公开(公告)号：US20190342188A1

公开(公告)日：2019-11-07

申请号：US15991632

申请日：2018-05-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Karthik RAMAN ,  Arsalan AHMAD ,  Momin Mahmoud AL-GHOSIEN ,  Mohammad DERAKHSHANI ,  Madhan GAJENDRAN ,  Ji HUANG ,  Kiran Kumar KOLLI ,  Sujit Vattathil KURUVILLA ,  Liang LI ,  Denis RYSTSOV ,  Pankaj SHARMA ,  Dharma SHUKLA ,  Hari Sudan SUNDAR ,  Shireesh Kumar THOTA ,  Swarnim VYAS

IPC: H04L12/24 ,  G06F17/30

Abstract: Data services are often provided with consistency guarantees of either strong consistency models, comprising uniform wall-clock consistency, or eventual consistency models, where temporary logical inconsistency is guaranteed to be resolved only after full data propagation. However, the performance characteristics of contemporary services often require an intermediate consistency model, where some aspects of the service have specific consistency expectations and other aspects of the service are flexible, such as bounded staleness (e.g., a maximum delay in reaching consistency); session consistency (e.g., individual sessions remain logically consistent, but ordering may vary across sessions); and prefix consistency (e.g., each view during a session is logically consistent, but ordering may vary between session views). Service guarantees may involve a selection within a range of consistency models that includes one or more intermediate consistency levels, and server configurations may be selected and applied to fulfill the intermediate consistency level selected in the service level agreement.

公开(公告)号：US20220335034A1

公开(公告)日：2022-10-20

申请号：US17855306

申请日：2022-06-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Karthik RAMAN ,  Momin Mahmoud AL-GHOSHIEN ,  Bhalakumaaran ERODE RANGANATHAN ,  Madhan GAJENDRAN ,  Ji HUANG ,  Atul KATIYAR ,  Mikhail Mikhailovich KOLTACHEV ,  Sujit Vattathil KURUVILLA ,  Digvijaysinh Govindbhai MAKWANA ,  Subramanyam PATTIPAKA ,  Ovidiu Constantin PLATON ,  Ankur Savailal SHAH ,  Pankaj SHARMA ,  Dharma SHUKLA ,  Shreshth SINGHAL ,  Shireesh Kumar THOTA

IPC: G06F16/23 ,  G06F16/27 ,  G06F11/20 ,  G06F16/22 ,  G06F16/2452 ,  G06F16/28 ,  G06F16/25 ,  G06F16/21 ,  H04L67/1008 ,  G06F9/50 ,  H04L41/0896 ,  H04L41/5009 ,  H04L47/72 ,  H04L47/762 ,  G06F16/182 ,  G06F16/903 ,  H04L41/5019 ,  H04L67/1012 ,  H04L67/1034 ,  H04L41/0803 ,  H04L41/5022 ,  H04L41/50 ,  H04L69/24

Abstract: Data services for workloads are often provided with a service level agreement specifying various performance guarantees (e.g., latency, availability, scalability, and consistency). Single-master architectures, in which updates t the data set are constrained to a single server, may limit the fulfillment of some performance guarantees. Presented herein are multi-master architectures, in which the server set is partitioned into at least two masters are permitted to update the data set and at least one non-master that is not permitted to update the data set. Non-masters that receive a request to update the data set forward the request to a master server for application to the data set. A master that receives the request applies it to the data set and propagates the update to other master and non-master servers. Conflicting updates may be resolved through a variety of conflict resolution techniques, optionally designating one master server as a conflict resolution server.

公开(公告)号：US20190342380A1

公开(公告)日：2019-11-07

申请号：US15991953

申请日：2018-05-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Shireesh Kumar THOTA ,  Momin Mahmoud AL-GHOSIEN ,  Rajeev Sudhakar BHOPI ,  Samer BOSHRA ,  Madhan GAJENDRAN ,  Atul KATIYAR ,  Abhijit Padmanabh PAI ,  Karthik RAMAN ,  Ankur Savailal SHAH ,  Pankaj SHARMA ,  Dharma SHUKLA ,  Shreshth SINGHAL ,  Hari Sudan SUNDAR ,  Lalitha Manjapara VISWANATHAN

IPC: H04L29/08 ,  H04L12/24 ,  H04L29/06

Abstract: Processing services are often provisioned by defining and adjusting the performance capabilities of individual servers, and in multitenancy scenarios, servers may allocate computational resources to ensure that a first client workload does not impact a second client workload. However, a reduced performance capability of a server may create a processing jam with respect to an upstream server of the process path of the workload, where the processing rate mismatch creates a risk of failing to fulfill the performance guarantee for the workload. Instead, the downstream server may monitor and compare its performance capability with the performance guarantee. If a performance guarantee failure risk arises, the server may transmit a performance capability alert to the upstream server, which may rate-limit the processing of the workload. Rate-limiting by the first server in the server path may limit workload intake to a volume for which the process path can fulfill the performance guarantee.

