公开(公告)号：US20080256389A1

公开(公告)日：2008-10-16

申请号：US11733872

申请日：2007-04-11

申请人： Madhanmohan Neethiraj ,  Costin Hagiu ,  Vishal D. Maru

发明人： Madhanmohan Neethiraj ,  Costin Hagiu ,  Vishal D. Maru

IPC分类号： G06F11/00

CPC分类号： G06F11/2294

摘要： A strategy is described in which multiple testing agents perform multiple respective tests in a multi-user environment. One such multi-user environment allows multiple clients to interact with remote applications that are executed on a server. According to one exemplary case, a central test management module coordinates the execution of the multiple tests by the testing agents. For instance, the test management module can prevent testing agents that make demands on a global state of the multi-user environment from interfering with other testing agents.

摘要翻译： 描述了一种策略，其中多个测试代理在多用户环境中执行多个相应的测试。 一个这样的多用户环境允许多个客户端与在服务器上执行的远程应用程序进行交互。 根据一个示例性情况，中央测试管理模块通过测试代理来协调多个测试的执行。 例如，测试管理模块可以防止对多用户环境的全局状态的需求的测试代理干扰其他测试代理。

公开(公告)号：US07035771B2

公开(公告)日：2006-04-25

申请号：US11181285

申请日：2005-07-14

申请人： Hammad Butt ,  Costin Hagiu

发明人： Hammad Butt ,  Costin Hagiu

IPC分类号： G06F15/00

CPC分类号： G06F11/3419 ,  G06F11/3414 ,  G06F11/3447 ,  G06F11/3457 ,  G06F11/3476 ,  G06F2201/88

摘要： Apparatuses and methods to test whether a multi-user system will provide satisfactory performance are described. Response times are logged for each individual user, and the measurements are aggregated together in a single file at the end of the test. For each action type, a graph is built that correlates the distribution of the response times as a function of the user load. A break point is determined for each action type at which a response time exceeds a predetermined threshold. By analyzing the different break points, the number of users that can be supported by the multi-user computer system is determined. Additionally, an optimal amount of memory may be determined to support a user load. The amount of memory required per user is computed based on the user load at the projected point where a line that is determined from page output peaks intersects the page input line.

摘要翻译： 描述用于测试多用户系统是否将提供令人满意的性能的装置和方法。 对每个用户记录响应时间，测试结束时将测量结果汇总在一个文件中。 对于每个动作类型，构建了将响应时间的分布与用户负载相关联的图表。 针对响应时间超过预定阈值的每个动作类型确定断点。 通过分析不同的断点，确定多用户计算机系统可以支持的用户数量。 另外，可以确定最佳的存储量来支持用户负载。 每个用户所需的内存量是根据投影点的用户负载计算的，其中从页面输出峰值确定的行与页面输入行相交。

公开(公告)号：US06766407B1

公开(公告)日：2004-07-20

申请号：US09818345

申请日：2001-03-27

申请人： Rafael S. Lisitsa ,  Dale A. Sather ,  Costin Hagiu

发明人： Rafael S. Lisitsa ,  Dale A. Sather ,  Costin Hagiu

IPC分类号： G06F15173

CPC分类号： H04L65/4084 ,  H04L29/06027 ,  H04L65/602 ,  H04L65/80

摘要： The present invention analyzes a user's or client application's requirements and searches for a solution based on the end-to-end latency requirements (requested or derived), data formats, control protocols, timing and synchronization, local streaming, and resource availability. The search for a solution is tracked to allow backtracking from the point of no solution. Once a solution is determined, the system translates the solution into requirements for the individual components of the graph.

