Qumulo, Inc.

Thomas Scott Urban

Michael Patrick Kirby

Steven Henry Haber

Thomas R Unger

Noah Trent Nelson

Robert Edward Gebert

Peter John Godman

Kevin Ross O'Neill

Nicholas J Wilson

Edward Brow

Michael Adam Krasnow

Graeme Williams

Benjamin Gregory Reeves

Alan Francisco Delgado Duran

Austin Elery Voecks

Michael R Fitz

Boyu Zhang

Aaron Passey

Neal Thomas Fachan

Justin Husted

Patrick Jakubowski

Philip Ernst Taron

John Brazel

Zacharie Lamont Kirsch

Robert Gebert

Embodiments are directed to workload allocation for file system maintenance. A file system that includes storage nodes and snapshots may be provided such that each snapshot may be associated with a plurality of data blocks. If snapshots are deleted further actions may be performed, including: determining the dead blocks associated with the deleted snapshots such that each dead block may be a data block that may be unassociated with undeleted snapshots; adding the plurality of dead blocks to dead trees located on the storage nodes; determining an urgency score based on a workload model and file system metrics; determining delete tasks based on the urgency score; determining a portion of the storage nodes based on a number of delete tasks; and executing the delete tasks on the portion storage nodes to delete the dead blocks to return storage capacity to the file system.

Workload allocation for file system maintenance

Embodiments are directed to sharing namespaces across file system clusters. A file in a spoke file system may be determined based on a command provided to the spoke file system such that the file may be associated with an inode mask. Data blocks associated with the file may be determined based on the command and the inode mask such that the data blocks may be absent from the spoke file system. Requests for leases may be generated based on the absent data blocks such that each lease request corresponds to a portion of the absent data blocks Employing the leases provided by a hub file system to: copy the absent data blocks from the hub file system where each portion of absent data blocks may be associated with a lease; updating the inode mask to include the leases and each copied portion of absent blocks.

Sharing namespaces across file system clusters

Various embodiments of a system and associated method for an electrically efficient motor including two parallel shafts, one or more rotors including a plurality of alternating permanent magnets mounted on each shaft, and an electromagnet operable for switching polarities in order to keep the one or more rotors, and consequently the two parallel shafts, in rotational motion.

Dual-rotor electrically efficient motor

A software and hardware facility persistently maintains metrics on directories at different levels within a tree of a filesystem. The facility hierarchically aggregates attributes of files contained by directories and stores them as metric values in inode date of each directory within a tree. The stored metric values represent summed or otherwise aggregated data from the descendant directories and files. The metric values are utilized to provide representative compositional samplings of data in the filesystem tree structure. Based on the metric value in its inode data, each directory is weighted in a manner that determines the likelihood that each file sample is taken from that directory.

Fair sampling in a hierarchical filesystem

Embodiments are directed to managing data in a file system. An object from the file system that has parent objects may be provided. A snapshot in a current epoch may be generated such that the first snapshot may be based on the object and descendants of the object. A coverage set may be provided for the object that references the snapshot and also references each other snapshot that includes the parent objects. Read-only access to a version of the object may be provided based on a correspondence of the version and a snapshot referenced by the coverage set of the object. A coverage engine compares the update to a coverage update epoch (cue) associated with the parent objects. The coverage engine updates coverage sets of the parent objects based on grandparents of the object.

Managing per object snapshot coverage in filesystems

Embodiments are direct to managing file systems. Alternate data streams (ADSs) of an object in a file system may be modified based on a request from a client and metrics associated with the ADSs may be modified. Values for reconcile fields associated with the object may be set based on the modified metrics such that the object with the modified ADSs may be included in a reconcile list. And, such that an acknowledgment of the request may be provided to the client. A reconcile engine may determine a parent object of the object. The object may be reconciled and the parent object may be placed on the reconcile list for reconciling in turn.

Aggregating alternate data stream metrics for file systems

Embodiments are directed to managing data in a file system. A query may be provided to determine characteristics associated with a file system and a sampling model. The sampling model may be employed to determine objects in the file system based on a traversal of the file system. The sampling model may be employed to determine metrics associated with the alternate data streams (ADSs) included in the objects such that each of the objects that includes a separate main data stream and the ADSs may be associated with data blocks and the ADSs may each be associated with other data blocks. The sampling model and the query may be employed to sample the objects to provide partial results such that the sampling may be distributed between the objects based on the sampling model and the metrics. A result to the query may be provided based on the partial results.

Fair sampling of alternate data stream metrics for file systems

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

A facility for snapshot space accounting for a storage system, such as a filesystem is disclosed. The facility enables users to quickly and easily determine the amount of storage space that would be released or recovered if a snapshot were to be purged. The facility may work in conjunction with, or as part of, a snapshot service. The facility maintains an expiration data structure and a count data structure and uses these data structures in implementing the disclosed snapshot space accounting techniques. The expiration data structure represents the life cycle of each snapshot element maintained by the facility while the count data structure represents, for pairs of snapshots, the size of the information stored in the snapshot data that expired and that spans the corresponding pair of snapshots.

Space accounting for storage system snapshots

A software and hardware facility persistently maintains metrics on directories at different levels within a tree of a filesystem. The facility hierarchically aggregates attributes of files contained by directories and stores them as metric values in each directory within a tree. The stored values represent summed or otherwise aggregated data from the descendant directories and files. The metric values represent aggregated attributes such as total space consumed by a directory and all the descendant directories and files, total number of files within a directory, total data blocks used by a directory and its descendant directories and data files, etc.

Growing community of inventors

Seattle, WA, United States of America

Thomas Scott Urban