公开(公告)号：US20120216194A1

公开(公告)日：2012-08-23

申请号：US13456683

申请日：2012-04-26

申请人： DAVID HADAS ,  VIVEK KASHYAP ,  JAYAKRISHNA KIDAMBI ,  RENATO J. RECIO ,  BENNY ROCHWERGER

发明人： DAVID HADAS ,  VIVEK KASHYAP ,  JAYAKRISHNA KIDAMBI ,  RENATO J. RECIO ,  BENNY ROCHWERGER

IPC分类号： G06F9/455

CPC分类号： H04L12/4641

摘要： A physical host executes a virtual machine monitor (VMM) in communication with a plurality of consumer virtual machines (VMs). In response to receipt of a packet, the VMM determines whether a service is to be performed for the packet by a service virtual machine (VM) in communication with the VMM. In response to determining that the service is to be performed for the packet by the service VM, the VMM applies a tag to the packet that differentiates the packet from any other packet sharing a common address with the packet but having a different associated consumer, passes the packet to the service VM for performance of the service, and thereafter removes the tag from the packet in response to receipt of the packet from the service VM following performance of the service. In response to receipt of the packet from the service VM, the VMM forwards the packet.

摘要翻译： 物理主机执行与多个消费者虚拟机（VM）通信的虚拟机监视器（VMM）。 响应于分组的接收，VMM确定与VMM通信的服务虚拟机（VM）是否对分组执行服务。 响应于确定要由服务VM对分组执行服务，VMM向分组应用标签，该分组将分组与与分组共享公共地址的任何其他分组区分开，但是具有不同的相关消费者，传递 将该分组发送到服务VM以执行该服务，然后在执行该服务之后响应于从该服务VM接收到该分组而从该分组中移除该标签。 响应于来自服务VM的分组的接收，VMM转发分组。

公开(公告)号：US20120207031A1

公开(公告)日：2012-08-16

申请号：US13456476

申请日：2012-04-26

申请人： ROBERT COWART ,  DAVID HADAS ,  DANIEL J. MARTIN ,  BRUCE RATCLIFF ,  RENATO RECIO

发明人： ROBERT COWART ,  DAVID HADAS ,  DANIEL J. MARTIN ,  BRUCE RATCLIFF ,  RENATO RECIO

IPC分类号： H04L12/26

CPC分类号： H04L45/22 ,  H04L45/50 ,  H04L45/58 ,  H04L45/74 ,  H04L49/3009 ,  H04L69/22

摘要： A physical host executes a virtual machine monitor (VMM) that instantiates a source virtual machine (VM). In response to the VMM receiving from the source VM a packet specifying a first destination address of a destination VM and a second destination address of a default gateway, the VMM determines whether the packet can be communicated to the destination VM without the packet being routed by the default gateway. In response to the VMM determining that the packet can be communicated to the destination VM without the packet being routed by the default gateway, the VMM forwards the packet to the destination VM such that the packet bypasses routing by the default gateway.

摘要翻译： 物理主机执行实例化虚拟机（VM）的虚拟机监视器（VMM）。 响应于从源VM接收到指定目的地VM的第一目的地地址的分组和默认网关的第二目的地地址的VMM，VMM确定分组是否可以被传送到目的地VM，而分组不被路由被分组 默认网关。 响应于VMM确定分组可以被传送到目的地VM而没有分组被默认网关路由，VMM将分组转发到目的地VM，使得分组绕过默认网关的路由。

公开(公告)号：US08131833B2

公开(公告)日：2012-03-06

申请号：US12623327

申请日：2009-11-20

申请人： David Hadas ,  Irit Loy ,  Benny Rochwerger ,  Julian Satran

发明人： David Hadas ,  Irit Loy ,  Benny Rochwerger ,  Julian Satran

IPC分类号： G06F15/16

CPC分类号： H04L65/4076

摘要： A method for managing communication between nodes in a virtual network is provided. A first computing system utilizes first information to forward first data to the second computing system in a physical network. If the first information is incorrect, the second computing system forwards an unlearning request to the first computing system, and the first computing system updates or deletes the first information. If the first information is not available, the first computing system forwards the first data to a group of computing systems in the physical network by way of a multicast service. Upon receiving the first data, the second computing system or a third computing system in the physical network forwards a learning request to the first computing system, and the first computing system utilizes the learning request to generate the first information.