摘要翻译： 本发明基于端到端等待时间要求（请求或派生），数据格式，控制协议，定时和同步，本地流传输和资源可用性来分析用户或客户端应用的需求并搜索解决方案。 跟踪搜索解决方案，以便从无解决方案的角度进行回溯。 一旦确定了解决方案，系统将解决方案转换为图表各个组件的需求。

公开(公告)号：US08924507B2

公开(公告)日：2014-12-30

申请号：US13225022

申请日：2011-09-02

申请人： Tong L. Wynn ,  Vladimir Stoyanov ,  Sridhar Sankuratri ,  Damien Saint Macary ,  Voicu Anton Albu ,  Costin Hagiu

发明人： Tong L. Wynn ,  Vladimir Stoyanov ,  Sridhar Sankuratri ,  Damien Saint Macary ,  Voicu Anton Albu ,  Costin Hagiu

IPC分类号： G06F15/16 ,  G06F15/173 ,  H04L29/08 ,  H04L29/06

CPC分类号： H04L67/08 ,  H04L67/40

摘要： An invention is disclosed for efficiently processing and transmitting graphics data in a remote desktop environment. In embodiments of the invention, a connection is established between a remote desktop server computer and a remote desktop client computer. The remote desktop server computer may process graphics data representative of a remote user desktop. The remote desktop server computer may divide the remote desktop screen in data regions and portions. The remote desktop server computer may then encode and transmit each region to the remote desktop client computer at a certain quality that may be adjusted progressively across the screen frames. The remote desktop server computer may also stop encoding and transmitting the portions of the data region that would not be visible to a user when the region is rendered on a display. The remote desktop user experiences an image quality gradually improving with each frame containing information about the image.

摘要翻译： 公开了一种用于在远程桌面环境中有效地处理和传输图形数据的发明。 在本发明的实施例中，在远程桌面服务器计算机和远程桌面客户端计算机之间建立连接。 远程桌面服务器计算机可以处理代表远程用户桌面的图形数据。 远程桌面服务器计算机可以在数据区域和部分中划分远程桌面屏幕。 然后，远程桌面服务器计算机可以以可以跨屏幕帧逐渐调整的一定质量对每个区域进行编码和传输到远程桌面客户端计算机。 远程桌面服务器计算机还可以停止编码和传输在显示器上呈现该区域时用户不可见的数据区域的部分。 远程桌面用户体验图像质量逐渐提高，每帧包含有关图像的信息。

公开(公告)号：US08640131B2

公开(公告)日：2014-01-28

申请号：US12016869

申请日：2008-01-18

申请人： Ara Bernardi ,  Costin Hagiu ,  Nelamangal Krishnaswamy Srinivas ,  Ashwin Palekar ,  Arun U. Kishan ,  Karthik Thirumalai

发明人： Ara Bernardi ,  Costin Hagiu ,  Nelamangal Krishnaswamy Srinivas ,  Ashwin Palekar ,  Arun U. Kishan ,  Karthik Thirumalai

IPC分类号： G06F9/46

CPC分类号： G06F9/5061 ,  G06F9/4881 ,  G06F2209/483 ,  G06F2209/5012 ,  G06F2209/508

摘要： Embodiments that facilitate the fair and dynamic distribution of central processing unit (CPU) time are disclosed. In accordance with one embodiment, a method includes organizing one or more processes into one or more groups. The method further includes allocating a CPU time interval for each group. The allocation of a CPU time interval for each group is accomplished by equally distributing a CPU cycle based on the number of groups. The method also includes adjusting the allocated CPU time intervals based on a change in the quantity of the one or more groups.

