Predictive Data Migration delivers advanced data protection.Today's massive capacity hard drives and stringent data availability Refers to the degree to which data can be instantly accessed. The term is mostly associated with service levels that are set up either by the internal IT organization or that may be guaranteed by a third party datacenter or storage provider. requirements are driving the need for more robust data protection and failure resiliency The ability to recover from a failure. The term may be applied to hardware, software or data. . With hard drives exceeding 500GBs in capacity and even larger drives on the horizon, the impact of a single drive failing and the resulting intensive XOR (eXclusive OR) A Boolean logic operation that is widely used in cryptography as well as in generating parity bits for error checking and fault tolerance. XOR compares two input bits and generates one output bit. The logic is simple. If the bits are the same, the result is 0. rebuild has reached the point of no return. During the rebuild process of the first failed drive, the likelihood of a second drive having an error or failing completely increases exponentially ex·po·nen·tial adj. 1. Of or relating to an exponent. 2. Mathematics a. Containing, involving, or expressed as an exponent. b. with both the size of the hard drives and the total capacity of the logical drive. With 400+GB hard drives, the amount of time required to completely rebuild a failed drive in a 12-15 drive RAID 5 logical drive is measured in days rather than hours. The longer the rebuild takes, the higher the risk to your data. In RAID 5, if you lose a second hard drive while the first one is still rebuilding, you lose 100 percent of your data. Even RAID 6 typically allows only two drives to fail before losing all data in the RAID set. Challenges These risks are magnified by the new applications environments that are incorporating SATA (Serial ATA) A serial version of the ATA (IDE) interface, which has been the de facto standard hard disk interface for desktop PCs for more than two decades. The original Parallel ATA (PATA) interface was launched in 1986. drives. The unprecedented capacity and data throughput of SATA technology have resulted in these drives being used in applications that have demanding availability requirements and little tolerance for downtime The time during which a computer is not functioning due to hardware, operating system or application program failure. or data loss. Conversely con·verse 1 intr.v. con·versed, con·vers·ing, con·vers·es 1. To engage in a spoken exchange of thoughts, ideas, or feelings; talk. See Synonyms at speak. 2. , SATA drives lack the sophisticated error recovery commands of SCSI SCSI in full Small Computer System Interface Once common standard for connecting peripheral devices (disks, modems, printers, etc.) to small and medium-sized computers. SCSI has given way to faster standards, such as Firewire and USB. drives, adding to the risk for potential data loss. While RAID 5 and 6 are great technologies for balancing performance, cost and capacity, they are negatively affected by drive failures and extended array rebuild times. Waiting for a hard drive to fail and then beginning the RAID engine intensive task of rebuilding a drive using XOR is no longer an option for today's organizations. A better solution is required. A unique technology called Predictive Data Migration (PDM (1) (Product Data Management) An information system used to manage the data for a product as it passes from engineering to manufacturing. The data includes plans, geometric models, CAD drawings, images, NC programs as well as all related project data, notes and ) can dramatically reduce the impact of SATA drive failures. PDM proactively detects possible drive failures before they occur and migrates data to a new healthy drive, minimizing the potential for data loss as well as the likelihood of a logical drive (array) going critical. Predictive Data Migration eliminates the need for a complicated and time-intensive RAID XOR drive rebuild altogether. Because PDM proactively monitors the health of all hard drives in the system, it activates before a drive fails and migrates data to a known healthy drive. This migration is a straight disk-to-disk copy that is many times faster and far less RAID engine-intensive than a full XOR rebuild. Using PDM, the time to migrate data from a 'sick' drive to a healthy one is up to five times faster than a traditional RAID 5 rebuild. A 1TB logical drive rebuild for RAID 5 can take an average of 32 hours. With PDM, the same logical drive can be migrated in less than 7 hours. Not only is it much faster to copy data from one drive to the next, it also has minimal impact on the performance of the RAID engine and the affected logical drive. Predictive Data Migration is part of PerfectRAID, a suite of data protection features that incorporates robust data handling and error management features including write hole prevention, read check tables and SMART support. In addition, the system takes advantage of advanced PerfectRAID features, including bad block remapping, and Media Patrol, which scan the system's drive media to ensure that even bad physical drives do not impact data availability. PerfectRAID features are carefully matched with the resilient See resiliency. RAID engine to deliver substantial data protection. Hammer Chien is engineering manager and Chi-chen Wu is vice president of engineering and chief technology officer at Promise Technology, Inc., Milpitas, CA www.promise.com |
|
||||||||||||||||||
Printer friendly
Cite/link
Email
Feedback
Reader Opinion