Abstract: Embodiments of the technology relate to storing user data and metadata in persistent storage in the event of a power failure and then recovering such stored data and metadata when power is restored.

Abstract: According to one embodiment, a first control module (CM) of a storage system receives a first request from a client device to read first data stored in a second storage location of a storage module, where the second storage location is associated with a second CM. The first CM includes a first processor and the second CM includes a second processor. The first CM transmits a first control signal the second CM via the inter-processor link to request the second CM to copy the first data from the second storage location to a first memory location associated with the first CM. The first CM initiates a first data transaction to transmit the first data from the first memory location to the client device through a communication fabric without having to go through the second CM.

Abstract: A storage system includes a first and second control modules (CMs) connected to a client and a storage module over a communication fabric. In response to a data fragment written to the storage module, the first CM is to create a table of contents (TOC) entry in a TOC page maintained in a first storage partition of the storage module, update its FTL map, determine whether the TOC page contains a predetermined number of TOC entries, and in response to determining that the TOC page contains the predetermined number of TOC entries, send a control signal to the second CM via an inter-processor link. In response to the control signal received from the first CM via the inter-processor link, the second CM is to copy the TOC page from the first storage partition to a memory associated with the second CM to allow the second CM to update its FTL map.

Abstract: Embodiments of the technology relate to storing user data and metadata in persistent storage in the event of a power failure and then recovering such stored data and metadata when power is restored.

Abstract: According to one embodiment, a first control module (CM) of a storage system receives a first request from a client device to read first data stored in a second storage location of a storage module, where the second storage location is associated with a second CM. The first CM includes a first processor and the second CM includes a second processor. The first CM transmits a first control signal the second CM via the inter-processor link to request the second CM to copy the first data from the second storage location to a first memory location associated with the first CM. The first CM initiates a first data transaction to transmit the first data from the first memory location to the client device through a communication fabric without having to go through the second CM.

Abstract: A storage system includes a first and second control modules (CMs) connected to a client and a storage module over a communication fabric. In response to a data fragment written to the storage module, the first CM is to create a table of contents (TOC) entry in a TOC page maintained in a first storage partition of the storage module, update its FTL map, determine whether the TOC page contains a predetermined number of TOC entries, and in response to determining that the TOC page contains the predetermined number of TOC entries, send a control signal to the second CM via an inter-processor link. In response to the control signal received from the first CM via the inter-processor link, the second CM is to copy the TOC page from the first storage partition to a memory associated with the second CM to allow the second CM to update its FTL map.

Abstract: Embodiments of the technology relate to storing user data and metadata in persistent storage in the event of a power failure and then recovering such stored data and metadata when power is restored.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable storage media for tracking and managing resource usage through a ledger feature that can trigger complex real-time reactions. The resource tracking can be managed through a ledger module and a ledger data structure. The ledger data structure can be updated each time a task requests a resource. Additionally, as part of the update, the ledger module can verify whether a resource has been over consumed. In response to the detection of an over consumption, the ledger module can set a flag. At some later pointer when the thread is in a stable, well-understood point, the ledger module can check if the flag has been set. If the flag has been set, the ledger module can call the appropriate callback function, which can react to the over consumption in a resource specific manner.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable storage media for tracking and managing resource usage through a ledger feature that can trigger complex real-time reactions. The resource tracking can be managed through a ledger module and a ledger data structure. The ledger data structure can be updated each time a task requests a resource. Additionally, as part of the update, the ledger module can verify whether a resource has been over consumed. In response to the detection of an over consumption, the ledger module can set a flag. At some later pointer when the thread is in a stable, well-understood point, the ledger module can check if the flag has been set. If the flag has been set, the ledger module can call the appropriate callback function, which can react to the over consumption in a resource specific manner.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable storage media for tracking and managing resource usage through a ledger feature that can trigger complex real-time reactions. The resource tracking can be managed through a ledger module and a ledger data structure. The ledger data structure can be updated each time a task requests a resource. Additionally, as part of the update, the ledger module can verify whether a resource has been over consumed. In response to the detection of an over consumption, the ledger module can set a flag. At some later pointer when the thread is in a stable, well-understood point, the ledger module can check if the flag has been set. If the flag has been set, the ledger module can call the appropriate callback function, which can react to the over consumption in a resource specific manner.

Abstract: Methods and systems for defining the partitioning between operating system environments are provided. In this method, network resources, devices, and pseudo-filesystems, etc. can be partitioned. This method provides the capability to support services from native and foreign operating environments without colliding on fixed resources. This method simplifies the task of supporting multiple different operating environments. By assigning each operating environment to its own zone, multiple instances of a single operating environment or multiple different operating environments can be simultaneously supported on a single operating system kernel.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable storage media for tracking and managing resource usage through a ledger feature that can trigger complex real-time reactions. The resource tracking can be managed through a ledger module and a ledger data structure. The ledger data structure can be updated each time a task requests a resource. Additionally, as part of the update, the ledger module can verify whether a resource has been over consumed. In response to the detection of an over consumption, the ledger module can set a flag. At some later pointer when the thread is in a stable, well-understood point, the ledger module can check if the flag has been set. If the flag has been set, the ledger module can call the appropriate callback function, which can react to the over consumption in a resource specific manner.

Abstract: A method for writing data to persistent storage. The method include receiving a first write request including a key and a value, hashing the key to obtain a hashed key, obtaining a hash table depth (d), obtaining d bits from the hashed key, and making a first determination that a hash frag associated with the d bits from the hashed key exists. In response to the first determination, obtaining the hash frag, making a second determination that there is available space to store a hash frag entry in the hash frag, storing the hash frag entry in the hash frag to obtain an updated hash frag, where the hash frag entry includes the hashed key and value information for the value, and storing the updated hash frag in the persistent storage.

Abstract: Methods and systems for efficiently interpreting operating system service requests on the same register or vector of a processor or CPU where the operating system service requests are initiated from native and non-native applications are provided. More particularly, a switching layer can enable processing of the operating system service requests by routing control of a particular request to an appropriate kernel subsystem or module based on the type of operating system service being requested and the type of application initiating the request. Additionally, the performance impact of the switching layer for native applications is overcome by dynamically reprogramming the processor or CPU on every change of active process so that only foreign applications are subject to the processing requirements of the switching layer.

Abstract: Methods and systems for defining the partitioning between operating system environments are provided. In this method, network resources, devices, and pseudo-filesystems, etc. can be partitioned. This method provides the capability to support services from native and foreign operating environments without colliding on fixed resources. This method simplifies the task of supporting multiple different operating environments. By assigning each operating environment to its own zone, multiple instances of a single operating environment or multiple different operating environments can be simultaneously supported on a single operating system kernel.

Abstract: A parallel filesystem remote access subsystem facilitates remote access to files in a parallel filesystem in a digital computer network, the network including at least one client computer and a plurality of server computers interconnected by a communication link, and each server computer storing a portion of at least one file in the parallel filesystem. The parallel filesystem remote access subsystem includes, associated with the server computer, a parallel filesystem input/output daemon, and, associated with the client computer, a parallel filesystem module and a parallel filesystem proxy daemon. The parallel filesystem module receives access requests generated to access a file in the parallel filesystem and refer the access requests to the parallel filesystem proxy daemon, and the parallel filesystem proxy daemon, in turn, generates server access request messages for transfer over the communications link.