Who Makes the Best Hard Disk Drives? 444
Hamsterdan writes "Backblaze, the cloud backup company who open sourced their Storage Pod a few years ago, is now providing information on drive failure rates. They currently have over 27,000 consumer grade drives spinning in Backblaze storage pods. There are over 12,000 drives each from Seagate and Hitachi, and close to 3,000 from Western Digital (plus a too-small-for-statistical-reporting smattering of Toshiba and Samsung drives). One cool thing: Backblaze buys drives the way you and I do: they get the cheapest consumer-grade drives that will work. Their workload is almost one hundred percent write. Because they spread the incoming writes over several drives, their workload isn't overly performance intensive, either. Their results: Hitachi has the lowest overall failure rate (3.1% over three years). Western Digital has a slightly higher rate (5.2%), but the drives that fail tend to do so very early. Seagate drives fail much more often — 26.5% are dead by the three-year mark."
Re:Sad to hear (Score:0, Insightful)
They are not legally required to so why would they? This is the major flaw of libertarian thinking. The notion of an informed consumer in a world where the corporations can hide data on the failure rate of their products is ludicrous. But don't dare require it because it's fucking communism!
Re:Amazing how times change. (Score:5, Insightful)
Seagate drives are terrible drives now. I've had three of there external drives not last more then a year.
Agree, I bought 3 2TB Seagates for my home server a few years back...2 of them failed within a year. Yet another brand name I used to trust, now shot to shit.
And what about... (Score:5, Insightful)
Re:100% write? (Score:2, Insightful)
Back-ups. For example, at my company we have thousands of DLT tapes and fill about a dozen of them a week. Every Monday, they're moved offsite to a bank safe deposit box. Other than for testing, not a single time in the seven years I've worked here have we read a tape after it was written. We have 100% write. A friend works for Backblaze, and he just confirmed that they have basically the same situation. The vast majority of their users write data that they never read back.
Re:Ignorant to their own research (Score:5, Insightful)
If they are fairly fault tolerant, a reasonable Seagate discount percentage would overcome that higher failure rate, even allowing for installation costs. They can spread that failure out. An individual cannot, therefore I appreciate that they released the statistics.
Re:Amazing how times change. (Score:4, Insightful)
Seagate drives are terrible drives now. I've had three of there external drives not last more then a year.
Agree, I bought 3 2TB Seagates for my home server a few years back...2 of them failed within a year. Yet another brand name I used to trust, now shot to shit.
This is why you just buy whatever is cheap and rig up a RAID 5. A drive craps out and you throw another one in and keep on going.
Re:Amazing how times change. (Score:3, Insightful)
I'm not accusing you here, but I just wanted to point out that everyone has anecdotal evidence suggesting that ${company-A}'s drives suck and that ${company-B}'s drives are awesome. The only problem is that everyone has a different opinion on who companyA and companyB are!
This is a perfect case study on consumerism and confirmation bias. People swear by a product until it fails, and then they hate it and love the replacement until it fails...
Re:Amazing how times change. (Score:5, Insightful)
Re:Amazing how times change. (Score:5, Insightful)
Re:Sad to hear (Score:3, Insightful)
Re:Amazing how times change. (Score:5, Insightful)
They bought maxtor. The evil was contagious.
Too young to remember the Conner acquisition?
Re:And what about... (Score:5, Insightful)
Write-mostly workloads to a bunch of consumer grade disks will have errors that you may never detect.
At Backblaze, we try to pass over the data about once every two weeks. We re-read it from disk, recalculate a SHA1 checksum to make sure there wasn't any bits flipped or lost. It is my (informed) opinion that *ALL* hard drives and *ALL* configurations will have errors you may never detect unless you do this. You can't ever trust any file system.
I think many people assume RAID does this checksumming, as far as I know RAID handles entire drives failing, but it doesn't really have anything to do with a drive that has begun to fail and is starting to flip a few bits here and there but the drive is still mostly responsive.
Re:More Backblaze slashvertising (Score:5, Insightful)
Re:And what about... (Score:4, Insightful)
Doesn't matter if the disks do that internally, AC. When your entire business plan revolves around "keeping data safe" you don't create single points of failure. If the onboard ECC can catch n bit errors but n+1 bit errors are happening, it'd suck to find out the hard way.
Re:Amazing how times change. (Score:5, Insightful)
Seagate drives are terrible drives now. I've had three of there external drives not last more then a year.
Agree, I bought 3 2TB Seagates for my home server a few years back...2 of them failed within a year. Yet another brand name I used to trust, now shot to shit.
Why? Because you bought three drives from the same batch. Perhaps they had an issue with that version, or the firmware. Hard drives are extremely cyclical in regards to quality. I remember when Micropolis, Seagate, Western Digital, Quantum, IBM, Conner, and a couple of others used to trade spots for being the best and worst drive manufacturers on an almost yearly basis. I've gone through a hell of a lot of drives over the years, and don't really have a favorite brand. I've had many WD and Seagate drives fail over the years, though proportionally more WD drives. Currently I have a bunch of Seagate and WD spinning drives, along with a couple of Samsung's. I am pretty superstitious regarding anything call Desk Star though. I've had at least half a dozen different models of Desk Stars from both IBM and Hitachi fail with little warning.
Re:Amazing how times change. (Score:5, Insightful)
DO NOT buy 5 identical drives at the same time from the same place and same manufacturer or face increased risk of more than one dying at (or near) the same time.
Also keep in mind that raid will not protect you from data corruption (or more correctly, it will assure that you retain corrupt data). The happiest event is when a drive flat out dies.
Re:Amazing how times change. (Score:5, Insightful)
Not only that but I prefer to keep my data in MY control and not shoot it up someplace where someone might decide they want to peek at it! Apparently encryption these days offered by vendors is something that can be counted on to be compromised if someone decides to serve them papers. I'll keep my stuff mine thanks...
Re:Ignorant to their own research (Score:5, Insightful)
A question if I may - what are the experiences of BackBlaze when it comes to so called "bit rot"? You guys have enough drives in operation that this is a potential issue and I'm curious as to experience and countermeasures if any. With the rise of ZFS and BTRFS etc. this has been something that has caught my eye but I'm not yet sure it's something I'm inclined to worry about so i'm curious as to unbiased experiences. i know there has been an article or two in the past about how BackBlaze works but I don't recall these kinds of low level details being in it. Can you share?