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

US08868707B2 Adaptive write-back and write-through caching for off-line data 有权
标题翻译：离线数据的自适应回写和直写缓存
公开(公告)号：US08868707B2
公开(公告)日：2014-10-21
申请号：US12485801
申请日：2009-06-16
申请人： Nikunj R. Mehta , Garret Swart , Colm Divilly , Ashish Motivala
发明人： Nikunj R. Mehta , Garret Swart , Colm Divilly , Ashish Motivala
IPC分类号： G06F15/173 , H04L29/08 , H04L29/06
CPC分类号： H04L63/0884 , H04L63/08 , H04L67/2842
摘要： Techniques for facilitating communication between an application and a server are provided. An intermediary sits between an application and a server. The intermediary intercepts and responds to communications on behalf of the intended recipient of the communication. In one technique, the intermediary relays a request to the server and receives a response from the server. The intermediary updates a local store with data that is implied by the protocol to which the request conforms and determined based on the request. In another technique, the intermediary intercepts a request to access data on the server. The intermediary determines, based on characteristics of a computing device, that the request should be responded to using data that is available in a local store. The intermediary responds to the request using that data.
摘要翻译：提供了用于促进应用和服务器之间的通信的技术。中间人坐在应用程序和服务器之间。中介人代表预期的通信接收者拦截和响应通信。在一种技术中，中间件将请求中继到服务器并从服务器接收响应。中介使用根据该请求符合和确定的协议隐含的数据来更新本地商店。在另一种技术中，中介拦截访问服务器上的数据的请求。中介根据计算设备的特征来确定该请求应当使用在本地商店中可用的数据进行响应。中间人使用该数据响应请求。

2. 发明申请

US20100318640A1 ADAPTIVE WRITE-BACK AND WRITE-THROUGH CACHING FOR OFF-LINE DATA 有权
标题翻译：适用于背离和写入的远程数据快速通道
公开(公告)号：US20100318640A1
公开(公告)日：2010-12-16
申请号：US12485801
申请日：2009-06-16
申请人： Nikunj R. Mehta , Garret Swart , Colm Divilly , Ashish Motivala
发明人： Nikunj R. Mehta , Garret Swart , Colm Divilly , Ashish Motivala
IPC分类号： G06F15/173
CPC分类号： H04L63/0884 , H04L63/08 , H04L67/2842
摘要： A method for facilitating communication between an application and a server is provided. An intermediary sits between an application and a server. The intermediary intercepts and responds to communications on behalf of the intended recipient of the communication.
摘要翻译：提供一种促进应用和服务器之间的通信的方法。中间人坐在应用程序和服务器之间。中介人代表预期的通信接收者拦截和响应通信。

3. 发明授权

US08549101B2 Portable embedded local server for write-through cache 有权
标题翻译：便携式嵌入式本地服务器，用于直写缓存
公开(公告)号：US08549101B2
公开(公告)日：2013-10-01
申请号：US12618654
申请日：2009-11-13
申请人： Nikunj R. Mehta , Garret Swart
发明人： Nikunj R. Mehta , Garret Swart
IPC分类号： G06F15/16 , G06F17/30 , H04L9/32
CPC分类号： H04L29/08846 , G06F17/30893 , H04L67/02
摘要： A method of facilitating, via an embedded local server, dynamic responses to requests originating from an application and directed to a server is disclosed. An intermediary intercepts requests responds to the requests with locally stored data. The intermediary may also forward requests to an embedded local server for processing based on local data.
摘要翻译：公开了一种通过嵌入式本地服务器促进从应用程序发起并被引导到服务器的请求的动态响应的方法。中间人拦截请求使用本地存储的数据响应请求。中介还可以根据本地数据将请求转发到嵌入式本地服务器进行处理。

