公开(公告)号：US6012090A

公开(公告)日：2000-01-04

申请号：US818057

申请日：1997-03-14

申请人： Pi-Yu Chung ,  Yennun Huang ,  Chih-Mei Lin ,  Yi-Min Wang

发明人： Pi-Yu Chung ,  Yennun Huang ,  Chih-Mei Lin ,  Yi-Min Wang

IPC分类号： H04L29/06 ,  H04L29/08 ,  H04L29/12 ,  G06F13/00

CPC分类号： H04L67/02 ,  H04L67/1023 ,  H04L29/12594 ,  H04L61/30 ,  H04L67/1002 ,  H04L67/34 ,  H04L69/329

摘要： A registration applet embedded in a registration page of a browser program allows a user to associate a user-specified group name with a plurality of UTRLs, HTTP POST or GET requests or other network service identifiers, such that the group name designates a category of information provided by corresponding network services. An access applet embedded in an access page of the browser allows a user to select one of several previously-registered group names, and an access mode for processing responses to service requests. A processor running the access applet automatically issues parallel requests to the network services associated with a selected group name in response to entry of a command by the user. The user may select a parallel-any access mode, in which the processor displays only the first response to the parallel requests, a parallel-all mode, in which the processor directs the display of multiple responses in a user-specified display format, or a retry access mode, in which the processor reissues a network service request if a response to a previous request is not received within a predetermined time period.

摘要翻译： 嵌入在浏览器程序的注册页面中的注册小应用程序允许用户将用户指定的组名称与多个UTRL，HTTP POST或GET请求或其他网络服务标识符相关联，使得组名称指定信息的类别 由相应的网络服务提供。 嵌入在浏览器的访问页面中的访问小应用程序允许用户选择几个先前注册的组名称之一，以及用于处理对服务请求的响应的访问模式。 运行访问小应用程序的处理器响应于用户的命令的输入，自动向与所选择的组名称相关联的网络服务发出并行请求。 用户可以选择并行 - 任何访问模式，其中处理器仅显示对并行请求的第一响应，并行 - 全部模式，其中处理器以用户指定的显示格式指示多个响应的显示，或 重试访问模式，其中如果在预定时间段内没有接收到对先前请求的响应，则处理器重新发布网络服务请求。

公开(公告)号：US6105148A

公开(公告)日：2000-08-15

申请号：US981298

申请日：1998-03-03

申请人： Pi-Yu Chung ,  Yennun Huang ,  Chandra Kintala ,  Kiem-Phong Vo ,  Yi-Min Wang

发明人： Pi-Yu Chung ,  Yennun Huang ,  Chandra Kintala ,  Kiem-Phong Vo ,  Yi-Min Wang

IPC分类号： G06F11/14

CPC分类号： G06F11/1438

摘要： By checkpointing and restoring a user application process, that includes a volatile state and a persistent state, recovery of an application process from the checkpoint position is possible. Specifically, a volatile state is checkpointed in a checkpoint position. Next, the persistent state is monitored to detect a file operation following a checkpoint position that will modify the persistent state. Then, portions of the persistent state are checkpointed if a modification of the persistent state is about to be performed. Then, a recovery to the checkpoint position can be performed such that modifications to the persistent state since the checkpoint position are undone. This allows for resumption of the user application process from the checkpoint position.

摘要翻译： PCT No.PCT / US95 / 07629 Sec。 371日期1998年3月3日 102（e）1998年3月3日PCT提交1995年6月16日PCT公布。 公开号WO97 / 00476 日期1997年1月3日通过检查和恢复包含易失性状态和持久状态的用户应用程序进程，可以从检查点位置恢复应用程序进程。 具体来说，检查点位置检查点处于易失状态。 接下来，监视持久状态以检测将修改持续状态的检查点位置之后的文件操作。 然后，如果要执行持久状态的修改，则检查点的持久状态的部分。 然后，可以执行到检查点位置的恢复，使得自检查点位置被撤销之后对持久状态的修改。 这允许从检查点位置恢复用户应用程序进程。

公开(公告)号：US5978829A

公开(公告)日：1999-11-02

申请号：US740908

申请日：1996-11-05

申请人： Pi-Yu Chung ,  Glenn Stephen Fowler ,  Yennun Huang ,  Kiem-Phong Vo ,  Yi-Min Wang

