Microsoft Technology Licensing, LLC

Other

Neeraj Kumar Singh

Arun Upadhyaya Kishan

Hari R Pulapaka

Neal Robert Christiansen

Rajsekhar Das

Kenneth Dean Johnson

James A Schwartz, Jr

Tristan Anthony Brown

Jason Stewart Wohlgemuth

Youssef M Barakat

Pedro Miguel Teixeira

Yanran Hao

Jeremiah S Samli

James A Schwartz Jr

Youssef Maged Barakat

The techniques disclosed herein enable file systems to streamline operations on cached file data. This is accomplished by utilizing a direct access path and an optimization flag that indicates the status of an external lock for a given file data. External locks can be utilized to lock some or all of a file to prevent unexpected changes during an operation and ensure consistency in file data. A direct access path is a file system method that enables a thread to directly access the storage locations defined by a cache map structure which reduces latency by omitting determinations of external lock conflicts. However, this omission must be performed safely, that is, when the external lock is inactive. By checking the optimization flag prior to executing an operation, the file system can determine whether it is safe to omit the determination of external lock conflicts thereby minimizing latency.

Streamlined file system memory input/output operations

The system described herein introduces a file system operation that enables a file system to delete a directory tree without the overhead associated with opening each file in the directory tree, marking the file for deletion, and closing the file. Accordingly, the file system is able to delete directories and files in the directory tree independent of communicating with, and being transparent to, filter drivers in the operating system. The file system operation is implemented via a directory tree delete attribute included in a request for deletion of a directory tree. The file system can perform the file system operation in a foreground manner or in a deferred manner based on the directory tree delete attribute respectively specifying foreground deletion or deferred deletion. By operating on files and directories in a single invocation, the file system can optimize overheads related to security checks and data transfer across a user-to-kernel boundary.

Directory tree delete as a supported file system operation

The techniques disclosed herein enable systems to efficiently interface with zoned namespace (ZNS) storage devices through a specialized management entity. To achieve this, the management entity receives write requests from a file system containing data intended for storage at the ZNS device. In response, the management entity selects a zone from the ZNS device to write the file data to. Accordingly, the file data is written by appending the file data to the zone at a location indicated by a write pointer. When the write operation is completed, the offset of the file data within the zone is observed and recorded by the file system in file metadata. In contrast to typical systems which allocate locations at the storage device prior to writing, appending file data and then recording the location enables improved efficiency in file system operations. Namely, that write operations can be issued to the ZNS device non-serially.

File system improvements for zoned storage device operations

The system described herein introduces a cache that a file system uses to determine, for a current object, if the process to merge different types of access control information into merged access control information has already been performed for a previous object. Stated alternatively, the file system uses the cache to determine whether a current object being processed for storage has the same combination of access control information as a previous object that has already been processed for storage. If the current object has the same combination of access control information as the previous object, the file system is able to associate merged access control information for the previous object with the current object via the use of a pointer. Consequently, the file system avoids having to perform the resource-intensive process of merging the different types of access control information for the current object.

Cache for identifiers representing merged access control information

The techniques disclosed herein enable systems to store file system metadata on append-only storage devices by the introduction of a metadata layout and relative references. To achieve this, a system analyzes a file metadata structure to select an approach to storing the metadata structure on the storage device. If the metadata structure is above a threshold size, it is separated into layers that are then appended to the storage device from lowest to highest. An offset is retrieved for appended layers and provided to upper-level layers that refer to them until the full structure is stored. For storing smaller pieces of metadata that refer to each other, the system configures upper-level nodes with relative references that express the location of metadata relative to the node. This enables atomic write operations for smaller metadata structures and/or portions of larger structures.

File system metadata layout for append-only storage

A processing system manages an ordered set of hierarchical data structures representing snapshots that define the state of a filesystem at different points in time. The data structures include nodes that store strong references, which can be utilized to read or write data, or weak references that can be only utilized to read data. In order to create a new snapshot, a root node is created for a new data structure representing the new snapshot by copying the root node of the data structure representing an active view of the filesystem. Any strong references stored in the copy of the root node are then changed to weak references. Snapshotting operations can then be performed with respect to the new snapshot utilizing the weak references stored in the root node of the new data structure.