摘要翻译： 公开了促进中央处理单元（CPU）时间的公平和动态分配的实施例。 根据一个实施例，一种方法包括将一个或多个过程组织成一个或多个组。 该方法还包括为每个组分配CPU时间间隔。 每个组的CPU时间间隔的分配通过基于组的数量均等地分配CPU周期来实现。 该方法还包括基于一个或多个组的数量的改变来调整分配的CPU时间间隔。

公开(公告)号：US08539020B2

公开(公告)日：2013-09-17

申请号：US12815073

申请日：2010-06-14

申请人： Mahesh Lotlikar ,  Sriram Sampath ,  Ara Bernardi ,  Costin Hagiu

发明人： Mahesh Lotlikar ,  Sriram Sampath ,  Ara Bernardi ,  Costin Hagiu

IPC分类号： G06F15/16 ,  G06F15/173

CPC分类号： G06F9/468 ,  G06F21/6281

摘要： Techniques are disclosed for enabling a system service executing in an isolated session to access system resources (such as a graphics processing unit) that it is isolated from. In an embodiment, the system service creates a “worker” session that is not isolated, and a “worker” process inside that worker session. Then, the system service is able to access the system resource that it is directly isolated from accessing by passing a request to the worker process to access the system resource on the system service's behalf. The worker process does so, and passes a result to the system service.

摘要翻译： 公开了使得在隔离会话中执行的系统服务能够访问与其隔离的系统资源（诸如图形处理单元）的技术。 在一个实施例中，系统服务创建不隔离的“工作者”会话，以及该工作者会话内的“工作者”进程。 然后，系统服务能够通过将请求传递给工作进程来代表其访问系统服务的系统资源，来访问它直接与访问隔离的系统资源。 工作进程执行此操作，并将结果传递给系统服务。

公开(公告)号：US20110307544A1

公开(公告)日：2011-12-15

申请号：US12815073

申请日：2010-06-14

申请人： Mahesh Lotlikar ,  Sriram Sampath ,  Ara Bernardi ,  Costin Hagiu

发明人： Mahesh Lotlikar ,  Sriram Sampath ,  Ara Bernardi ,  Costin Hagiu

IPC分类号： G06F15/16

CPC分类号： G06F9/468 ,  G06F21/6281

摘要： Techniques are disclosed for enabling a system service executing in an isolated session to access system resources (such as a graphics processing unit) that it is isolated from. In an embodiment, the system service creates a “worker” session that is not isolated, and a “worker” process inside that worker session. Then, the system service is able to access the system resource that it is directly isolated from accessing by passing a request to the worker process to access the system resource on the system service's behalf. The worker process does so, and passes a result to the system service.

摘要翻译： 公开了使得在隔离会话中执行的系统服务能够访问与其隔离的系统资源（诸如图形处理单元）的技术。 在一个实施例中，系统服务创建不隔离的“工作者”会话，以及该工作者会话内的“工作者”进程。 然后，系统服务能够通过将请求传递给工作进程来代表其访问系统服务的系统资源，来访问它直接与访问隔离的系统资源。 工作进程执行此操作，并将结果传递给系统服务。

公开(公告)号：US20110219112A1

公开(公告)日：2011-09-08

申请号：US12719669

申请日：2010-03-08

申请人： Graham Edward Fagg ,  Rajneesh Mahajan ,  Moshe Zilberstein ,  Guatam Swaminathan ,  Costin Hagiu

发明人： Graham Edward Fagg ,  Rajneesh Mahajan ,  Moshe Zilberstein ,  Guatam Swaminathan ,  Costin Hagiu

IPC分类号： G06F15/16

CPC分类号： H04L43/50 ,  G06F15/16 ,  H04L41/083 ,  H04L43/08 ,  H04L43/0811 ,  H04L67/1004 ,  H04L67/40

摘要： In various embodiments, methods and systems are disclosed for the real time detection of network conditions in conjunction with a remote presentation protocol. The link quality may represent the quality of the end-to-end connection between client and server with upper and lower bounds on the injection of additional traffic used for measurement. In some embodiments, the measurement technique may be selected based on the type of measurement that is desired. Accuracy may be maintained by selecting the type of measurement used based on current and previous network conditions. In one embodiment, a state model is used to determine the frequency of measurement and to determine when the measurements have produced a stable estimate of the link quality.

