公开(公告)号：GB2528333A

公开(公告)日：2016-01-20

申请号：GB201414485

申请日：2014-07-15

Applicant: IBM

Inventor： ILIADIS ILIAS ,  JELITTO JENS ,  KIM YUSIK ,  SARAFIJANOVIC SLAVISA ,  VENKATESAN VINODH

IPC: G06F3/06

Abstract: A device and method for determining a number of storage devices for each tier in a multi-tiered storage system comprises; classifying and assigning data to the tiers based on parameters indicating characteristics of both the data and the storage devices and a further set of parameters defining configuration rules; determining the number of storage devices assigned to each of the tiers based on the data assignment, a received cost value and an estimated performance metric; updating the further set of parameters; and re-assigning the data based on the update further set of parameters. The data characteristics might comprise data unit size, an average request size, and an average request rate. The device characteristics might comprise storage capacity, bandwidth and a seek time. The re-assignment of the data might be iterated in a control loop, which is terminated when the estimated performance metric fulfils a termination condition.

公开(公告)号：GB2519815A

公开(公告)日：2015-05-06

申请号：GB201319286

申请日：2013-10-31

Applicant: IBM

Inventor： LLIADIS LLIAS ,  VENKATESAN VINODH

IPC: G06F11/10

Abstract: A redundant array of independent discs has a one or more controllers 20 connected to one or more placement nodes 40. The controllers generate parity blocks for the data blocks written to the array. The placement nodes determine the locations in the array, at which the data and parity blocks to be written. The data is then written to the storage devices 50. The coding scheme used to generate the parity blocks may be used to select where to write the blocks. The locations are stored in placement metadata 30 accessible to the placement nodes. When reading or updating the blocks, the placement nodes use the metadata to retrieve the blocks.

公开(公告)号：GB2529670A

公开(公告)日：2016-03-02

申请号：GB201415249

申请日：2014-08-28

Applicant: IBM

Inventor： CHERUBINI GIOVANNI ,  LLIADIS LLIAS ,  JELITTO JENS ,  VENKATESAN VINODH

IPC: G06F17/30 ,  G06F3/06

Abstract: A data segment including metadata is received (S1) by a processing unit for storage in a storage tier of a storage unit comprising at least two storage tiers. Metadata of data segments stored in the storage unit is received by the processing unit. The processing unit may classify (S3) the data segment according to relevance classes. The processing unit determines (S4) the storage tier to store the received data segment to and a protection level is determined dependent on the metadata of data segments stored in the storage unit and dependent on the metadata of the received data segment. Data segments can be files, blocks or pages of data. The assigned protection level can result in the application of (a) error correction code to the data segment; (b) an erasure code to the data segment, or (c) providing (redundant) copies or replicas of the data segment in the storage unit. Data analysis (S7) and updating parameters (S8) may be provided to re-classify stored data segments by monitoring access frequency and updating criteria for data segment placement.

公开(公告)号：GB2529669A

公开(公告)日：2016-03-02

申请号：GB201415248

申请日：2014-08-28

Applicant: IBM

Inventor： CHERUBINI GIOVANNI ,  LLIADIS LLIAS ,  JELITTO JENS ,  VENKATESAN VINODH

IPC: G06F3/06

Abstract: A storage system comprises a storage unit 2 with at least two storage tiers 21, and an access pattern evaluator 24 configured to provide information about a frequency at which data segments stored in one or more of the at least two storage tiers are accessed. A classification unit 1 is configured to assign at least one out of a set of at least two relevance classes to a data segment received for storing in the storage unit dependent on information comprised in the data segment. A selector 14 is configured to determine a storage tier out of the at least two storage tiers for storing the classified data segment to dependent on at least access frequency information provided by the access pattern evaluator for data segments in the same relevance class, and configured to determine a level of protection for the classified data segment dependent on at least the relevance class assigned. Logic 22 is provided for storing the classified data segment including the assigned relevance class to the determined storage tier and according to the determined level of protection. The system can also have a storage tier relocation manager and storage capacity manager. The system is designed to deal with emerging big data applications.