Archive

Posts Tagged ‘raid’

Portable Backup Drives Certified to Hold 12TB

December 22nd, 2011 Comments off

Portable Backup Drives,12TB,RAIDHighly Reliable Systems lately certified 4TB drives to be used within their RAIDPac detachable drives. Each RAIDPac consists of 3 SATA drives along with a RAID controller, supplying 12TB of detachable storage in each bay from the RAIDFrame backup solution.

Highly Reliable Systems of Reno, NV introduced their RAIDFrame DAS (Direct Attached Storage) backup system will support Hitachi and Seagate 4TB hard disk drives once they ship (expected first quarter of 2012). In RAID0 mode each RAIDPac holds 12TB of information, which makes it the earth’s biggest detachable backup cartridge. A RAIDPac consists of 3 drives as well as an integrated controller that travels using the backup cartridge. The machine attaches straight to a fileserver or NAS having a single eSATA or USB 3. cable

The organization intends to to produce niche NAS with detachable drive support according to Ubuntu Linux within the first quarter of 2012. The RAIDFrame will come in 1 bay, 2 bay, and 5 bay enclosures. The Two bay systems (pictured) allow further redundancy by permitting two RAIDPacs to become shown a configuration the organization calls “RAID 51”. Using hardware automatic reflecting technology implies that changing inside a new RAIDPac initiates one more block level copy from the primary backup. The RAIDFrame is made for high capacity and rapid server recovery and offers a method to supplement or replace cloud and/or tape methods.

RAIDPacs could be set up with RAID0 for optimum speed or with RAID5 to safeguard against single drive failures. Once the Seagate and Hitachi 4TB drives ship they’ll increase RAIDPac capabilities to 12TB/8TB (RAID0/5). Based on Tom Hoops, the organization CTO, no special motorists are essential since each RAIDPac sometimes appears through the host system like a single detachable hard disk. Unlike tapes a RAIDPac could be utilized directly in desperate situations with no RAIDFrame enclosure. Additionally towards the standard self-centering connector created for daily swap within the RAIDFrame, each RAIDPac has standard SATA and USB3 connections around the back.

Redundancy is accomplished using RAID5 and/or by reflecting to a different RAIDPac. By utilizing multiple tubes (just like tapes – a replacement every day in rotation), past full backup copies could be maintained with time. The whole line continues to be upgraded to permit faster RAID5, faster reflecting, and software management. Backup and restore performance surpasses 400Gigabytes each hour using imaging software on modern servers.

Highly Reliable Systems sells the merchandise through merchants. 6TB RAIDPacs (that contains three 2TB drives and RAID controller) are $1208 MSRP.

For more information call 877-384-6838.

Data Backup Glossary (Letter Q)

October 26th, 2011 Comments off

Data Backup Glossary (Letter Q)RAID
See redundant array of independent (or inexpensive) disks.

RAIN
See redundant array of independent nodes.

Raised floor
A type of flooring supported by a metal grid and typically used in data centers. Raised flooring can be removed in pieces to allow for cabling, wiring, and cooling systems to run under the floor space. When the floor is raised, it usually can accommodate space for walking or crawling in.

Recovery
The recreation of a past operational state of an entire application or computing environment. Recovery is required after an application or computing environment has been destroyed or otherwise rendered unusable. It may include restoration of application data, if that data has been destroyed as well.

Recovery point objective
Recovery point objective (RPO) is the maximum acceptable time period prior to a failure or disaster during which changes to data may be lost as a consequence of recovery. Data changes preceding the failure or disaster by at least this time period are preserved by recovery. Zero is a valid value and is equivalent to a “zero data loss” requirement.

Recovery time objective
Recovery time objective (RTO) is the period of time after an outage in which the systems and data must be restored to the predetermined recovery point.

Red Hat Global File System
Red Hat Global File System (GFS) is an open source cluster file system and volume manager that executes on Red Hat Enterprise Linux servers attached to a storage area network (SAN). It enables a cluster of Linux servers to share data in a common pool of storage to provide a consistent file system image across server nodes. Red Hat Global File System works on all major server and storage platforms supported by Red Hat.

Redundancy
The inclusion of extra components of a given type in a system (beyond those required by the system to carry out its function) for the purpose of enabling continued operation in the event of a component failure.

