公开(公告)号：US06681230B1

公开(公告)日：2004-01-20

申请号：US09276218

申请日：1999-03-25

申请人： Stephen M. Blott ,  Yuri Breitbart ,  Thomas M. Cliff, Jr. ,  Frank Frastaci, Jr. ,  Henry F. Korth

发明人： Stephen M. Blott ,  Yuri Breitbart ,  Thomas M. Cliff, Jr. ,  Frank Frastaci, Jr. ,  Henry F. Korth

IPC分类号： G06F1700

CPC分类号： G06F8/38 ,  Y10S707/99945 ,  Y10S707/99948

摘要： A real-time event processing system (EPS) for processing a sequence of events generated by one or more applications. In an illustrative embodiment, the EPS includes a set of real-time analysis engines (RAEs) operating in parallel, e.g., a set of clusters each including one or more RAEs, and one or more mappers for mapping a given input event to a particular one of the clusters. A main-memory database system is coupled to the RAEs, and the RAEs process events associated with input streams from one or more data sources and deliver output streams to one or more data sinks. The data source and data sinks may be, e.g., network elements, clients, databases, etc. The events are processed in accordance with services implemented in the RAEs, and utilize data stored in a memory portion of the main-memory database system accessible to the RAEs. The data may include, e.g., a subscription table storing subscription information indicating the service or services that should be executed for a given event. The services are generated in a service authoring environment (SAE) in the EPS, using a declarative language. The SAE generates the services in the form of object code components, e.g., dynamically linked libraries, which may be dynamically linked into the RAEs without interrupting event processing. Recovery information regarding a recovery point for a given RAE or set of RAEs in the EPS may be stored in a memory portion of the main-memory database system, and utilized to implement a roll-back of the RAE to the recovery point.

摘要翻译： 一种用于处理由一个或多个应用产生的事件序列的实时事件处理系统（EPS）。 在说明性实施例中，EPS包括并行操作的一组实时分析引擎（RAE），例如，一组包括一个或多个RAE的集群，以及一个或多个映射器，用于将给定的输入事件映射到特定的 其中一个集群。 主存储器数据库系统耦合到RAE，并且RAE处理与来自一个或多个数据源的输入流相关联的事件，并将输出流传送到一个或多个数据宿。 数据源和数据宿可以是例如网络元件，客户端，数据库等。根据在RAE中实现的服务来处理事件，并利用存储在主存储器数据库系统的存储器部分中的数据可访问 RAE。 数据可以包括例如存储指示应当为给定事件执行的服务或服务的订阅信息的订阅表。 这些服务是使用声明性语言在EPS中的服务创作环境（SAE）中生成的。 SAE以目标代码组件的形式生成服务，例如动态链接的库，其可以动态地链接到RAE而不中断事件处理。 关于EPS中的给定RAE或RAE集合的恢复点的恢复信息可以存储在主存储器数据库系统的存储器部分中，并且用于实现RAE到恢复点的回滚。

