数据库高速缓存执行本地查询部分来传递最新结果，或者是否需要通过以下方式从远程数据库检索结果： 执行Janus查询计划的远程查询部分。