公开(公告)号：US20190342379A1

公开(公告)日：2019-11-07

申请号：US15991062

申请日：2018-05-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Dharma SHUKLA ,  Momin Mahmoud AL-GHOSIEN ,  Rajeev Sudhakar BHOPI ,  Samer BOSHRA ,  Madhan GAJENDRAN ,  Artavazd GINOSIAN ,  Atul KATIYAR ,  Liang LI ,  Karthik RAMAN ,  Ankur Savailal SHAH ,  Pankaj SHARMA ,  Hari Sudan SUNDAR ,  Krishnan SUNDARAM ,  Shireesh Kumar THOTA ,  Lalitha Manjapara VISWANATHAN

IPC: H04L29/08 ,  H04L12/911 ,  H04L12/923 ,  H04L12/24 ,  G06F9/50

Abstract: Workloads are often performed by a server set according to a service level agreement, and are often provisioned and load-balanced by dedicating selected computational resources (e.g., servers and bandwidth) for application to the workload. However, resource-based provisioning may not accurately reflect the computational resource expenditure of the workload, leading to overprovisioning or underprovisioning of servers for the workload. Instead, the workload may be evaluated according to a service unit as a measurement of a volume of computational resources consumed by a workload unit, including performance dimensions specified in the service level agreement. The service level agreement may indicate a service unit rate for the workload. The workload may therefore be allocated to a subset of servers in portions according to a service unit rate, where the sum of the service unit rates for the portions allocated to the servers satisfies the service unit rate specified in the service level agreement.

公开(公告)号：US20190158580A1

公开(公告)日：2019-05-23

申请号：US16199732

申请日：2018-11-26

Applicant: Microsoft Technology Licensing, LLC

Inventor： Dharma SHUKLA ,  Madhan GAJENDRAN ,  Quetzalcoatl BRADLEY ,  Shireesh Kumar THOTA ,  Karthik RAMAN ,  Mark Connolly BENVENUTO ,  John MACINTYRE ,  Nemanja MATKOVIC ,  Constantin DULU ,  Elisa Marie FLASKO ,  Atul KATIYAR

IPC: H04L29/08

CPC classification number: H04L67/1006

Abstract: A server set may provide a document service to various clients in view of considerations such as availability, fault tolerance, flexibility, and performance. Presented herein are document service architectures that involve partitioning the document set into at least two document ranges, and assigning the respective document ranges to an agent that is deployed to at least one assigned server. A request to apply an operation to a selected document may be fulfilled by identifying the document range of the document; identifying a selected server of the server set that hosts the agent to which the range is assigned; and forwarding the request to the selected server. In some variations, servers may retain detailed information about neighboring servers (e.g., according to logical and/or physical proximity) and scant information about distant servers, thereby avoiding both the extensive information exchange of highly informed network architectures and the inefficiency of uninformed routing algorithms.

公开(公告)号：US20240143414A1

公开(公告)日：2024-05-02

申请号：US17975506

申请日：2022-10-27

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Sanjay RAMANUJAN ,  Rakesh KELKAR ,  Hari Krishnan SRINIVASAN ,  Karthik RAMAN ,  Hema Vishnu POLA ,  Sagar TANEJA ,  Mradul KARMODIYA

IPC: G06F9/50

CPC classification number: G06F9/5077 ,  G06F9/505 ,  G06F2209/501 ,  G06F2209/5019 ,  G06F2209/508

Abstract: The techniques disclosed herein enable systems to perform repeatable and iterative load testing and performance benchmarking for artificial intelligence models deployed in a cloud computing environment. This is achieved by utilizing load profiles and representative workloads generated based on the load profiles to evaluate an artificial intelligence model under various workload contexts. The representative workload is then executed by the artificial intelligence model utilizing available computing infrastructure. Performance metrics are extracted from the execution and analyzed to provide insight into various performance dynamics such as the relationship between latency and data throughput. In addition, load profiles and input datasets are dynamically adjusted to evaluate different scenarios and use cases enabling the system to automatically test the artificial intelligence model across diverse applications. Furthermore, by comparing various iterations of the artificial intelligence model, a quality gate can be constructed to enforce a consistent and high-quality user experience.

