Application of duplicate data deletion in primary storage

Nowadays, the data de-duplication technology is no longer unfamiliar, and its value has been fully reflected in the backup domain, how to play the maximum value of duplicate data deletion technology is another problem that manufacturers need to think about. The extension of the data de-duplication technology to the primary storage domain (NetApp has pioneered the primary storage application of data deduplication) also gives us a glimpse of the vendors ' expectation that the technology will be more valuable. In the 2009 SNW China Conference, HIFN to show you its BITWACKR data de-duplication and data reduction technology, I also take the opportunity to HIFN with the sales director of China, Mr. Qiang Zhao on the value of data deduplication technology in the main storage area.

Do primary storage data require duplicate data deletion?

Primary storage is a natural way to avoid duplicate data deletion because it stores critical business data for the enterprise, and users are not affected by security and the production system. Some might even ask: Do primary storage require data deduplication? This starts with the data stored on the primary storage.

Unlike a backup, in primary storage, the system is at any time in the I/O exchange operation, the primary storage data changes are occurring at any time, this feature also determines that primary storage is not like the backup domain (typical example: Enterprise to do a daily incremental backup, a weekly full backup, and the last, cycle) There is a lot of duplication of data, and there may be a significant security cost (data in primary storage is critical), so we need to locate which data in primary storage is appropriate for duplicate data deletion or data compression.

Figure I: The difference between applying a duplicate data deletion on primary storage and backup storage

There is no doubt that virtualized data is a much more repetitive data in primary storage, with the rapid development and popularization of virtualization, the rapid increase of virtual machines, which makes this part of the data also increased rapidly, therefore, how to this part of the data security and reliable duplication of data deletion and data compression is a challenge to the manufacturers.

Figure II: The schematic diagram of HIFN Bitwackr technology to the virtual data weight