摘要翻译： 提供了一种用于管理虚拟网络中的节点之间的通信的方法。 第一计算系统利用第一信息将物理网络中的第一数据转发到第二计算系统。 如果第一信息不正确，则第二计算系统将未学习请求转发给第一计算系统，并且第一计算系统更新或删除第一信息。 如果第一信息不可用，则第一计算系统通过多播服务将第一数据转发到物理网络中的一组计算系统。 在接收到第一数据时，物理网络中的第二计算系统或第三计算系统将学习请求转发到第一计算系统，并且第一计算系统利用学习请求来生成第一信息。

公开(公告)号：US10142218B2

公开(公告)日：2018-11-27

申请号：US13006614

申请日：2011-01-14

申请人： Robert Cowart ,  David Hadas ,  Daniel J. Martin ,  Bruce Ratcliff ,  Renato Recio

发明人： Robert Cowart ,  David Hadas ,  Daniel J. Martin ,  Bruce Ratcliff ,  Renato Recio

IPC分类号： H04L12/707 ,  H04L12/775 ,  H04L12/723 ,  H04L29/06 ,  H04L12/935 ,  H04L12/741

摘要： A physical host executes a virtual machine monitor (VMM) that instantiates a source virtual machine (VM). In response to the VMM receiving from the source VM a packet specifying a first destination address of a destination VM and a second destination address of a default gateway, the VMM determines whether the packet can be communicated to the destination VM without the packet being routed by the default gateway. In response to the VMM determining that the packet can be communicated to the destination VM without the packet being routed by the default gateway, the VMM forwards the packet to the destination VM such that the packet bypasses routing by the default gateway.

公开(公告)号：US20120303799A1

公开(公告)日：2012-11-29

申请号：US13118424

申请日：2011-05-29

申请人： David Hadas ,  Irit Loy ,  Kenneth Nagin ,  Benny Rochwerger

发明人： David Hadas ,  Irit Loy ,  Kenneth Nagin ,  Benny Rochwerger

IPC分类号： G06F15/173

CPC分类号： G06F9/4856 ,  H04L41/28 ,  H04L63/0407

摘要： Systems and methods for migrating a virtual resource from a source host in a source network to a destination host in a destination network are provided. In one embodiment, the method comprises establishing a secure communication connection between a source proxy in the source network and a destination proxy in the destination network; and monitoring migration traffic directed from the source host to the source proxy and forwarding said traffic to the destination proxy which in turn forwards the traffic to the destination host over the secure communication connection between the source proxy and the destination proxy, such that the communication addresses of the source host and the destination host remain guarded from direct access by an entity outside of the source network or the destination network.

摘要翻译： 提供了将虚拟资源从源网络中的源主机迁移到目标网络中的目标主机的系统和方法。 在一个实施例中，该方法包括在源网络中的源代理和目的地网络中的目的地代理之间建立安全通信连接; 以及监视从源主​​机引导到源代理的迁移流量，并将所述流量转发到目的地代理，所述目的地代理又通过源代理和目的地代理之间的安全通信连接将流量转发到目的地主机，使得通信地址 源主机和目标主机保持不受来自源网络或目的网络之外的实体的直接访问。

公开(公告)号：US08924541B2

公开(公告)日：2014-12-30

申请号：US13118424

申请日：2011-05-29

申请人： David Hadas ,  Irit Loy ,  Kenneth Nagin ,  Benny Rochwerger ,  Alexander Glikson ,  Liran Schour

发明人： David Hadas ,  Irit Loy ,  Kenneth Nagin ,  Benny Rochwerger ,  Alexander Glikson ,  Liran Schour

IPC分类号： G06F15/173 ,  G06F15/16

CPC分类号： G06F9/4856 ,  H04L41/28 ,  H04L63/0407

摘要： Systems and methods for migrating a virtual resource from a source host in a source network to a destination host in a destination network are provided. In one embodiment, the method comprises establishing a secure communication connection between a source proxy in the source network and a destination proxy in the destination network; and monitoring migration traffic directed from the source host to the source proxy and forwarding said traffic to the destination proxy which in turn forwards the traffic to the destination host over the secure communication connection between the source proxy and the destination proxy, such that the communication addresses of the source host and the destination host remain guarded from direct access by an entity outside of the source network or the destination network.

摘要翻译： 提供了将虚拟资源从源网络中的源主机迁移到目标网络中的目标主机的系统和方法。 在一个实施例中，该方法包括在源网络中的源代理和目的地网络中的目的地代理之间建立安全通信连接; 以及监视从源主​​机引导到源代理的迁移流量，并将所述流量转发到目的地代理，所述目的地代理又通过源代理和目的地代理之间的安全通信连接将流量转发到目的地主机，使得通信地址 源主机和目标主机保持不受来自源网络或目的网络之外的实体的直接访问。

公开(公告)号：US20140068620A1

公开(公告)日：2014-03-06

申请号：US13598638

申请日：2012-08-30

申请人： Michael E. Factor ,  David Hadas ,  Elliot K. Kolodner

发明人： Michael E. Factor ,  David Hadas ,  Elliot K. Kolodner

IPC分类号： G06F9/46

CPC分类号： G06F9/5027 ,  G06F11/1438 ,  G06F11/2028 ,  G06F11/2035 ,  G06F11/2046 ,  G06F2209/5018 ,  G06F2209/508

摘要： Machines, systems and methods for task management in a computer implemented system. The method comprises registering a task with brokers residing on one or more nodes to manage the execution of a task to completion, wherein a first broker is accompanied by a first set of worker threads co-located on the node on which the first broker is executed, wherein the first broker assigns responsibility of execution for the task to the one or more worker threads in the first set of co-located worker threads, wherein in response to a failure associated with a first worker thread in the first set, the first broker reassigns the responsibility of execution for the task to a second worker thread in the first set, wherein in response to a failure associated with the first broker, a second broker assigns responsibility of execution for the task to one or more co-located worker threads.

