Amazon Technologies, Inc.

Sidharth Bajaj

Jacob Taylor Wires

Valeri Atamaniouk

Wesley Shawn Davis

Leon Thrane

Nikolaos Koutsikos Tsatsalmas

Yuri Zarubin

Marcin Marek Wolicki

Sumit Kumar

Julien Mascart

Jingmin Zhu

Jun Dai

Vignesh Natarajan

Jared Alan Bergman

Zhiyuan Lin

Henry A Spang

Tejal Borkar

Shreyas Yagna

Dmytro Sukhariev

Ming Yiu Andy Siu

Sets of asynchronous replication operations may be tracked to ensure consistency. A tracking service may receive notifications of pending asynchronous replication tasks, and responsive to receiving a manifest indicating a request to be notified upon completion of a set of pending replication asynchronous tasks, matches individual ones of the tasks within the set to tasks indicated as pending. The tracking service may then select a routing table based on a most recent sequence number associated with the set of tasks, determine one of more tracking nodes assigned to track the set of tasks, and send the manifest to each of the tracking nodes. As individual ones of the tasks complete, notifications of completion may be sent to the tracking nodes and an aggregator node aggregates the completion notifications for the set. Once all completion notifications are received, a response to the request indicating completion may be sent.

Granular tracking of replication consistency using subsets of asynchronous replication tasks

Dynamic management of data traffic workflows is performed. An event to perform a data traffic workflow at a remote performance location may be received. Computing resources to perform the data traffic workflow may be identified. Operations to perform the data traffic workflow may be dynamically directed by the identified computing resources to adaptively balance performance of the operations with operations for other data traffic workflows in order to meet respective performance requirements of the data traffic workflows.

Dynamically managed data traffic workflows

Methods, systems, and computer-readable media for scalable job transformation and management are disclosed. A plurality of tasks expressed in a first format are received at a host. The tasks are associated with a shard identifier based at least in part on one or more criteria, and the tasks are acquired by the host based at least in part on the shard identifier. A subset of the tasks having a common characteristic are determined. The subset of the tasks are aggregated into a job expressed in a second format, where the job represents the subset of the tasks. The job is provided to a job manager, and the subset of the tasks are scheduled for processing using the job manager.

Scalable job transformation and management

The performance of asynchronous tasks may be dynamically configured. An evaluation of pending tasks that includes updates for new tasks and completed tasks being removed is performed. A target capacity for the data traffic workflow is determined from the evaluation of pending tasks in order to satisfy a performance requirement for the data traffic workflow. Modifications to a performance configuration for the data traffic workflow are then made based on a comparison with the target capacity.

Dynamic performance configuration for data traffic workflows

Growing community of inventors

Vancouver, Canada

Sidharth Bajaj