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

US07770154B2 Lightweight highly available infrastructure to trace program execution 有权
标题翻译：轻量级高可用性的基础架构跟踪程序执行
公开(公告)号：US07770154B2
公开(公告)日：2010-08-03
申请号：US11173675
申请日：2005-07-01
申请人： Ivan Tinlung Lam , Sunil Kumar , Alok Kumar Srivastava
发明人： Ivan Tinlung Lam , Sunil Kumar , Alok Kumar Srivastava
IPC分类号： G06F9/45
CPC分类号： G06F11/3471 , G06F11/3636
摘要： A portable tracing utility provides trace configuration, trace instrumentation and trace management functionality for single or multithreaded programs. Through various application programming interfaces (“APIs”) of the tracing utility, a client may control tracing behavior to setup in-memory data structures for storing trace records that record the program's history of execution or to alter the granularity of execution history being traced. The trace behavior can be modified during the life of a program by using the APIs, either dynamically when the program assumes certain states, or through remote procedure calls issued by, for example, an external interface. Programs are instrumented with these APIs to record the history of execution, which during execution of the program is stored in circular in-memory buffers.
摘要翻译：便携式跟踪实用程序为单个或多线程程序提供跟踪配置，跟踪检测和跟踪管理功能。通过跟踪实用程序的各种应用程序编程接口（“API”），客户端可以控制跟踪行为来设置内存中的数据结构，以存储跟踪记录，记录程序的执行历史或更改正在跟踪的执行历史的粒度。跟踪行为可以在程序生命周期内通过使用API进行修改，或者通过例如外部接口发出的远程过程调用，动态执行某些状态。使用这些API对程序进行测试，以记录执行历史，在执行程序期间将其存储在循环内存缓冲区中。

2. 发明授权

US07200588B1 Method and mechanism for analyzing trace data using a database management system 有权
标题翻译：使用数据库管理系统分析跟踪数据的方法和机制
公开(公告)号：US07200588B1
公开(公告)日：2007-04-03
申请号：US10209612
申请日：2002-07-29
申请人： Alok Kumar Srivastava , Ivan Tinlung Lam , Sunil Kumar
发明人： Alok Kumar Srivastava , Ivan Tinlung Lam , Sunil Kumar
IPC分类号： G06F17/30
CPC分类号： G06F17/30595 , G06F11/3636 , Y10S707/99933 , Y10S707/99943
摘要： The present invention provides a method and mechanism for analyzing trace data using a database management system (DBMS). According to an embodiment, trace data may be loaded onto one or more databases within a DBMS. With this aspect of the invention, several advantages are gained, including the ability to use the query tool of the DBMS to analyze the trace data and the ability to build a trace repository to analyze the history of the trace data.
摘要翻译：本发明提供了一种使用数据库管理系统（DBMS）分析跟踪数据的方法和机制。根据实施例，跟踪数据可以被加载到DBMS内的一个或多个数据库上。通过本发明的这个方面，获得了几个优点，包括使用DBMS的查询工具来分析跟踪数据和构建跟踪存储库以分析跟踪数据的历史的能力。

3. 发明授权

US07512954B2 Method and mechanism for debugging a series of related events within a computer system 有权
标题翻译：在计算机系统内调试一系列相关事件的方法和机制
公开(公告)号：US07512954B2
公开(公告)日：2009-03-31
申请号：US10208120
申请日：2002-07-29
申请人： Alok Kumar Srivastava , Ivan Tinlung Lam , Sunil Kumar
发明人： Alok Kumar Srivastava , Ivan Tinlung Lam , Sunil Kumar
IPC分类号： G06F3/00 , G06F9/44 , G06F9/46 , G06F13/00 , G06F11/00
CPC分类号： G06F11/3636 , G06F9/546
摘要： The present invention provides a method and mechanism for debugging a series of related events within a computer system. According to an embodiment, when tracing a series of related events that span across a plurality of threads, a token may be passed from one thread to another, thereby allowing a link between the threads to be marked within the one or more traces. The token may be passed via a messaging API, such as a network layer API or a shared resource. With this aspect of the invention, sufficient information will be provided within the one or more traces to allow all the related trace data to be linked together.
摘要翻译：本发明提供一种用于在计算机系统内调试一系列相关事件的方法和机制。根据实施例，当跟踪跨越多个线程的一系列相关事件时，令牌可以从一个线程传递到另一个线程，从而允许在一个或多个跟踪内标记线程之间的链接。令牌可以经由诸如网络层API或共享资源的消息传递API来传递。利用本发明的这个方面，将在一个或多个轨迹内提供足够的信息以允许所有相关的跟踪数据链接在一起。

4. 发明授权

US07165190B1 Method and mechanism for managing traces within a computer system 有权
标题翻译：在计算机系统内管理跟踪的方法和机制
公开(公告)号：US07165190B1
公开(公告)日：2007-01-16
申请号：US10208129
申请日：2002-07-29
申请人： Alok Kumar Srivastava , Ivan Tinlung Lam , Sunil Kumar
发明人： Alok Kumar Srivastava , Ivan Tinlung Lam , Sunil Kumar
IPC分类号： G06F11/00
CPC分类号： G06F11/3476 , G06F11/0709 , G06F11/0778 , G06F11/0781 , G06F11/302 , G06F11/3055 , G06F11/3072 , G06F11/3089 , G06F11/3409 , G06F11/3466 , G06F11/3636 , G06F2201/81
摘要： A method and mechanism for managing traces with a computer system having a plurality of resources is disclosed. One or more conditions can be established for the computer system. The resources may then be monitored to determine whether the computer system has reached the one or more conditions. If so, then the parameters of the traces may be changed according to the one or more conditions that have been reached.
摘要翻译：公开了一种用具有多个资源的计算机系统管理跟踪的方法和机构。可以为计算机系统建立一个或多个条件。然后可以监视资源以确定计算机系统是否已经达到一个或多个条件。如果是这样，则可以根据达到的一个或多个条件来改变迹线的参数。

5. 发明授权

US06675315B1 Diagnosing crashes in distributed computing systems 有权
标题翻译：诊断分布式计算系统中的崩溃
公开(公告)号：US06675315B1
公开(公告)日：2004-01-06
申请号：US09565787
申请日：2000-05-05
申请人： Daniel Semler , Yuriy S. Granat , Alok Srivastava , Ivan Tinlung Lam
发明人： Daniel Semler , Yuriy S. Granat , Alok Srivastava , Ivan Tinlung Lam
IPC分类号： G06F1100
CPC分类号： G06F11/2294 , G06F11/0709 , G06F11/0748
摘要： Mechanisms are provided for preserving data wherein one or more nodes in a distributed computing system experiences an error. In one embodiment, when an error occurs, an error event is identified. Based on this error event, a set of identified execution units is suspended and a set of identified data is collected. All suspended execution units are then released, i.e., allowed to continue execution at the point where the units were suspended. The data collected during suspension is then used to diagnose the cause of the error.
摘要翻译：提供了用于保存数据的机制，其中分布式计算系统中的一个或多个节点遇到错误。在一个实施例中，当发生错误时，识别错误事件。基于该错误事件，一组已识别的执行单元被暂停，并且收集一组所识别的数据。然后释放所有暂停的执行单元，即允许在单元暂停的时刻继续执行。然后将暂停期间收集的数据用于诊断错误的原因。

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