公开(公告)号：US5864851A

公开(公告)日：1999-01-26

申请号：US843196

申请日：1997-04-14

申请人： Yuri Breitbart ,  Henry F. Korth

发明人： Yuri Breitbart ,  Henry F. Korth

IPC分类号： G06F17/30

CPC分类号： G06F17/30356 ,  Y10S707/99938 ,  Y10S707/99943 ,  Y10S707/99953

摘要： Method and system for managing transactions operating on replicated data items at multiple physical sites in a distributed database system. The transactions include local transactions each being processed at one of the physical sites and global transactions each being processed at multiple physical sites. Each transaction originates at one of the physical sites, and is permitted to read data items only at that physical site. In addition, only transactions originating at a physical site at which a primary copy of a data item is located are permitted to update that data item. A number of virtual sites are defined such that a given virtual site VS.sub.i.sup.j at a particular point in time includes a set S.sub.i.sup.j of all data items at a physical site s.sub.j that a given transaction T.sub.i has accessed from an initial operation up to that point in time. A replication graph is maintained to represent the relationships between the transactions and the virtual sites. The replication graph includes a first set of nodes for the transactions, and a second set of nodes for the virtual sites. A node for a transaction T.sub.i and a node for a virtual site VS.sub.i.sup.j are connected in the graph if a schedule of transaction operations includes a write operation by transaction T.sub.i on a replicated data item in the set of data items associated with virtual site VS.sub.i.sup.j. The replication graph is maintained as part of a concurrency-control protocol and the absence of cycles in the graph may be used to indicate whether a given schedule is globally serializable.

摘要翻译： 用于管理在分布式数据库系统中的多个物理站点处对复制数据项进行操作的事务的方法和系统。 这些事务包括每个在物理站点之一处理的本地事务和在多个物理站点处理的全局事务。 每个事务发生在一个物理站点，并允许只在该物理站点读取数据项。 此外，仅允许在数据项的主副本所在的物理站点处发起的事务更新该数据项。 定义多个虚拟站点，使得在特定时间点的给定虚拟站点VSij包括给定事务Ti从初始操作到该时间点的物理站点sj处的所有数据项的集合Sij 。 维护复制图以表示事务和虚拟站点之间的关系。 复制图包括用于事务的第一组节点，以及用于虚拟站点的第二组节点。 如果事务操作的调度包括与虚拟站点VSij相关联的数据项集合中的复制数据项上的事务Ti的写入操作，则用于事务Ti的节点和用于虚拟站点VSij的节点连接在图中。 复制图作为并发控制协议的一部分进行维护，并且图中不存在周期可用于指示给定的调度是否是全局可序列化的。

公开(公告)号：US5999931A

公开(公告)日：1999-12-07

申请号：US953571

申请日：1997-10-17

申请人： Yuri Breitbart ,  Henry F. Korth ,  Abraham Silberschatz

发明人： Yuri Breitbart ,  Henry F. Korth ,  Abraham Silberschatz

IPC分类号： G06F9/46 ,  G06F17/30

CPC分类号： G06F17/30575 ,  G06F17/30356 ,  G06F9/466 ,  Y10S707/99938

摘要： The invention provides protocols for managing transactions operating on replicated data items at multiple physical sites in a distributed database system. The protocols make use of dynamically changing sets of data items referred to as "virtual sites" and a replication graph or other suitable globally consistent representation of the relationships between the transactions and the virtual sites. Illustrative embodiments of the invention include a static global serializability (SGS) protocol, a commit-oriented protocol (COP) and a multiversion optimistic protocol (MOP). The SGS protocol broadcasts the data access set of a given transaction to all physical sites, and applies the Thomas Write Rule (TWR) to write-write conflicts on secondary copies of data items. The COP protocol defers testing of the replication graph until a transaction is ready to commit, and each transaction is allowed to proceed at its origination site independently of other transactions that are executing at other sites. The MOP protocol uses two versions of each data item to ensure global multiversion serializability. The two versions are the current version of the data item, and a "last certified version" of the data item. All read-only transactions read the last certified version, and can therefore proceed without delay. The protocols ensure global serializability while substantially reducing communication overhead relative to conventional protocols.

摘要翻译： 本发明提供用于管理在分布式数据库系统中的多个物理站点处对复制数据项进行操作的协议。 这些协议利用动态变化的数据项集称为“虚拟站点”，以及复制图或其他合适的全局一致性表示的事务和虚拟站点之间的关系。 本发明的说明性实施例包括静态全局可串行化（SGS）协议，面向提交的协议（COP）和多向乐曲协议（MOP）。 SGS协议将给定事务的数据访问集合广播到所有物理站点，并且将Thomas Write Rule（TWR）应用于数据项的辅助副本上的写入冲突。 COP协议延迟对复制图的测试，直到事务准备好提交，并且允许每个事务在其始发站点独立于在其他站点执行的其他事务进行。 MOP协议使用每个数据项的两个版本来确保全局多版本可串行化。 这两个版本是数据项的当前版本，以及数据项的“最后一个认证版本”。 所有只读事务读取最后一个认证版本，因此可以毫不拖延地继续。 协议确保全局可序列化，同时大大降低了传统协议的通信开销。

