Facebook Experimenting With Blu-ray As a Storage Medium 193
s122604 links to CNN's explanation of what may be the future of cold (or at least lukewarm) storage at Facebook, which is experimenting with massive arrays of Blu-Ray discs for seldom-accessed user files. Says the report: The discs are held in groups of 12 in locked cartridges and are extracted by a robotic arm whenever they're needed.
One rack contains 10,000 discs, and is capable of storing a petabyte of data, or one million gigabytes.
Blu-ray discs offer a number of advantages versus hard drives. For one thing, the discs are more resilient: they're water- and dust-resistant, and better able to withstand temperature swings. Their data can be restored more quickly, and they're easier to transport.
Most important, though, is cost. Because the Blu-ray system doesn't need to be powered when the discs aren't in use, it uses 80% less power than the hard-drive arrangement, cutting overall costs in half.
Why not just use hard drives and then store... (Score:2, Insightful)
... those drives offline or come up with a system to power up the drives via custom san hardware when you want to access them? With facebooks cash it should be do-able.
Re: (Score:3)
Re:Why not just use hard drives and then store... (Score:5, Informative)
They'd also be cheaper, even at the bulk HDD rate that FB would pay.
A quick on-line search show a spindle of fifty 50GB Blu-Ray discs (2.5 TB) retails for about $100. A 4TB HDD costs about $140. So HDD is actually cheaper per byte of storage. Maybe wholesale price ratios are way different from retail, but I see no reason to assume that. So BluRay doesn't win on price, volume, or access speed. The concerns about moisture and big temperature swings seems odd. Are Facebook data centers exposed to the weather?
Re:Why not just use hard drives and then store... (Score:5, Funny)
This is a company who's product stack is written in PHP.
Re: (Score:3)
If you are going to slag someone about their use of the English language you could at least tell them the correct word. In this case "whose" is the correct word.
Re: (Score:3)
Re: (Score:3)
This estimate also ignores the cost of a robotic system, powering that system, and maintanence and doesn't factor in costs for redundancy (they need two robotic systems, not one.) The whole thing is phenomenally stupid. As someone already pointed out before I got here to say the same, if you want to take data offline simply literally take it offline. Power down the friggin hard drive array completely. Power it back up when needed.
Bingo... but given the mass of data Facebook has set themselves up to store they would
do well to try a multitude of things.
And redundancy of two at this scale is not going to be sufficient.
The media will need to be organized as a RAID larger and wider
than anything folk are used to thinking about.
A read error on one disc will need to be validated by a very big ECC code
on the media and also on redundant media local and far away. Two copies
gives little voting confidence as to which is incorrect so dust off
Re:Why not just use hard drives and then store... (Score:5, Interesting)
What you describe is called a MAID and over the years it has proven quite unreliable. Hard disks are sensitive creatures and don't age well when being powered-on/powered-off randomly, and because of the nature of cold storage it is difficult to achieve a right balance of redundancy and power savings.
Also I would advise you to be careful when you label something as "phenomenally stupid" otherwise in instances like this one it may make you look like you are "phenomenally uninformed".
Re: (Score:2)
According to the article itself, this BD storage farm only gains an edge once you bring power costs into the equation. So everyone's inclinations to go WTF aren't that far off the mark really.
Re:Why not just use hard drives and then store... (Score:5, Insightful)
When you deal with cold storage you have to look at things from a node level, not in global storage size. If your basic unit is a 50GB device instead of a 4TB device, this means that each request you make to recall data has a much smaller footprint.
Let's say that each stored account takes up 1GB of space. That's 50 accounts per BD drive, and 4000 accounts per hard disk. This means that when some dude comes out of jail and tries to access the photo his mom posted on his Facebook wall in 2010, there are 3999 accounts that are pulled out of their coma with it for no reason. On a BD that's only 49.
As long as you partition stuff properly it's unlikely that a single request will span multiple BD drives. You may have to deal with clusters of BD disks and this requires a bit of tuning, but even with the best indexing system in the world you can't power up only part of a hard disk. So BD is a clear winner here, especially if to that footprint issue you add the fact that spinners die quickly when you keep playing with the on/off switch.