公开(公告)号：US20210011747A1

公开(公告)日：2021-01-14

申请号：US16509306

申请日：2019-07-11

Applicant: Microsoft Technology Licensing, LLC

Inventor： Willis LANG ,  Karthik RAMAN

IPC: G06F9/455 ,  G06F9/54 ,  G06F16/25

Abstract: A method of bridging a first database and a second database. The method includes maintaining a state machine representing a state of a virtual node in the first database, wherein the state of the virtual node conforms to a native protocol for native nodes of the first database, said native protocol of the first database differing from a foreign protocol of the second database. The method further includes receiving an incoming message for the virtual node from one of the native nodes according to the native protocol, and based on the incoming message, accessing the second database. The method further includes updating the state of the virtual node based on the incoming message according to the native protocol, and based on the state of the virtual node as updated, sending an outgoing message to one or more of the native nodes according to the native protocol.

公开(公告)号：US20190340265A1

公开(公告)日：2019-11-07

申请号：US15991223

申请日：2018-05-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Karthik RAMAN ,  Momin Mahmoud AL-GHOSIEN ,  Rajeev Sudhakar BHOPI ,  Madhan GAJENDRAN ,  Atul KATIYAR ,  Liang LI ,  Ankur Savailal SHAH ,  Pankaj SHARMA ,  Dharma SHUKLA ,  Hari Sudan SUNDAR ,  Shireesh Kumar THOTA

IPC: G06F17/30 ,  G06F11/20

Abstract: A data service may be distributed over a set of servers in order to provide a database with properties such as low latency, high availability, and support for various consistency levels. Presented herein is a particular architecture that promotes rapid provisioning to promote scalability and failover; adaptive load-balancing to accommodate fluctuations in demand; and resiliency in the event of various types of failure, such as network partitions or regional outages. For a service comprising a resource set, a container is provided that hosts a set of replicas of a partition, and that is assigned an allocation of computing capabilities of one or more servers. The resource set of the service may be distributed over the replicas of the container. Scalability is achieved by adding replicas to the container, and load-balancing may be provided by splitting, merging, or otherwise refactoring the partition to accommodate anticipated and unanticipated fluctuations in service demand.

公开(公告)号：US20240411658A1

公开(公告)日：2024-12-12

申请号：US18208192

申请日：2023-06-09

Applicant: Microsoft Technology Licensing, LLC

Inventor： Sanjay RAMANUJAN ,  Karthik RAMAN ,  Rakesh KELKAR ,  Pei-Hsuan HSIEH

IPC: G06F11/34 ,  G06Q30/0283

Abstract: This document relates to predicting performance of large artificial intelligence (LAI) models that are too large to be handled by a single computing device. One example can receive a sample workload for a trained LAI model and identify multiple nodes functioning as a cluster to instantiate an instance of the trained LAI model. The example can predict performance characteristics for accomplishing the sample workload on the cluster and can cause at least some of the predicted performance characteristics to be presented on a user interface.

公开(公告)号：US20190340291A1

公开(公告)日：2019-11-07

申请号：US15991880

申请日：2018-05-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Karthik RAMAN ,  Momin Mahmoud AL-GHOSIEN ,  Samer BOSHRA ,  Brandon CHONG ,  Madhan GAJENDRAN ,  Mikhail Mikhailovich KOLTACHEV ,  Orestis KOSTAKIS ,  Aravind Ramachandran KRISHNA ,  Liang LI ,  Jayanta MONDAL ,  Balachandar PERUMALSWAMY ,  Karan Vishwanath POPALI ,  Adrian Ilcu PREDESCU ,  Vivek RAVINDRAN ,  Ankur Savailal SHAH ,  Pankaj SHARMA ,  Dharma SHUKLA ,  Ashwini SINGH ,  Vinod SRIDHARAN ,  Hari Sudan SUNDAR ,  Krishnan SUNDARAM ,  Shireesh Kumar THOTA ,  Oliver Drew Leonard TOWERS ,  Siddhesh Dilip VETHE

IPC: G06F17/30

Abstract: Databases are often provided according to various organizational models (e.g., document-oriented storage, key/value stores, and relational database), and are accessed through various access models (e.g., SQL, XPath, and schemaless queries). As data is shared across sources and applications, the dependency of a data service upon a particular organizational and/or access models may become confining. Instead, data services may store data in a base representation format, such as an atom-record-sequence model. New data received in a native item format may be converted into the base representation format for storage, and converted into a requested format to fulfill data requests. Queries may be translated from a native query format into a base query format that is applicable to the base representation format of the data set, e.g., via translation into an query intermediate language (such as JavaScript) and compilation into opcodes that are executed by a virtual machine within the database engine.