International Business Machines Corporation

Huawei Technologies Co., Limited

University of Toronto

Huawei Technologies Canada Co., Ltd.

Huawei Cloud Computing Technologies Co., Ltd.

Zhenhua Hu

Yonggang Hu

Alicia Elena Chin

Rui Zhang

Prasenjit Sarkar

Reshu Jain

Zhimin Lin

Li Feng Zhang

Jian Tan

Michael Feiman

Jason T S Lam

Xiaoqiao Meng

Shicong Meng

Khalid Ahmed

David Bigagli

Qiang Xu

Jingwen Wang

Hao Hai Ma

Wentao Tang

Amir Asif

Vida Movahedi

Chong Chen

Jian Qiang Liu

Lei Su

Qi Wang

Ming Chen

Xiao Ming Bao

Hao Zhou

Zhi Zhao

Wen Yan Bai

Haohai Ma

Daesuk Kang

Gui Fu

Heng Kuang

Min Li

Yandong Wang

Xiaodi Ke

Yashar Ganjali

Eyal De Lara

Luna Xu

Chung-Man Abelard Chow

Zhigang Luo

Seyed Hossein Mortazavi

Hongwu Chen

Shaohui Xu

Zhike Zhang

Moshe Gabel

Farid Zandi

Parsa Pazhooheshy

Soheil Abbasloo

Sepehr Abbasi Zadeh

Kajaruban Surendran

Khaled Ziya Aeen

In cloud computing, for various reasons such as load-balancing, hotspot elimination, server consolidation, energy and cost savings, and system maintenance, there is a need to migrate a virtual sub-network of virtual entities from a source network of servers to a destination set of servers. Existing migration methods are limited to the migration of VM memory and controller states, where network entities are migrated individually. Embodiments of this disclosure include systems and methods for the stateful live migration of a multi-layer network, while maintaining live state convergence and consistency, and preventing network connection losses, packet disordering and packet drops.

Systems and methods to migrate a virtual sub-network

Methods and systems for data management are described, particularly for processing global queries. Each global query includes a user-defined query constraint value, such as laxity or query response time limit. The query receiving node maintains a copy of the previously updated data from all of its children node. The query receiving node first searches for the requested query data in its local data storage to minimize children node query. If any portion of the requested data in the local data storage fails to meet the query constraint value, then the child node from which the data came from is tasked with recursively executing the global query.

Method to improve global query performance in an edge network

A technique for managing pooled resources in a distributed computing environment includes a resource manager that receives resource allocation requests from workload managers for running one or more applications. The applications are initiated by a consumer through at least one of the workload managers where each workload manager is configured to translate demand requests from the applications into resource allocation requests. A determination is made whether there are available resources to satisfy the resource allocation requests. Responsive to determining that there is an unmet resource allocation request, a candidate resource meeting some but not all attributes needed to satisfy the unmet resource allocation request is identified and reconfigured to have the attributes needed to satisfy the unmet resource allocation request.

Resource manager for managing the sharing of resources among multiple workloads in a distributed computing environment

Systems and methods for controlling management operations and shared memory space are disclosed. A cloud cache management controller may receive multiple sets of service attributes. Each set of the multiple sets of service attributes may be related to a cloud cache service instance. The cloud cache management controller may receive a first cloud cache management request. The cloud cache management request may comprise a cloud cache management operation. The cloud cache management controller may retrieve a set of service attributes from the multiple sets of service attributes based on an evaluation of the cloud cache management operation. The cloud cache management controller may send the first cloud cache management request to a corresponding CCSI based on a priority value for the first cloud cache management request calculated based on the retrieved set of service attributes.

System and method to schedule management operations and shared memory space for multi-tenant cache service in cloud

Systems and methods for cross-region active-active data replication are described. A system includes a cross-region replication service (CRS), a cross-region synchronization service (CSS), and a conflict-free replication data type (CRDT) module executed by a cache service instance.

Systems and methods for cross-region data management in an active-active architecture

A method for multi-layer quality of service (QoS) management in a distributed computing environment includes receiving a workload and identifying a workload QoS class for the workload. The workload is scheduled to be run compute nodes. The workload QoS class is translated to a plurality of different resource layer QoS classes, and the plurality of QoS classes are communicated to a workload execution manager of the compute nodes. The workload execution manager extends the plurality of different resource layer QoS classes to respective resource layers involved in the running of the workload.

Multi-layer QOS management in a distributed computing environment

A system for multi-layer quality of service (QoS) management in a distributed computing environment includes a management node hosting a workload scheduler configured to receive a workload and identify a workload QoS class for the workload. The workload scheduler schedules running of the workload on compute nodes, translate the workload QoS class to a plurality of different resource layer QoS classes, and communicates the plurality of QoS classes to a workload execution manager of the compute nodes. The workload execution manager is configured to extend the plurality of different resource layer QoS classes to respective resource layers involved in the running of the workload.

