Nutanix, Inc.

Lightbeam.ai, Inc.

Abhinay Nagpal

Himanshu Shukla

Bharat Kumar Beedu

Karan Gupta

Aditya Ramesh

Varun Kumar Arora

Cong Liu

Sujeet Mishra

Rahul Singh

Binny Sher Gill

Miao Cui

Venkata Vamsi Krishna Kothuri

Gaurav Poothia

Roger Sean Liao

Jianjun Wen

Shyama Sundar Duriseti

Zihong Lu

Srinivas Bandi Ramesh Babu

Vinayak Hindurao Khot

Harry Hai Yang

Biswa Ranjan Panda

Bharath Kumar Beedu

Arun Navasivasakthivelsamy

Deepthi Srinivasan

Weiheng Chen

Alexander J Kaufmann

Surendran Madheswaran

Jason Sims

Shuo Yang

Sourav Kumar

A dynamically-managed microservices platform. The microservices platform is configured to selectively accept admission of microservices and to selectively throttle microservices based on a continually-trained machine learning model. The system is configured to implement multiple microservice lifecycle strategies, where individual ones of the multiple microservice lifecycle strategies use a prediction model having long-term and short term demand predictions. One or another of the multiple microservice lifecycle strategies are invoked at different times under different conditions. Under a first set of conditions, a prediction model is used to select a first strategy to admit or throttle a microservice based upon long-term or short-term demand predictions. Under a second set of conditions, the prediction model is used to select a different strategy to admit or throttle a microservice. The prediction model is continually trained such that new sets of observations and new sets of predicted outputs are codified into the machine learning model.

Microservice admission control based on learned demand predictions

Microservice throttling based on learned demand predictions

Datasource processors may communicate with an artificial intelligence (AI) engine in order to generate, in parallel, object summaries from datasource objects received from datasources. Each object summary may include an object identifier, one or more local entities, and a mapping from each of the one or more local entities to one or more attributes. A global entity resolver may augment the object summaries by mapping each of the local entities to a global entity. Policy engines may evaluate, in parallel, the object summaries with respect to a security and/or privacy policy. If a security and/or privacy violation is recognized, a remediation measure may be applied in connection with the datasource object for which the security and/or privacy violation exists.

Method for maintaining privacy and security of data

In accordance with some aspects of the present disclosure, an apparatus is disclosed. The apparatus includes a processor and a memory, wherein the memory includes programmed instructions that when executed by the processor, cause the apparatus to receive a request to join a plurality of entity data structures using a first join order, determine a first performance cost of the first join order, determine a second performance cost of a second join order, determine whether the second performance cost is lower than the first performance cost, in response to determining that the second performance cost is lower than or exceeds the first performance cost, select the second join order or the first join order, respectively, join the plurality of entity data structures using the selected join order, and send the joined plurality of entity data structures.

Intelligent query planning for metric gateway

A method for time series analysis of time-oriented usage data pertaining to computing resources of a computing system. A method embodiment commences upon collecting time series datasets, individual ones of the time series datasets comprising time-oriented usage data of a respective individual computing resource. A plurality of prediction models are trained using portions of time-oriented data. The trained models are evaluated to determine quantitative measures pertaining to predictive accuracy. One of the trained models is selected and then applied over another time series dataset of the individual resource to generate a plurality of individual resource usage predictions. The individual resource usage predictions are used to calculate seasonally-adjusted resource usage demand amounts over a future time period. The resource usage demand amounts are compared to availability of the resource to form a runway that refers to a future time period when the resource is predicted to be demanded to its capacity.

Method for forecasting distributed resource utilization in a virtualization environment

Systems and methods for scheduling storage management tasks over predicted user tasks in a distributed storage system. A method commences upon receiving a set of historical stimulus records that characterize management tasks that are run in the storage system. A corresponding set of historical response records comprising system metrics associated with execution of the system tasks is also received. A learning model is formed from the stimulus records and the response records and formatted to be used as a predictor. A set of forecasted user tasks is input as new stimulus records to the predictor to determine a set of forecasted system metrics that would result from running the forecasted user tasks. Management tasks are selected so as not to impact the forecasted user tasks. Management tasks can be selected based on non-contentions resource usage between historical management task resource usage and predictions of resource usage by the user tasks.

Dynamic scheduling of distributed storage management tasks using predicted system characteristics

Systems for cluster computing. A method for detection and remediation of degraded nodes in a cluster commences upon measuring operational aspects of the nodes in the cluster, then determining, based on the measurements and other factors, a suspect set of nodes comprising one or more suspect nodes from the nodes in the cluster that have measurements that are determined to be outliers with respect to remaining nodes that are determined not to be the outliers. A density-based spatial clustering analysis is performed over the suspect set and remediation actions are initiated when results of the density-based spatial clustering analysis identifies a suspect node as being a degraded node.

