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 caching data on a solid-state storage device. The solid-state storage device maintains metadata pertaining to cache operations performed on the solid-state storage device, as well as storage operations of the solid-state storage device. The metadata indicates what data in the cache is valid, as well as information about what data in the nonvolatile cache has been stored in a backing store. A backup engine works through units in the nonvolatile cache device and backs up the valid data to the backing store. During grooming operations, the groomer determines whether the data is valid and whether the data is discardable. Data that is both valid and discardable may be removed during the grooming operation. The groomer may also determine whether the data is cold in determining whether to remove the data from the cache device. The cache device may present to clients a logical space that is the same size as the backing store. The cache device may be transparent to the clients.
摘要:
An apparatus, system, and method are disclosed for efficiently mapping virtual and physical addresses. A forward mapping module uses a forward map to identify physical addresses of data of a data segment from a virtual address. The data segment is identified in a storage request. The virtual addresses include discrete addresses within a virtual address space where the virtual addresses sparsely populate the virtual address space. A reverse mapping module uses a reverse map to determine a virtual address of a data segment from a physical address. The reverse map maps the data storage device into erase regions such that a portion of the reverse map spans an erase region of the data storage device erased together during a storage space recovery operation. A storage space recovery module uses the reverse map to identify valid data in an erase region prior to an operation to recover the erase region.
摘要:
An apparatus, system, and method are disclosed for storage space recovery after reaching a read count limit. A read module reads data in a storage division of solid-state storage. A read counter module then increments a read counter corresponding to the storage division. A read counter limit module determines if the read count exceeds a maximum read threshold, and if so, a storage division selection module selects the corresponding storage division for recovery. A data recovery module reads valid data packets from the selected storage division, stores the valid data packets in another storage division of the solid-state storage, and updates a logical index with a new physical address of the valid data.
摘要:
An apparatus, system, and method are disclosed for sharing a device between multiple hosts. The apparatus, system, and method include an RDMA setup module and an RDMA execution module. The RDMA setup module prepares a solid-state storage controller for an RDMA operation to transfer data of a file or of an object between the solid-state storage controller and a requesting device in response to a storage request. The storage request may be substantially free of the data, and the solid-state storage controller may control a solid-state storage via a storage input/output (“I/O”) bus. The solid-state controller controls storage of data in the solid-state storage, and the requesting device is connected to the solid-state controller through a computer network. The RDMA execution module executes the RDMA operation to transfer the data between the requesting device and the solid-state storage controller.
摘要:
An apparatus, system, and method are disclosed for efficiently managing commands in a solid-state storage device that includes a solid-state storage arranged in two or more banks. Each bank is separately accessible and includes two or more solid-state storage elements accessed in parallel by a storage input/output bus. The solid-state storage includes solid-state, non-volatile memory. The solid-state storage device includes a bank interleave that directs one or more commands to two or more queues, where the one or more commands are separated by command type into the queues. Each bank includes a set of queues in the bank interleave controller. Each set of queues includes a queue for each command type. The bank interleave controller coordinates among the banks execution of the commands stored in the queues, where a command of a first type executes on one bank while a command of a second type executes on a second bank.
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 a front-end, distributed redundant array of independent drives (“RAID”). A storage request receiver module receives a storage request to store object or file data in a set of autonomous storage devices forming a RAID group. The storage devices independently receive storage requests from a client over a network, and one or more of the storage devices are designated as parity-mirror storage devices for a stripe. The striping association module calculates a stripe pattern for the data. Each stripe includes N data segments, each associated with N storage devices. The parity-mirror association module associates a set of the N data segments with one or more parity-mirror storage devices. The storage request transmitter module transmits storage requests to each storage device. Each storage request is sufficient to store onto the storage device the associated data segments. The storage requests are substantially free of data.
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 a front-end, distributed redundant array of independent drives (“RAID”). A storage request receiver module receives a storage request to store object or file data in a set of autonomous storage devices forming a RAID group. The storage devices independently receive storage requests from a client over a network, and one or more of the storage devices are designated as parity-mirror storage devices for a stripe. The striping association module calculates a stripe pattern for the data. Each stripe includes N data segments, each associated with N storage devices. The parity-mirror association module associates a set of the N data segments with one or more parity-mirror storage devices. The storage request transmitter module transmits storage requests to each storage device. Each storage request is sufficient to store onto the storage device the associated data segments. The storage requests are substantially free of data.