Data Deduplication
Powered by Albireo Data Optimization Software
First generation deduplication technology attempted to solve just a backup issue. Permabit Deduplication, powered by Albireo Data Optimization Software, addresses the real storage management problem — optimizing your entire storage environment.
Permabit’s Albireo technology combines high performance data deduplication with traditional compression techniques. Permabit’s massively scalable deduplication approach is content aware and identifies segments of data within incoming data streams that are duplicates of segments already stored. Instead of storing additional redundant copies of these segments, Permabit stores additional references to the existing copies. Traditional compression techniques then compress any remaining segments before data is stored to disk.
Permabit’s Albireo second generation deduplication technology is much more effective than traditional data deduplication techniques alone because it compares new incoming data with a complete history of all previously stored data.
Optimized Snapshots
SDR also enables fast and efficient data snapshot capabilities. Permabit snapshots can be later used to access information that may have been inadvertently deleted from an active Permabit volume. Snapshots of a volume are created automatically at scheduled intervals or can be triggered manually by an administrator.
These snapshots can be used for versioning, for compliance purposes (to prove the state of data at a specific point in time), and as a fast and efficient data restoration mechanism for recovering inadvertently deleted information.
Optimized Replication
Figure 1. Permabit’s Scalable Data Reduction™ (SDR) technology combines high performance in–line data deduplication with traditional compression techniques without the need for any separate licenses, software, or additional hardware.
SDR is also utilized within Permabit’s replication technology. This allows replication to be optimized for a Wide Area Network (WAN) by only transmitting unique data that doesn’t already exist at the destination storage grid. The access nodes compare digital fingerprints across sites and if there is a match, the data is not sent over the wire, only a pointer is updated. This reduces the total amount of data that needs to be transmitted making replication very efficient and reduces line costs.
Permabit SDR Features:
- Built–in: SDR is a standard feature of Enterprise Archive. There are no additional licenses, software, or hardware to purchase.
- Massively Scalable: Patented technology allows SDR to scale across an entire storage grid making Permabit Enterprise Archive the most scalable data deduplication–based archive in the industry.
- In–line Deduplication: Data is deduplicated in–line and real–time allowing for data to be written directly to the storage nodes. This technique saves storage space because you don’t need to cache the information and process it afterwards.
- Sub–file Level Deduplication: Sub–file level deduplication provides a much higher reduction rate than file–based single instance storage technologies.
- Secure Digital Fingerprinting: Deduplication leverages the highest standard SHA–256 hashing algorithm, avoiding potential hash collisions that can be found in commonly used MD5 and SHA–1 hashing algorithms.
- Compression: Compression can be enabled to further reduce the storage footprint.
- Replication: SDR is utilized within Permabit’s replication technology providing a WAN optimized solution that eliminates replicating redundant data.
- Snapshots: SDR is leveraged within Permabit’s snapshotting technology allowing for thousands of snapshots to be taken while only consuming a fraction of the storage that the original data set required.
Key Benefits
- Store massive amounts of data in a fraction of their original storage footprint. This can drive effective cost per gigabyte to be less than $1.
- Reduce data center storage footprint by storing more data in less physical space.
- Save money by delaying incremental primary storage purchases. By archiving static data to the Permabit Enterprise Archive™ and reducing the overall storage footprint, primary storage purchases can be delayed for potentially years.
- Reduce power requirements by storing more information on less spinning disks.
- Reduce the amount of archive data being replicated for disaster recovery.
- Allows for snapshots to be taken on a regular basis without consuming massive amounts of storage.
The Permabit Advantage
| The Permabit Way | The Other Way |
|---|---|
| Dedupe — For all data. | Dedupe 1.0 — For backup only |
| In-line Deduplication — No additional disk space required and no de-dupe window needed. | Post-processing Deduplication — Requires disk staging area to hold data until it is processed for deduplication. Also, requires off –line window to process information. |
| Sub-file Deduplication — Reduces duplicate information at the block level allowing for higher deduplication rates. | File-level Single Instance Storage — Reduces duplicate information at the file level resulting in much lower “deduplication” rates. |
| Massively Scalable — Grid architecture allows deduplication to scale to hundreds of terabytes. | Not Scalable — Index databases limit scalability to maximum of tens of terabytes. |
| Secure — Leverages SHA–256 hashing algorithm to prevent against collisions during digital fingerprinting. | MD5 and SHA–1 — Known security threats already exist allowing for hash collisions jeopardizing data integrity. |