Qumulo, Inc.

Microsoft Technology Licensing, LLC

Patrick Jakubowski

Thomas Gregory Rothschilds

Philip Ernst Taron

Francislav Petrov Penov

Peter John Godman

John E Brezak

Wissam S Kazan

Edward Carpenter

Remi Bernotavicius

Duncan Robert Fairbanks

Zexuan Wang

David A Nichols

David Allison Bennett

Thomas Scott Urban

Thomas R Unger

Albert Peter Hwang

Felipe Luis Naranjo

Oded Yehuda Shekel

Ronakkumar N Desai

Adam D Stritzel

Gyorgy K Schadt

Ciprian Gociman

Mona Akmal

Shazaan Bahrainwala

Joerg Christof Zender

Porter Michael Smith

György K Schadt

Chin Hung Lam

Conner Saltiel Hansen

Hanqing Zhang

David Patrick Rogers, Iii

Sarita Gupta

Nicholas Malaguti

Amandeep S Ghag

A file system with distributed resource caching that includes cache volumes and agents that may be associated with clients of the file system may be provided. A cache allocation for each agent may be determined based on a capacity of the cache volumes and a number of the agents such that each cache allocation is associated with tokens that each represents a reserved portion of free space in the cache volumes. Storage jobs may be provided to the agents. Data associated with the storage jobs may be stored in the cache volumes. The cache allocation for each agent may be reduced based on the data stored for each agent.

Distributed resource caching by reallocation of storage caching using tokens and agents with non-depleted cache allocations

Embodiments are directed to a file system engine that provides a file system that includes a plurality of blocks on a file storage tier with portion of the blocks associated with a cache storage tier. A cache engine provides heat extents that include a heat score and a run length value such that the heat extents are represent activities associated with the blocks. Heat extents associated with file system activities are determined based on a position of the blocks that corresponds with the run length values of the heat extents and sectors on the file storage tier. Heat scores associated with the heat extents may be modified based on the activities and distribution models to conform the heat extents with the distribution models. Blocks associated with heat scores that are less than a threshold value provided by the distribution models may be disassociated from the cache storage tier.

File system cache tiers

A facility for managing filesystem object storage quotas (i.e., size limits) in a storage environment is disclosed. The facility enables users to establish, modify, and remove quotas on directories and files within a filesystem. Each quota acts as a soft limit on the size of the associated filesystem object, including any child objects of the filesystem object. The facility improves the speed at which the system can test for and identify violations of quotas established for individual filesystem objects by using aggregation and reconciliation techniques rather than constantly traversing a filesystem in its entirety to test for violations of quotas.

Managing storage quotas in a shared storage system

Embodiments are directed to managing data in a file system over a network. A file system that includes a master node and client nodes may be provided. A master quorum value and a client quorum value having the same value may be provided. A profile catalog associated with the master node that includes parameters may be provided. Profile registers associated with the client nodes may be provided. Change actions may be executed on each client node based on change information provided by the master node. In response to errors, access to the file system may be suspended; the master quorum value may be modified to indicate that the file system is out of quorum; recovery actions may be executed; the client quorum value at each client node may be modified to correspond with the master quorum value; and access to the file system may be restored.

Change notification in distributed file systems

Mechanisms for synchronizing an object set with a remote data store are often performed at a particular frequency, e.g., once per hour or day. However, the objects of the object set may have different priorities, and it may be advantageous to synchronize higher-priority objects more often than regular-priority objects. The synchronization mechanisms may also differ (e.g., high-priority object synchronization may be direct and/or holistic, while regular-priority object synchronization may be differential, cached, and/or involving version and/or conflict resolution). Additionally, a resource-based threshold may be applied to the high-priority objects (e.g., a bandwidth cap) in order to reduce resource exhaustion, and high-priority objects that are not synchronized within the threshold may be synchronized with the regular-priority objects. These techniques may be particularly advantageous for synchronizing objects comprising an application state of applications of current or recent usage by a user, where application state 'staleness' is acutely visible to the user.

Opportunistic, priority-based object synchronization

Techniques for data synchronization policies are described. In one or more implementations, techniques may be employed to set data synchronization ('sync') policies for devices in a data sync environment. The sync policies specify parameters for sync operations in the sync environment, such as how frequently data sync operations are performed, what types of data are synced to particular devices, how frequently particular types of data are synced, and so on. In implementations, the sync policies consider the number of devices that are participating in a sync environment and attributes of the devices in specifying parameters for sync operations. Data can be synchronized among devices in the sync environment based on the sync policies.

Data synchronization policies

Social network service synchronization techniques are described. In an implementation, a determination is made by a client that a browser has been used to navigate to a website. A prompt is displayed by the client, responsive to the determination, that is selectable to cause data that describes activities that are performable in conjunction with the website to be communicated to a social network service to be stored in conjunction with a user account of the user at the social network service.

Social network service synchronization

A method described herein includes receiving data that identifies a web page, wherein the data that identifies the web page is desirably displayed to a first individual and resolving the web page to generate a markup language document, wherein the markup language document comprises unstructured data. The method also includes extracting portions of the markup language document and generating a structured data object, wherein the structured data object includes the portions of the markup language document. The method further includes causing a summary of the web page to be displayed to the first individual, wherein the summary of the web page is based at least in part upon the structured data object.

Generating structured data objects from unstructured web pages

Growing community of inventors

Seattle, WA, United States of America

Patrick Jakubowski