发明人： Pi-Yu Chung ,  Glenn Stephen Fowler ,  Yennun Huang ,  Kiem-Phong Vo ,  Yi-Min Wang

IPC分类号： G06F9/46 ,  G06F9/50 ,  G06F11/34 ,  G06F15/16 ,  G06F15/177 ,  G06F9/00

CPC分类号： G06F9/5072 ,  G06F9/5088 ,  G06F11/3495

摘要： The present invention relates to systems for sharing idle workstation computers that are connected together through a network and shared file system. More particularly, a user of a local host workstation may submit jobs for execution on remote workstations. The systems of the present invention select a remote host that is idle in accordance with a decentralized scheduling scheme and then continuously monitor the activity of the remote host on which the job is executing. If the system detects certain activity on the remote host by one of the remote host's primary users, the execution of the job is immediately suspended to prevent inconvenience to the primary users. The system also suspends job execution if the remote host's load average gets too high. Either way, the suspended job is migrated by selecting another idle remote workstation to resume execution of the suspended job (from the point in time at which the last checkpoint occurred).

摘要翻译： 本发明涉及用于共享通过网络和共享文件系统连接在一起的空闲工作站计算机的系统。 更具体地，本地主机工作站的用户可以提交作业以在远程工作站上执行。 本发明的系统根据分散调度方案选择空闲的远程主机，然后连续地监视作业正在执行的远程主机的活动。 如果系统由远程主机的主用户之一检测到远程主机上的某些活动，则该作业的执行将立即暂停，以避免对主要用户造成不便。 如果远程主机的负载平均值太高，系统也会挂起作业执行。 无论哪种方式，通过选择另一个空闲的远程工作站来恢复挂起的作业，以恢复执行挂起的作业（从最后一个检查点发生的时间起）。

公开(公告)号：US06470389B1

公开(公告)日：2002-10-22

申请号：US08818989

申请日：1997-03-14

申请人： Pi-Yu Chung ,  Om P. Damani ,  Yennun Huang ,  Chandra M. Kintala ,  Yi-Min Wang

发明人： Pi-Yu Chung ,  Om P. Damani ,  Yennun Huang ,  Chandra M. Kintala ,  Yi-Min Wang

IPC分类号： G06F1516

CPC分类号： H04L29/06 ,  G06F2209/462 ,  H04L29/12047 ,  H04L29/12292 ,  H04L29/12783 ,  H04L61/15 ,  H04L61/2069 ,  H04L61/35 ,  H04L67/1002 ,  H04L67/1023 ,  H04L67/1034 ,  H04L67/42 ,  H04L69/16

摘要： Methods and apparatus for hosting a network service on a cluster of servers, each including a primary and a secondary Internet Protocol (IP) address. A common cluster address is assigned as the secondary address to each of the servers in the cluster. The cluster address may be assigned in UNIX-based servers using an ifconfig alias option, and may be a ghost IP address that is not used as a primary address by any server in the cluster. Client requests directed to the cluster address are dispatched such that only one of the servers of the cluster responds to a given client request. The dispatching may use a routing-based technique, in which all client requests directed to the cluster address are routed to a dispatcher connected to the local network of the server cluster. The dispatcher then applies a hash function to the client IP address in order to select one of the servers to process the request. The dispatching may alternatively use a broadcast-based technique, in which a router broadcasts client requests having the cluster address to all of the servers of the cluster over a local network. The servers then each provide a filtering routine, which may involve comparing a server identifier with a hash value generated from a client address, in order to ensure that only one server responds to each request broadcast by the router.