4. 发明申请

US20100319054A1 PORTABLE EMBEDDED LOCAL SERVER FOR WRITE-THROUGH CACHE 有权
标题翻译：便携式嵌入式本地服务器，用于写入高速缓存
公开(公告)号：US20100319054A1
公开(公告)日：2010-12-16
申请号：US12618654
申请日：2009-11-13
申请人： Nikunj R. Mehta , Garret Swart
发明人： Nikunj R. Mehta , Garret Swart
IPC分类号： G06F15/16 , G06F17/30 , H04L9/32
CPC分类号： H04L29/08846 , G06F17/30893 , H04L67/02
摘要： A method of facilitating, via an embedded local server, dynamic responses to requests originating from an application and directed to a server is disclosed. An intermediary intercepts requests responds to the requests with locally stored data. The intermediary may also forward requests to an embedded local server for processing based on local data.
摘要翻译：公开了一种通过嵌入式本地服务器促进从应用程序发起并被引导到服务器的请求的动态响应的方法。中间人拦截请求使用本地存储的数据响应请求。中介还可以根据本地数据将请求转发到嵌入式本地服务器进行处理。

5. 发明授权

US09032416B2 Load balancing using progressive sampling based on load balancing quality targets 有权
标题翻译：基于负载平衡质量目标的逐行采样进行负载平衡
公开(公告)号：US09032416B2
公开(公告)日：2015-05-12
申请号：US13561383
申请日：2012-07-30
申请人： Garret Swart , Smriti R. Ramakrishnan
发明人： Garret Swart , Smriti R. Ramakrishnan
IPC分类号： G06F9/46 , G06F9/50
CPC分类号： G06F9/5066 , G06F9/5083 , G06F2209/5022
摘要： A method, system, and computer program product for of load balancing in a parallel map/reduce paradigm. The method commences by sampling a first set of input records, and forming a prospective load balancing assignment by assigning the first set of input records to the plurality of worker tasks based on a workload estimate for each of the worker tasks. To measure the prospective load balancing assignment, the method compares the workload variance over the plurality of worker tasks to a workload variance target, and also calculates a confidence level based on the sampled first set of input records. If the measured quality of the prospective load balancing assignment is not yet achieved, then the method samples additional input records; for example when the calculated workload variance is greater than the maximum workload variance target or when the calculated confidence level is lower than a confidence level threshold.
摘要翻译：一种用于平行映射/减少范例中的负载平衡的方法，系统和计算机程序产品。该方法通过对第一组输入记录进行采样开始，并且基于每个工作任务的工作量估计，通过将第一组输入记录分配给多个工作任务来形成预期的负载平衡分配。为了测量预期的负载平衡分配，该方法将多个工作任务上的工作量方差与工作负载方差目标进行比较，并且还基于所采样的第一组输入记录来计算置信水平。如果尚未实现预期负载均衡分配的测量质量，则该方法对附加输入记录进行采样; 例如当所计算的工作负荷方差大于最大工作量方差目标时或计算出的置信水平低于置信水平阈值时。

6. 发明授权

US5956713A Techniques for reducing the number of snapshots of a database 失效
标题翻译：减少数据库快照数量的技术
公开(公告)号：US5956713A
公开(公告)日：1999-09-21
申请号：US838967
申请日：1997-04-23
申请人： Roger Bamford , Boris Klots , Garret Swart
发明人： Roger Bamford , Boris Klots , Garret Swart
IPC分类号： G06F17/30
CPC分类号： G06F17/30356 , Y10S707/99938 , Y10S707/99952 , Y10S707/99953
摘要： A method and apparatus for reducing the number of snapshots in use within a database is provided. A transaction that accesses one or more data items in a database is assigned to a snapshot of the database when the transaction completes execution. At that time, it is determined whether a first snapshot includes any transactions that updated the one or more data items. If the first snapshot includes any transactions that updated the one or more data items, then the transaction is assigned to a different snapshot that includes the first snapshot. If the first snapshot does not include any transactions that updated the one or more data items, then the transaction is assigned to the first snapshot. This technique allows multiple transactions to the same snapshot, consequently reducing the actual number of snapshots of the database.
摘要翻译：提供了一种用于减少在数据库内使用的快照数量的方法和装置。当事务完成执行时，访问数据库中一个或多个数据项的事务被分配给数据库的快照。此时，确定第一快照是否包括更新一个或多个数据项的任何事务。如果第一个快照包含更新一个或多个数据项的任何事务，则将事务分配给包含第一个快照的不同快照。如果第一个快照不包括更新一个或多个数据项的任何事务，则将事务分配给第一个快照。这种技术允许多个事务到相同的快照，从而减少实际的数据库快照数量。

