Amazon Technologies, Inc.

Himanshu Jindal

Christoph Saalfeld

Nicholas Andrew Gochenaur

Paritosh Mohan

Calvin Yue-Ren Kuo

Jonathan I Turow

Dominique Fortier

Alexandra Elizabeth Baoboe Lee

Gary Keith Wicker

Eeshan Shreeram Thakar

Venkata Harish Kommaraju

Jared Sharfin

Frank Miley

Saurabh Chatterjee

Systems and methods for implementing record locking for transactions using a probabilistic data structure are described. This probabilistic structure enables adding of data records without growth of the data structure. The data structure includes a hash table for each of multiple hash functions, where entries in the respective hash tables store a transaction time and locking state. To lock a record, each hash function is applied to a record key to provide an index into a respective hash table and a minimum of the values stored in the hash tables is retrieved. If the retrieved value is less than a transaction time for a transaction attempting to lock the record, locking is permitted and the transaction time is recorded to each of the hash tables. To commit the transaction, the probabilistic data structure is atomically updated as part of the commit operation.

Record-level locks with constant space complexity

After a service receives a request from another service, the service determines an amount of time to process the request by the service as well as a remaining time allotment to complete processing the request (e.g., a timeout value). Based on the remaining time allotment and the amount of time to process the request by at least the service (predicted time or actual time), the service may determine whether to continue processing the request (e.g., by the service and/or one or more subsequent services) or fail the request. In response, the service may then continue processing the request (e.g., continue processing at the service itself or propagate the request to the next service), or the service may fail the request.

Using distributed services to continue or fail requests based on determining allotted time and processing time

Adaptive load balancing may be implemented for a distributed system. An evaluation of criteria for creating a mapping for an identifier associated with requests may be performed. The created mapping may route requests to a distributed system to request handling nodes that cache request information for performing the requests. When requests are received, if an identifier determined to be associated with the request is mapped to request handling nodes, then the request may be sent to the identified request handling nodes instead of performing a load balancing technique to select a request handling node for the request.

Adaptive load balancing for distributed systems

Systems and methods are provided for dynamically configuring an IoT communications system. The IoT communications system receives a client message from an IoT device. The client message includes an endpoint designation (such as by specifying an endpoint in the Server Name Indication (SNI) field of the TLS client hello message). The IoT communications system determines whether the endpoint is associated with a custom or default processing logic and/or settings. Either custom or default processing logic is executed or custom or default settings are applied.

Configurable internet of things communications system

A message broker of a publish-subscribe messaging system (e.g., using the MQTT protocol or other publish-subscribe protocol) detects a life-cycle event for topic subscription and notifies a publisher of the life-cycle event. The message broker may detect a transition in a number of subscribers to a topic from zero subscribers to one or more subscribers or from one or more subscribers to zero subscribers. In response, the message broker provides an indication to the publisher that the number of subscribers to the topic has transitioned from zero to one or more (or from one or more to zero). This causes the publisher to begin publishing messages on the publisher's topic (or to stop publishing messages on the publisher's topic).

Notifying a publisher of life-cycle events for topic subscription

Technology is described for sending subscription-based messages to devices. A message associated with a defined topic may be received. A first subset of devices may be identified that subscribe to the defined topic. A first subset of messages may be provided to a message queue for transmission to devices indicated in the first subset of devices. A second subset of devices may be identified that subscribe to the defined topic. A second subset of messages may be provided to the message queue for transmission to devices indicated in the second subset of devices. The second subset of messages may include an increased subset size as compared to the first subset of messages. The subset size may be increased at a rate to enable sending the message to the plurality of device subscribed to the defined topic within a defined time period.

Transmission of subscription-based messages to internet of things (IoT) devices

A technology is described for distributing a publication message. An example method may include receiving a message at a first device gateway to broadcast to devices subscribed to a broadcast topic. The first device gateway maintains a first subscription table indicating which devices connected to the first device gateway are subscribed to the broadcast topic. The first device gateway distributes the message to the devices indicated in the first subscription table as being subscribed to the broadcast topic. In addition, the first device gateway may distribute the message to a second device gateway which maintains a second subscription table indicating which devices connected to the second device gateway are subscribed to the broadcast topic, and the second device gateway distributes the message to the devices indicated in the second subscription table as being subscribed to the broadcast topic.

Distributing publication messages to devices

A technology is provided for adapting a quorum size of messaging nodes in a service provider environment. An adaptive quorum evaluation is executed to determine a number of messaging nodes for a quorum of messaging nodes. A messaging environment trigger is identified to change the number of messaging nodes used for the quorum of messaging nodes. The number of messaging nodes used for the quorum of messaging nodes is changed based on the messaging environment trigger. Data for the message is synchronized with a quorum of messaging nodes before delivering the message.

Growing community of inventors

Seattle, WA, United States of America

Himanshu Jindal