摘要翻译： 在服务器集群上托管网络服务的方法和装置，每个服务器包括主要和辅助因特网协议（IP）地址。 将通用群集地址分配给群集中的每个服务器的辅助地址。 可以使用ifconfig别名选项在基于UNIX的服务器中分配群集地址，并且可能是群集中的任何服务器未被用作主地址的ghost IP地址。 调度定向到集群地址的客户端请求，使得只有一个集群的服务器响应给定的客户端请求。 调度可以使用基于路由的技术，其中指向集群地址的所有客户端请求被路由到连接到服务器集群的本地网络的分派器。 调度员然后将哈希函数应用于客户端IP地址，以便选择其中一个服务器来处理该请求。 调度可以替代地使用基于广播的技术，其中路由器通过本地网络向群集的所有服务器广播具有簇地址的客户端请求。 然后，服务器每个提供过滤例程，其可以涉及将服务器标识符与从客户端地址生成的散列值进行比较，以便确保只有一个服务器响应路由器广播的每个请求。

公开(公告)号：US6044475A

公开(公告)日：2000-03-28

申请号：US981297

申请日：1998-03-03

申请人： Pi-Yu Chung ,  Yennun Huang ,  Chandra Kintala ,  Kiem-Phong Vo ,  Yi-Min Wang

发明人： Pi-Yu Chung ,  Yennun Huang ,  Chandra Kintala ,  Kiem-Phong Vo ,  Yi-Min Wang

IPC分类号： G06F11/14

CPC分类号： G06F11/1438

摘要： A checkpoint and restoration system is disclosed to provide checkpoint and restoration techniques for user application processes which save the process state, including the volatile state and desired portions of the persistent state, during normal execution, and thereafter restore the saved state. A lazy checkpoint technique is disclosed which delays the taking of the persistent state checkpoint until an inconsistency between the checkpointed volatile state and a portion of the persistent state is about to occur. The disclosed checkpoint and restoration system allows a user or a user application process to specify selected portions of the persistent state to be excluded from a checkpoint. A selected portion of the pre-restoring process state, such as a return value argument, may be protected before restoring the user application process to a checkpointed state, so that the pre-restoration values of the protected state are retained following restoration of the checkpoint. The retained return value allows one or more segments of restoration code to be executed following a restoration and a normal execution mode to be distinguished from a restoration mode.

摘要翻译： PCT No.PCT / US95 / 07660 Sec。 371日期1998年3月3日 102（e）1998年3月3日PCT提交1995年6月16日PCT公布。 出版物WO97 / 00477 日期1997年1月3日公开了一种检查点和恢复系统，用于为正常执行期间保存处理状态（包括易失性状态和持久状态的期望部分）的用户应用进程提供检查点和恢复技术，然后恢复保存状态 。 公开了一种延迟的检查点技术，其延迟持续状态检查点的获取，直到检查点的易失性状态和持续状态的一部分之间的不一致将要发生。 所公开的检查点和恢复系统允许用户或用户应用进程指定要从检查点排除的持久状态的所选部分。 在将用户应用进程恢复到检查点状态之前，可以保护预恢复过程状态的所选部分（诸如返回值参数），使得在恢复检查点之后保留保护状态的恢复前值 。 保留的返回值允许在恢复之后执行恢复代码的一个或多个段，并且将正常执行模式与恢复模式区分开。

公开(公告)号：US06266781B1

公开(公告)日：2001-07-24

申请号：US09119139

申请日：1998-07-20

申请人： Pi-Yu Chung ,  Yennun Huang ,  Deron Liang ,  Chia-Yen Shih ,  Shalini Yajnik

发明人： Pi-Yu Chung ,  Yennun Huang ,  Deron Liang ,  Chia-Yen Shih ,  Shalini Yajnik

IPC分类号： G06F1100

CPC分类号： G06F11/2097 ,  G06F11/0757 ,  G06F11/1438 ,  G06F11/2023 ,  G06F11/2038

摘要： An application module (A) running on a host computer in a computer network is failure-protected with one or more backup copies that are operative on other host computers in the network. In order to effect fault protection, the application module registers itself with a ReplicaManager daemon process (112) by sending a registration message, which message, in addition to identifying the registering application module and the host computer on which it is running, includes the particular replication strategy (cold backup, warm backup, or hot backup) and the degree of replication associated with that application module. The backup copies are then maintained in a fail-over state according to the registered replication strategy. A WatchDog daemon (113), running on the same host computer as the registered application periodically monitors the registered application to detect failures. When a failure, such as a crash or hangup of the application module, is detected, the failure is reported to the ReplicaManager, which effects the requested fail-over actions. An additional backup copy is then made operative in accordance with the registered replication style and the registered degree of replication. A SuperWatchDog daemon process (115-1), running on the same host computer as the ReplicaManager, monitors each host computer in the computer network. When a host failure is detected, each application module running on that host computer is individually failure-protected in accordance with its registered replication style and degree of replication.

