Amazon Technologies, Inc.

Nishanth Shankaran

Reto Kramer

Venkates Paramasivam Balakrishnan

Christopher Whitaker

Daniel Lee Osiecki

Shyam Krishnamoorthy

Rajaprabhu Thiruchi Loganathan

Clint Joseph Sbisa

Rajat Arya

Dong Shou

Geoffrey Scott Pare

Avinash Jaisinghani

Blake Meike

Prashant Jayaraman

Jaykumar Harish Gosar

Adam M Thomas

Jeffrey Lloyd Baker

Danny Rabbani

Venkates P Balakrishnan

Shyam Kirshnamoorthy

A resource provisioning service allows users to provision multiple, different network resources in an atomic manner and with a single call to a resource provisioning service. In some instances, the multiple, different network resources comprise individual types of resources that form a portion of one or more cloud-computing platforms. For instance, one or more entities may host and operate a cloud-computing platform that includes different types of network resources, such a storage service, a load balancing service, a compute service, a security service, or any other similar or different type of network-accessible service.

Provisioning multiple network resources

Techniques are described that enable a user to upgrade a stack of resources by providing a template that reflects the desired end state of the stack. Upon receiving a new template, the system automatically detects changes that should be performed and determines the order in which the changes should be performed. The system can also detect if the desired changes to the stack are a result of direct modifications; because parameters to the resources have changed; or the changes are indirectly caused by other dependency/attribute changing. Additionally, the system determines whether the changes require creating new resources or if the changes can be made to the resources live. In case of replacement of resources, the system will first create the new resource, move that new resource into the stack and remove the old resource(s). In case of failures, the system ensures that the stack rolls back to the initial state.

Using a template to update a stack of resources

A cache or other cluster is configuration-aware such that initialization and changes to the underlying structure of the cluster can be dynamically updated for use by a client. A client may use a client driver as an intermediary that is responsible for managing the communication with the cluster. For example, a client driver may resolve an alias from a static configuration endpoint to a storage node. The client driver may request an initial configuration from the storage node and then update configuration from one or more storage nodes that store current configuration of the cluster.

Distributed caching cluster client configuration

A management system may enable and monitor a cache or other cluster to make the cluster configuration-aware such that initialization and changes to the underlying structure of the cluster can be dynamically updated. For example, a distributed memory caching system may provide initial configuration to a client from a memory caching node referenced by an alias provided by a configuration endpoint. Updates of configuration may be retrieved from memory caching nodes, each storing current configuration of the cache cluster. A management system monitors changes to the cache cluster, such as provisioning of new caching nodes, and updates the configuration stored in the caching nodes for retrieval by a client.

Distributed caching cluster management

A cache or other cluster is configuration-aware such that initialization and changes to the underlying structure of the cluster can be dynamically updated. For example, a client may resolve an alias from a static configuration endpoint to a node in a cluster. The client may request initial configuration from the node and then update configuration from nodes that store the current configuration of the cluster.

Distributed caching cluster configuration

A cache cluster is configuration-aware such that client initialization, access to replicated cached data and changes to the underlying structure of the cache cluster can be dynamically updated. For example, a management system monitoring a cache cluster notices a large number of requests for a key that causes a significant load on a first memory caching node. To reduce the load on the first memory caching node, the management system may cause cached data related to the key to be replicated to a second memory caching node. A configuration stored in one or more of the memory caching nodes may be updated by the management system to allow both memory caching nodes to serve the requests for the key to clients.

Replication in distributed caching cluster

Growing community of inventors

Kirkland, WA, United States of America

Nishanth Shankaran