Abstract: Methods and apparatus for buffer allocation and memory management are described. A plurality of buffers of a memory may be allocated, by a memory controller, with the buffers having variable sizes. The memory controller may maintain a mapping table that associates each of a plurality of access keys to a respective one of a plurality of page addresses of a plurality of pages of the memory. Each of the buffers may respectively include one or more contiguous pages of the plurality of pages of the memory. Each page of the plurality of pages may include one or more blocks of the memory.

Abstract: Techniques are described in which a device, such as a network device, compute node or storage device, is configured to utilize a work unit (WU) stack data structure in a multiple core processor system to help manage an event driven, run-to-completion programming model of an operating system executed by the multiple core processor system. The techniques may be particularly useful when processing streams of data at high rates. The WU stack may be viewed as a stack of continuation work units used to supplement a typical program stack as an efficient means of moving the program stack between cores. The work unit data structure itself is a building block in the WU stack to compose a processing pipeline and services execution. The WU stack structure carries state, memory, and other information in auxiliary variables.

Abstract: A new processing architecture is described that utilizes a data processing unit (DPU). Unlike conventional compute models that are centered around a central processing unit (CPU), the DPU that is designed for a data-centric computing model in which the data processing tasks are centered around the DPU. The DPU may be viewed as a highly programmable, high-performance I/O and data-processing hub designed to aggregate and process network and storage I/O to and from other devices. The DPU comprises a network interface to connect to a network, one or more host interfaces to connect to one or more application processors or storage devices, and a multi-core processor with two or more processing cores executing a run-to-completion data plane operating system and one or more processing cores executing a multi-tasking control plane operating system. The data plane operating system is configured to support software functions for performing the data processing tasks.

Abstract: A highly-programmable access node is described that can be configured and optimized to perform input and output (I/O) tasks, such as storage and retrieval of data to and from storage devices (such as solid state drives), networking, data processing, and the like. For example, the access node may be configured to execute a large number of data I/O processing tasks relative to a number of instructions that are processed. The access node may be highly programmable such that the access node may expose hardware primitives for selecting and programmatically configuring data processing operations. As one example, the access node may be used to provide high-speed connectivity and I/O operations between and on behalf of computing devices and storage components of a network, such as for providing interconnectivity between those devices and a switch fabric of a data center.

Abstract: A new processing architecture is described in which a data processing unit (DPU) is utilized within a device. Unlike conventional compute models that are centered around a central processing unit (CPU), example implementations described herein leverage a DPU that is specially designed and optimized for a data-centric computing model in which the data processing tasks are centered around, and the primary responsibility of, the DPU. For example, various data processing tasks, such as networking, security, and storage, as well as related work acceleration, distribution and scheduling, and other such tasks are the domain of the DPU. The DPU may be viewed as a highly programmable, high-performance input/output (I/O) and data-processing hub designed to aggregate and process network and storage I/O to and from multiple other components and/or devices. This frees resources of the CPU, if present, for computing-intensive tasks.

Abstract: Methods and apparatus for memory management are described. In a disclosed embodiment, a system has a first and a second processor, with each processor able to access a memory system. A first work unit is received for execution by the first processor, with the memory system being accessed. A second work unit is generated for execution by a second processor upon execution of a first work unit. Only after the memory system is updated does processing of the second work unit by the second processor occur. This work unit message based ordering provides relay consistency for memory operations of multiple processors.

Abstract: A method and apparatus are provided for navigating through a media object collection using a mobile device. Users navigate to the target media objects by repeatedly specifying filters. After a user specifies a filter, the filter is applied in combination with all previously specified filters to produce a filtered set of media objects. After a filter is applied, a display level is selected for each hierarchical dimension for which the media objects have metadata. The selection of the display level may be based on the number of distinct values that the media objects in the filtered set have for each level of the hierarchical dimension. Single-action controls are then displayed for each of the values that the media objects in the filtered set have for the selected display level.

Abstract: Methods and apparatus for buffer allocation and memory management are described. A plurality of buffers of a memory may be allocated, by a memory controller, with the buffers having variable sizes. The memory controller may maintain a mapping table that associates each of a plurality of access keys to a respective one of a plurality of page addresses of a plurality of pages of the memory. Each of the buffers may respectively include one or more contiguous pages of the plurality of pages of the memory. Each page of the plurality of pages may include one or more blocks of the memory.

Abstract: A method and apparatus are provided for navigating through a media object collection using a mobile device. Users navigate to the target media objects by repeatedly specifying filters. After a user specifies a filter, the filter is applied in combination with all previously specified filters to produce a filtered set of media objects. After a filter is applied, a display level is selected for each hierarchical dimension for which the media objects have metadata. The selection of the display level may be based on the number of distinct values that the media objects in the filtered set have for each level of the hierarchical dimension. Single-action controls are then displayed for each of the values that the media objects in the filtered set have for the selected display level.

Abstract: A method and apparatus are provided for navigating through a media object collection using a mobile device. Users navigate to the target media objects by repeatedly specifying filters. After a user specifies a filter, the filter is applied in combination with all previously specified filters to produce a filtered set of media objects. After a filter is applied, a display level is selected for each hierarchical dimension for which the media objects have metadata. The selection of the display level may be based on the number of distinct values that the media objects in the filtered set have for each level of the hierarchical dimension. Single-action controls are then displayed for each of the values that the media objects in the filtered set have for the selected display level.