摘要翻译： 在各种实施例中，公开了结合远程呈现协议实时检测网络状况的方法和系统。 链路质量可以表示客户端和服务器之间的端到端连接的质量，具有注入用于测量的附加流量的上限和下限。 在一些实施例中，可以基于期望的测量类型来选择测量技术。 可以通过根据当前和以前的网络条件选择使用的测量类型来维持精度。 在一个实施例中，使用状态模型来确定测量的频率并确定测量何时产生了链路质量的稳定估计。

公开(公告)号：US20100146127A1

公开(公告)日：2010-06-10

申请号：US12331298

申请日：2008-12-09

申请人： Wilhelm R. Schmieder ,  Nelamangal Krishnaswamy Srinivas ,  Costin Hagiu ,  Nadim Y. Abdo ,  Vladimir K. Stoyanov ,  Ahmed M. Tolba ,  Gautam Swaminathan ,  Srinivasa Reddy Neerudu

发明人： Wilhelm R. Schmieder ,  Nelamangal Krishnaswamy Srinivas ,  Costin Hagiu ,  Nadim Y. Abdo ,  Vladimir K. Stoyanov ,  Ahmed M. Tolba ,  Gautam Swaminathan ,  Srinivasa Reddy Neerudu

IPC分类号： G06F15/173

CPC分类号： G06F9/545

摘要： Techniques are disclosed for a user-mode based remote desktop protocol (RDP) encoding architecture. A user mode desktop application and user mode virtual channel application run in user-mode session space. Virtual channel data from the virtual channel application is marshaled and sent to a RDP encoder process in user-mode system space. There it is converted to RDP protocol data units (PDU) and sent to a remote client across a communications network. Graphics data from the desktop application is sent to a display driver in kernel-mode session space and then to a graphics reflector that marshals the graphics data and sends it to the RDP encoder for a similar transformation.

摘要翻译： 公开了基于用户模式的远程桌面协议（RDP）编码架构的技术。 用户模式桌面应用程序和用户模式虚拟通道应用程序在用户模式会话空间中运行。 来自虚拟通道应用的虚拟通道数据被封送并发送到用户模式系统空间中的RDP编码器进程。 它被转换成RDP协议数据单元（PDU），并通过通信网络发送到远程客户端。 来自桌面应用程序的图形数据被发送到内核模式会话空间中的显示驱动程序，然后发送到图形反射器，该图形反射器用于编排图形数据并将其发送到RDP编码器进行类似的转换。

公开(公告)号：US20090204975A1

公开(公告)日：2009-08-13

申请号：US12028707

申请日：2008-02-08

申请人： Costin Hagiu ,  Wilhelm R. Schmieder ,  Gabriel Hera

发明人： Costin Hagiu ,  Wilhelm R. Schmieder ,  Gabriel Hera

IPC分类号： G06F3/00

CPC分类号： G06F9/542 ,  G06F11/3419 ,  G06F2201/805 ,  G06F2201/88 ,  G06F2209/545 ,  H04L67/10

摘要： A method for measuring application responsiveness measures the time elapsed between receiving and processing a trailing tag message inserted into the application's message queue. The method receives a message, generates a trailing tag message associated with the message, and inserts the trailing tag message into the application's message queue. The trailing tag message includes a timestamp indicating when the trailing tag message was queued. A default message handler calculates the time elapsed between when the trailing tag message was queued and when the trailing tag message was processed. The elapsed time may then be used to calculated system responsiveness.

摘要翻译： 用于测量应用响应度的方法测量在接收和处理插入到应用的消息队列中的尾部标签消息之间经过的时间。 该方法接收消息，生成与消息相关联的尾部标签消息，并将尾随标签消息插入到应用程序的消息队列中。 尾部标签消息包括一个时间戳，指示尾随标记消息何时排队。 默认消息处理程序计算尾随标记消息排队之间的时间和尾随标签消息的处理时间。 然后可以使用经过的时间来计算系统响应性。