Amazon Technologies, Inc.

Marcin Piotr Kowalski

Andries Petrus Johannes Dippenaar

Duncan Matthew Clough

James Alfred Gordon Greenfield

Mathew Daniel

Kevin Christopher Miller

Diwakar Gupta

Richard Alan Hamman

Roland Paterson-Jones

Gavin Alexander Bramhill

Gideon Jan-Wessel Redelinghuys

Jacob Adam Gabrielson

Roland Alexander Paterson-Jones

Joseph Elmar Magerramov

Matthew James Eddey

Colm Gearóid MacCárthaigh

Frans Adriaan Lategan

David R Richardson

Colin Laird Lazier

Peter Nicholas Desantis

Atle Normann Jorgensen

Almero Gouws

Wesley Gavin King

Gideon Klompje

Tai Geoffrey Lucas

Johannes Stephanus Jansen Van Rensburg

Jacobus Johannes Nicolaas Van Der Merwe

Karel Scott

Michael David Marr

Marc John Brooker

Christopher Richard Jacques De Kadt

Ian Paul Nowland

Nathan Dye

Mikhail Danilov

Richard Hazen Galliher, Iii

Xuan Li

Alec Peterson

Christopher Sam Goosen

Brian L Barker

Gina Louise Morris

Anton Andre Eicher

Terence Lewis

Anna Clara Nagy

Robert Martin Wise

Methods and apparatus for client-directed placement of remotely configured service instances are described. One or more placement target options are selected for a client of a network-accessible service based on criteria such as service characteristics of the placement targets. The selected options, including a particular placement target that includes instance hosts configurable from remote control servers, are indicated programmatically to the client. A determination is made that a service instance is to be configured at the particular placement target on behalf of the client. A remote control server is configured to issue administrative commands to an instance host at the particular placement target to configure the service instance.

Client-directed placement of remotely-configured service instances

A request to initiate a launch procedure of a compute instance at a virtualization host configured to access a remote storage device over a network is received. A memory buffer of the host is allocated as a write-back cache for use during a portion of the launch procedure. In response to a write request directed to remote storage during the portion of the launch procedure, the write payload is stored in the buffer and an indication of fulfillment of the write is provided independently of obtaining an acknowledgement that the payload has been propagated to the remote storage. Subsequent to the portion of the launch procedure, payloads of other write requests are transmitted to the remote storage device.

Parameterized launch acceleration for compute instances

Methods and apparatus for flexible batch job scheduling in virtualization environments are disclosed. A descriptor for a batch job requested by a client is received at a job scheduling service. The descriptor comprises an indication of a time range during which a job iteration may be performed. A target time for executing the iteration is determined based on an analysis of a plurality of received descriptors. An indication of the target time at which the iteration is to be scheduled is provided to a selected execution platform.

Flexible batch job scheduling in virtualization environments

Techniques are described for providing service availability zones for computing-related services provided by a cloud provider network. According to some embodiments, the use of service availability zones enables users to achieve greater availability assurance for workloads sensitive to downtime or outages. The sensitivity of such workloads to downtime may be due to financial, regulatory, safety, or other reasons. Such availability-sensitive applications may in some cases be configured to run in multiple regions of a cloud provider network to increase their availability compared to running in a single availability zone. However, for some applications, the implementation of an application across multiple regions may not be feasible or desirable. The use of service availability zones provides user-visible fault domains within a single region of a cloud provider network, thereby enabling users to readily and reliably achieve application layer availability of approximately 99.999% for a service within a single region.

Service availability zones for high availability workloads

A storage manager implements adaptive snapshot chunk sizing, wherein snapshot chunks are sized differently based on an access pattern for volume data to be included in the respective snapshot chunks. For example, sequentially accessed sectors of a volume may be grouped into snapshot chunks of varying sizes and individually accessed sectors may be snapshotted as individual snapshot chunks. When a volume is populated from the snapshot chunks, the volume data is re-mapped into standard sized volume blocks. In some embodiments, an optimized manifest is generated indicting an order in which the snapshot chunks are to be used to populate a volume to perform a launch process using the volume. In some embodiments, adaptively sized snapshot chunks and a corresponding optimized manifest are used to accelerate performing a launch using a volume populated from a snapshot, such as launching an operating system, an application, a database, a machine image, etc.

