Amazon Technologies, Inc.

Harvo Reyzell Jones

Craig Wesley Howard

Nathan Dye

Anton Stephen Radlein

Hardeep Singh Uppal

Bradley E Marshall

Jonathan B Corley

Ryan F Watson

Imran S Patel

Prashanth A Acharya

Lee B Rosen

Ronald James Snyder, Jr

John K Loendorf

Colm MacCarthaigh

Dennis Marinus

Dhiraj Gupta

Jorge Peixoto Vasquez

Joseph Elmar Magerramov

Brad Eugene Marshall

Nalin Goel

Mohanish Narayan

Thomas Bradley Scholl

Donavan Miller

Seyed Arash Sadrieh

Julien Ridoux

Ali Khayam

Michael W Palladino

Bobby Brown

Fiachra John Groarke

Eric Charles Briffa

Tahir Azim

Rafael Ortiz

Tom Scholl

Abdul Salam Faisal Padinjareveetil

Mykhailo Ponomarenko

Joan Barcelo Llado

Kenan Yang

Amogh Dhananjay Dhamdhere

Ryan Waters

Amr Rashad

Nikhil Ashok Arjunagi

Rajat Chaudhary

Robert Louis Mosher

Kevin Bliss

Subramanian Ganapathy

Aditya Srinivasan

Fan Mo

Axel David Velazquez

Snehal Mahadik

Technologies are disclosed for performing context-aware routing of traffic based on an application of a series of filters and/or selectors to determine an optimal group of interfaces for servicing traffic relating to a prefix. A traffic management control plane processes input data corresponding to aggregated telemetry data for a network by determining candidate groups of interfaces to service a network prefix and applies tunable filters and/or selectors to the candidate groups to determine a targeted group to use for servicing traffic corresponding to the prefix. The determined targeted group is mapped to the prefix in a mapping result, which is then provided to an actuator interface to control network devices to inject the new mapping into the network to control traffic according to the mapping.

Network traffic management

The present disclosure generally relates to a first network device in a primary region that can failover network traffic into a second network device in a failover region. The first network device can receive routing criteria identifying how traffic originating in the primary region should be routed. The first network device can transmit this routing criteria to the second network device in the failover region. Based on determining the occurrence of a failover event, the first network device may transmit network traffic originating in the primary region to the second network device in the failover region. The second network device can determine how to route the network traffic based on the routing criteria of the primary region. In some embodiments, the second network device can determine how to route the network traffic based on the routing criteria of the failover region.

Systems and methods for enabling a failover service for block-storage volumes

A computing system that receives and stores configuration information for the application in a data store. The configuration information comprises (1) identifiers for a plurality of cells of the application that include at least a primary cell and a secondary cell, (2) a defined state for each of the plurality of cells, (3) one or more dependencies for the application, and (4) a failover workflow defining actions to take in a failover event. The computing system receives an indication, from a customer, of a change in state of the primary cell or a request to initiate the failover event. The computing system updates, in the data store, the states for corresponding cells of the plurality of cells based on the failover workflow and updates, in the data store, the one or more dependencies for the application based on the failover workflow.

Systems and methods for enabling a highly available managed failover service

a computing system that receives and stores configuration information for the application in a data store. The configuration information comprises (1) identifiers for a plurality of cells of the application that include at least a primary cell and a secondary cell, (2) a defined state for each of the plurality of cells, (3) one or more dependencies for the application, and (4) a failover workflow defining actions to take in a failover event. The computing system receives an indication, from a customer, of a change in state of the primary cell or a request to initiate the failover event. The computing system updates, in the data store, the states for corresponding cells of the plurality of cells based on the failover workflow and updates, in the data store, the one or more dependencies for the application based on the failover workflow.

Techniques are described for managing preloading of data for client computing systems. A client computing system may provide one or more persistent data storage caches on local storage, such as to support a particular software program executing on the client computing system (e.g., a Web browser program, with the persistent data storage cache designed to store browser cookies and other data for later access by the Web browser program). Additional data may be stored in such a persistent data storage cache by preloading those data groups before they are requested by the client computing system (e.g., based on interactions of a user of the client computing system with an executing program on the client computing system). Particular data groups to preload may be selected in various manners, including to provide a specified type of minimum functionality to a client computing system based on the preloaded data groups.

Managing preloading of data on client systems

A system and method for endpoint selection in a global accelerator system. The global accelerator system includes client devices communicating with a global access point to access various endpoints that can host services. Multiple endpoints are grouped geographically according to different data centers. Client service requests are received at a global access point, which in turns selects an endpoint to service the request. A selection mechanism utilized by the global access point implements a distribution algorithm that facilitates that distribution of endpoint requests according to a product of distribution criteria and geographic criteria. Additionally, the global access point can then identify individual endpoints within the group to process the request using a consistent hashing algorithm that ensures an endpoint can be continuously selected over the course of interaction with a client.