Redundant array of independent (or inexpensive) disks
Redundant array of independent (or inexpensive) disks (RAID) is a category of disk drives that employ two or more drives in combination for fault tolerance and performance. RAID disk drives are used frequently on servers but aren’t generally necessary for personal computers. RAID allows you to store the same data redundantly (in multiple places) in a balanced way to improve overall performance.

Redundant array of independent nodes
Redundant array of independent nodes (RAIN) is a data storage and protection system architecture. It uses an open architecture that combines standard computing and networking hardware with management software to create a system that is more distributed and scalable. RAIN is based on the idea of linking RAID nodes together into a larger storage mechanism. In a RAIN setup, there are multiple servers, each with disk drive and RAID functionality, all working together as a RAIN, or a parity or mirrored implementation. RAIN may also be called storage grid.

Remote offices/branch offices (ROBOs)
Refers to corporate offices externally connected to a WAN or a LAN. These offices will often have one or more servers to provide branch users with file, print, and the other services required to maintain the daily routine.

Replicate
(n.)  A copy of a collection of data.
(v.) The action of making a replicate as defined above.

Restore
To bring a desired data set back from the backup media.

Rotational latency
Also called rotational delay, the amount of time it takes for the desired sector of a disk (for example, the sector from which data is to be read or written) to rotate under the read-write heads of the disk drive. The average rotational latency for a disk is half the amount of time it takes for the disk to make one revolution. The term typically is applied to rotating storage devices, such as hard disk drives and floppy drives (and even older magnetic drum systems), but not to tape drives.

RPO
See recovery point objective.

RTO
See recovery time objective.

Run length limited
Run length limited (RLL) is an encoding scheme used to store data on newer PC hard disks. RLL produces fast data access times and increases a disk’s storage capacity over the older encoding scheme called MFM (modified frequency modulation).

Tips For Replacing A Hard Drive From A Failed RAID

January 18th, 2011 Comments off

Tips For Replacing A Hard Drive From A Failed RAIDThere are some items to consider when replacing a hard drive from a failed RAID. If you are building a new RAID, then all hard drives in the array should be the identical model if at all possible. However, if you must replace a failed hard drive, it can sometimes be difficult to find the same model if that model is out of production.

Below are some tips to follow when selecting a replacement:

Keep in mind that the controller may or may not allow different models in a RAID, so check the RAID controller documentation.

Product life: What is the expected life of the remaining drives? If the other drives are approaching the end of their useful life, then it may be time to replace the entire RAID.

Capacity: The replacement drive should be the same or higher capacity than the original drive. Do not just look at the capacity on the box, since a few megabytes could make the difference between whether the drive will work or not.

(You should check the number of LBAs (or sectors) on the hard drive. Some RAID controllers will allow you to substitute larger drives if the exact capacity is not available, while other controllers require an exact match. Check with the controller manufacturer if the documentation doesn’t make it clear!)

Performance: The replacement drive should match the performance of the remaining drives as closely as possible. If your failed drive was 15,000 RPM, avoid replacing it with a 10,000 RPM drive. RAID arrays depend on the timing between drives to write data. Thus, if one drive doesn’t keep up, it may cause the entire array to fail or at least experience irritating problems.

Interface: Make sure the replacement drive uses the same type of interface connection as the failed drive. If the failed drive used a SCSI SCA (80-Pin) interface then don’t try to replace it with a 68-pin SCSI interface. With Seagate products the last two digits of the model number indicate the interface. For example: LW = 68-Pin, LC = 80-Pin.

The 80-pin LC drives are hot-swappable with backplane connections.

Cache Buffer: It is recommended that the cache buffer for each drive be the same value.  Most RAID controllers will consider drives with mismatching cache buffers to be ineligible for addition to a striped or parity array.

Glossary of Western Digital Hard Disk Drive (Letter R)

August 28th, 2010 Comments off

radial path
A straight-line path from the center of a disk to the outer edge.

RAFF™
Rotary Acceleration Feed Forward. WD technology that maintains the highest possible data transfer performance in the high rotational vibration environments commonly found in servers and storage arrays.

RAID
Redundant array of independent disks. A grouping of hard drives in a single system to provide greater performance and data integrity.

RAID 0
RAID protocol in which data is striped across multiple hard drives, enabling the accelerated reading and recording of data by combining the work of two or more drives to increase performance. See also striping.