公开(公告)号：US06963914B1

公开(公告)日：2005-11-08

申请号：US09328657

申请日：1999-06-09

申请人： Yuri Breitbart ,  Radek Vingralek

发明人： Yuri Breitbart ,  Radek Vingralek

IPC分类号： G06F15/173 ,  H04L29/08

CPC分类号： H04L67/1095 ,  H04L67/1002 ,  H04L67/1008 ,  H04L67/327

摘要： A method and apparatus for communicating files over a communications network in which links, such as hyperlinks, to files are logical in nature, rather than physical in nature, i.e., associated with a particular electronic address. An up-to-date replication directory is maintained on each server and each server inserts current physical references corresponding to a file's logical references into a requested parent file, along with a reference to a server selection program, before the parent file is transmitted to the requesting client. The server selection program selects physical references in the order of their likelihood of providing the fastest response. If a queried server does not currently store the file, an alternate server is queried. Servers communicate with each other to create and delete replicas of files and to make corresponding updates to each server's replication directory.

摘要翻译： 一种用于在通信网络上传送文件的方法和装置，其中诸如超链接的链接在本质上是逻辑上的，而不是物理本质上，即与特定电子地址相关联。 在每个服务器上维护最新的复制目录，并且每个服务器将对应于文件的逻辑引用的当前物理引用插入到请求的父文件中，以及在将服务器选择程序发送到 请求客户端。 服务器选择程序按照提供最快响应的可能性的顺序选择物理参考。 如果查询的服务器当前不存储该文件，则会查询备用服务器。 服务器相互通信以创建和删除文件的副本，并对每个服务器的复制目录进行相应的更新。

公开(公告)号：US06721314B1

公开(公告)日：2004-04-13

申请号：US09316118

申请日：1999-05-20

申请人： Stephen Michael Blott ,  Yuri Breitbart ,  Clifford Eric Martin

发明人： Stephen Michael Blott ,  Yuri Breitbart ,  Clifford Eric Martin

IPC分类号： H04L1228

CPC分类号： H04L12/1877

摘要： Duplicate processing at network operators is avoided by applying once-only processing at operators which are adjacent to either the source or destination host of a data packet. An operator is adjacent to a host if there exists a path between the operator and the host containing no other operators. In one embodiment, an operator determines that it is adjacent to a host if it receives a special broadcast data packet from the host. To ensure that no other operators receive the special broadcast data packet, the adjacent operator drops the packet. In another embodiment, operators determine whether they are adjacent to identified hosts by transmitting special ping packets to the hosts. If an operator receives a ping response from the host, the operator determines that it is adjacent to the host. To ensure that only adjacent operators receive ping responses, intervening operators drop special ping packets received from other operators.

摘要翻译： 通过在与数据包的源或目的主机相邻的运营商处应用一次性处理来避免网络运营商的重复处理。 如果操作员和不包含其他操作符的主机之间存在路径，则操作员与主机相邻。 在一个实施例中，如果运营商从主机接收到特殊的广播数据分组，则运营商确定它与主机相邻。 为了确保没有其他运营商接收到特殊的广播数据包，相邻的运营商丢弃该数据包。 在另一个实施例中，运营商通过向主机发送特殊的ping分组来确定它们是否与所标识的主机相邻。 如果操作员从主机接收到ping响应，则操作员确定它与主机相邻。 为了确保只有相邻的运营商才能收到ping响应，中介运营商会丢弃其他运营商收到的特殊ping报文。