Bytes are bytes when you live in a software world. But physical factors and limitations come into play when you deal with storage, and that's why most people with a software background can see WTF where there is instead good engineering.
Re: (Score:2)
The Blu-ray disc needs to be mounted before it can be accessed. The ratio of robotic mechanisms to discs becomes important. If you need to mount ten discs, it takes ten times as long (if they're all using the same arm) whereas you could spin up ten hard drives simultaneously.
I've worked with large scale robotics since the late 80's. The performance of the arms has not increased significantly since then. When you're dealing with scientific datasets or backups it's not as much of a problem. In random acc
Re:Why not just use hard drives and then store... (Score:5, Informative)
So HDD is actually cheaper per byte of storage.
If the HD needs to be replaced much more frequently than the Blu-Ray media the advantage switches quite quickly. For example, if the HD is replaced every 5 years and the Blu-Ray media is replaced every 20 years the HD would have to cost 1/4 of the Blu-Ray to match the hardware price.
The concerns about moisture and big temperature swings seems odd.
Temperature and humidity control are very expensive as it takes a lot of electricity. If the media can handle higher temperature and humidity swings then operation costs will be much lower.
Re: (Score:2)
If the HD needs to be replaced much more frequently than the Blu-Ray ...
Do they? I have seen estimates of 10-15 years for recorded BluRay, but that assumes they are kept cool and dry. If they are kept in a humid environment with big swings in temp, the lifetime might be much shorter.
Also, you are assuming the replacement price of a new HDD five years from now would be the same as now. This is almost certainly not true. HDD prices have historically fallen much faster than Moore's Law. So in five years, you may be able to get 20GB for what a 4GB HDD costs today. Historically
Re: (Score:3)
It all depends on the numbers which we don't have. The problem is the use of relative terms like "wide range" and "higher humidity". For example, High humidity in the tropic is much different than high humidity in the desert. If BR media can handle a wider range of temperature and a higher humidity level there will be savings in HVAC.
So in five years, you may be able to get 20GB for what a 4GB HDD costs today.
That is an assumption and I bet that Facebook has looked at what is coming down the pipe. It is quite possible that these price decreases will slow. By the way HD prices [jcmit.com] have
Re: (Score:2)
You're not factoring in the 2011 Thailand flood that set back Moore's Law for hard drives by 2+ years...
This might have set back manufacturing and availability of existing products
at the time, but whyTF would it have set back R&D for new products?
Re: (Score:3)
Building storage with hard drives doesn't get you an article on Slashdot (or CNN); pretending you're going to build storage out of optical discs does.
Re: (Score:3)
They'd also be cheaper, even at the bulk HDD rate that FB would pay.
A quick on-line search show a spindle of fifty 50GB Blu-Ray discs (2.5 TB) retails for about $100. A 4TB HDD costs about $140. So HDD is actually cheaper per byte of storage. Maybe wholesale price ratios are way different from retail, but I see no reason to assume that. So BluRay doesn't win on price, volume, or access speed. The concerns about moisture and big temperature swings seems odd. Are Facebook data centers exposed to the weather?
Seldom used data sitting in spinning power draining disks has a continuous power cost.
Power and cooling are important data center considerations.
Facebook has an astounding pile of data in picture archives that after a couple months are
only called on once in a while if ever again.
Layers of storage from the modern very quick SSD devices to spinning rust disks to perhaps BluRay
seem to have a place when access time and space considerations come to play. I wish them luck.
One problem with BlueRay, DVD and CDROM
Re: (Score:2)
Seldom used data sitting in spinning power draining disks has a continuous power cost.
Seldom accessed HDDs can be spun down, or even completely powered off.
Re: (Score:2)
Seldom used data sitting in spinning power draining disks has a continuous power cost.
Why is it that you can turn off blue ray drives, but not hard drives?
Last I checked, my hard drives were simple to power on and off on the fly.