摘要翻译： 在计算机网络中的主计算机上运行的应用模块（A）由在网络中的其他主机上运行的一个或多个备份副本进行故障保护。 为了实现故障保护，应用模块通过发送注册消息向ReplicaManager守护进程（112）注册自己，除了识别注册应用模块和运行它的主计算机之外，该消息还包括特定的 复制策略（冷备份，热备份或热备份）以及与该应用模块相关联的复制程度。 然后根据注册的复制策略将备份副本保持在故障切换状态。 与注册应用程序在同一主机上运行的WatchDog守护程序（113）定期监视注册的应用程序以检测故障。 当检测到故障（如应用程序模块的崩溃或挂起）时，会将故障报告给副本管理器，这会影响所请求的故障转移操作。 然后根据注册的复制风格和注册的复制程度使额外的备份副本生效。 与ReplicaManager在同一主机上运行的SuperWatchDog守护进程（115-1）监视计算机网络中的每台主机。 当检测到主机故障时，根据其注册的复制风格和复制程度，在该主机上运行的每个应用程序模块都单独进行故障保护。

公开(公告)号：US06195760B1

公开(公告)日：2001-02-27

申请号：US09119140

申请日：1998-07-20

申请人： Pi-Yu Chung ,  Yennun Huang ,  Deron Liang ,  Chia-Yen Shih ,  Shalini Yajnik

发明人： Pi-Yu Chung ,  Yennun Huang ,  Deron Liang ,  Chia-Yen Shih ,  Shalini Yajnik

IPC分类号： G06F1108

CPC分类号： G06F11/1438 ,  G06F11/0757

摘要： An application module (A) running on a host computer in a computer network is failure-protected with one or more backup copies that are operative on other host computers in the network. In order to effect fault protection, the application module registers itself with a ReplicaManager daemon process (112) by sending a registration message, which message, in addition to identifying the registering application module and the host computer on which it is running, includes the particular replication strategy (cold backup, warm backup, or hot backup) and the degree of replication associated with that application module. The backup copies are then maintained in a fail-over state according to the registered replication strategy. A WatchDog daemon (113), running on the same host computer as the registered application periodically monitors the registered application to detect failures. When a failure, such as a crash or hangup of the application module, is detected, the failure is reported to the ReplicaManager, which effects the requested fail-over actions. An additional backup copy is then made operative in accordance with the registered replication style and the registered degree of replication. A SuperWatchDog daemon process (115-1), running on the same host computer as the ReplicaManager, monitors each host computer in the computer network. When a host failure is detected, each application module running on that host computer is individually failure-protected in accordance with its registered replication style and degree of replication.

摘要翻译： 在计算机网络中的主计算机上运行的应用模块（A）由在网络中的其他主机上运行的一个或多个备份副本进行故障保护。 为了实现故障保护，应用模块通过发送注册消息向ReplicaManager守护进程（112）注册自己，除了识别注册应用模块和运行它的主计算机之外，该消息还包括特定的 复制策略（冷备份，热备份或热备份）以及与该应用模块相关联的复制程度。 然后根据注册的复制策略将备份副本保持在故障切换状态。 与注册应用程序在同一主机上运行的WatchDog守护程序（113）定期监视注册的应用程序以检测故障。 当检测到故障（如应用程序模块的崩溃或挂起）时，会将故障报告给副本管理器，这会影响所请求的故障转移操作。 然后根据注册的复制风格和注册的复制程度使额外的备份副本生效。 与ReplicaManager在同一主机上运行的SuperWatchDog守护进程（115-1）监视计算机网络中的每台主机。 当检测到主机故障时，根据其注册的复制风格和复制程度，在该主机上运行的每个应用程序模块都单独进行故障保护。

公开(公告)号：US20070226272A1

公开(公告)日：2007-09-27

申请号：US11753290

申请日：2007-05-24

申请人： Xiao Huang ,  Magnus Vejlstrup ,  David Rabbers ,  Pi-Yu Chung ,  Martin Susser ,  Aaron Hansen ,  Brian Scott ,  David George