公开(公告)号：US06697338B1

公开(公告)日：2004-02-24

申请号：US09428419

申请日：1999-10-28

申请人： Yuri Breitbart ,  Minos N. Garofalakis ,  Clifford Eric Martin ,  Rajeev Rastogi ,  Srinivasan Seshadri ,  Abraham Silberschatz

发明人： Yuri Breitbart ,  Minos N. Garofalakis ,  Clifford Eric Martin ,  Rajeev Rastogi ,  Srinivasan Seshadri ,  Abraham Silberschatz

IPC分类号： H04L1228

CPC分类号： H04L41/12

摘要： Physical connectivity is determined between elements such as switches and routers in a multiple subnet communication network. Each element has one or more interfaces each of which is physically linked with an interface of another network element. Address sets are generated for each interface of the network elements, wherein members of a given address set correspond to network elements that can be reached from the corresponding interface for which the given address set was generated. The members of first address sets generated for corresponding interfaces of a given network element, are compared with the members of second address sets generated for corresponding interfaces of network elements other than the given element. A set of candidate connections between an interface of the given network element and one or more interfaces of other network elements, are determined. If more than one candidate connection is determined, connections with network elements that are in the same subnet as the given network element are eliminated from the set.

摘要翻译： 在多个子网通信网络中的诸如交换机和路由器的元件之间确定物理连接性。 每个元件具有一个或多个接口，每个接口与另一个网络元件的接口物理连接。 为网络元件的每个接口生成地址集，其中给定地址集合的成员对应于可以从生成给定地址集的相应接口到达的网络元素。 将给定网元的相应接口生成的第一地址集的成员与为给定元素以外的网元的相应接口生成的第二地址集的成员进行比较。 确定给定网络元件的接口与其他网络元件的一个或多个接口之间的一组候选连接。 如果确定了多个候选连接，则与组中与网络元素位于与给定网络元素相同的子网中的连接被消除。

公开(公告)号：US20050091350A1

公开(公告)日：2005-04-28

申请号：US10672535

申请日：2003-09-26

申请人： Yigal Bejerano ,  Yuri Breitbart ,  Ariel Orda ,  Rajeev Rastogi ,  Alexander Sprintson

发明人： Yigal Bejerano ,  Yuri Breitbart ,  Ariel Orda ,  Rajeev Rastogi ,  Alexander Sprintson

IPC分类号： G06F15/173 ,  H04Q3/00

CPC分类号： H04Q3/0079

摘要： Systems and methods for provisioning QoS paths with restoration in a network. In one embodiment, one system includes: (1) a primary path generator configured to identify a suitable primary path between source and destination nodes in a network, (2) an auxiliary graph generator, associated with the primary path generator, configured to construct a directed auxiliary graph from an undirected graph representing the network by reversing each link in a primary QoS path of the undirected graph and replacing each other link in the undirected graph by two directed links, (3) a walk identifier, associated with the auxiliary graph generator, configured to identify a walk in the auxiliary directed graph corresponding to a set of bridges in the network and (4) a bridge identifier, associated with the walk identifier, configured to identify a set of bridges in the network such that at least one link of the primary path is protected by a bridge.

摘要翻译： 用于通过网络恢复来提供QoS路径的系统和方法。 在一个实施例中，一个系统包括：（1）主路径发生器，被配置为识别网络中源节点和目的节点之间的适当主路径，（2）辅助图生成器，其与主路径生成器相关联， 通过反转无向图的主QoS路径中的每个链路并且通过两个有向链接替换无向图中的每个其他链路，（3）与辅助图生成器相关联的步行标识符，来自表示网络的无向图中的定向辅助图 ，被配置为识别对应于所述网络中的一组桥的辅助有向图中的步行，以及（4）与所述步行标识符相关联的桥标识符，被配置为识别所述网络中的一组桥，使得至少一个链路 的主要路径由桥梁保护。