Facebook has an astounding pile of data in picture archives that after a couple months are
only called on once in a while if ever again.
And thats not what these are being used for because the page would time out before it pulled any of those pictures off the disc for display. This is for archiving what you do on the Internet once the data has been materialized by their algorithms. It can be restored and reprocessed if they want/need to.
One problem with BlueRay, DVD and CDROM media is the lack of data as storage beyond
five years or so
Not sure where you live, but writable blu ray was available in
Re: (Score:2)
Why is it that you can turn off blue ray drives, but not hard drives?
Last I checked, my hard drives were simple to power on and off on the fly.
Check again. Hard drives are not designed to be cycled on and off a lot
Re: (Score:2)
Not sure where you live, but writable blu ray was available in 2002 initially. DVD in 1997, CD in 1988. We're a little past 5 years. Thats 12 for BD, 17 for DVD, and 26 for CD. There is a wealth of data on storage life on all of them if you know where to look.
Yes,
yet there was a big deal not too long ago where DVD media began to come apart
after about five years. The rumor was that it was a manufacturing FUBAR that lasted
a couple years and impacted a lot of big name players.
I picked five years to comment because apparently the life of media has two statistical humps.
The five year one points to short term risks unknown at day one and the 12 and 17 year data gives
hope that the 40 to 100 year storage life expectation is possible. Bursts of defective media dis
Re: (Score:2)
Re: (Score:2)
If they were seriously concerned about price, theyd be using something like LTO5, which is like ~$20/TB.
Re: (Score:2)
I thought that too. My only guess was that Blu-Ray seeks faster, allowing quicker access to a single file or single archive in the middle of the disk.
Re: (Score:2)
Re: (Score:3)
While a hard drive may be cheaper at time of initial purchase,it likely has a significantly shorter lifespan as well
This is just conjecture, unless you have some actual data on recorded BluRay lifespans.
more reliable "Enterprise" drives typically cost three times as much)
"Enterprise" HDDs are NOT more reliable. That is a myth promulgated by HDD vendors. Facebook uses "consumer" grade HDDs in their data centers. So does Google. So do all other informed non-idiots.
Re: (Score:2)
A quick on-line search show a spindle of fifty 50GB Blu-Ray discs (2.5 TB) retails for about $100. A 4TB HDD costs about $140. So HDD is actually cheaper per byte of storage.
The initial hardware is cheaper with HDDs. Operational overhead might be entirely different. An HDD needs to be plugged in all the time (consuming power) while a Blu-Ray (or DVD for that matter) does not. Also, an infrequently accessed Blu-Ray, stored properly, is likely to have a much longer shelf-life than a drive that is always powered up, leading to lower overhead in the form of replacement/recovery costs.
Re: (Score:2)
Re: (Score:3)
I think there is plenty of reason to assume that the retail markup on writable Blu-Ray disks (a niche market at best)
They are for sale on hundreds of sites, and hundreds more sellers on eBay. Not a "niche" market at all.
I wouldn't be surprised at all if Facebook can buy 50 BD-R discs for $10.
No way. That is 20 cents each. The lowest price, from eBay sellers in China, is $2 each. There is absolutely no way that a 90% margin could be maintained in a competitive market. If they wholesaled for 20 cents, someone would be hawking them on eBay for a 10% markup, or 22 cents. Maybe less.
Re: (Score:2)
Re: (Score:2)
You could have a robot unplug/plug HDs, but once you're accepting the latency of disk changes and spin-up, I imagine Blu-Ray disks would be much, much cheaper than a similar capacity of HDs.
Re: (Score:2)
Re: (Score:2)
You could have a robot unplug/plug HDs, but once you're accepting the latency of disk changes and spin-up, I imagine Blu-Ray disks would be much, much cheaper than a similar capacity of HDs.
Yes except the connectors are not rated for many disconnects and reconnects.
Hard drive media needs to spin up often. If the drive is not spun then there are
risks of the media and heads having problems. The complexity of the electronics
and component life expectancy on the drives may be less than Blu-Ray media.
