Amazon Technologies, Inc.

Karthik Uthaman

Ronil Sudhir Mokashi

Prashant Verma

Alexander Korobeynikov

Ted David Middleton

Sayalee Uday Wandkar

Samrat Karak

Edge functions at an edge location of a content delivery network (CDN) may use APIs of a datastore engine in order to read/write or create/delete local tables at the edge location. Data may be accumulated in the local tables and the new data may be used to enhance decision at the edge. Some of the local tables may be initially populated from a back-end database. This allows the functions to modify the data from the back-end database, without affecting the actual source data at the back-end database (modifications to local tables remain local to the edge location).

Low latency writes to local tables by event-triggered functions at the edge

A system, method, and computer readable medium for distributing data objects that are dynamically customized for users in a content delivery network. The system obtains information based on content accessed by a user, the content being accessed by the user through a content delivery network device. The system associates the user with other users based on the obtained information, the other users having accessed another content through the content delivery network device. The system generates a cluster, the cluster comprising a plurality of nodes representative of the user and the associated other users. The system determines a set of tags for the cluster, the set of tags derived from a plurality of websites accessed by the user.

Interest based advertising inside a content delivery network

Systems and methods are described for implementing a multi-tenant caching service. The multi-tenant caching service provides a scalable infrastructure with dedicated per-tenant cache widths for tenants of a hosted computing environment, and allows tenants to implement a caching layer between cloud-based services that would otherwise need to scale up in response to load. Tenants may also use the service as a public facing endpoint that caches content provided by backend servers. Content provided by the tenants may be distributed and cached across a cell-based architecture, each cell of which may include a set of storage volumes that are partitioned into caches for individual tenants and configured to store a portion of the content provided by that tenant. Eviction policies may be implemented based on tenant cache usage across multiple cells, and geolocation policies may be implemented to ensure that cached content remains within a particular geographic region.

Multi-tenant caching service in a hosted computing environment

System and methods are provided for sharding at the content level and routing content requests. Each point of presence (PoP) can initially identify the PoP that should serve content by using hashing. A PoP can encode a domain name with the identified PoP in metadata and redirect the client computing device. A client computing device transmits a DNS query for the encoded domain name. A DNS server receives the encoded domain name and decrypts and decodes the domain name label. The DNS server uses the decrypted and decoded metadata to make a further routing decision. The DNS server sends, to the client computing device, a DNS reply with the Internet Protocol (IP) address of the selected PoP. The client computing device requests content from the PoP identified by the provided IP address.

Content-based sharding and routing system

Various embodiments of apparatuses and methods for protecting data integrity in a content distribution network ('CDN') are described. Code or data in one of the servers or instances of a CDN might sometimes become incorrect or corrupt. One corrupted server or instance can potentially impact a considerable portion of the CDN. To solve these and other problems, various embodiments of a CDN can designate one or more parameters, which are then identified in a request for content to another entity. In these embodiments, the CDN can generate an encoding of the expected values of the designated parameters. The CDN can then compare, in these embodiments, its encoding of the expected values to an encoding of the values received from the other entity in response to the request. The CDN can validate the content of the response, as well as the identity of the other entity, in some embodiments.

Protecting data integrity in a content distribution network

Techniques for dynamic content delivery network (CDN) selection using the domain name service (DNS) protocol are described. A DNS resolver utilizes a network identifier provided within a DNS query seeking to resolve a domain to select between different CDNs. The selection can be based on an analysis of network metric summary data corresponding to the CDNs from the perspective of an approximate location of the requesting client, as determined via the network identifier as a proxy. The selection process and involved network metric types can be configured by the user associated with the domain via a selection policy. Network metrics can be provided by the user or collected based on reported data generated by remote clients through provided metric-generating code, and thereafter transformed into network metric summary data that is used for resolution.