RAID 1
RAID protocol in which two copies of the data are instantaneously recorded – each on separate hard drives. RAID 1 ensures the protection of users’ data because in the event that one of the hard drives fails, the other hard drive(s) will continue to read and write data until the faulty hard drive is replaced and rebuilt to once again safely mirror the data. See also mirroring.

RAID 5
For systems with three or more drives, RAID 5 offers fast performance by striping data across all drives; data protection by dedicating a quarter of each drive to fault tolerance leaving three quarters of the system capacity available for data storage.

RAM
Random access memory. Memory that allows any storage location to be accessed randomly.

Ramp Load/Unload (LUL)
Ramp load parks the recording head off the media when the drive is idle and on spin up, maximizing available disk space and minimizing power usage, which results in lower heat and long-term drive reliability.

RE
RAID edition. A WD drive engineered to thrive in a high-intensity RAID system while still offering traditional desktop value.

read channel
The channel that performs data encoding and conversion that a drive requires to write computer generated information onto a magnetic medium and read back that information with a high degree of accuracy.

read verify
A data accuracy check performed by having a disk read data from a controller, which in turn checks for errors but does not pass data to the system.

read/write head
See head.

recoverable error
A read error that can be corrected by ECC or by re-reading data.

RLL
Run length limited. An encoding scheme used during write operations to facilitate reading that data.

RoHS
Restriction of Hazardous Substances. This compliance Directive 2002/95/EC of the European Parliament, which is effective in the EU beginning July 1, 2006, aims to protect human health and the environment by restricting the use of certain hazardous substances such as lead, mercury, hexavalent chromium, cadmium, polybrominated biphenyl flame retardants, and polybrominated diphenyl ether flame retardants in new equipment.

ROM
Read-only memory. An integrated circuit memory chip containing programs and data that the computer or host can read but cannot modify. A computer can read instructions from ROM but cannot store data in ROM.

rotational latency
The amount of delay in obtaining information from a disk due to disk rotation. For a disk rotating at 5400 RPM, the average rotational latency is 5.5 milliseconds. See also mechanical latency.

RPM
Rotations per minute. Also known as spindle speed. Rotational speed of a medium (disk). Hard drives typically spin at a constant speed. The lower the RPM, the higher the mechanical latency. Disk RPM is a critical component of drive performance, as it directly affects rotational latency.

RPS™
Reduced power spinup. The WD-optimized spinup feature specifically designed for the external hard drive and consumer electronics markets.

Tips for Replacing a Drive from a Failed RAID

June 2nd, 2010 Comments off

Replace a drive from a Failed Raid There are several items to consider when replacing a drive from a failed RAID. If you are building a new RAID, then all drives in the array should be the identical model if at all possible.

However, if you must replace a failed drive, it can sometimes be difficult to find the same model if that model is out of production. Below are some tips to follow when selecting a replacement.

Note: Keep in mind that the controller may or may not allow different models in a RAID, so check the RAID controller documentation.

1. Product life: What is the expected life of the remaining drives? If the other drives are approaching the end of their useful life, then it may be time to replace the entire RAID.

2. Capacity: The replacement drive should be the same or higher capacity than the original drive. Do not just look at the capacity on the box, since a few megabytes could make the difference between whether the drive will work or not.

You should check the number of LBAs (or sectors) on the drive. Some RAID controllers will allow you to substitute larger drives if the exact capacity is not available, while other controllers require an exact match. Check with the controller manufacturer if the documentation doesn’t make it clear.

3. Performance: The replacement drive should match the performance of the remaining drives as closely as possible. If your failed drive was 15,000 RPM, avoid replacing it with a 10,000 RPM drive. RAID arrays depend on the timing between drives to write data. Thus, if one drive doesn’t keep up, it may cause the entire array to fail or at least experience irritating problems.

4. Interface: Make sure the replacement drive uses the same type of interface connection as the failed drive. If the failed drive used a SCSI SCA (80-Pin) interface then don’t try to replace it with a 68-pin SCSI interface. With Seagate products the last two digits of the model number indicate the interface.
For example:
LW = 68-Pin
LC = 80-Pin
The 80-pin LC drives are hot-swappable with backplane connections.

5. Cache Buffer: It is recommended that the cache buffer for each drive be the same value.  Most RAID controllers will consider drives with mismatching cache buffers to be ineligible for addition to a striped or parity array.