There are just too many moving (active) parts in the drive to believe that media with
no moving parts has an equal MTBF value.
With deep pockets and money in the bank... this is worth a hard look.
Re:Why not just use hard drives and then store... (Score:5, Interesting)
You're actually talking about MAID (Massive Array of Idle Disks), a technology that I first encountered in 2002. Now-bankrupt Copan Systems was the company I first encountered that was doing MAID, and New SGI (i.e. former Rackable Systems) bought their assets out of bankruptcy in 2010. Most storage companies now offer MAID add-ons for their storage arrays, though not all of them allow completely powering down the drive like Copan's solution did.
The upsides of MAID: Disks are cheap. Turning on and spinning up a hard drive to pull up some bits is faster than a robot fetching a Blu-Ray disk, placing it into a drive in the jukebox, and waiting for the disk to spin up and come online. You could store many more bytes in a cabinet with MAID than you could in an optical disk cabinet.
Downsides: The disk drives in a MAID array simply don't last that long, comparatively speaking. Spinning them up and down all the time is hard on a drive. So you end up having to replicate data and from time to time migrate data to new drives as old drives reach their service life. The service life of rarely used Blu-Ray media that has always been handled robotically (i.e., nothing touching its surfaces ever) is such that Blu-Ray media from ten years ago is probably still usable, the technology itself will become obsolete like DVD-RAM long before the media wears out. Not so much with hard drives, though disk arrays basically have unlimited life given typical failure patterns (i.e., if you're using RAID6, a drive develops errors, you remove the failing drive from the array, rebuild the array on a new drive, and chances of having two more drives fail during rebuild and thus losing the array are slim for a 12-drive array). So MAID has not really taken off the way we expected ten years ago.
At the time I first encountered MAID I was working for a company called DISC Storage, which had a NAS head which would automatically migrate little-used data to an optical jukebox in a way similar to what Facebook appears to be attempting. I designed and implemented the clustering function that would replicate the data between two NAS heads / optical jukeboxes, since the DVD-RAM platters were not themselves RAID'ed, as well as implemented a lot of the back end functionality for jukebox control and so forth. In any event, it looked like a NAS head but most of the files had been migrated to the DVD-RAM platters, and if you accessed one of those files, you would (at some point maybe 15 seconds later) get your data back as the file got read back onto the hard drive. It worked. But it was somewhat slow and cumbersome, because you're relying on a robot to go out and fetch the disk and put it in a drive, and disk robots then, and now, simply aren't that fast compared to media that's already in a drive ready to be spun up and read.
So anyhow, it was fairly obvious to me by mid 2003 that optical jukeboxes simply weren't going to be the future. In the ten years since DISC went under (there is a German company by that name now but it isn't the same company, it bought the name and some of the IP), I have not had any inclination to work for a company doing optical storage, because it's clear that for most problems it isn't the solution. It's too slow, too bulky, and magnetic disk drives and magnetic tape drives just continue getting bigger and cheaper every day. And now, with SSD coming on strong, optical jukeboxes look even less compelling.
So color me amazed. Optical jukebox and optical media technology essentially has barely moved on in the past ten years and what wasn't particularly compelling then, is even less compelling now. If you have need to keep data for a *long* time, this is how you do it... but frankly, I will be surprised if Facebook even exists ten years from now given the pace of innovation in the industry (though I'm just as surprised that Slashdot still exists!), so I question why they would do this rather than invest in LTO tape libraries, which have the advantage of being significantly denser.
Powered down hard drive (Score:2)
Re: (Score:2)
Re: (Score:2)
I know that enterprise grade hard drive are made to be spinning for years without fail
Facebook does not use "enterprise grade" HDDs. There is no evidence that "enterprise grade" HDDs are faster, or more reliable. "Enterprise grade" is really just a label slapped on some drives to give stupid people something to spend their money on.
Right to be forgotten? (Score:5, Interesting)
Re: (Score:2)
Re: (Score:3, Funny)
Can I ask Facebook to delete my stuff from one of those (assuming I had a Facebook account in the first place)
You can ask, yes.
