|
|
|
Stop the RAID0 Insanity!
|
2004-07-02
|
|
In February of 2003, we took a brief time-out from our standard, single-drive testing to formally address what we normally refuse to touch with a 12-foot pole- a RAID0 array. Why? The StorageReview Discussion community, mirroring forums around the net, burgeoned with hundreds of posts from readers seeking advice on which RAID adapter to get and which hard drives to stripe for their power rigs. Simple theory, however, indicated that striping would not significantly help the localized (as opposed to both random and sequential), low-depth usage that dominated even highly-multitasked, single-user scenarios. The best advice, as a result, was to avoid striping. Many readers, however refused to believe. The February test combined a pair of 200-gig Maxtor DiamondMax 9 drives with a Promise PATA RAID controller and demonstrated that the gains in striping them were minimal especially when one considered that a large portion of what gain there was due to the doubling of capacity and the resulting smaller distances that the actuator must travel to execute the same chain of disk accesses. There were still objections, irrational as they were:
“It’s only 7200 RPM! 10,000 RPM drives would have done better!”
“It’s only PATA! SATA would have done better!”
“It’s only eye-dee-eee! SCSI would have done better!”
“You tested only two drives! A larger array would have done better!”
And so on.Our recent TCQ, RAID, SCSI, and SATA article examined the performance of a myriad of controller/interface/drive-count/raid-level combinations that addressed the objections above (though admittedly as a side effect of testing TCQ’s effects on RAID arrays; we do not believe further empirical results were really necessary to back logic and theory). Many readers here at SR and across the net, unfortunately, seemed to have missed the article… though it is extremely relevant to those debating the relative merits or lack thereof of RAID arrays for non-server use. Consider this interesting example: In the “SR Gaming DriveMark… a 4 drive Cheetah array.. lags a single Raptor running on the "dumbest" of SATA controllers by a margin of 9%.”
If you’re still confused about RAID, you owe it to yourself to check out the review. Though the idea that RAID0 does not significantly assist desktop performance is not new to SR, AnandTech has recently corroborated the idea with results of their own. Confirming that no significant gain is realized when striping a pair of Raptors off of an ICH5 controller, Anand writes:
"If you haven't gotten the hint by now, we'll spell it out for you: there is no place, and no need for a RAID-0 array on a desktop computer."
Interestingly, the feedback associated with Anand’s article reads like a laundry list of the same irrational objections SR had to overcome. Anand is free, of course, to link to SR’s articles which, ironically, address virtually every objection raised by his RAID0 proponents ;).It is our hope that these findings taken as a whole will stem an internet-wide trend where enthusiast-oriented websites blithely incorporate RAID0 into their "high-end" single-user boxes, ignorant to both theory and empirical results. More discussion may be found here- weigh in with your thoughts!
|
 Previous Headlines... |
|
|
|
Recent Reviews & Articles
|
|
|
Seagate Savvio 15K.1
2007-05-01
Seagate's latest 15K RPM screamer isn't a Cheetah, but rather a diminutive 2.5 inch Savvio cranked up to rotate at the highest of speeds. Join StorageReview as we take a look at the latest arrival in the transition to a 2.5" enterprise market: The Savvio 15K.1.
|
Seagate Barracuda ES
2006-12-01
The server version of Seagate's consumer-oriented Barracuda 7200.10 brings the highest-ever capacity to the enterprise market. StorageReview takes a look to see how the 750 GB monster compares to the largest offerings from Hitachi, Maxtor, and WD.
|
Seagate Cheetah 15K.5
2006-09-21
Seagate's latest is the first SCSI drive to incorporate perpendicular recording technology and pushes the bar for 15K RPM spindle speeds to an impressive 300 GB. How does the industry giant's newest fare? Join SR as we put the 15K.5 to the test!
|
SATA in the Enterprise - A 500 GB Drive Roundup
2006-07-13
With cost, capacity, and interoperability driving change, SATA drives have made considerable headway into the enterprise sector. Seagate, Maxtor and Western Digital have all introduced capacious alternatives squarely aimed at a market served by SCSI and Fibre offerings. StorageReview takes a look at how the NL35.2, MaXLine Pro, and Caviar RE2 stack up!
|
SR's 250 GB Drive Roundup
2006-02-02
As a rule, StorageReview evaluates the largest, "flagship" drive within a given family. While this tenet permits impartial selection of review drives, it has at times created inequitable comparisons as some manufacturers tend to lag behind others when it comes to sheer capacity. Now, however, we'll take a break from the practice as we take a look at how affordable, 250 GB drives stack up from all five SATA manufacturers. Join us as we put drives from Hitachi, Maxtor, Samsung, Seagate, and WD to the test!
|
Western Digital Raptor WD1500
2006-01-03
WD’s long-awaited update to the 10,000 RPM SATA Raptor has arrived! The family’s new bellwether ups capacity up to 150 gigabytes and claims to significantly increase performance while maintaining the line’s admirable power and noise levels. Join StorageReview as we pit the Raptor WD1500 up against every currently available SCSI and SATA flagship in our comprehensive test suite!
Updated Jan 5th with information on the "Raptor X" (gaming) version.
|
|
More Articles...
|
|