发明人： Xiao Huang ,  Magnus Vejlstrup ,  David Rabbers ,  Pi-Yu Chung ,  Martin Susser ,  Aaron Hansen ,  Brian Scott ,  David George

IPC分类号： G06F17/30

CPC分类号： G06F17/30578 ,  G06F17/30581 ,  Y10S707/99954

摘要： A method and system for synchronizing a main database of a server and a local database of a handheld device. A user can use an application residing in the handheld device to make transactions in the local database. During a synchronization operation, the handheld device and server are coupled. The system then determines whether the application should be updated and, if so, causes the server to provide an update. The system also causes the handheld device to provide to the server information related to the transactions made by the user to the local database. The system causes the server to perform transactions on the main database based on the transaction information. The system also causes the server to extract data from the main database. The server can then provide at least some of the extracted data to the handheld device to update the local database.

摘要翻译： 一种用于使服务器的主数据库和手持设备的本地数据库同步的方法和系统。 用户可以使用驻留在手持设备中的应用程序在本地数据库中进行交易。 在同步操作期间，手持设备和服务器被耦合。 然后，系统确定应用程序是否应该更新，如果是，则使服务器提供更新。 系统还使得手持设备向服务器提供与用户对本地数据库进行的交易相关的信息。 该系统使服务器根据交易信息在主数据库上执行交易。 该系统还使服务器从主数据库中提取数据。 然后，服务器可以将提取的数据中的至少一些提供给手持设备来更新本地数据库。

公开(公告)号：US20070016695A1

公开(公告)日：2007-01-18

申请号：US09992511

申请日：2001-11-05

申请人： David Rabbers ,  Martin Susser ,  Pi-Yu Chung

发明人： David Rabbers ,  Martin Susser ,  Pi-Yu Chung

IPC分类号： G06F15/16

CPC分类号： G06F17/30581 ,  Y10S707/99952

摘要： A method and system for synchronizing a main database of a server and a local database of a handheld device. A user can use an application residing in the handheld device to make transactions in the local database. In a synchronization operation, a synchronization client is used to: establish a connection between a server and the synchronization client; receive an identifier for the main database's structure from the server; receive an identifier for the version of the handheld application from the server; send transaction information to the server; receive metadata to update the handheld application; and receive data extracted from the main database from the server. The synchronization client is also used to update filter information used by the server to reduce the size of the data downloaded to the handheld device.

摘要翻译： 一种用于使服务器的主数据库和手持设备的本地数据库同步的方法和系统。 用户可以使用驻留在手持设备中的应用程序在本地数据库中进行交易。 在同步操作中，使用同步客户端来建立服务器与同步客户端之间的连接; 从服务器接收主数据库结构的标识符; 从服务器接收手持应用程序版本的标识符; 将交易信息发送到服务器; 接收元数据以更新手持应用程序; 并从服务器接收从主数据库提取的数据。 同步客户端还用于更新服务器使用的过滤器信息，以减少下载到手持设备的数据的大小。

公开(公告)号：US08533154B2

公开(公告)日：2013-09-10

申请号：US11753290

申请日：2007-05-24

申请人： Xiao Fei Huang ,  Magnus Vejlstrup ,  David L. Rabbers ,  Pi-Yu Chung ,  Martin Susser ,  Aaron B. Hansen ,  Brian Scott ,  David J. George

发明人： Xiao Fei Huang ,  Magnus Vejlstrup ,  David L. Rabbers ,  Pi-Yu Chung ,  Martin Susser ,  Aaron B. Hansen ,  Brian Scott ,  David J. George

IPC分类号： G06F7/00 ,  G06F15/16

CPC分类号： G06F17/30578 ,  G06F17/30581 ,  Y10S707/99954

摘要： A method and system for synchronizing a main database of a server and a local database of a handheld device. A user can use an application residing in the handheld device to make transactions in the local database. During a synchronization operation, the handheld device and server are coupled. The system then determines whether the application should be updated and, if so, causes the server to provide an update. The system also causes the handheld device to provide to the server information related to the transactions made by the user to the local database. The system causes the server to perform transactions on the main database based on the transaction information. The system also causes the server to extract data from the main database. The server can then provide at least some of the extracted data to the handheld device to update the local database.