Re: (Score:2)
Anything you have ever put online can reasonably be assumed to be permanent. If you had a blog once and deleted it, years ago, you can often still reactivate it with all of the previous content still totally intact. Aside from the companies themselves keeping all data of any sort forever, odd creatures like the Wayback Machine and RSS feeds eager to slurp down text will preserve your drunken 3am ramblings for posterity. Data space is very cheap, right now, and text in particular barely makes a tiny blip on
Re: (Score:2)
Educated guess: since some files will eventually have to be modified/deleted, and they aren't about to toss a disc every time, I'm guessing they log file (block?) invalidation for deletes/updates. Once the disc has too little valid data, the valid data (likely of several discs in the same condition) is copied to a new disc and the old one goes to the shredder.
If regulations internal or legal) specify that some data has to be effectively destroyed at the moment, then just skip the invalidation bit and replac
Re: (Score:2)
Re: (Score:2)
Yes you can. They won't do it, but you can ask. This doesn't actually represent a policy change though.
Re: (Score:2)
There's no such right, though there are some EU governments creating an enforced privilege, even for stuff paraded out in public.
For everybody else, check the agreement you enter into voluntarily when creating an account.
Re: (Score:2)
The filesystem used on these discs does allow for files to be deleted, although of course the data is not physically removed and is recoverable. I think most EU data protection laws would be satisfied with that though, as the point is to stop the company using the data.
Re: (Score:2)
The right to be forgotten should apply to Facebook as well. What it doesn't apply to is first-party stuff that gets covered by freedom of the press, as that is considered to trump the privacy freedom. Don't ask me how they decide whether or not to consider Facebook "press". I quickly get lost in the mind-boggling logic of telling Google not to list something in an index that is sitting publicly on a website.
Re: (Score:2)
What should be the case is that your personal information belong to YOU and not google or facebook. Then you get to call the shots.
Everything old is new again. (Score:5, Informative)
Enterprises have been doing this with tape for 30 years.
In fact, modern tape technology probably has a higher "volumetric" density than BD.
Re: (Score:2)
Re: (Score:2)
Tape may have better density, but Blu-Ray probably has better access time. Sounds like this is still stuff they want to have "live", they are just willing to have be a little "less live" than HD latencies.
Re: (Score:3)
Re: (Score:2)
It's not the access time, it's the fact that accessing a random file on tape causes wear as the tape has to be wound to the right point and a read head has to make contact with it. Optical discs don't have those problems.
Re: (Score:2)
Re: (Score:2)
Say 1GB per user profile on average, a tape will then hold 1000+ profiles. 300 reads from a tape before it dies suddenly doesn't sound so good.
Re: (Score:2)
they've been doing this with CD for 30 years (Score:2)
they had cold-storage CD jukeboxes at (well-known HVAC) back that far for old catalog crep. heck, they had rooms full of videotape carts in TV stations back that far... take your pick, VHS pro or Beta Pro. robotic storage is way old, just the medium changes, depending on what you are used to in your industry.
Re: (Score:2)
And besides, HD-DVD is better than Bluray for this stuff.
Re:Everything old is new again. (Score:4, Interesting)
Tape has always had a limited life-span and is too easily damaged to completely trust with high-value archival data. Instead, archival on tape usually means "we're not quite confident enough to just delete this crap".
Meanwhile, Sony's enterprise-grade write-once (WORM) magneto-optical (MO) discs have been around for decades, are physically tougher, and impervious to magnetic fields, sold with 100-year warranties that even cover data-loss recovery costs.
BD-RW can certainly be seen as Sony's MO technology being brought down dramatically in price due to economies of scale, and intentionally to allow them to compete in the consumer space.
Re: (Score:2)
Tape has always had a limited life-span and is too easily damaged to completely trust with high-value archival data. Instead, archival on tape usually means "we're not quite confident enough to just delete this crap".
Maybe the cheap crap. I've pulled 7 year old data off of SuperDLT tapes.