Performing snapshotting operations using data structures storing weak references

A system for exception handling is configured to, in response to detection of an exception during a function call, search for an exception handler to handle the detected exception by unwinding a stack across a plurality of frames. A binary includes functions associated with one of a first application binary interface (ABI) or a second ABI. The stack includes a transition frame created between frames of the first ABI and the second ABI during execution of the binaries. The system is configured to detect the transition frame in the stack when encountering a change from a frame of one ABI to a frame of another ABI, and translate an interface context therebetween to handle the exception.

Stack frame unwinding for exception handling

One or more techniques and/or systems are provided for suspending logically related processes associated with an application, determining whether to resume a suspended process based upon one or more wake policies, and/or managing an application state of an application, such as timer and/or system message data. That is, logically related processes associated with an application, such as child processes, may be identified and suspended based upon logical relationships between the processes (e.g., a logical container hierarchy may be traversed to identify logically related processes). A suspended process may be resumed based upon a set of wake policies. For example, a suspended process may be resumed based upon an inter-process communication call policy that may be triggered by an application attempting to communicate with the suspended process. Application data may be managed while an application is suspended so that the application may be resumed in a current and/or relevant state.

Managing processes within suspend states and execution states

Heterogeneous thread scheduling techniques are described in which a processing workload is distributed to heterogeneous processing cores of a processing system. The heterogeneous thread scheduling may be implemented based upon a combination of periodic assessments of system-wide power management considerations used to control states of the processing cores and higher frequency thread-by-thread placement decisions that are made in accordance with thread specific policies. In one or more implementations, a system workload context is periodically analyzed for a processing system having heterogeneous cores including power efficient cores and performance oriented cores. Based on the periodic analysis, cores states are set for some of the heterogeneous cores to control activation of the power efficient cores and performance oriented cores for thread scheduling. Then, individual threads are scheduled in dependence upon the core states to allocate the individual threads between active cores of the heterogeneous cores on a per-thread basis.

Heterogeneous thread scheduling

One or more techniques and/or systems are provided for suspending logically related processes associated with an application, determining whether to resume a suspended process based upon a wake policy, and/or managing an application state of an application, such as timer and/or system message data. That is, logically related processes associated with an application, such as child processes, may be identified and suspended based upon logical relationships between the processes (e.g., a logical container hierarchy may be traversed to identify logically related processes). A suspended process may be resumed based upon a wake policy. For example, a suspended process may be resumed based upon an inter-process communication call policy that may be triggered by an application attempting to communicate with the suspended process. Application data may be managed while an application is suspended so that the application may be resumed in a current and/or relevant state.

The auto caddy of the present invention may include a main housing having one or more receptacles for holding drinks or other items, and may include one or more attachment members having one or more sets of openings through which a vehicle headrest seat post may extend on installation with two points of contact, which may increase the stability of the auto caddy, especially during sudden movement of a vehicle. The auto caddy may include optional components for subdividing receptacles, one or more hooks from which a tray may be suspended, a strap for securing the tray, and slots for suspending a trash receptacle such as a plastic grocery bag. The auto caddy may also include offset sides for manufacturing cost efficiency, in which case offset washers (which may be hook-shaped) may be used at installation to maximize vertical and horizontal alignment and stability of the auto caddy.

Automobile caddy

The safety sheet of the present invention may include a bed sheet with sleeves along one or more sides. The sleeves may be continuous or slotted and may accommodate inserts constructed of a material soft enough to avoid injury yet sturdy enough to provide an effective barrier to lateral motion of a bed's occupant. The safety sheet may include solid or hollow inserts. Portability of the safety sheet may be maximized by the use of inflatable/deflatable inserts. Inserts may vary in size and shape, and the sleeves may vary in size to accommodate a range of insert sizes. Alternatively, the sleeves may be stuffed with soft materials such as socks or other clothing when inserts are unavailable. The safety sheet may be reversed with inserts in place for aesthetic and comfort purposes or without inserts to hide the sleeves when inserts are no longer needed.

Growing community of inventors

Seattle, WA, United States of America

Neeraj Kumar Singh