International Business Machines Corporation

Intellectual Business Machines Corporation

Harald Seipp

Nils Haustein

Daniel James Winarski

Slavisa Sarafijanovic

Thorsten Krause

Simon Lorenz

Robert Haas

Dominic Mueller-Wicke

Khanh V Ngo

Takeshi Ishimoto

Evangelos Stavros Eleftheriou

Jens Jelitto

Ioannis Koltsidas

Frank Krick

Ulf Troppens

Bernd Freitag

Tim Oswald

Alexander Saupp

Michael Edward Factor

Robert Beverley Basham

Arnon Amir

William W Owen

Thomas D Weigold

Rainer Richter

A method includes receiving a plurality of files where each file represents an object. The method further combines selected files of the plurality of files into an aggregation file and stores the aggregation file on low-latency storage media, such as disk storage media. The method represents the aggregation file with a single inode that is stored on the low-latency storage media. The method migrates the aggregate file to high-latency storage media, such as tape storage media, while leaving the single inode representing the aggregation file on the low-latency storage media. By collecting files into larger aggregation files, the number of files archived is significantly reduced and the files archived are of larger size. The reduced number of files and increased size of the files improves archival and retrieval performance due to reduced metadata operation overhead. A corresponding system and computer program product are also disclosed.

Performance- and cost-efficient archiving of small objects

A method includes receiving a plurality of files where each file represents an object. The method further combines selected files of the plurality of files into an aggregation file and stores the aggregation file on low-latency storage media, such as disk storage media. The method represents the aggregation file with a single inode that is stored on the low-latency storage media. The method migrates the aggregate file to high-latency storage media, such as tape storage media. By collecting files into larger aggregation files, the number of files archived is significantly reduced and the files archived are of larger size. The reduced number of files and increased size of the files improves archival and retrieval performance due to reduced metadata operation overhead. A corresponding system and computer program product are also disclosed.

A method for verification of content of tape cartridges in a tape library system using tape drives of the tape library, is provided. The method includes instructing the tape drive to perform tape cartridge verification on the tape cartridge. The method further includes after completion of the tape cartridge verification, unloading the tape cartridge to its original storage position. The method further includes transmitting verification data of the tape cartridge verification to a database of the tape library system for analysis.

Tape library initiated media verification

A computer-implemented method according to one embodiment includes receiving a request to perform a high-latency media (HLM) action on an object or a group of objects, identifying metadata associated with the object or group of objects, and conditionally allowing the HLM action to be performed on the object or group of objects, based on the HLM action and the metadata associated with the object.

Regulating migration and recall actions for high latency media (HLM) on objects or group of objects through metadata locking attributes

An object-based data storage system includes a memory and a processor for executing machine executable instructions configured for implementing logical containers for data objects each having a global identifier. The containers are configured for storing metadata including a first parameterization value descriptive of a number of storage nodes and a second parameterization value descriptive of a classification of the data objects. The machine executable instructions are further configured for implementing a first object storage ring for addressing storage locations across the multiple storage nodes using a surjective function. Execution of the instructions causes the processor to: instantiate the first object storage ring, receive the global identifier and the metadata by the first object storage ring, and generate a storage address by the first object storage ring for the data object using the global identifier, the first parameterization value and the second parameterization value as input to the surjective function.

Data object storage across multiple storage nodes

For data backup and recovery based on linked file repositories with each of the linked file repositories representing an individual file system capable of storing at least one version of a file and being connected to at least one server system, each of the linked file repositories are placed in a certain position for storing a certain version of the file. Each position of each of the linked file repositories is continuously numbered. A number of the versions of the file are determined by the position of the one of the linked file repositories.

Method and system for backup and recovery

A tape drive system server includes a non-volatile memory used as a cache memory for storing data files, at least part of the cache memory comprising a first region managed using a First In First Out policy management and a second region managed using a Least Recently Used policy management; a file system interface for interacting with data files stored on a tape drive system; an interface for allowing one or more remote systems reading and writing data stored on the cache memory; the server configured to: receive from the one or more remote systems one or more write requests for writing one or more data files; interpret attributes associated to data files instructed to be written by the one or more remote systems; and store data files instructed to be written by the remote systems according to the interpreted attributes.

Tape drive system server

An approach for managing a data package is provided. Network throughput is determined to exceed a threshold. A sender computer determines a hash digest of the data package by using a hash function selected based on central processing unit utilization. If the hash digest is in a sender hash table, then without sending the data package, the sender computer sends the hash digest and an index referring to the hash digest so that a recipient computer can use the index to locate a matching hash digest and the data package in a recipient hash table. If the hash digest is not in the sender hash table, then the sender computer adds the data package and the hash digest to the sender hash table and sends the data package and the hash digest to the second computer to check the integrity of the data package based on the hash digest.

Integrity checking and selective deduplication based on network parameters

For data backup and recovery based on linked file repositories with each of the linked file repositories representing an individual file system capable of storing at least one version of a file and being connected to at least one server system, each of the linked file repositories are placed in a certain position for storing a certain version of the file. Each position of each of the linked file repositories is continuously numbered. A number of the versions of the file are determined by the position of the one of the linked file repositories. A version-movement process over each of the linked file repositories is implemented to perform a read operation of the at least one version of the file.

An approach for managing a data package is provided. Network utilization is determined to exceed a threshold. A sender computer determines a hash digest of the data package by using a hash function selected based on central processing unit utilization. If the hash digest is in a sender hash table, then without sending the data package, the sender computer sends the hash digest and an index referring to the hash digest so that a recipient computer can use the index to locate a matching hash digest and the data package in a recipient hash table. If the hash digest is not in the sender hash table, then the sender computer adds the data package and the hash digest to the sender hash table and sends the data package and the hash digest to the second computer to check the integrity of the data package based on the hash digest.

A system and method for reading files stored on a storage system is disclosed. The method includes communicatively coupling one or more remote systems for reading files stored in storage with a first set of files according to a predetermined data format and in a cache memory with a second set of files, the second set of files being a subset of the first set of files. Next one or more remote systems are received at least one read request for reading a sequence of files. A determination is made, among the files of the sequence of files, whether one or more cached files are already stored in the cache memory and whether one or more remaining files are not already stored in the cache memory. Creating, within the one or more remaining files, an order according to which the remaining files should be read on the storage system.

Reading files stored on a storage system

Embodiments of the invention relate to creating an identical copy of a data storage tape cartridge. In one aspect, data contents of a source tape cartridge are copied to a destination tape cartridge. The source tape being formatted by a file system and includes at least one file system metadata block. Data blocks are read from the source tape to a memory buffer. Whether the blocks read are file system metadata blocks and whether the metadata blocks include cartridge-specific and/or cartridge-dependent content is determined. The content is adapted to the destination cartridge, thereby creating consistent file system metadata on the destination tape. The buffered blocks are written to the destination tape, thereby creating a file system on the destination tape that is a physical copy of the file system and data contents on the source tape.

Growing community of inventors

Mainz, Germany

Harald Seipp