Veritas Technologies LLC

Shengzhao Li

Xianbo Zhang

Weibao Wu

Shuangmin Zhang

Kai Lin Li

Kai Li

Yingsong Jia

Hong Yu Jia

Xu Jiang

Yongguo Yan

Xiangrui Liu

A method includes creating a deduplicated universal share (US) of data objects, which in turn includes receiving a US of the data objects, deduplicating the US, wherein deduplicating the US includes: hashing segments of the US to generate respective US segment fingerprints; comparing US segment fingerprints to fingerprints for respective segments held in deduplication storage in order to identify segments in the deduplication storage that equate to the US segments, respectively, of the US; storing identifiers that directly or indirectly identify locations, respectively, of the segments, respectively, in the deduplication storage that equate to the US segments, respectively, of the US. After creating the deduplicated universal share, a deduplicated backup of the US is created without reassembling the US from segments held in the deduplication storage, the creating the deduplicated backup including: creating a list that comprises copies of the stored identifiers, and storing the list.

Optimize backup from universal share

Systems, apparatuses, methods, and computer readable mediums for implementing an I/O router to route requests based on characteristics of the requests. The I/O router may receive requests targeting a single file, and the I/O router may route requests to multiple extent maps based on characteristics of the requests. For example, requests of a first size may be mapped to a first extent map, requests of a second size may be mapped to a second extent map, requests of a third size may be mapped to a third extent map, and so on. Additionally, the system may utilize different deduplication policies for the different types of requests which are mapped to different extent maps.

Routing I/O requests to improve read/write concurrency

Disclosed herein are methods, systems, and processes to improve backup performance after backup failure. It is determined whether a backup operation is successful. In response to a determination that the backup operation was unsuccessful, backup metadata associated with the backup operation is replaced with snapshot metadata associated with a snapshot that is taken at a first point in time that is prior to initiation of the backup operation. A rolled-back snapshot that permits another backup operation to be performed at a second point in time based on the snapshot metadata is then generated.

Backup performance after backup failure

The disclosed computer-implemented method for reducing data fragmentation may include (1) identifying update data which updates an initial data set; (2) categorizing, using a database manager, the update data based on how the update data is expected to impact digital storage device resources; (3) storing the update data in a physical storage device in a physical order based on the category of the update data; and (4) updating, after storing the update data, an extent map indicating a mapping of logical locations of the update data to physical locations at which the update data is stored. Various other methods, systems, and computer-readable media are also disclosed.

Systems and methods for reducing data fragmentation

Growing community of inventors

Shanghai, China

Shengzhao Li