Re: (Score:2)
Re: (Score:2)
MO and Bluray are fundamentally different technologies and are not even remotely comparable. MO disks require (IIRC) a bit to be raised to a very high temperature to alter, while bluray just requires the organic dye to degrade (as they all do). Bluray has an impressive operational history of ~8 years, Tape (ie LTO techs) have operational records going back decades.
Calling tape a poor archival choice is hillariously backwards. You'd have to be ignorant or foolish to rely on dye-based mediums like bluray f
Re: (Score:3)
There are at least 3 distinct types of Blu-ray discs: Commercially pressed, -R, and -RW (well, they call them -RE, but... meh).
Only one of the three types uses an organic dye that degrades. Instead BD-RW has much in common with MO discs, and was reportedly the first format Sony developed, thanks to their existing MO technology.
Re: (Score:2)
I've personally handled tens of thousands of LTO tapes, and I've had less than five go bad. Three had soft media errors (where there was no data loss, just stuff that ECC codes were able to handle), and two had issues with being handled by the grippers in the robot.
I've also have recently pulled data from DLT IV tapes from 1998, no errors.
Plus, tape isn't expensive. The hard part is the drives and libraries, as well as suitable backup software. Once past that, individual tape cartridges are quite inexpen
Re: (Score:2)
LTO didn't even exist 30 years ago, so your experience says little to nothing about archival quality.
Re: (Score:3)
I'm willing to bet tape has a MUCH longer life span too. CD-R's start dieing in less than 10 years, I doubt blu-ray lasts any longer. Even the archival grade disks where they claim to last longer than 0 years I'm not sure I believe them. The nice thing about magnetic tape is that they tend to last forever and only go bad from wear or exposure to magnetic fields.
Re: (Score:2)
Sony and Panasonic have put a lot of effort into archival grade Bluray for use in broadcast as an alternative to digital tape. They also sell them to consumers and they do appear to live up to their claims.
Tape certainly doesn't last forever, and they wear out when read back. The heads make contact with the tape, and the motor drive stretches it. Tape also takes up more space for the same capacity.
Re: (Score:2)
Re: (Score:2)
Blu-ray, like other WORM (write-once read-many) storage devices, fills a particular niche - long-term archival and storage of static data. It doesn't really fit Facebook's particular use case (dynamic data), unless they're planning to use it as an excuse not to have to delete user data upon request.
Get facts straight (Score:2)
>"Their data can be restored more quickly"
Than a hard drive? I think not.
> "the Blu-ray system doesn't need to be powered when the discs aren't in use, it uses 80% less power than the hard-drive arrangement, cutting overall costs in half."
Say what? When my backup hard drives are not being used, they also use zero power because they are not plugged in. And when they ARE plugged in, they "power down" after a few min of no usage, which I think is like 1% of normal power.
The density of storage for blur
Re: (Score:2)
I think the point is that if you want access to stuff from an HD, it's got to be plugged into something. The more storage you have, the more of those "somethings" you need, along with the routers and logic to connect them all together. All of that stuff takes power, even when the HDs themselves are asleep.
You could do something similar to the Blu-Ray setup, where a robot plugged/unplugged hard drives instead. But I'll bet once you're going to accept that kind of latency, a robotic Blu-ray juke-box with l
Re: (Score:2)
My issue is that they were comparing on-line hard drive backup to off-line bluray but with an expensive and fancy robot system. Which is not quite a "fair" comparison. The Bluray drives also have to be connected and use power. The robot uses power. A spun down stand-by hard drive uses only about 0.75 watts! That means you could have half a PETABYTE of ONLINE storage for about the power of a single traditional lightbulb.
At the rate hard drive density keeps going up, it seems optical storage just can't k
There's just one problem with this... (Score:5, Funny)
When you first access this data, you have to sit through 42 previews before you get to it.
Backup, not storage (Score:4, Informative)
I read TFA. They're not using them as "storage" in the sense of active, accessible storage. It's a backup system.
What they're trying is, instead of storing redundant copies of everything on multiple drives (for resilience and geolocality), they're keeping one copy live and keeping backups on blu-ray.