Multi-layer QoS management in a distributed computing environment

A technique for managing pooled resources in a distributed computing environment includes a resource manager executable to receive resource allocation requests from a plurality of workload managers for running one or more applications. The applications are initiated by a consumer through the workload managers. Each workload manager is configured to translate demand requests from the applications into resource allocation requests. A determination is made whether there are available resources to satisfy the resource requests according to a resource allocation policy. Resources are allocated to the workload managers where the applications can continue running on the allocated resources if the resource manager suffers downtime or is taken offline. The resource allocation policy is determined by a consumer profile of the consumer specifying ownership and share rights to the requested resources.

Systems and methods for rate limiting one or more clusters of service instances using at least one rate limit controller are described herein. A token distribution is determined for each one of a plurality of rate limiters. The token distribution comprising a maximum number of tokens and a token generating rate. The maximum number of tokens and the token generating rate are assigned to each one of the plurality of rate limiters. At least one request for additional tokens is received from at least a given one of the plurality of rate limiters. The token distribution of at least the given one of the plurality of rate limiters is adjusted based on the request and on token consumption information of at least the given one of the plurality of rate limiters. An adjusted token distribution is assigned to the given one of the plurality of rate limiters.

Method and system for cluster rate limiting in a cloud computing system

A computer-implemented method, according to one embodiment, includes: splitting a video stream into a plurality of sub-streams, and encoding each of the sub-streams. A packet is also transmitted to a receiver, where the packet includes a number of the encoded sub-streams. Moreover, the number of the encoded sub-streams that are included in the packet transmitted to the receiver corresponds to a quality of service associated with a service cost incurred by the receiver. Other systems, methods, and computer program products are described in additional embodiments.

Video encoding and transcoding for multiple simultaneous qualities of service

A single workload scheduler schedules sessions and tasks having a tree structure to resources, wherein the single workload scheduler has scheduling control of the resources and the tasks of the parent-child workload sessions and tasks. The single workload scheduler receives a request to schedule a child session created by a scheduled parent task that when executed results in a child task; the scheduled parent task is dependent on a result of the child task. The single workload scheduler receives a message from the scheduled parent task yielding a resource based on the resource not being used by the scheduled parent task, schedules tasks to backfill the resource, and returns the resource yielded by the scheduled parent task to the scheduled parent task based on receiving a resume request from the scheduled parent task or determining dependencies of the scheduled parent task have been met.

Computing session workload scheduling and management of parent-child tasks using a blocking yield API to block and unblock the parent task

Implementing a fair share of resources among one or more scheduling peers. Resource allocations are received for a plurality of scheduling peers. For each scheduling peer, a usage percentage difference is determined between their respective usage percentage and configured share ratio. For a first competing peer that is served more than a second competing peer, resource allocation is adjusted such that resources from the first competing peer are allocated to the second competing peer based, at least in part, on a time decay factor function that gives less weight to the usage percentage difference as an age of the usage percentage difference increases.

Hierarchical fairshare of multi-dimensional resources

Systems and methods are disclosed herein for allocating computing resources for execution of workloads in a distributed computing system with resource acquisition cycles and workload scheduling cycles. One or more resource offer managers transmit resource offers to each of one or more of schedulers. Each scheduler transmits a resource request and/or resource release request in response to each resource offer manager. Each resource offer manager computes a resource allocation for each scheduler after resolving conflicts and assigns the resources to each scheduler according to the resource allocation decisions. The resource acquisition cycle and the workload scheduling cycle are decoupled.

Systems and methods for allocating computing resources in distributed computing

A system for multi-layer quality of service (QoS) management in a distributed computing environment includes a management node hosting a workload scheduler operable to receive a workload and identify a workload QoS class for the workload. The system also includes a plurality of distributed compute nodes. A workload scheduler schedules running of the workload on the compute nodes, translates the workload QoS class to a storage level QoS class, and communicates the storage level QoS class to a workload execution manager of the compute nodes. The workload scheduler communicates the storage level QoS class to one or more storage managers where the storage managers manage storage resources, and the storage managers are operable to extend the storage level QoS class to the storage resources to support the workload QoS class.

A technique for multi-layer quality of service (QoS) management in a distributed computing environment includes receiving a workload to run in a distributed computing environment. A workload quality of service (QoS) class for the workload is identified, and the workload QoS class is translated to a storage level QoS class. The workload is scheduled to run on a compute node of the environment, and the storage level QoS class is communicated to a workload execution manager of the compute node. The storage level QoS class is communicated to one or more storage managers of the environment where the storage managers manage storage resources in the environment. The storage managers extend the storage level QoS class to the storage resources to support the workload QoS class.

Growing community of inventors

Toronto, Canada

Zhenhua Hu