摘要:
An auto-commit memory is capable of implementing a pre-configured, triggered commit action in response to a failure condition, such as a loss of power, invalid shutdown, fault, or the like. A computing device may access the auto-commit memory using memory access semantics (using a memory mapping mechanism or the like), bypassing system calls typically required in virtual memory operations. Since the auto-commit memory is pre-configured to commit data stored thereon in the event of a failure, users of the auto-commit memory may view these memory semantic operations as being instantly committed. Operations to commit the data are taken out of the write-commit path.
摘要:
An apparatus and system are disclosed for an in-server storage area network (“SAN”). A first storage controller is included within a first server. The first storage controller controls at least one storage device. The first server includes a network interface shared by the first server and the first storage controller. A storage communication module is included that facilitates communication between the first storage controller and at least one device external to the first server, where the communication between the first storage controller and the external device is independent from the first server. An in-server SAN module is included that services a storage request using at least one of a network protocol and a bus protocol. The in-server SAN module services the storage request independent from the first server, the service request received from a client.
摘要:
An apparatus, system, and method are disclosed for bad block remapping. A bad block identifier module identifies one or more data blocks on a solid-state storage element as bad blocks. A log update module writes at least a location of each bad block identified by the bad block identifier module into each of two or more redundant bad block logs. A bad block mapping module accesses at least one bad block log during a start-up operation to create in memory a bad block map. The bad block map includes a mapping between the bad block locations in the bad block log and a corresponding location of a replacement block for each bad block location. Data is stored in each replacement block instead of the corresponding bad block. The bad block mapping module creates the bad block map using one of a replacement block location and a bad block mapping algorithm.
摘要:
An apparatus, system, and method are disclosed for storing information in a storage device that includes multi-level memory cells. The method involves storing data that is written to the storage device in the LSBs of the multi-level memory cells, and storing audit data in the MSBs of the multi-level memory cells. The audit data can be read separately from the data and used to determine whether or not there has been any unintended drift between states in the multi-level cells. The audit data may be used to correct data when the errors in the data are too numerous to be corrected using error correction code (ECC). The audit data may also be used to monitor the general health of the storage device. The monitoring process may run as a background process on the storage device. The storage device may transition the multi-level memory cells to operate as single-level memory cells.
摘要:
An apparatus, system, and method are disclosed for storage space recovery in solid-state storage. A sequential storage module sequentially writes data packets in a storage division. The storage division includes a portion of a solid-state storage. The data packets are derived from an object. The data packets are sequentially stored by order of processing. A storage division selection module selects a storage division for recovery. A data recovery module reads valid data packets from the storage division selected for recovery, queues the valid data packets with other data packets to be written sequentially, and updates an index with a new physical address of the valid data. The index includes a mapping of physical addresses of data packets to object identifiers. A storage division recovery module marks the storage division selected for recovery as available for sequentially writing data packets in response to completing copying valid data from the storage division.
摘要:
An apparatus, system, and method are disclosed for bad block remapping. A bad block identifier module identifies one or more data blocks on a solid-state storage element as bad blocks. A log update module writes at least a location of each bad block identified by the bad block identifier module into each of two or more redundant bad block logs. A bad block mapping module accesses at least one bad block log during a start-up operation to create in memory a bad block map. The bad block map includes a mapping between the bad block locations in the bad block log and a corresponding location of a replacement block for each bad block location. Data is stored in each replacement block instead of the corresponding bad block. The bad block mapping module creates the bad block map using one of a replacement block location and a bad block mapping algorithm.
摘要:
An apparatus, system, and method are disclosed for ensuring data validity in a data storage process. A data receiver module receives a storage block and existing parity information. An ECC generation module generates error correcting code (“ECC”) check bits for the data of the storage block in response to receiving the storage block and the existing parity information. The ECC check bits for the storage block are generated using a block code, a convolutional code, etc. A pre-storage consistency module uses the data of the storage block, the existing parity information, and the ECC check bits to determine if the data of the storage block, the existing parity information, and the ECC check bits are consistent. A data storage module stores the data of the storage block and the ECC check bits the data storage device without storing the existing parity information.
摘要:
An apparatus, system, and method are disclosed for solid-state storage as cache for high-capacity, non-volatile storage. The apparatus, system, and method are provided with a plurality of modules including a cache front-end module and a cache back-end module. The cache front-end module manages data transfers associated with a storage request. The data transfers between a requesting device and solid-state storage function as cache for one or more HCNV storage devices, and the data transfers may include one or more of data, metadata, and metadata indexes. The solid-state storage may include an array of non-volatile, solid-state data storage elements. The cache back-end module manages data transfers between the solid-state storage and the one or more HCNV storage devices.
摘要:
An apparatus, system, and method are disclosed for managing data in a solid-state storage device. A solid-state storage and solid-state controller are included. The solid-state storage controller includes a write data pipeline and a read data pipeline The write data pipeline includes a packetizer and an ECC generator. The packetizer receives a data segment and creates one or more data packets sized for the solid-state storage. The ECC generator generates one or more error-correcting codes (“ECC”) for the data packets received from the packetizer. The read data pipeline includes an ECC correction module, a depacketizer, and an alignment module. The ECC correction module reads a data packet from solid-state storage, determines if a data error exists using corresponding ECC and corrects errors. The depacketizer checks and removes one or more packet headers. The alignment module removes unwanted data, and re-formats the data as data segments of an object.
摘要:
An apparatus, system, and method are disclosed for detecting and replacing failed data storage. A read module reads data from an array of memory devices. The array includes two or more memory devices and one or more extra memory devices storing parity information from the memory devices. An ECC module determines, using an error correcting code (“ECC”), if one or more errors exist in tested data and if the errors are correctable using the ECC. The tested data includes data read by the read module. An isolation module selects a memory device in response to the ECC module determining that errors exists in the data read by the read module and that the errors are uncorrectable using the ECC. The isolation module also replaces data read from the selected memory device with replacement data and available data wherein the tested data includes the available data combined with the replacement data.