Pillar first past 2TB post Pillar Data is the first manufacturer to incorporate 2TB SATA drives in its arrays, doubling the Axiom product's capacity. CEO Mike Workman says the firm is using Western Digital's 5400rpm 2TB drive. Pillar was also the first array manufacturer to use 1TB drives, which came from Hitachi GST. Array subsystem manufacturer …
The first to use 2TB drives in a RAID unit? Or, rather, the first one to boast that on the web?
There are other reasons to take this message with a grain of salt. I've met customers who specified minimum guaranteed IOps per TB required. The modern desktop drives with 1.5 TB and above may well be below that target even for fairly boring applications such as "file sharing" websites... you get a nominally huge storage box, but effectively you cannot make use of all the free space - you cannot access it fast enough.
That sort of drives can be good enough for round-robin surveillance video archival or maybe HD video capture+editing (provided that the FS doesn't require too many IOps, and that you don't unleash too many parallel users unto the RAID box). The resulting IOps throughput is also a matter of what RAID level you configure...
No - SATA is not suitable for video capture as the drives are prone to thermal recalibration outages. Given SATA drives use inferior positioning mechanics (when compared to SAS and FC) this is really quite a horrible operation when you're streaming data.
2TB is an extremely bad idea if there's ever a chance you're going to lose part of your RAID set as the reconstruction times will be horrendous.
There's a very good reason most manufacturers have not implemented 2TB SATA-II.
You're absolutely right about SATA in workstation / homeboxes - the performance is woeful compared to equivalent SAS drives.
"If we moved 50,000 PB stored on 1TB disk to half the number of 2TB spindles, we could save the world more than $100M a year in energy costs."
Is this calculation including energy spent to manufacture, ship the new drives and waste the old ones ? I guess they could say the same next year with 4TB drives.
I would have thought a data centre upgrading from 1TB drives to 2TB drives would have to run for many years on those drives for the energy savings to add up firstly to the cost of the drives and secondly to the energy cost of manufacturing the drives.
50,000PB = 50,000,000 x 1TB drives (roughly)
50,000PB = 25,000,000 x 2TB drives
Let's say 2TB is about $300 (probably a lot more for 'enterprise' models)
25,000,000 x $300 = $7.5B
$7.5B / $100m per annum energy savings = 75 years to recoup costs.
Do the drives have a 75 year warranty then?
Exactly. People who opt for the bleeding edge "bits per square inch" on the platters, combined with four platters in a drive, should be prepared to replace a couple drives over the first month of operation, and some more over the first two years.
Neither SATA protocol-level compatibility, nor the drive size per se (compatibility with RAID firmware) have been too much of a problem lately, even with some lower-end RAID brands. It's nowadays a fairly safe bet that you can plug the latest drive into your two-year-old RAID box and it's gonna work. But the first deliveries of every bleeding-edge HDD model coming out can have maybe 20% of the drives essentially "dead on arrival", i.e. failing in RAID assembly burn-in. That's at least 10 times more compared to trailing-edge drives, such as the 80GB Barracuda 7200.10 being phased out just now.
Let me suggest a recipe: always warn the early adopters among your customers. When assembling a RAID unit, give it a thorough burn-in under generated load in your lab and replace any misbehaving drives before you ship the box to your customer. Keep a few pcs of the drives in stock for quick replacements. Favour RAID levels with more parity. If the RAID firmware is capable of that, schedule some periodic surface testing (exhaustive whole-surface reading) to prevent sudden "multiple failures" (bad sectors piling up undiscovered for a long time). When a drive fails, don't blame drive firmware, blame bad sectors on the high-density platters.
Of course I am biased, but ...
c.f http://scalability.org/?p=1693 and http://scalability.org/?p=1706 . That unit was shipped to a customer more than a month ago. We've shipped a number of 2TB units to customers over the last several months. So far, the drive reliability is pretty good. Far better than the early 750GB units, and 1TB units.
As for some of the other comments on performance ... well ... I prefer real measurements to speculation on performance, as I've found speculation often is at odds with actual results. Bug me at the above site if you want the io-bm.c code to see how things stack up. We've found it very useful, and are extending it. I also recommend fio (http://freshmeat.net/projects/fio/ ).
Joe
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2024
