利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

72 条记录 (耗时 0.037 秒)

    System and method for predicting cache performance
    2.
    发明授权
    System and method for predicting cache performance 有权
    用于预测缓存性能的系统和方法

    公开(公告)号：US06952664B1

    公开(公告)日：2005-10-04

    申请号：US09834342

    申请日：2001-04-13

    申请人： Tirthankar Lahiri ,  Juan R. Loaiza ,  Arvind Nithrakashyap ,  William H. Bridge

    发明人： Tirthankar Lahiri ,  Juan R. Loaiza ,  Arvind Nithrakashyap ,  William H. Bridge

    IPC分类号： G06F17/50 ,  G06G17/50

    CPC分类号： G06F17/5022

    摘要： A system and methods for simulating the performance (e.g., miss rate) of one or more caches. A cache simulator comprises a segmented list of buffers, with each buffer configured to store a data identifier and an identifier of the buffer's segment. Data references, which may be copied from an operational cache, are applied to the list to conduct the simulation. Initial estimates of each cache's miss rate include the number of references that missed all segments of the list plus the hits in all segments not part of the cache. A correction factor is generated from the ratio of actual misses incurred by the operational cache to the estimated misses for a simulated cache of the same size as the operational cache. Final predictions are generated by multiplying the initial estimates by the correction factor. The size of the operational cache may be dynamically adjusted based on the final predictions.

    摘要翻译： 用于模拟一个或多个高速缓存的性能（例如，错过率）的系统和方法。 缓存模拟器包括分段缓冲器列表，其中每个缓冲器被配置为存储数据标识符和缓冲器段的标识符。 可以从操作缓存复制的数据引用被应用于列表以进行模拟。 每个缓存的未命中率的初始估计包括丢失列表的所有段的引用数量加上不是高速缓存的一部分的所有段中的命中。 由操作缓存引起的实际未命中率与与操作缓存大小相同的模拟高速缓存的估计未命中的比率产生校正因子。 最终预测是通过将初始估计乘以校正因子而产生的。 可以基于最终预测来动态地调整操作高速缓存的大小。

    Techniques for automated allocation of memory among a plurality of pools
    3.
    发明授权
    Techniques for automated allocation of memory among a plurality of pools 有权
    在多个池中自动分配存储器的技术

    公开(公告)号：US07783852B2

    公开(公告)日：2010-08-24

    申请号：US10746471

    申请日：2003-12-23

    申请人： Tirthankar Lahiri ,  Poojan Kumar ,  Brian Hirano ,  Arvind Nithrakashyap ,  Kant Patel ,  Kiran Goyal ,  Juan R. Loaiza

    发明人： Tirthankar Lahiri ,  Poojan Kumar ,  Brian Hirano ,  Arvind Nithrakashyap ,  Kant Patel ,  Kiran Goyal ,  Juan R. Loaiza

    IPC分类号： G06F12/00

    CPC分类号： G06F9/5016 ,  G06F12/023

    摘要： Allocation of memory is optimized across multiple pools of memory, based on minimizing the time it takes to successfully retrieve a given data item from each of the multiple pools. First data is generated that indicates a hit rate per pool size for each of multiple memory pools. In an embodiment, the generating step includes continuously monitoring attempts to access, or retrieve a data item from, each of the memory pools. The first data is converted to second data that accounts for a cost of a miss with respect to each of the memory pools. In an embodiment, the second data accounts for the cost of a miss in terms of time. How much of the memory to allocate to each of the memory pools is determined, based on the second data. In an embodiment, the steps of converting and determining are automatically performed, on a periodic basis.