摘要翻译： 计算机实现系统中任务管理的机器，系统和方法。 该方法包括将驻留在一个或多个节点上的代理登记任务以管理要完成的任务的执行，其中第一代理伴随着共同位于执行第一代理的节点上的第一组工作线程 ，其中所述第一代理将所述任务的执行的责任分配给所述第一组同位置的工作线程中的一个或多个工作者线程，其中响应于与所述第一组中的第一工作线程相关联的故障，所述第一代理 将任务的执行责任重新分配给第一组中的第二工作线程，其中响应于与第一代理相关联的故障，第二代理将任务的执行责任分配给一个或多个同位置的工作线程。

公开(公告)号：US20120182993A1

公开(公告)日：2012-07-19

申请号：US13006758

申请日：2011-01-14

申请人： DAVID HADAS ,  VIVEK KASHYAP ,  JAYAKRISHNA KIDAMBI ,  RENATO J. RECIO ,  BENNY ROCHWERGER

发明人： DAVID HADAS ,  VIVEK KASHYAP ,  JAYAKRISHNA KIDAMBI ,  RENATO J. RECIO ,  BENNY ROCHWERGER

IPC分类号： H04L12/56

CPC分类号： H04L12/4641

摘要： A physical host executes a virtual machine monitor (VMM) in communication with a plurality of consumer virtual machines (VMs). In response to receipt of a packet, the VMM determines whether a service is to be performed for the packet by a service virtual machine (VM) in communication with the VMM. In response to determining that the service is to be performed for the packet by the service VM, the VMM applies a tag to the packet that differentiates the packet from any other packet sharing a common address with the packet but having a different associated consumer, passes the packet to the service VM for performance of the service, and thereafter removes the tag from the packet in response to receipt of the packet from the service VM following performance of the service. In response to receipt of the packet from the service VM, the VMM forwards the packet.

公开(公告)号：US20120182992A1

公开(公告)日：2012-07-19

申请号：US13006614

申请日：2011-01-14

申请人： ROBERT COWART ,  DAVID HADAS ,  DANIEL J. MARTIN ,  BRUCE RATCLIFF ,  RENATO RECIO

发明人： ROBERT COWART ,  DAVID HADAS ,  DANIEL J. MARTIN ,  BRUCE RATCLIFF ,  RENATO RECIO

IPC分类号： H04L12/56

CPC分类号： H04L45/22 ,  H04L45/50 ,  H04L45/58 ,  H04L45/74 ,  H04L49/3009 ,  H04L69/22

摘要： A physical host executes a virtual machine monitor (VMM) that instantiates a source virtual machine (VM). In response to the VMM receiving from the source VM a packet specifying a first destination address of a destination VM and a second destination address of a default gateway, the VMM determines whether the packet can be communicated to the destination VM without the packet being routed by the default gateway. In response to the VMM determining that the packet can be communicated to the destination VM without the packet being routed by the default gateway, the VMM forwards the packet to the destination VM such that the packet bypasses routing by the default gateway.

公开(公告)号：US20120023208A1

公开(公告)日：2012-01-26

申请号：US13006836

申请日：2011-01-14

申请人： David Hadas ,  Irit Loy ,  Benny Rochwerger ,  Julian Satran

发明人： David Hadas ,  Irit Loy ,  Benny Rochwerger ,  Julian Satran

IPC分类号： G06F15/16

CPC分类号： H04L65/4076

摘要： A method for managing communication between nodes in a virtual network is provided. A first computing system utilizes first information to forward first data to the second computing system in a physical network. If the first information is incorrect, the second computing system forwards an unlearning request to the first computing system, and the first computing system updates or deletes the first information. If the first information is not available, the first computing system forwards the first data to a group of computing systems in the physical network by way of an unknown network service. Upon receiving the first data, the second computing system or a third computing system in the physical network forwards a learning request to the first computing system, and the first computing system utilizes the learning request to generate the first information.

摘要翻译： 提供了一种用于管理虚拟网络中的节点之间的通信的方法。 第一计算系统利用第一信息将物理网络中的第一数据转发到第二计算系统。 如果第一信息不正确，则第二计算系统将未学习请求转发给第一计算系统，并且第一计算系统更新或删除第一信息。 如果第一信息不可用，则第一计算系统通过未知网络服务将第一数据转发到物理网络中的一组计算系统。 在接收到第一数据时，物理网络中的第二计算系统或第三计算系统将学习请求转发到第一计算系统，并且第一计算系统利用学习请求来生成第一信息。