7. 发明申请

US20140033223A1 LOAD BALANCING USING PROGRESSIVE SAMPLING BASED ON LOAD BALANCING QUALITY TARGETS 有权
标题翻译：基于负载平衡质量目标的逐步采样的负载平衡
公开(公告)号：US20140033223A1
公开(公告)日：2014-01-30
申请号：US13561383
申请日：2012-07-30
申请人： Garret Swart , Smriti R. Ramakrishnan
发明人： Garret Swart , Smriti R. Ramakrishnan
IPC分类号： G06F9/46
CPC分类号： G06F9/5066 , G06F9/5083 , G06F2209/5022
摘要： A method, system, and computer program product for of load balancing in a parallel map/reduce paradigm. The method commences by sampling a first set of input records, and forming a prospective load balancing assignment by assigning the first set of input records to the plurality of worker tasks based on a workload estimate for each of the worker tasks. To measure the prospective load balancing assignment, the method compares the workload variance over the plurality of worker tasks to a workload variance target, and also calculates a confidence level based on the sampled first set of input records. If the measured quality of the prospective load balancing assignment is not yet achieved, then the method samples additional input records; for example when the calculated workload variance is greater than the maximum workload variance target or when the calculated confidence level is lower than a confidence level threshold.
摘要翻译：一种用于平行映射/减少范例中的负载平衡的方法，系统和计算机程序产品。该方法通过对第一组输入记录进行采样开始，并且基于每个工作任务的工作量估计，通过将第一组输入记录分配给多个工作任务来形成预期的负载平衡分配。为了测量预期的负载平衡分配，该方法将多个工作任务上的工作量方差与工作负载方差目标进行比较，并且还基于所采样的第一组输入记录来计算置信水平。如果尚未实现预期负载均衡分配的测量质量，则该方法对附加输入记录进行采样; 例如当所计算的工作负荷方差大于最大工作量方差目标时或计算出的置信水平低于置信水平阈值时。

8. 发明申请

US20090006399A1 COMPRESSION METHOD FOR RELATIONAL TABLES BASED ON COMBINED COLUMN AND ROW CODING 审中-公开
标题翻译：基于组合列和编码的关系表的压缩方法
公开(公告)号：US20090006399A1
公开(公告)日：2009-01-01
申请号：US11772058
申请日：2007-06-29
申请人： Vijayshankar Raman , Garret Swart
发明人： Vijayshankar Raman , Garret Swart
IPC分类号： G06F7/00
CPC分类号： G06F16/2453 , G06F16/221 , G06F16/2282 , G06F16/2456
摘要： A robust method to compress relations close to their entropy while still allowing efficient queries. Column values are encoded into variable length codes to exploit skew in their frequencies. The codes in each tuple are concatenated and the resulting tuplecodes are sorted and delta-coded to exploit the lack of ordering in a relation. Correlation is exploited either by co-coding correlated columns, or by using a sort order that can leverage the correlation. Also presented is a novel Huffman coding scheme, called segregated coding, that preserves maximum compression while allowing range and equality predicates on the compressed data, without even accessing the full dictionary. Delta coding is exploited to speed up queries, by reusing computations performed on nearly identical records.
摘要翻译：一种可靠的方法来压缩接近熵的关系，同时仍然允许有效的查询。列值被编码成可变长度代码以利用其频率的偏差。每个元组中的代码被级联，并且所得到的分组被分类和加密编码以利用关系中的排序缺乏。相关性通过共同编码相关列或通过使用可以利用相关性的排序顺序来利用。还提出了一种新颖的霍夫曼编码方案，称为分离编码，其保留最大压缩，同时允许压缩数据上的范围和等式谓词，甚至不访问完整的字典。利用增量编码来加快查询速度，重复使用几乎相同的记录执行的计算。

