-
公开(公告)号:GB2514555A
公开(公告)日:2014-12-03
申请号:GB201309484
申请日:2013-05-28
Applicant: IBM
Inventor: CIDECIYAN ROY DARON , JELITTO JENS , SARAFIJANOVIC SLAVISA , STANEK JAN
Abstract: Data objects, to be stored on a storage medium, are divided into data segments or chunks. A hash of each data segment is generated. The hash tag and the physical location at which the segment is to be stored on the medium are stored in an index. When a new data segment is processed, its hash is used to determine whether an identical segment is already stored on the medium. If so, the new data segment is not stored. Otherwise, the new data segment is stored in a location, which is physically close to other data segments in the same data object. Consecutive segments of a data object may be stored in a single extent on the medium. The data object may be a file. The storage medium may be a sequential access medium, such as a magnetic tape.
-
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:DE112012005271T5
公开(公告)日:2014-11-27
申请号:DE112012005271
申请日:2012-11-20
Applicant: IBM
Inventor: ELEFTHERIOU EVANGELOS STAVROS , HAAS ROBERT , HAUSTEIN NILS , JELITTO JENS , SEIPP HARALD , KOLTSIDAS IOANNIS , SARAFIJANOVIC SLAVISA , SAUPP ALEXANDER
IPC: G06F3/06 , G06F12/00 , G06F12/0804 , G06F12/0871 , G06F12/123 , G06F17/30
Abstract: Es wird ein Bandlaufwerksystem-Server vorgeschlagen, aufweisend: – einen nichtflüchtigen Cachespeicher, der als ein Cachespeicher (106) zum Speichern von Datendateien verwendet wird, wobei zumindest ein Teil des Cachespeichers eine erste Region (40), die unter Verwendung einer Verwaltung einer „First-In/First-Out”-Richtlinie verwaltet wird, und eine zweite Region (42), die unter Verwendung einer Verwaltung einer „Least Recently Used”-Richtlinie verwaltet wird, aufweist; – eine Dateisystem-Schnittstelle zum Interagieren mit auf einem Bandlaufwerksystem (104) gespeicherten Datendateien; – eine Schnittstelle, um einem oder mehreren entfernt angeordneten Systemen (110, 120) ein Lesen und Schreiben von auf dem Datenspeichermittel und/oder dem Cachespeicher gespeicherten Daten zu ermöglichen; wobei der Server eingerichtet ist um: – von dem einen oder den mehreren entfernt angeordneten Systemen eine oder mehrere Schreibanfragen zum Schreiben von einer oder mehreren Datendateien auf das Bandlaufwerksystem und den Cachespeicher zu empfangen; – Attribute zu interpretieren, die Datendateien zugeordnet sind, die angewiesen sind, durch das eine oder die mehreren entfernt angeordneten Systeme auf das Bandlaufwerksystem und auf den Cachespeicher geschrieben zu werden; und – Datendateien zu speichern, die angewiesen sind, durch die entfernt angeordneten Systeme gemäß den interpretierten Attributen geschrieben zu werden.
-
公开(公告)号:GB2517913A
公开(公告)日:2015-03-11
申请号:GB201315434
申请日:2013-08-30
Applicant: IBM
Inventor: JELITTO JENS , MITTELHOLZER THOMAS , SARAFIJANOVIC SLAVISA , SORNIOTTI ALESSANDRO , STANEK JAN
Abstract: A method includes providing (S10), by at least one client, files to be stored on a remote server. The method then includes evaluating (S20) popularity of the files (e.g. the number of copies provided by different users). And storing (S30) the files on the server in a form that depends on the popularity of the files, files with a first level of popularity being stored in a deduplicated form and files with a second level of popularity being stored in an encrypted form, the first level of popularity being higher than the second level of popularity. More popular files may be seen as not intended to be confidential and therefore storable in a duplicated form. The method may further include repeatedly providing copies of the same file by different users, thereby increasing popularity of the file, and comprises storing said copies in a semantically secure encrypted form before the file reaches the first level of popularity, and in the deduplicated form after said file has reached the first level of popularity. The method may further include, upon the file reaching the first level of popularity, decrypting previously stored copies and performing deduplication on said copies.
-
-
-