Amazon Technologies, Inc.

Oracle International Corporation

Chris Higgins

Vivek Bhanu

Jagwinder Singh Brar

Peter John Hill

Abhoy Bhaktwatsalam

David Allen McArthur

Edward L Wallace

Brian A Scanlan

Techniques for exposing a subset of hosts on an overlay network, without exposing another subset of hosts on the overlay network, are disclosed. A component associated with an overlay network exposes a subset of hosts on the overlay network to components external to the overlay network. The component exposes the subset of hosts by distributing a mapping between (a) the hosts to-be-exposed and (b) the substrate addresses associated with the hosts. Alternatively, a component external to an overlay network exposes a subset of hosts on the overlay network to additional components external to the overlay network. The component exposes the subset of hosts by distributing a mapping between (a) the hosts to-be-exposed and (b) a substrate address associated with the particular component. In either embodiment, a mapping for hosts to-be-hidden is not distributed.

Exposing a subset of hosts on an overlay network to components external to the overlay network without exposing another subset of hosts on the overlay network

According to one embodiment, a computer-implemented method includes executing code for an application using a computing resource of a first computing device. The application requests execution of a first thread and a second thread. The first thread is executed using the computing resource of the first computing device. A second computing device is selected from a plurality of computing devices. The second computing device has an available computing resource to execute the second thread. The second thread is assigned to the second computing device. The second computing device is operable to execute the second thread using the available computing resource.

Executing threads of an application across multiple computing devices in a distributed virtual machine environment

Techniques are disclosed for identifying an unauthorized device in a network environment that comprises a plurality of heterogeneous devices. In some embodiments, tests may be performed about a device, using information provided by the device, information about the device obtained from a neighboring device, or information about a placement of the device within a network topology. These tests may be used to determine whether a device is unauthorized for the network.

Unauthorized device detection in a heterogeneous network

A service oriented architecture (SOA) provides on-demand service call debugging and call stack tracing. The service call (e.g., an API) includes a new field and optional signature value. The field is a 'debug-requested' field, and the optional field is a unique call-id signature. The service provider can enable debugging in accordance with the debug-requested field for this service call, and tag all debugged data with the unique call-id. If it is necessary to call other services to fulfill the request, then the service can pass the 'debug-requested' field and the &#x2018;unique id&#x2019; in the call to that service. Using this mechanism, detailed debugging can be supported across an entire stack for only those requests that need it and the performance/latency impact of having debugging enabled only applies to the subset of calls which need debugging.

Dynamic service debugging in a virtual environment

In certain embodiments, a computer-implemented method includes detecting, by a first processing system, that a failure event operable to cause the first processing system to become inoperable has occurred. The method further includes communicating, by the first processing system using multicasting, a notification to two or more proxy processing systems. At least one of the proxy processing systems is operable to receive the notification and communicate the notification to a second processing system on behalf of the first processing system using a reliable communications protocol.

Reliable intermediate multicast communications

According to one embodiment, an apparatus comprises an interface and one or more processors. The interface receives a request for a web page from a web browser. The one or more processors select a subset of web servers from a resource pool according to a load balancing determination. The one or more processors send the request to at least two of the web servers of the subset before receiving any response from the other web servers. Upon receiving one or more responses from distinct web servers, the one or more processors selects a response to communicate to the web browser.

Load balancer

In order to protect against various load balancing failures, the host selection algorithm on the load balancer can be modified to take into account data available about the state of the entire service and each host server in the cluster. The state can include a number of metrics, including the sampled response time taken by the selected host service. The load balancer can use the state information in order to detect anomalies among the host services. For example, the load balancer can determine that the sampled response time of one host service has deviated by more than a standard deviation limit (or other predetermined threshold) from the sampled response times of the other host services in the cluster. If such an anomaly is detected, the load balancer can take various remedial actions, such as disabling the routing of incoming requests to the potentially faulty host service.

Load balancer host selection and fault detection

Ethernet Y-cables are provided that include first, second and third Ethernet cable segments, each of which has a first end and a second end and at least eight insulated conductors. These cables further include a housing that receives the respective first ends of the first, second and third Ethernet cable segments and a switching mechanism that is disposed at least partly in the housing. The switching mechanism is configured to selectively connect the at least eight conductors of the first Ethernet cable segment to respective ones of either the at least eight conductors of the second Ethernet cable segment or the at least eight conductors of the third Ethernet cable segment. Related Ethernet Y-switches and methods of using the Ethernet Y-cables and Y-switches are also provided.

Growing community of inventors

Sammamish, WA, United States of America

Chris Higgins