Abstract: A containerized stream microservice is described. The containerized stream microservice is configured to provide the functionality of volume presentation along with all related interactions including the receipt and processing of IO requests and related services. The containerized stream microservice preferably implements stream metadata in the management of storage operations, and interacts with a store to provide underlying data storage. The store, which may also be referred to as a data store, is where underlying data is stored in a persistent manner. In one example, the store is an object store.

Abstract: A containerized storage microservice is described. The containerized storage microservice, and its corresponding architecture, provide an environment wherein an application container accesses containerized storage services through a direct connection. This allows the operating system file system to be effectively bypassed in the provision of storage services. In one example, a library provides a basic file system and is arranged underneath the application container. The library essentially intercepts storage requests and emulates a thin file system. Instead of invoking the kernel of the operating system to process each storage request, the library allows the storage request to bypass the kernel and pass the storage request to the storage microservice. The containerized storage microservices are available in different types, and are configured so that they can be stacked to provide customized sets of storage services to different types of application containers.

Abstract: An LRU buffer configuration for performing parallel IO operations is disclosed. In one example, the LRU buffer configuration is a doubly linked list of segments. Each segment is also a doubly linked list of buffers. The LRU buffer configuration includes a head portion and a tail portion, each including several slots (pointers to segments) respectively accessible in parallel by a number of CPUs in a multicore platform. Thus, for example, a free buffer may be obtained for a calling application on a given CPU by selecting a head slot corresponding to the given CPU, identifying the segment pointed to by the selected head slot, locking that segment, and removing the buffer from the list of buffers in that segment. Buffers may similarly be returned according to slots and corresponding segments and buffers at the tail portion.

Abstract: Command list processing in performing parallel IO operations is disclosed. In one example, handling IO requests directed to an operating system having an IO scheduling component entails allocating a command to a thread in association with an IO request. The command is allocated from one of a plurality of command lists accessible in parallel, and the command is also linked to one of a plurality of active command lists that are accessible in parallel. The command lists can be arranged as per-CPU command lists, with each per-CPU command list corresponding to one of a plurality of CPUs on a multi-core processing platform on which the IO requests are processed. Similarly, each of the active command lists can respectively correspond to one of the plurality of CPUs on the multi-core processing platform. Per-volume queues can also be implemented for respective volumes presented to applications.

Abstract: A node based architecture that supports arbitrary access to any node in a system for data representation and access, while still providing virtual volume coherency that is global to all of the nodes in the system, and while providing underlying data management services that are also variously accessible from any node in the system.

Abstract: Methods and apparatus for data request scheduling in performing parallel IO operations are disclosed. In one example, IO requests directed to an operating system having an IO scheduling component are processed. There, an IO request directed from an application to the operating system is intercepted. A determination is made whether the IO request is subject to immediate processing using available parallel processing resources. When it is determined that the IO request is subject to immediate processing using the available parallel processing resources, the IO scheduling component of the operating system is bypassed. The IO request is directly and immediately processed and passed back to the application using the available parallel processing resources.

Abstract: Load balancing in a multimedia conference is disclosed, involving one or more internal terminals and one or more internal nodes separated from one or more external terminals and one or more external nodes by a firewall. Media data is forwarded through the firewall to at least a second one of the nodes, and received media data at the at least a second one of said nodes are processed. At a first event, reconfiguration is performed of said first one of said nodes to process received media data and of said second one of said nodes to forward received media data to said first one of said nodes. At a second event, loading is done of at least a part of said received media data being processed at the first one or second one of said nodes to at least a third one of said nodes.

Abstract: Command list processing in performing parallel IO operations is disclosed. In one example, handling IO requests directed to an operating system having an IO scheduling component entails allocating a command to a thread in association with an IO request. The command is allocated from one of a plurality of command lists accessible in parallel, and the command is also linked to one of a plurality of active command lists that are accessible in parallel. The command lists can be arranged as per-CPU command lists, with each per-CPU command list corresponding to one of a plurality of CPUs on a multi-core processing platform on which the IO requests are processed. Similarly, each of the active command lists can respectively correspond to one of the plurality of CPUs on the multi-core processing platform. Per-volume queues can also be implemented for respective volumes presented to applications.

Abstract: Methods and apparatus for data request scheduling in performing parallel IO operations are disclosed. In one example, IO requests directed to an operating system having an IO scheduling component are processed. There, an IO request directed from an application to the operating system is intercepted. A determination is made whether the IO request is subject to immediate processing using available parallel processing resources. When it is determined that the IO request is subject to immediate processing using the available parallel processing resources, the IO scheduling component of the operating system is bypassed. The IO request is directly and immediately processed and passed back to the application using the available parallel processing resources.

Abstract: A node based architecture that supports arbitrary access to any node in a system for data representation and access, while still providing virtual volume coherency that is global to all of the nodes in the system, and while providing underlying data management services that are also variously accessible from any node in the system.

Abstract: A stream architecture for data representation is disclosed. A stream is retained with respect to write transactions to a given volume. The stream includes the write transactions and provides a sequence of the write transactions according to the order in which the write transactions were received for the given volume. By way of example, a stream image can be associated to the stream. The stream image provides a representation of the data in the given volume for a point in time by referencing a non-contiguous subset of the sequence of write transactions in the stream.

Abstract: Load balancing in a multimedia conference is disclosed, involving one or more internal terminals (Terminal 3) and one or more internal nodes (Node B) separated from one or more external terminals (Terminal 1, Terminal 2) and one or more external nodes (Node A) by a firewall. Media data from at least one of said terminals received at at least a first one of said nodes are forwarded through the firewall to at least a second one of the nodes, and received media data at the at least a second one of said nodes are processed by the second one of the nodes. At a first event, reconfiguration is performed of said first one of said nodes to process received media data and of said second one of said nodes to forward received media data to said first one of said nodes. At a second event, loading is done of at least a part of said received media data being processed at the first one or second one of said nodes to at least a third one of said nodes.

Abstract: A tool for completing the mounting of a bicycle tire onto its rim that is superior to those provided by the tools of the prior tire irons. The use of a tool is usually required to complete the job of mounting a bicycle tire to its rim due to the high tension developed in the bead of the tire at that stage. The present invention does not rely on a levering arrangement at all, but instead employs a traveling inclined plane to progressively lift the tire bead to a height above the rim's edge, and a downwardly sloped incline to allow the so lifted bead to then slide down into the rim's interior. The invention utilizes the flange, or rim sidewall, of the wheel rim for both support and guidance as it is impelled forward on the rim by impacts on its trailing surface from an object suitable for the function, such as a hammer. A slot is incorporated into the invention to receive the wheel's flange.

Abstract: A method for the catalytic manufacture of MIBK and DIBK from DMK and/or IPA (optionally in the presence of water) while obtaining improved control over the ratio of DIBK to MIBK in the product stream, comprising reacting, in the presence of an aldol condensation catalyst, a reactant mixture comprising DMK and/or IPA and an effective amount of an additional reactant selected from the group consisting of mesityl oxide (MSO) and methyl isobutyl carbinol (MIBC) and mixtures thereof. Reaction temperature may also be changed to affect the product ratio obtained. The preferred catalyst is copper-based. An overall excess of hydrogen is desired, and this may be achieved by introducing or recycling hydrogen, and/or by balancing exothermic and endothermic reactions. By this invention, the product ratio of DIBK to MIBK is altered such that, as DMK and/or IPA conversion is increased, a lesser amount of DIBK than normal is produced, resulting in improved ability to control the product ratio of these materials.