Detection of outlier nodes in a cluster

A system and method for dynamically adjusting the amount of memory allocated to a virtual machine includes generating, by a memory resizing system, a current memory usage profile for the virtual machine. The memory resizing system and the virtual machine are part of a virtual computing system and the current memory usage profile is generated by mapping, as a function of time, memory usage information from the virtual machine. The system and method also include computing an upper baseline based upon a peak memory usage in the current memory profile, updating an initial memory allocation of the virtual machine based upon the upper baseline and a predetermined threshold for obtaining an initial revised memory allocation, determining a moving average of memory usage from a historical memory usage profile, and updating the initial revised memory allocation based upon the moving average of memory usage for obtaining a final revised memory allocation.

System and method for memory resizing in a virtual computing environment

Systems for distributed data storage. A method embodiment commences upon capturing a history of storage I/O activity over a recent time period. A predictive model is derived from the captured storage I/O activity, and the predictive model is then used for predicting future storage I/O activity. A set of snapshot planning parameters comprising objectives (e.g., to minimize costs or to maximize likelihood completing a snapshot activity by a prescribed time) and/or constraints (e.g., don't wait more than one day to start a snapshot) are applied to the predicted storage I/O characteristics to generate a set of feasible snapshot plans. One of the feasible snapshot plans is selected for scheduling so as to begin the planned snapshot activity at a prescribed time. The snapshot planning parameters are normalized based on the predicted storage I/O characteristics.

Dynamic data snapshot management using predictive modeling

Systems for alerting in computing systems. A method commences by defining a plurality of analysis zones bounded by respective ranges of system metric values, which ranges in turn correspond a plurality of system behavior classifications. System observations are taken while the computing system is running. A system observation comprising a measured metric value is classified into one or more of the behavior classifications. Based on the classification, one or more alert analysis processes are invoked to analyze the system observation and make a remediation recommendation. An alert or remediation is raised or suppressed based on one or more zone-based analysis outcomes. An alert is raised when anomalous behavior is detected. The system makes ongoing observations to learn how and when to classify a measured metric value into normal or anomalous behaviors. As changes occur in the system configuration, the analysis zones are adjusted to reflect changing bounds of the zones.

Computing system monitoring

Systems for distributed resource system management. A first computing system operates in a first computing environment. A predictive model is trained in the first computing environment to form a trained resource performance predictive model that comprises a set of trained model parameters to capture at least computing and storage IO parameters that are responsive to execution of one or more workloads that consume computing and storage resources in the first computing environment. When the trained resource performance predictive model is deployed to a second computing environment, various computing system configuration differences, and/or workload differences and/or other differences between the first computing environment and the second computing environment are detected and measured. Responsive to the detected differences and/or measurements, some of the trained resource performance predictive model parameters are modified to adapt the trained resource performance predictive model to any of the detected and/or measured characteristics of the second computing environment.

Adapting a pre-trained distributed resource predictive model to a target distributed computing environment

Resource allocation techniques for distributed data storage. A set of distributed storage system historical resource usage measurements are collected and stored using distributed storage system measurement techniques. The resource usage metrics are associated with and/or derived from processing entities in the distributed storage computing system. An analysis module determines a training window time period corresponding to a portion of the collected distributed storage system historical resource usage measurements. The training window time period is determined so as to provide an earlier time boundary and a later time boundary that defines a periodically recurring portion of the distributed storage system historical resource usage measurements. A latest cycle of those periodically recurring measurements are then used to train a predictive model, which in turn is used to produce distributed storage system predicted resource usage characteristics. Resource allocation decisions are made based at least in part on predictions from the trained predictive model.

Dynamic resource distribution using periodicity-aware predictive modeling

Systems and methods for 'what-if' scenario planning of a distributed data storage system. A scenario planning engine has a user interface to facilitate user interactions to describe 'what if' scenarios. A method comprises steps to collect system performance measurements pertaining to measurable characteristics of the distributed storage system. A predictive model is generated and formatted for use as a predictor of one or more predictive model parameters that are derived from the collected system performance measurements and/or any calculated predictions and/or correlations. A user can vary a set of scenario input parameters so as to characterize one or more &#x201c;what if&#x201d; scenarios. The user-defined scenario input parameters are formatted and used as predictive model inputs. The predictive model is used to simulate predicted system performance parameters corresponding to respective &#x201c;what-if&#x201d; planning scenarios. A user interface is provided to present a graphical depiction of predicted system performance corresponding to the scenarios.

Growing community of inventors

San Jose, CA, United States of America

Abhinay Nagpal