Load balanced access to distributed endpoints

In a network environment, network health is monitored by a monitoring platform and related monitoring services. A method may include receiving metrics data from a plurality of data sources, overlaying a traffic profile for a client of the network with the metrics data to determine an experience score for the client, and detecting an impairment in the network based on the metrics data and/or the experience score. The method may further include performing a triangulation process to determine a cause of the impairment in the network based on the metrics data, and generating, for display via a user interface, a report indicating the impairment and the cause of the impairment.

Real-time network monitoring

a data store and a proxy system. The data store may store state data relating to a cell of the application, each cell having a state. The proxy system may identify whether the cell is operating in the active state, the passive state, or the fenced state and access a database of acceptable and unacceptable commands for the cell's state. For each request directed to the cell received, the proxy system may identifies the request as an acceptable request based on identifying that one or more commands of the request are acceptable to process in the cell's state or identifies the request as an unacceptable request based on identifying that one or more commands of the request are unacceptable to process in the cell's state. The proxy system then conveys the acceptable requests and unacceptable requests appropriately.

A hybrid content request routing system is described herein. The hybrid content request routing system may use aspects of the anycast routing technique and aspects of the domain name server (DNS) resolver-based routing technique to identify the appropriate network address to provide to a user device in response to receiving a DNS query. For example, the hybrid content request routing system may include one or more points of presence (POPs), with some or all of the POPs forming one or more virtual POPs. Individual POPs may be assigned unique network addresses and POPs that form a virtual POP may be assigned the same anycast network address. The hybrid content request routing system can measure latencies from user devices to the individual POP network addresses and to the anycast network addresses and use the measured latencies to identify the network address that may result in the lowest latency.

Hybrid content request routing system

A system and method for management of communications for components in a global accelerator system is provided. The global accelerator system includes client devices communicating with a global access point via a public network to access various endpoints that can host services. In turn, a global access point communicates to various endpoints, which are organized into different data centers, via a private network. To facilitate exchanges on behalf of different client devices, the global access points can characterize groupings of endpoints into subgroups or braids. Individual braid communications can be encapsulated and are routed at the data center by a networking equipment using 5-tuple information in packets. The components within individual braids can broadcast or multi-cast state information via management messages to ensure failover or mitigate duplicative processing.

Management of distributed endpoints

A computer implemented availability checking system and method is provided for use with a service provider configured to communicate with one or more client devices and with a content provider. The system includes a computer storage device operative to store an availability data store comprising a list of a plurality of potential endpoints of the service provider and a corresponding plurality of availability information for the plurality of potential endpoints. The plurality of potential endpoints is distributed across a plurality of resource cache components. The system further includes an availability query component operative to transmit a plurality of queries to the plurality of potential endpoints and to receive a plurality of responses from the plurality of potential endpoints. The system further includes an availability analysis component operative to analyze the plurality of responses, to generate the plurality of availability information, and to update the availability data store.

Monitoring availability of content delivery networks

Systems and methods are described to enable the load-balanced use of globalized network addresses, addressable throughout a network to access a network-accessible service. A set of global access points are provided, which advertise availability of the globalized network addresses. On receiving a request to access a network-accessible service, a global access point can select an endpoint for the service from among a number of data centers, based on a desired distribution of traffic among the data centers. The access point then forwards the traffic to the selected endpoint. In one embodiment, the access point applies network address translation to enable the traffic to be routed to the endpoint without terminating a connection at the endpoint. The access point may use a variety of techniques to ensure resiliency of the network and knowledge of available endpoints.

Load balanced access to distributed endpoints using anycasted global network addresses and network address translation

Systems and methods are described to enable the load-balanced use of globalized network addresses, addressable throughout a network to access a network-accessible service. A set of global access points are provided, which advertise availability of the globalized network addresses. Globalized network addresses can be divided among different pools, and each service can be associated with addresses of more than one pool. To increase resiliency, access points can advertise different pools of addresses to different neighboring devices, creating different pathways to reach the access point. If an error occurs on a neighboring network, a client can try to access the service via an address of a different pool, which can be expected to be routed through a different neighboring network, thus enabling the client to reach the access point.

Load balanced access to distributed endpoints using resiliently advertised global network addresses

Growing community of inventors

Gig Harbor, WA, United States of America

Harvo Reyzell Jones