Microsoft Technology Licensing, LLC

Other

Ajay Mani

Thomas Moscibroda

James Ernest Johnson

Saad Syed

Sushant Pramod Rewaskar

Yang Chen

Abhishek Kumar Singh

Nisarg Tarakkumar Sheth

Mark Eugene Russinovich

Ying Yan

Jurgen Aubrey Willis

Jiaxing Zhang

Haoran Wang

Akram Hassan

Pavithra Tyamagondlu Nagesharao

Christopher Paul Almida

Gaurav Jagtiani

Wei Zhao

Thiruvengadam Venketesan

Yong Xu

Qingwei Lin

Marcus Felipe Fontoura

Muhammad Umer Azad

Karthikeyan Subramanian

Luis Irun-Briz

Shandan Zhou

Si Qin

Bryan William Tuttle

Saurabh Agarwal

Eli Cortez

Sorin Iftimie

Wakkas Rafiq

Murtuza Rizvi

Akram M H Hassan

Srikanth Raghavan

Alejandro Matute Gonzalez

Ana-Maria Constantin

Wanghai Gu

Sandeep Ramji

Paul Naveen Selvaraj

Huy Vu-Bao Hoang

David Allen Dion

Pavel Anatolievich Dournov

Ashish B Shah

Todd F Pfleiger

Esaias Engelbertus Greeff

Haizhi Xu

Shailesh Padmakar Joshi

Prajakta Patil

James E Johnson

Esaias Englebertus Greeff

Todd Pfleiger

Shailesh P Joshi

Abhishek Singh

Ashish Shah

Akram MH Hassan

Sushant Pramad Rewaskar

Systems and methods are taught for providing customers of a cloud computing service to control when updates affect the services provided to the customers. Because multiple customers share the cloud's infrastructure, each customer may have conflicting preferences for when an update and associated downtime occurs. Preventing and resolving conflicts between the preferences of multiple customers while providing them with input for scheduling a planned update may reduce the inconvenience posed by updates. Additionally, the schedule for the update may be transmitted to customers so that they can prepare for the downtime of services associated with the update.

Tenant-controlled cloud updates

The present disclosure relates to systems, methods, and computer readable media for predicting expansion failures and implementing defragmentation instructions based on the predicted expansion failures and other signals. For example, systems disclosed herein may apply a failure prediction model to determine an expansion failure prediction associated with an estimated likelihood that deployment failures will occur on a node cluster. The systems disclosed herein may further generate defragmentation instructions indicating a severity level that a defragmentation engine may execute on a cluster level to prevent expansion failures while minimizing negative customer impacts. By uniquely generating defragmentation instructions for each node cluster, a cloud computing system can minimize expansion failures, increase resource capacity, reduce costs, and provide access to reliable services to customers.

Predicting expansion failures and defragmenting cluster resources

The present disclosure relates to systems, methods, and computer readable media for rightsizing virtual machine deployments on a cloud computing system. For example, systems disclosed herein may predict utilization of resources for a customer deployment and determine a desired goal state including a deployment of virtual machines having rightsized specifications that align more closely with the predicted utilization. Systems disclosed herein may utilize the goal state in view of the deployment data, policies, and other information to determine an action plan including deployment actions for transitioning a current state of a customer deployment to the goal state. By rightsizing virtual machine deployments, systems described herein may affect more efficient utilization of cloud computing resources and decrease costs associated with over-allocation of cloud computing resources.

Rightsizing virtual machine deployments in a cloud computing environment

The present disclosure relates to systems, methods, and computer readable media that utilize a low-impact live-migration system to reduce unfavorable impacts caused as a result of live-migrating computing containers between physical server devices of a cloud computing system. For example, systems disclosed herein evaluates characteristics of computing containers on server devices to determine a predicted unfavorable impact of live-migrating the computing containers between the server devices. Based on the predicted impact, the systems disclosed herein can selectively identify which computing containers to live-migrate as well as carry out live-migration of the select computing containers in such a way the significantly reduces unfavorable impacts to a customer or client device associated with the computing containers.

Minimizing impact of migrating virtual services

In various embodiments, methods and systems for optimizing allocation of multi-priority service instances are provided. In embodiments, a quality metric associated with each candidate node to which a service instance could be allocated is determined. An eviction cost or a survival metric associated with at least a portion of the candidate nodes to which the service instance could be allocated are determined. The eviction costs generally indicate a cost to evict a service instance from a corresponding node such that another service instance can be allocated to that node. At least a portion of the quality metrics and either the eviction costs or the survival metrics are used to select a node from the candidate nodes to which to allocate the service instance.

Multi-priority service instance allocation within cloud computing platforms

Techniques are disclosed for providing opportunistic virtual machine migration. In response to determining that a virtual machine will be rebooted, a determination is made whether the virtual machine should be migrated from the computing device that is currently hosting the virtual machine. Based on one or more criteria, a destination computing device for the virtual machine is identified. When a performance threshold is met, subsequent to shutting down the virtual machine at the current host and prior to rebooting the virtual machine at a new host, the virtual machine is migrated to the destination computing device.

Opportunistic virtual machine migration

According to examples, an apparatus may include a processor and a memory on which is stored machine readable instructions that are to cause the processor to receive an allocation request from an allocator client, determine a resource allocation for the received job allocation request, store a record of the determined resource allocation in a records store, and send the determined resource allocation to the allocator client, in which an acknowledgement to the sent determined resource allocation is to be received from the allocator client. The instructions may also cause the processor to manage a state of the determined resource allocation using the record stored in the records store based on whether the acknowledgement is received from the allocator client.

Resource allocation state management

In various embodiments, methods and systems for optimizing allocation of dynamic resources are provided. A user service request resource instance is received at an allocator. The user service request resource instance is based on a dynamic resource protocol that supports generating and communicating resource instances between components in a resource allocation platform. The dynamic resource protocol also defines a set of rules for translating and representing resources as logical resource types and logical units. At a node, a node resource instance is generated and communicated, based on the dynamic resource protocol, from the node to the allocator. The node resource instance specifically comprises a resource interaction matrix that indicates dependencies between resource types. A resource allocation instance is generated at the allocator for the user service request resource instance. The resource allocation instance is communicated, such that, resource types on the node are allocated based on the resource allocation instance.

Optimal allocation of dynamic cloud computing platform resources

In various embodiments, methods and systems for optimizing allocation of multi-priority service instances are provided. In embodiments, a packing quality metric associated with each candidate node to which a service instance could be allocated are determined. An eviction cost associated with at least a portion of the candidate nodes to which the service instance could be allocated are determined. The eviction costs generally indicate a cost to evict a service instance from a corresponding node such that another service instance can be allocated to that node. At least a portion of the packing quality metrics and the eviction costs are used to select a node from the candidate nodes to which to allocate the service instance.

Embodiments described herein are directed to migrating affected services away from a faulted cloud node and to handling faults during an upgrade. In one scenario, a computer system determines that virtual machines running on a first cloud node are in a faulted state. The computer system determines which cloud resources on the first cloud node were allocated to the faulted virtual machine, allocates the determined cloud resources of the first cloud node to a second, different cloud node and re-instantiates the faulted virtual machine on the second, different cloud node using the allocated cloud resources.

Healing cloud services during upgrades

Tenant-controlled cloud apparatus

Growing community of inventors

Woodinville, WA, United States of America

Ajay Mani