    摘要翻译： 基于最小化从多个池中的每一个成功检索给定数据项所需的时间，内存分配在多个内存池之间进行了优化。 生成第一个数据，指示每个多个内存池的每个池大小的命中率。 在一个实施例中，生成步骤包括连续地监视从每个存储器池访问或检索数据项的尝试。 第一个数据被转换成相对于每个存储器池来计算缺失成本的第二数据。 在一个实施例中，第二数据考虑到时间方面的错过的成本。 基于第二数据确定分配给每个存储器池的存储器的多少。 在一个实施例中，周期性地自动执行转换和确定的步骤。

    Method and mechanism for efficient implementation of ordered records
    4.
    发明授权
    Method and mechanism for efficient implementation of ordered records 有权
    有效执行有序记录的方法和机制

    公开(公告)号：US07039773B2

    公开(公告)日：2006-05-02

    申请号：US10426471

    申请日：2003-04-29

    申请人： Wei Ming Hu ,  Juan R. Loaiza ,  Roger J. Bamford ,  Vikram Joshi ,  Arvind Nithrakashyap ,  Tudor Bosman ,  Vinay Srihari ,  Alok Pareek

    发明人： Wei Ming Hu ,  Juan R. Loaiza ,  Roger J. Bamford ,  Vikram Joshi ,  Arvind Nithrakashyap ,  Tudor Bosman ,  Vinay Srihari ,  Alok Pareek

    IPC分类号： G06F12/00

    CPC分类号： G06F17/30595 ,  Y10S707/99953

    摘要： An improved method, mechanism, and system for implementing, generating, and maintaining records, such as redo records and redo logs in a database system, are disclosed. Multiple sets of records may be created and combined into a partially ordered (or non-ordered) group of records, which are later collectively ordered or sorted as needed to create an fully ordered set of records. With respect to a database system, redo generation bottleneck is minimized by providing multiple in-memory redo buffers that are available to hold redo records generated by multiple threads of execution. When the in-memory redo buffers are written to a persistent storage medium, no specific ordering needs to be specified with respect to the redo records from the different in-memory redo buffers. While the collective group of records may not be ordered, the written-out redo records may be partially ordered based upon the ordered redo records from within individual in-memory redo buffers. At recovery, ordering and/or merging of redo records may occur to satisfy database consistency requirements.

    摘要翻译： 公开了一种用于在数据库系统中实现，生成和维护记录（如重做记录和重做日志）的改进方法，机制和系统。 可以创建多组记录，并将其组合成部分有序（或非有序）的记录组，这些记录集合随后根据需要进行统一排序或排序以创建完全有序的记录集。 对于数据库系统，通过提供多个可用于保存由多个执行线程生成的重做记录的内存中重做缓冲区，可以使重做生成瓶颈最小化。 当内存中重做缓冲区被写入持久存储介质时，不需要针对来自不同内存中重做缓冲区的重做记录指定特定顺序。 虽然可能不会对集体记录进行排序，但是写出的重做记录可能会根据内部存储器重做缓冲区内的重做记录进行部分排序。 在恢复时，可能会发生重做记录的排序和/或合并，以满足数据库一致性要求。

    Method and apparatus for performing selective encryption/decryption in a data storage system
    7.
    发明授权
    Method and apparatus for performing selective encryption/decryption in a data storage system 有权
    用于在数据存储系统中执行选择性加密/解密的方法和装置

    公开(公告)号：US08892905B2

    公开(公告)日：2014-11-18

    申请号：US11726428

    申请日：2007-03-21

    申请人： Adam Y. Lee ,  Varun Malhotra ,  Daniel ManHung Wong ,  Tirthankar Lahiri ,  Kiran Goyal ,  Juan R. Loaiza ,  Paul Youn

    发明人： Adam Y. Lee ,  Varun Malhotra ,  Daniel ManHung Wong ,  Tirthankar Lahiri ,  Kiran Goyal ,  Juan R. Loaiza ,  Paul Youn

    IPC分类号： G06Q30/02 ,  H04L9/08

    CPC分类号： H04L9/0894

    摘要： One embodiment of the present invention provides a system for performing selective encryption/decryption in a data storage system. During operation, the system receives a data block from a storage medium at an input/output layer, wherein the input/output layer serves as an interface between the storage medium and a buffer cache. Next, the system determines whether the data block is an encrypted data block. If not, the system stores the data block in the buffer cache. Otherwise, if the data block is an encrypted data block, the system retrieves a storage-key, wherein the storage-key is associated with a subset of storage, which is associated with the encrypted data block. Using the storage-key, the system then decrypts the encrypted data block to produce a decrypted data block. Finally, the system stores the decrypted data block in the buffer cache, wherein the data block remains encrypted in the storage medium.

