Amazon Technologies, Inc.

Barry Bailey Hunter, Jr

Grant Alexander Macdonald McAlister

Swaminathan Sivasubramanian

Kiran-Kumar Muniswamy-Reddy

David Alan Lutz

Jai Vasanth

Silas M Brazil

Timothy Andrew Rath

Yijun Lu

Maximiliano Maccanti

Parikshit Shivajirao Pol

Jian Wang

Wei Xiao

Akshat Vig

Somasundaram Perianayagam

Tanmoy Dutta

Qiang Liu

Stuart Henry Seelye Marshall

Adam Douglas Morley

Xianglong Huang

Dennis Tighe

Jiandan Zheng

Matthew Walters

Mark Porter

Rahul Nambiar

Bharath Subramanian Pichai

Ying Lin

Daniel Myers

Replicated instances in a distributed computing environment provide for automatic failover and recovery. A component monitors the status of event processors in a set or bucket and handles the failure of an event processor. For a large number of instances, the data environment can be partitioned such that each monitoring component is assigned a partition of the workload. At intervals, each event processor sends a 'heartbeat' message to the event processors in the bucket covering the same workload partition, to inform the other event processors of the status of the event processor sending the heartbeat. If it is determined that a heartbeat is received from each event processor in the bucket, a current process can continue. In the event of monitoring component failure, the instances can be repartitioned, and the remaining monitoring components can be assigned to the new partitions to substantially evenly distribute the workload.

Monitoring of replicated data instances

Resources hosted in different virtualization platforms may be managed across the different virtualization platform. Requests to perform types of actions with respect to a resource hosted in a type of virtualization platform may be received. Mapping information between types of actions and actions available via interfaces for different types of virtualization platforms may be evaluated to select actions for an interface of the type of virtualization platform that hosts the resource. The selected actions may then be performed via the interface to perform the action with regard to the resource.

Managing hosted resources across different virtualization platforms

A hosted service may limit access to a table initially comprising one or more partitions. Access to the table may be limited to a provisioned capacity. A client of the service may request an increased capacity. A minimum number of partitions for providing the increased capacity may be determined. Proportions of the increased capacity may be allocated among members of successive generations of partitions to be provided by a member of a generation or its descendants. The proportions may be allocated to minimize the costs associated with splitting partitions based on the minimum number of partitions.

Distributed system capacity dial-up

Detecting replica faults within a replica group and dynamically scheduling replica healing operations are described. Status metadata for one or more replica groups may be accessed. Based, at least in part, the status data a number of available replicas for at least one replica group may be determined to incompliant with a healthy state definition for the replica group. One or more healing operations to restore the number of available replicas for the at least one replica group to the respective healthy state definition may be dynamically scheduled. In some embodiments, one or more resource constraints for performing healing operations and one or more resource requirements for each of the one or more healing operations may be used to order the one or more healing operations.

Dynamic replica failure detection and healing

Replicated instances in a database environment provide for automatic failover and recovery. A monitoring component can obtain a lease enabling the component to periodically communicate with, and monitor, one or more data instances in the data environment, where the data instance can be a replicated instance including a primary and a secondary replica. For a large number of instances, the data environment can be partitioned such that each monitoring component can be assigned a partition of the workload. In the event of a failure of a monitoring component, the instances can be repartitioned and the remaining monitoring components can be assigned to the new partitions to substantially evenly distribute the workload.

A system that implements distributed storage may schedule and track control plane operations for performance at the distributed storage service. Information may be maintained for control plane events detected at a distributed storage system. Resource utilization for currently performing control plane operations and currently scheduled control plane operations of the distributed storage system may be determined. The information about detected control plane events may be analyzed to schedule control plane operations to be performed in response to detecting the control plane events. As part of scheduling control plane operations, resource constraints may be applied to the determine resource utilization for the distributed storage system.

Scheduling and tracking control plane operations for distributed storage systems

An automated system may be employed to perform detection, analysis and recovery from faults occurring in a distributed computing system. Faults may be recorded in a metadata store for verification and analysis by an automated fault management process. Diagnostic procedures may confirm detected faults. The automated fault management process may perform recovery workflows involving operations such as rebooting faulting devices and excommunicating unrecoverable computing nodes from affected clusters.

Distributed computing fault management

The monitoring and recovery of data instances, data stores, and other such components in a data environment can be performed automatically using a separate control environment. A monitoring component of the control plane can include a set of event processors for monitoring a workload of the data environment, where an event processor detecting a problem in the data plane can cause a recovery workflow to be generated in order to recover from the detected problem. The event processors can communicate with each other such that if one of the event processors becomes unavailable, the other event processors in a set are able to automatically redistribute responsibility for the workload.

Monitoring and automated recovery of data instances

The monitoring and recovery of data instances, data stores, and other such components in a data environment can be performed automatically using a separate control environment. A monitoring component of the control plane can include a set of event processors for monitoring a workload of the data environment, where an event processor detecting a problem in the data plane can cause a recovery workflow to generated in order to recover from the detected problem. The event processors can communicate with each other such that if one of the event processors becomes unavailable, the other event processors in a set are able to automatically redistribute responsibility for the workload.

Growing community of inventors

Sammamish, WA, United States of America

Barry Bailey Hunter, Jr