Abstract: Techniques for maintaining and using cached child-to-parent mappings in a content-addressable storage system are provided. A cache of child-to-parent mappings is maintained. Each child-to-parent mapping corresponds to a particular chunk in a hierarchy of chunks stored in a content-addressable chunk store, and maps the particular chunk to a parent chunk in the hierarchy of chunks. The hierarchy of chunks includes a first root chunk associated with a file system volume. In response to a change to the file system volume that causes associating a new root chunk with the file system volume, the cache is updated by adding one or more first child-to-parent mappings based on traversing at least a portion of a current file system hierarchy from the new root chunk, and removing one or more second child-to-parent mappings based on traversing at least a portion of a prior file system hierarchy from the first root chunk.

Abstract: A method and apparatus are provided for navigating through a media object collection using a mobile device. Users navigate to the target media objects by repeatedly specifying filters. After a user specifies a filter, the filter is applied in combination with all previously specified filters to produce a filtered set of media objects. After a filter is applied, a display level is selected for each hierarchical dimension for which the media objects have metadata. The selection of the display level may be based on the number of distinct values that the media objects in the filtered set have for each level of the hierarchical dimension. Single-action controls are then displayed for each of the values that the media objects in the filtered set have for the selected display level.

Abstract: Techniques for representing directory structure in content-addressable storage systems are provided. A directory structure of a file system is represented using a plurality of chunks in a content-addressable storage system. The directory structure includes a set of objects arranged in an object hierarchy. The set of objects includes a particular directory that has, within the object hierarchy, a set of child objects. The plurality of chunks includes a directory object chunk for the particular directory. The plurality of chunks further includes a particular set of child object chunks. The particular set of child object chunks are object chunks for each child object in the set of child objects. The plurality of chunks further includes at least one hash set chunk with hash values for object chunks in the particular set of child object chunks.

Abstract: Various techniques are provided for performing garbage collection in a chunk store that is being used to implement a hierarchical file system. In general, the techniques involve a “trace” phase in which all chunks that correspond to current versions of files are marked, and then a sweep phase in which all chunks that were not marked during the trace phase are reclaimed. Various techniques are also described for using snapshots to avoid the need to halt operations on the file system while the trace phase is being performed. In addition, techniques are provided for using a cache of last-touched timestamps to avoid the need to mark all current chunks in each trace phase.

Abstract: Techniques for maintaining and using cached child-to-parent mappings in a content-addressable storage system are provided. A cache of child-to-parent mappings is maintained. Each child-to-parent mapping corresponds to a particular chunk in a hierarchy of chunks stored in a content-addressable chunk store, and maps the particular chunk to a parent chunk in the hierarchy of chunks. The hierarchy of chunks includes a first root chunk associated with a file system volume. In response to a change to the file system volume that causes associating a new root chunk with the file system volume, the cache is updated by adding one or more first child-to-parent mappings based on traversing at least a portion of a current file system hierarchy from the new root chunk, and removing one or more second child-to-parent mappings based on traversing at least a portion of a prior file system hierarchy from the first root chunk.

Abstract: Techniques are provided for using near-full bloom filters for efficiently identifying hash slices in which the deviation between replicas is sufficient to justify remedial measures. Techniques are also described for adjusting the size of slices and the size of the bloom filters, so that the bloom-filter-to-bloom-filter comparison serves as an accurate indicator of the degree to which the contents of the slices of a slice pair have deviated. Slice size may vary from slice pair to slice pair, so that relatively sparsely populated portions of the ring (access key ranges into which fewer chunks fall) are represented by relatively larger slices, while relatively densely populated portions of the ring (access key ranges into which more chunks fall) are represented by relatively smaller slices.

Abstract: Techniques for representing directory structure in content-addressable storage systems are provided. A directory structure of a file system is represented using a plurality of chunks in a content-addressable storage system. The directory structure includes a set of objects arranged in an object hierarchy. The set of objects includes a particular directory that has, within the object hierarchy, a set of child objects. The plurality of chunks includes a directory object chunk for the particular directory. The plurality of chunks further includes a particular set of child object chunks. The particular set of child object chunks are object chunks for each child object in the set of child objects. The plurality of chunks further includes at least one hash set chunk with hash values for object chunks in the particular set of child object chunks.

Abstract: A content addressable storage (CAS) system is provided in which each storage unit is assigned to one of a plurality of sibling groups. Each sibling group is assigned the entire hash space. Within each sibling group, the hash space is partitioned into hash segments which are assigned to the individual storage units that belong to the sibling group. Chunk retrieval requests are submitted to all sibling groups. Chunk storage requests are submitted to a single sibling group. The sibling group to which a storage request is submitted depends on whether any sibling group already stores the chunk, and which sibling groups are considered full.

Abstract: A method and apparatus are provided for navigating through a media object collection using a mobile device. Users navigate to the target media objects by repeatedly specifying filters. After a user specifies a filter, the filter is applied in combination with all previously specified filters to produce a filtered set of media objects. After a filter is applied, a display level is selected for each hierarchical dimension for which the media objects have metadata. The selection of the display level may be based on the number of distinct values that the media objects in the filtered set have for each level of the hierarchical dimension. Single-action controls are then displayed for each of the values that the media objects in the filtered set have for the selected display level.

Abstract: Methods, systems, and apparatus, including computer program products, for identifying regions of interest in an image and identifying a barcode in a degraded image are provided. A region of interest is identified by pre-processing an image, generating a binary image based on a metric calculated on the pre-processed image, and analyzing regions of the image identified using connected components and other analysis. A barcode is identified by searching a population of barcodes, degrading ideal image intensity profiles of candidate barcodes, and comparing the degraded ideal image intensity profiles to an image intensity profile of the degraded image.