9. 发明授权

US5806076A Tracking dependencies between transactions in a database 失效
标题翻译：跟踪数据库中的事务之间的依赖关系
公开(公告)号：US5806076A
公开(公告)日：1998-09-08
申请号：US740544
申请日：1996-10-29
申请人： Gary C. Ngai , Roger J. Bamford , Garret Swart
发明人： Gary C. Ngai , Roger J. Bamford , Garret Swart
IPC分类号： G06F9/46 , G06F17/30
CPC分类号： G06F17/30356 , G06F9/466 , Y10S707/99953 , Y10S707/99954
摘要： A method and an apparatus for tracking of the dependencies between transactions is provided. Every time a data item is updated, a record is made of the transaction that updated the data item. Before another transaction locks a data item previously locked by the transaction, the entry is updated to indicate that the transaction committed and the commit time of the transaction. These entries are contained in a list head that is maintained on the same block as the data item, and a list tail that is stored separate from the data block that contains the data item. A depends-on time is maintained for each transaction. Whenever the transaction updates a data item, the depends-on time is set to the greater of the current depends-on time and the commit time of the most recently committed transaction that updated the version of the data item. Whether a transaction depends on a committed transaction is then determined based on a simple comparison between the depends-on time associated with the transaction and the commit time of the committed transaction.
摘要翻译：提供了用于跟踪事务之间的依赖关系的方法和装置。每次更新数据项时，都会对更新数据项的事务进行记录。在另一个事务锁定先前由事务锁定的数据项之前，将更新该条目以指示事务已提交和事务的提交时间。这些条目包含在与数据项相同的块上维护的列表头中，以及与包含数据项的数据块分开存储的列表尾。维护每个交易的依赖时间。每当事务更新数据项时，依赖时间被设置为当前依赖时间的更大值以及更新数据项版本的最近提交的事务的提交时间。然后，基于与事务相关联的依赖时间与承诺事务的提交时间之间的简单比较来确定事务是否依赖于提交的事务。

10. 发明授权

US09589036B2 Query-level access to external petabyte-scale distributed file systems 有权
标题翻译：查询级访问外部PB级分布式文件系统
公开(公告)号：US09589036B2
公开(公告)日：2017-03-07
申请号：US13564204
申请日：2012-08-01
申请人： Robert Hanckel , Garret Swart
发明人： Robert Hanckel , Garret Swart
IPC分类号： G06F17/30
CPC分类号： G06F17/30557 , G06F17/30126 , G06F17/30194 , G06F17/30283 , G06F17/30445 , G06F17/30516 , G06F17/3056
摘要： A system to implement query-level access by a database engine to an external distributed file system by identifying a results file location of one or more results files on the external distributed file system, and storing the results file locations in external table files on the database engine for subsequent use during retrieval of data from the results files. The database engine serves to process queries where the query specifies the external table (which in turn references locations of the results files). Execution of the query streams data from the external distributed file system into the database engine. The data from the external distributed file system is not stored in the external table files on the database engine; rather, the external table files specify a location of code or operational directives which, when executed, streams results from the external distributed file system to at least one parallel query engine.
摘要翻译：通过在外部分布式文件系统上识别一个或多个结果文件的结果文件位置，并将结果文件位置存储在数据库中的外部表格文件中，来实现数据库引擎对外部分布式文件系统的查询级别访问的系统引擎，用于在从结果文件检索数据时随后使用。数据库引擎用于处理查询，其中查询指定了外部表（又反映了结果文件的位置）。从外部分布式文件系统执行查询流数据到数据库引擎。来自外部分布式文件系统的数据不存储在数据库引擎的外部表文件中; 相反，外部表文件指定代码或操作指令的位置，当执行时，将来自外部分布式文件系统的结果传送到至少一个并行查询引擎。

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