    摘要翻译： 本发明的一个实施例提供一种用于在数据存储系统中执行选择性加密/解密的系统。 在操作期间，系统在输入/输出层从存储介质接收数据块，其中输入/输出层用作存储介质和缓冲器高速缓存之间的接口。 接下来，系统确定数据块是否是加密数据块。 如果没有，系统将数据块存储在缓冲区高速缓存中。 否则，如果数据块是加密数据块，则系统检索存储密钥，其中存储密钥与与加密数据块相关联的存储子集相关联。 使用存储密钥，系统然后解密加密的数据块以产生解密的数据块。 最后，系统将解密的数据块存储在缓冲器高速缓存中，其中数据块在存储介质中保持加密。

    Partial key indexes
    9.
    发明授权
    Partial key indexes 有权
    部分关键指标

    公开(公告)号：US08429133B2

    公开(公告)日：2013-04-23

    申请号：US11956287

    申请日：2007-12-13

    申请人： Tirthankar Lahiri ,  Dheeraj Pandey ,  Juan R. Loaiza ,  Michael Zoll ,  Kiran B. Goyal ,  Neil J. S. Macnaughton

    发明人： Tirthankar Lahiri ,  Dheeraj Pandey ,  Juan R. Loaiza ,  Michael Zoll ,  Kiran B. Goyal ,  Neil J. S. Macnaughton

    IPC分类号： G06F7/00 ,  G06F17/00 ,  G06F17/30

    CPC分类号： G06F17/30327

    摘要： A partial reverse key index is described, which allows distributed contention as resources vie to insert data into an index as well as allows range scans to be performed on the index. To do so, before an index entry for a key value is inserted into an index, the key value is transformed using a transformation operation that affects a subset of the order of the key value. The index entry is then inserted based on the transformed key value. Because the transformation operation affects the order of the key value, the transformed values associated with two consecutive key values will not necessarily be consecutive. Therefore, the index entries associated with the consecutive key values may be inserted into unrelated portions of the index.

    摘要翻译： 描述了部分反向密钥索引，其允许分布式争用作为将数据插入到索引中的资源，并且允许在索引上执行范围扫描。 为此，在将键值的索引条目插入索引之前，将使用影响键值顺序子集的转换操作来转换键值。 然后基于转换的键值插入索引条目。 由于转换操作影响键值的顺序，与两个连续的键值相关联的变换值不一定是连续的。 因此，可以将与连续键值相关联的索引条目插入索引的无关部分。

    Reducing disk IO by full-cache write-merging
    10.
    发明授权
    Reducing disk IO by full-cache write-merging 有权
    通过全缓存写入合并来减少磁盘IO

    公开(公告)号：US07194589B2

    公开(公告)日：2007-03-20

    申请号：US10645987

    申请日：2003-08-22

    申请人： Tirthankar Lahiri ,  Juan R. Loaiza ,  Richard L. Frank ,  Kiran Goyal

    发明人： Tirthankar Lahiri ,  Juan R. Loaiza ,  Richard L. Frank ,  Kiran Goyal

    IPC分类号： G06F13/00

    CPC分类号： G06F12/0804 ,  G06F12/0866

    摘要： An electronic and computerized system that coalesces write operations using a buffer cache which stores data waiting to be written back to a disk of the electronic and computerized system is described. Dirty data blocks with consecutive data block addresses in the buffer cache are coalesced and written to the disk together. The disk head movements for performing the disk IOs are significantly reduced, thereby allowing the electronic and computerized system to maintain a high IO throughput and high peak performance with fewer disks.

    摘要翻译： 描述了使用存储等待被写回到电子和计算机化系统的盘的数据的缓冲器高速缓存来合并写入操作的电子和计算机化系统。 缓冲区高速缓存中具有连续数据块地址的脏数据块被合并并且一起写入磁盘。 用于执行磁盘IO的盘头运动显着减少，从而允许电子和计算机系统以更少的磁盘保持高IO吞吐量和高峰值性能。