Distributed metric collection for dynamic content delivery network selection using DNS

Dynamic content delivery network selection using DNS

Techniques for detection of the fraudulent use of content delivery network (CDN) served byte streams are described. A fraud detection service obtains CDN log data, distribution data, and account data and uses elements therefrom to perform a distribution-centric fraud analysis using machine learning techniques. Based on the likelihood of fraud determined by the analysis, the fraud detection service can rapidly perform actions to address the fraud, such as the termination of service for the distribution, throttling of resources provided for the distribution, or further investigation techniques.

Detection of fraudulent use of content delivery network served byte streams

A datastore engine at an edge location of a content delivery network (CDN) may perform low-latency query processing and data retrieval for multiple types of databases at one or more origin servers. When a client sends a query to the edge location, the datastore engine translates the query from a back-end database format into a native format of the local edge datastore. If the requested data is not there, then the datastore engine retrieves the data from the back-end table and inserted inserts the data into the local edge datastore. By using multiple queries over time to re-construct data from the backend database tables at the edge, the datastore engine may provide low-latency access to data from the backend database tables (avoiding the need to retrieve data from the back-end tables to serve subsequent queries).

Low latency query processing and data retrieval at the edge

Various embodiments of apparatuses and methods for transaction processing at edge servers in a content distribution network ('CDN') are described. In some embodiments, an edge server receives an initial request from a client for content associated with a particular origin, and then provides the content to the client. The edge server can then receive another request from the client that might include an indicator for transaction processing. The edge server determines that transaction processing is indicated for handling this new request, in some embodiments. The edge server can then send a transaction notification to the origin, receive a transaction continuation response from the origin, and then execute a data transaction with transaction entities that are distinct from the content distribution network and the origin, in some embodiments. If the transaction is successful, the edge server can notify the client and the origin of the successful transaction, in some embodiments.

Transaction processing at edge servers in a content distribution network

A content delivery network may store forensic trail metadata for cache entries in order to identify and evict poisoned cache entries, mitigating the effects of a poisoned cache due to corrupted cache servers. Each entry of a cache server may include the cached item as well as forensic metadata. The forensic metadata includes identifiers for cache servers that the item was served from, as well as a timestamp for the time that the item was served. The cache server also maintains a list of corrupted servers, as well as a time window for each corrupted server. The cache server determines, based on the list of corrupted servers and the forensic metadata, whether to evict cache entries.

Using forensic trails to mitigate effects of a poisoned cache

A cache system may maintain size and/or request rate metrics for objects in a lower level cache and for objects in a higher level cache. When an L1 cache does not have an object, it requests the object from an L2 cache and sends to the L2 cache aggregate size and request rate metrics for objects in the L1 cache. The L2 cache may obtain a size metric and a request rate metric for the requested object and then determine, based on the aggregate size and request rate metrics for the objects in the L1 cache and the size metric and the request rate metric for the requested object in the L2 cache, an indication of whether or not the L1 cache should cache the requested object. The L2 cache provides the object and the indication to the L1 cache.

Intelligent hierarchical caching based on metrics for objects in different cache levels

Techniques for using one or more satellites as a part of a content delivery network are described. For example, in some instances a satellite of a cluster of satellites is to receive a request for a resource hosted by the content delivery network; determine that the request for the resource cannot be served by the cluster of satellites; determine a first entity to ask for the resource; send a secondary request for the resource to the determined first entity; receive the resource from the determined first entity; and respond, to a user of the content delivery network, to the request using the received resource for the resource.

Content and compute delivery platform using satellites

Techniques for using a satellite as a part of a content delivery network are described. For example, in some instances a satellite is to receive a request for a resource hosted by the content delivery network, determine that the request for the resource cannot be served by the satellite, determine a first entity to ask for the resource, send a secondary request for the resource to the determined first entity, receive the resource from the determined first entity, respond, to a user of the content delivery network, to the request using the received resource for the resource, and respond to a subsequent request using the cached received resource.

Growing community of inventors

Seattle, WA, United States of America

Karthik Uthaman