Microsoft Technology Licensing, LLC

Emily Nicole Wilson

Mehmet Iyigun

Yevgeniy Bak

Kirsten Valery Stark

Patrick L Stemen

Brian E King

Neel K Jain

Vasilios Karagounis

Sushu Zhang

James A Schwartz, Jr

Alain Franck Gefflaut

Nicholas Stephen Judge

Andrew D Rogers

Vladimir Sadovsky

Arun Upadhyaya Kishan

Hari R Pulapaka

Robin Andrew Alexander

Shira Weinberg

Janet Lynn Schneider

Jon Robert Berry

Gurpreet Virdi

Paresh J Maisuria

Jared Adam Brown

Qian Liu

Peter Hanpeng Jiang

Mohammed Nashaat Soliman

William Jefferson Westerinen

Cenk Ergan

Michael Richard Fortin

Dan Teodosiu

Michael James Zwilling

Mark Joseph Zbikowski

Hanumantha Rao Kodavalla

Scott Chao-Chueh Lee

Nathan Steven Obr

John M Parchem

Innokentiy Basmov

Clark David Nicholson

James George Cavalaris

Shen Wang

Scott Daniel Anderson

David John Linsley

Alex Mark Semenko

Rajeev Y Nagar

Jason Stewart Wohlgemuth

Richard Allen Pletcher

Brett Kenneth Dodds

James Anthony Schwartz, Jr

Therron Powell

Daniel Sebastian Berger

Gaurav Jagtiani

Kinshuman Kinshumann

Malcolm James Smith

Michael J Grass

Dean L DeWhitt

Naga Govindaraju

Yuri Dotsenko

Alex Bendetov

Surenda Verma

John A Strange

Andrey Shedel

James Aaron Holmes

Binit Ranjan Mishra

Ramakoti R Bhimanadhuni

Minsang Kim

Aacer Hatem Daken

Cody D Hartwig

Steven Adrian West

Emma Sutherland Boyd

Pallavi Baral

Bhuvan Malladihalli Shashidhara

Emily Cara Clemens

John Robert Berry

Jasmine Grace Schlichting

Michael Wayne Stephenson

Farah Farzana

Sebastien Nathan R Levy

Josh Charles Moore

Ahu Oral

Arhatha Bramhanand

Juan Arturo Herrera Ortiz

Aaron M Farmer

Christina Margaret Tobias

Charlotte Gauchet

Troy E Shaw

Vijaybalaji Madhanagopal

Christina Marianne Curlette

Mukhtar Ahmed

Sri Harsha Kanukuntla

Drew Douglas Cross

Sharon Scarlet Tang

Jennifer Marie Bourlier

Terence Kwok Tak Chan

Raz Meir Aloni

Kirsten V Stark

Neel Jain

The disclosure herein describes training and using an uncorrectable error (UE) state prediction model based on telemetry error data. Sets of UE state labels and non-UE state labels are generated from a first set of collected telemetry data, wherein the UE state labels each reference a UE and telemetry data of an interval prior to the referenced UE. Statistical features are extracted from telemetry data of the sets of UE state labels and non-UE state labels, and the extracted statistical features are used to train a UE state prediction model. A second set of collected telemetry data is obtained, and a UE event is predicted based on the second set of collected telemetry data using the trained UE state prediction model. A preventative operation is performed on a memory page of the system based on the predicted UE event, whereby the predicted UE event is prevented from occurring.

Training and using a memory failure prediction model

In-place recovery of fatal system errors at virtualization hosts. A device identifies an occurrence of a fatal system error in the first instance of a host operating system (OS) executing in a computer system. The device determines to perform an in-place recovery for the fatal system error. The device performs the in-place recovery, including pausing the execution of a virtual machine (VM) by the first instance of the host OS, preserving a state of the VM within system memory of the computer system, and resuming the execution of the VM by a second instance of the host OS executing in the computer system based on the state of the VM that is preserved within the system memory of the computer system.

In-place recovery of fatal system errors at virtualization hosts

Pooling computing resources based on inferences about a plurality of hardware devices. The method includes identifying inference information about the plurality of devices. The method further includes based on the inference information optimizing resource usage of the plurality of hardware devices.

User presence prediction driven device management

Computing resource management of computing devices

Fast computer startup is provided by, upon receipt of a shutdown command, recording state information representing a target state. In this target state, the computing device may have closed all user sessions, such that no user state information is included in the target state. However, the operating system may still be executing. In response to a command to startup the computer, this target state may be quickly reestablished from the recorded target state information. Portions of a startup sequence may be performed to complete the startup process, including establishing user state. To protect user expectations despite changes in response to a shutdown command, creation and use of the file holding the recorded state information may be conditional on dynamically determined events. Also, user and programmatic interfaces may provide options to override creation or use of the recorded state information.

Fast computer startup

In order to provide a more efficient persistent storage device, one or more long-term storage media are included along with a non-volatile memory. In one embodiment, one portion of the non-volatile memory is used as a write buffer and a read cache for writes and reads to the long-term storage media. Interfaces are provided for controlling the use of the non-volatile memory as a write buffer and a read cache. Additionally, a portion of the non-volatile memory is used to provide a direct mapping for specified sectors of the long-term storage media. Descriptive data regarding the persistent storage device is stored in another portion of the non-volatile memory.

Non-volatile memory cache performance improvement

Controlling background activity in a computing device or system during a low-power mode is described. In some example techniques, when a computing device or system is in a low power mode, a determination is made whether to block one or more trigger events from causing an activation of one or more respective background task operations. Based at least in part on the determination, at least one trigger event may be allowed to cause an activation of a respective background task operation during the low power mode.

Selective blocking of background activity

Embodiments of the disclosure provide access to data in a compressed container through dynamic redirection, without storing decompressed data in persistent memory. The compressed container is stored in a first portion of memory. User data and reference files, with redirect pointers, for accessing corresponding files in the compressed container are stored in a second portion of memory. A command to access data is detected by a computing device. The redirect pointer in the reference file associated with the command redirects access to the corresponding compressed version of data stored in the compressed container. The corresponding accessed compressed version of data is decompressed on the fly and provided in response to the command without storing the decompressed data in persistent memory. Some embodiments provide integrity protection to validate the data coming from the compressed container.

Accessing data in a compressed container through dynamic redirection

Processes for identifying and recovering a lost transient storage device are provided. In some processes, information regarding the owner of the device is obtained. The device ownership information may be stored on a remote service with which the device is registered and/or may be stored on the device itself. In one process, the remote service provides the device with customized device-executable code when the device is registered. The device may also contain information regarding trusted systems. The process includes obtaining status information indicating whether a device is lost when the device is connected to a host system. In some processes, the status is determined by a remote service. In other processes, the status is determined by the device. If the device is lost then a device recovery plan is executed. Portions of a device recovery plan may be executed on the remote service, the host system, and/or the device.

Systems for finding a lost transient storage device

Growing community of inventors

Seattle, WA, United States of America

Emily Nicole Wilson