Adaptive snapshot chunk sizing for snapshots of block storage volumes

Disclosed are various embodiments for a system that hardware locks a virtual machine to a host machine. The host machine can include a processor and a memory. A hypervisor can be stored in the memory that, when executed by the processor, causes the computing device to host one or more virtual machines. In addition, machine readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least: receive a request to perform an operation on a virtual machine hosted by the hypervisor; evaluate the request to determine that the request complies with a policy; and in response to a determination that the request complies with the policy, cause the hypervisor to initiate the operation.

Locked virtual machines for high availability workloads

A first communicating entity determines session state parameters of a security protocol session between itself and a second communicating entity. The first entity uses the session state parameters to transmit a first set of messages of the session to the second entity via a first communication mechanism. The first entity also uses the session state parameters to transmit a second set of messages of the session to the second entity via a second communication mechanism.

Decoupling secure communication sessions from transport mechanisms

Methods and apparatus that allow clients to specify custom network rules for their resource instances or network constructs in a provider network environment. Services and interfaces may be provided that allow a client to provide an executable module that implements custom rules for their resources, or alternatively to specify or select custom rules for their resources. The module may be installed on a host device, and may apply the custom rules to packets to and from the client's resources. Alternatively, the client-defined rules may be applied to packet flows according to the custom rules specified by the client and applied by a client rules service implemented on the provider network external to the host device or on a client resource instance on the host device. The custom network rules may, for example, extend or modify standard network rules for the client's resources on the host device.

Client-defined rules in provider network environments

Systems and methods are disclosed to implement a request routing layer of a service provider system, where the request routers are aware of different versions of a service implemented by the servers of the system. In embodiments, the request routers may discover the different versions of the service via periodic health messages or request responses from the servers. Requests are routed to the servers according to a routing policy that specifies the relative proportions of requests that are to be routed to each version. Version metrics generated from the requests may be captured and provided to a version change manager, which may update the routing policy based on the metrics, either increasing or decreasing the proportion of requests for the different versions. In embodiments, the request router may implement additional rules that control their routing behavior in response to detected error conditions.

Request routing based on server software versions

Techniques for monitoring computer system components for degraded operation are described. In some embodiments, a baseline performance metric value is received from a system monitoring service, a request directed to an input/output (I/O) device is received that was generated by a first computing device, a timer is started, the timer having a duration based on the baseline performance metric value, the received request is sent to the I/O device, an error message is generated upon expiration of the duration of the timer before a response to the request is received from the I/O device, and the generated error message is sent to a second computing device to cause the second computing device to perform at least one action in response to the generated error message.

Detecting and mitigating hardware component slow failures

Techniques are described for enabling customers of a service provider network to modify and extend the functionality of application programming interfaces (APIs) provided to customers by various services of the provider network. Services of a service provider network provide interfaces that enable customers and other users to define custom API actions representing functionality to be performed by the services upon receipt of corresponding API requests. In this manner, the functionality exposed by provider network services to customers via APIs becomes extensible and customizable to fit customers' particular use cases and without the provider network needing to contemplate and explicitly implement all possible customer-specific API action variations.

User-customizable application programming interfaces in a provider network

Methods and apparatus for profile-guided preloading for virtualized resources are described. A block-level storage volume whose contents are to be populated via data transfers from a repository service is programmatically attached to a compute instance. An indication of data transfers from the repository to a block storage service implementing the volume is obtained, corresponding to a particular phase of program execution at the compute instance. A storage profile is generated, based at least in part on the indication of data transfers. The storage profile is subsequently used to pre-load data from the repository service on behalf of other compute instances.

Profile-guided data preloading for virtualized resources

Growing community of inventors

Cape Town, South Africa

Marcin Piotr Kowalski