International Business Machines Corporation

Amir Kredi

Lior Aronovich

Aviad Zlotnick

Henry Esmond Butterworth

Shira Ben-Dor

Shira Ben Dor

Shay Haim Akirav

Yariv Bachar

Orit Nissan-Messing

Rafael Buchbinder

Amit Schreiber

Harry Butterworth

Adam Wolman

Avied Zlotnick

Various embodiments for managing data in a data storage having data deduplication. For a back reference data structure incorporating reference information for at least one user data segment to a storage block, a user data segment identification (ID) representative of the at least one user data segment is removed from the back reference data structure.

Removal of reference information for storage blocks in a deduplication system

Various embodiments for managing data in a data storage having data deduplication. In response to a portion of the data storage determined to be inaccessible, an identifier of a user data segment is queried by examining a corresponding back reference data structure, the back reference data structure implemented as an approximation of a relationship between the user data segment and a particular storage block in the data storage. If the outcome of the query is negative, the user data segment is determined not associated with the particular storage block. If the outcome of the query is positive, the user data segment is warranted be examined further to determine if the user data segment is associated with the particular storage block.

Detection of data affected by inaccessible storage blocks in a deduplication system

Various embodiments for managing data in a data storage having data deduplication. A back reference data structure is configured for user data segments as a mechanism to identify an affected storage block to which information in the back reference data structure refers. The back reference data structure is initialized such that a resolution of the back reference data structure diminishes as a number of the user data segments referencing the affected storage block increases.

Back referencing of deduplicated data

A data storage system including at least one storage controller having a first color policy and operative to store data onto a first data storage unit at a primary site as part of a current color of the primary site, at least one storage controller having a second color policy and operative to store data onto a second data storage unit at the primary site as part of the current color, and a color control node operative to provide each of the controllers with new color information while maintaining the integrity of dependent writes across color boundaries.

Write set boundary management for heterogeneous storage controllers in support of asynchronous update of secondary storage

Various embodiments writing data are provided. In one embodiment, the data arranged in a plurality of write intervals is loaded into a plurality of buffers, the totality of the plurality of buffers configured as a sliding write window mechanism adapted for movement to accommodate the write intervals. The data may reach the storage system out of a sequential order, and by loading it appropriately into the said buffers the data is ordered sequentially before it is written to the storage media. When a commencing section of the sliding write window is filled up with written data, this section is flushed to the storage media, and the window slides forward, to accommodate further data written by the writers. The writers are synchronized with the interval reflected by the current position of the sliding write window, and they send data to be written only where this data fits into the current interval of the window.

Sliding write window mechanism for writing data

A color control node includes an interface for communicating with multiple storage controllers, wherein the storage controllers maintain a primary storage system at a primary site and a secondary storage system at a secondary site; and wherein the storage controllers maintain a current color and associate all writes with the current color without polling the color control node. The color control node also includes operational capability for issuing a polling command to instruct the storage controllers to poll the color control node for the current color prior to associating each write with a new color; receiving an acknowledgment of receipt of the polling command; changing the current color to a new color responsive to receiving the acknowledgment; issuing a storage command to the storage controllers indicating the new color; and instructing each storage controller to cease polling the color control node for the current color.

Write set boundary management in support of asynchronous update of secondary storage

Methods, systems and apparatus for maintaining colors and color boundaries across multiple storage controllers by instructing a polling storage controller to poll a color control node for current color information, changing the current color to a new color, and instructing the polling storage controller to cease polling the color control node for the current color information.

Growing community of inventors

Tel Aviv, Israel

Amir Kredi