Emc IP Holding Company LLC

Emc Corporation

Alexey Valentinovich Romanovskiy

Tianqing Wang

Vasily Olegovich Zalunin

Andrey Pakhomov

Nikolay Dmitrievich Egorov

Marat Ravilevich Gilmutdinov

Roman Alexandrovich Sokolovskiy

Victor Anatolievich Yastrebov

Dmitry Vadimovich Novikov

A technique for managing cache in a data storage system is disclosed. Data storage system cache memory is arranged into multiple input/output (IO) cache macroblocks, where a first set of IO cache macroblocks are configured as compressed IO cache macroblocks, each compressed IO cache macroblock storing a plurality of variable sized compressed IO data blocks, and a second set of IO cache macroblocks are configured as non-compressed IO cache macroblocks, each non-compressed IO cache macroblock storing a plurality of fixed sized non-compressed IO data blocks. A write request is receive at the data storage system. If the IO data associated with the write request is determined to be compressible, the IO data is compressed in-line and written to an IO data block in a compressed IO cache macroblock, otherwise non-compressed IO data is written to an IO data block in a non-compressed IO cache macroblock.

Managing cache compression in data storage systems

A technique for managing data storage in a data storage system is disclosed. Data blocks are written to a data storage system cache, pluralities of the data blocks being organized into cache macro blocks, the IO cache macro blocks having a fixed size. Access requests for the data blocks are processed, wherein processing includes generating block access statics. Using access statics, data blocks stored in the cache macroblocks having block a access times that overlap are identified. Data blocks identified as having overlapping access times are rearranged into one or more overlap cache macroblocks. Data storage system cache memory is arranged into multiple input/output (IO) cache macroblocks, where a first set of IO cache macroblocks are configured as compressed IO cache macro blocks, each compressed IO cache macro block storing a plurality of variable sized compressed IO data blocks, and a second set of IO cache macroblocks are configured as non-compressed IO cache macroblocks, each non-compressed IO cache macroblock storing a plurality of fixed sized non-compressed IO data blocks. A write request is receive at the data storage system. If the IO data associated with the write request is determined to be compressible, the IO data is compressed in-line and written to an IO data block in a compressed IO cache macroblock, otherwise non-compressed IO data is written to an IO data block in a non-compressed IO cache macroblock.

Cache data placement for compression in data storage systems

A method for selectively compressing data in a data storage system is provided. Data storage system cache memory is arranged into multiple input/output (IO) cache macroblocks, wherein a first set of IO cache macroblocks are configured as compressed IO cache macroblocks storing a plurality of variable sized compressed IO data blocks, and a second set of IO cache macroblocks are configured as non-compressed IO cache macroblocks storing a plurality of fixed sized non-compressed IO data blocks. An IO activity level of IO data blocks stored in IO cache macroblocks is determined. Multiple macroblock groups are created which correspond to a particular IO activity level. IO data blocks are arranged into macroblocks belonging to a macroblock category according to data block IO activity level. Each macroblock group is compressed, wherein compressing includes selecting a compression algorithm based on the macroblock category. The macroblocks are written to corresponding macroblocks in persistent storage.

Selective compression in data storage systems

A method includes (a) writing blocks of data to a storage device, pluralities of the blocks of data being organized into macroblocks, macroblocks having a first fixed size, pluralities of the macroblocks being organized into segments, segments having a second fixed size, (b) marking some of the written blocks as deleted, (c) computing a ratio of storage marked as deleted (SMD) from a segment and storage written (SW) to the segment (ratio SMD:SW), and (d) in response to the computed ratio exceeding a threshold value, performing a compaction operation on the segment. Performing the compaction operation on the segment includes (1) copying blocks which have not been marked as deleted from within macroblocks that contain at least one block marked as deleted to a new macroblock of the first fixed size and (2) in response to copying, marking the macroblocks from which the blocks were copied as free for reuse.

Techniques for automatically freeing space in a log-structured storage system based on segment fragmentation

Improved techniques of managing storage in a data storage system involve compressing a subset of block and macroblock metadata. Advantageously, a data storage system operating according to the improved techniques is able to store more metadata in volatile memory even for huge data objects.

Metadata structures for low latency and high throughput inline data compression

In some embodiments, a request to retrieve a photograph is received. The request is interpreted and associated metadata for the requested photograph is retrieved. A determination is then made as to whether to retrieve the content of the photograph from either a multi-image container file or from a photo cache. The content of the photograph is then retrieved from the determined source. Finally, the content of the photograph and associated metadata are displayed on a display.

Lightweight appliance for content retrieval

An improved lossless image compression technique involves adaptively selecting between spatial prediction and inter-component prediction techniques depending on which allows better results for any given component of a digital image pixel.

Lossless color image compression adaptively using spatial prediction or inter-component prediction

A method, article of manufacture, and apparatus for lightweight storage of content is disclosed. In some embodiments, a request to store a photograph is received from a user. The content of the photograph is then compressed. A list of multi-image container files associated with the user and with sufficient storage space available to store the compressed content of the photograph is then retrieved. The compressed content of the photograph is stored in a multi-image container file. Finally, the modified multi-image file is stored in a storage device.

Growing community of inventors

St. Petersburg, Russia

Alexey Valentinovich Romanovskiy