摘要:
A method and apparatus for retention of active data stored in memory using multiple indexing systems for data storage. An embodiment of a method for retention of active data in a storage server includes reading data into a first location of a main memory of the storage server. The data in the first location indexes data elements in a long-term data storage in a first manner. The method further provides for copying the data from the first location into a second location in the main memory of the storage server, where the data in the second location indexing the data elements in the long-term data storage in a second manner.
摘要:
A method and system for performing data manipulation on a storage device is disclosed. A data manipulation command is created on a computing device, wherein the computing device is separate from the storage device. The computing device is a client or a server that requests services of a storage system to store data on a storage medium. The computing device and the storage device are connected over a network. The computing device executes a host application, and its data is stored on the medium. The computing device issues a command to the storage device to be performed on the data. The storage device executes the command and sends the result to the computing device. As a result, the data is not sent to the computing device for manipulation.
摘要:
Systems, computer-readable media storing instructions, and methods can infer a state of behavior. Such a method can include constructing a graph including nodes representing hosts and domains based on an event dataset. The graph can be seeded with information external to the event dataset. A belief whether each of the nodes is in a particular state of behavior can be calculated based on marginal probability estimation.
摘要:
A system and method are provided for estimating compressibility of data in a storage device. This is accomplished by actually running a compression algorithm on at least one data element in a storage device, without necessarily storing the compressed data. By this feature, the results of the compression may be compared with the original data element, to gauge an extent to which a compression algorithm is effective in compressing data in the storage device. To this end, in various embodiments, a user may be better able to estimate compression algorithm effectiveness before actually implementing the same.
摘要:
The present invention provides a streaming media cache configured to select a timing interval, chosen from a set of one or more predetermined timing intervals, for each client that requests a data stream from the streaming media cache. Illustratively, clients requesting data streams below a predetermined bit rate (“bandwidth”) are assigned longer timing intervals than clients requesting data streams above the predetermined bit rate. More specifically, because the server can accommodate a larger number of relatively low-bandwidth clients than relatively high-bandwidth clients, the server selects timing intervals of longer duration for the relatively low-bandwidth clients so it may have more time to schedule send times for their requested packets.
摘要:
A method for mounting volumes to a storage server in a storage system, including, speeding up initialization of the storage server by staging volume mounting in two or more stages. The method further includes mounting at least one of the volumes when a request for accessing the volume is received.
摘要:
A storage server is configured to receive a request to store a data block from a client. The request to store the data block is serviced by the storage server by compressing the data block into a compression group which includes a number of compressed data blocks. The storage server stores the compression group in a non-volatile memory and flushes the compression group from the non-volatile memory to a physical storage device in response to reaching a consistency point. By compressing data to be stored in system memory of a storage servers the amount of data that can be processed during a given time period by a data storage system is increased. Furthermore, an increase in performance can be achieved at a lower cost, since the cost of additional physical system memory modules can be avoided,
摘要:
A storage server maintains an active file system and at least one read-only, persistent point-in-time image (RPPI) of the active file system. The booting time of the storage server is reduced by delaying the mounting of the RPPI(s) until the storage server receives a request to access a corresponding RPPI after the storage server has already booted.
摘要:
A method and system for estimating space in a compressed volume to enable a storage server to respond to write requests before actually compressing and/or allocating data on disk. In some embodiments, in response to receiving a request to store data, the storage server estimates the amount of storage space required to store the data on disk. The storage server compares the estimated amount with the amount of available disk space. When the amount of available disk space is less than the estimated space, the storage server sends a response indicating that the request failed. Otherwise, when the amount of available disk space is greater than or equal to the estimate space, the storage server sends a response indicating that the request succeeded. The response is sent before the storage server allocates any disk space in connection with the request.
摘要:
A technique for organizing data to facilitate data deduplication includes dividing a block-based set of data into multiple “chunks”, where the chunk boundaries are independent of the block boundaries (due to the hashing algorithm). Metadata of the data set, such as block pointers for locating the data, are stored in a tree structure that includes multiple levels, each of which includes at least one node. The lowest level of the tree includes multiple nodes that each contain chunk metadata relating to the chunks of the data set. In each node of the lowest level of the buffer tree, the chunk metadata contained therein identifies at least one of the chunks. The chunks (user-level data) are stored in one or more system files that are separate from the buffer tree and not visible to the user.