International Business Machines Corporation

Globalfoundries Inc.

Takashi Ashida

Hiroshi Itagaki

Terue Watanabe

Tohru Hasegawa

Shinsuke Mitsuma

Setsuko Masuda

Atsushi Abe

Tsuyoshi Miyamura

Takeshi Ishimoto

Yutaka Oishi

Hiroyuki Tanaka

Thomas D Weigold

Slavisa Sarafijanovic

Martin Petermann

Mathias Bjoerkqvist

Kenichi Satoh

Masahide Washizawa

Nao Takekawa

Yasutaka Kanayama

Communicating data with a medium is provided. A cache is provided for storing target data of a file identified by an access request from an application of a host. The cache is divided into a read cache, a write cache, and an index cache. Responsive to receiving the access request: the medium is loaded onto a drive using a file system; target data is stored to the write cache and to the read cache; and the index file stored in the index cache is updated to reflect position metadata about the target data stored in the write cache. Responsive to initiating unloading of the medium from the drive: the updated index file stored in the index cache is written to the index partition of the medium; and the target data stored in the write cache is written onto a data partition of the medium without using the file system.

Reading and writing via file system for tape recording system

Rolling back data on tape in a file system is provided. A management tape is prepared. The management tape has only index files recorded thereon. The index files contain information about start positions and lengths of corresponding data files recorded on normal tapes. The index files further contain identification information for the normal tapes. A first index file of the management tape is read. The first index file is related to a data file to be rolled back. The first index file is read out from the management tape mounted on a first tape drive. The data file to be rolled back is read out of a first normal tape. The first normal tape is identified based on information in the first index file. The first normal tape is mounted on a second tape drive.

File system for rolling back data on tape

One or more processors receive data records from a file system, and convert the data records to a tape image having a format defined by the file system. The tape image is written to a first storage device, and a sequence of data types of the first storage device and a second storage device are monitored to determine whether the first storage device sequence of data types differs from the sequence of data types of the second storage device. Determining that the sequence of data types of the first storage device and second storage device do differ, one or more processors copying, to the second storage device, the data records from the first storage device, from the position on the first storage device that corresponds to the end-of-data position of the second storage device, to the end-of-data position of the first storage device.

Duplexing file system data

A system according to one embodiment includes a processor and logic integrated with and/or executable by the processor. The logic is configured to cause the processor to store hierarchically-organized global configuration information for each node and each tape library resource in a storage cluster to at least one memory accessible by each node of the storage cluster. The storage cluster includes at least one tape library. Also, the logic is configured to cause the processor to migrate data to and/or recall data from a tape cartridge pool within a tape library, using the hierarchically-organized global configuration information and via a node which has access to the tape cartridge pool, in response to receiving a migration and/or recall request at any node of the storage cluster. Other systems, methods, and computer program products for management of data and resources in a tiered data storage system are described in more embodiments.

Scalable and efficient access to and management of data and resources in a tiered data storage system

According to one embodiment, a method includes presenting a medium to more than one user as being exclusively occupied by whichever user attempts to access at least one file from the medium, writing a first file managed by a first user to a data partition of the medium, and storing a first user identifier (ID) that identifies the first user as metadata to an index partition of the medium in response to writing the first file managed by the first user. In another embodiment, a method includes reading metadata from an index partition of a medium from a first user of a plurality of users, extracting first file attribute information associated with a first user ID that indicates a first user from the metadata, and reading a first file based on the first file attribute information associated with the first user ID from a data partition of the medium.

Method for divisionally managing files on a user basis, and a storage system and computer program product thereof

A mechanism is provided for improved file synchronization of a magnetic tape. A destination device determines whether one or more file checksums exist in an extended file attribute associated with an identified file. Responsive to one or more file checksums existing in the extended file attribute associated with the identified file, the destination device reads the one or more file checksums out of the extended file attribute without accessing the magnetic tape. The destination device transmits the one or more file checksums to a source device. The source device segments the data of the new file into fixed-length blocks that do not overlap one another. The source device calculates one or more new file checksums for each of the fixed-length blocks. The source device transmits the one or more new file checksums to the destination device.

Efficiency of file synchronization in a linear tape file system

Managing a file on a tape. In response to a request to write a first file to a tape, whether a second file including data identical to the first file already exists on the tape is detected. If the second file exists, a first index of the second file is updated. After completing the write of the first file, metadata, including data starting position and size of the first file, is added to the first index. In response to a request to read the first or second files, the metadata of the first and second indexes are read. Based on the metadata, which of the first or second files can be accessed faster from a current head position is determined. The first file or the second file that can be accessed faster is then read from the tape.

Method of managing, writing, and reading file on tape

In a general embodiment, a method includes storing hierarchically-organized global configuration information for each node and each tape library resource in a storage cluster to at least one memory accessible by each node of the storage cluster, the storage cluster comprising at least one tape library. The method further includes migrating and/or recalling, using the hierarchically-organized global configuration information, data to and/or from a tape cartridge pool within a tape library. The migration or recall is performed by an appropriate node of the storage cluster and in response to receiving a migration or recall request at an arbitrary node of the storage cluster.

The embodiments deal with files that are already present in a storage when mounting the storage in a file system and files created after the mounting as different groups. (Metadata of) the files is classified. The files are each divided into metadata (index) and a file main body and are recorded on different storage areas, that is, an index partition (IP) and a data partition (DP), associated with each other. This file system is effective in a storage format in which a new file is merely written and an already written file is not updated or deleted (for example, a tape medium used in the LTFS). The embodiments implement a WORM file system by rejecting a request to update or delete a file that is present at mounting as a WORM file and permitting update or deletion of a file that is created after mounting until the storage is unmounted.

File system implementing write once read many (WORM)

A file system to controls access to a tape library that selectively loads and unloads a plurality of cartridges from a plurality of slots to a drive for transmitting to the file system archived data retrieved from a particular cartridge. The file system includes a cache and receives a request from a requestor to access the tape library, estimates a first data transfer rate from an anticipated tape library operation completion duration and from a capacity of cached data to be transmitted from the cache to the requestor, initiates access to the tape library, and adapts the first data transfer rate to a second data transfer rate to transmit the capacity of the cached data to the requestor throughout the anticipated tape library operation completion duration.

Growing community of inventors

Yamato, Japan

Takashi Ashida