So there's never a latency of minutes while it loads data from Blu-Ray, you just might be routed to Siberia or something to get the one active copy. If that copy's bad, error (restore from backup during next nightly batch or something).
Dupity dupe (Score:2)
How is this different from the last time the topic was on the front-page of /.?
http://hardware.slashdot.org/s... [slashdot.org]
From the article ... (Score:3)
"Those data demands will only increase with time, particularly as personal cameras and smartphones become capable of capturing higher-quality images."
From Facebook: "We automatically take care of resizing and formatting your photos for you when you add them to Facebook. [facebook.com]"
Re: (Score:2)
Yes, for display on your wall or whatever its called. The archive the originals in their original form so they can be reprocessed later if they want/need to.
Re: (Score:2)
That's interesting and something I didn't know. I'd like to include it in my presentation. Where may I find a citation?
Thank you.
Re: (Score:2)
Also, I am curious about the Exif information in the original photos. I have been saying that Facebook strips that information. If Facebook retains the original photo, perhaps they keep that information as well?
Gotta be overhyped (Score:3)
I dunno. I've never been pleased with the performance of optical media. I'd think being in a data center, heating up and cooling down from usage and storage is going to have very bad effects on recordable optical discs (CDs, DVDs, Blurays). Not to mention, it's always a pretty well known fact, consumer recorded media (the ones with dyes and stuff) aren't terribly reliable in the long term. My personal experience with recordable optical media is poor at best, I have very very few discs that've remained readable and error free after just five years of relatively decent care and storage. And this is not even using them every day, heating them up and cooling them down, just stored in a dark cool place.
Seems... overhyped. I simply can't come to believe this is an actual viable storage medium for any kind of large scale operation. But enh, if it works for them, good deal. Seems like you'd get more bang for your buck using high capacity tapes which hold up much better to heating up and cooling down.
The power saving claim also seems silly. This could be easy done with standard hard drives in a cartridge type system they're saying they're using, powering down unused drives and putting them into a storage position (though for me, I think it'd be much smarter to make the connector the moving part and just plug into the right bank of HDs, instead of moving HDs around in a cartridge.)
The more I think about this operation, the less intelligent and efficient it seems to be.
Well, that does it for Facebook. (Score:2, Insightful)
Not that I had any trust in them anyway.
Blu-Ray, and indeed any modern optical storage, is very short-lived precisely because it's designed to be cheap. The laser disks used to store the Doomsday Project in Britain were still readable after 20 years. Modern optical storage decays typically within 5. Less, as the density goes up. And failures take out far larger percentages of the storage.
Magnetic tape is still the only trusted long-term backup medium. I wouldn't suggest it for something like Facebook purely
Access time (Score:2)
Tales of ~150,000ms access time (Score:3)
Okay, so we need disc 101 from tray 1010101 and the robot arm is busy, three other fetches already in the queue. After 30,000ms client Javascript times out and substitutes a "retrieving data, re-try for a few minutes" place holder, sets a longer camp-on timeout and releases the request.
The reason the robotic arm is busy is that despite random assignment to storage pools with some localized album grouping, web crawler activity for public albums, and bulk pre-fetch requests for semi-private albums by browser plugins run by logged-in users (which became more popular as access time increased) ... the lukewarm storage facilities are running hot and queues are full most of the time.
Despite the polished and smoothly functioning presentation that encourages the users to "just wait a bit" ... a dark rumor grows deep in the hearts of many that the data is not merely delayed, they must brush off dust and cobwebs, or root for it because it had been haphazardly tossed into a pile of rubbish somewhere, relegated to the digital Basement. Facebook does not think your photograph is of sufficient merit. Grandmother has long passed and you had not wished to look at her last week, so... why should you be interested now?
The effects are complex, but the cause is clear: the Internet is perverse. It re-routes around any attempt to take immediate access data off-line by degrees, accomplishing this through a series of countermeasures such as unwelcome crawlers depleting your cache, hitting your 'public' cold data systematically and regularly, then finally bankrupting your company as users migrate to another service whose superior performance does not arise from superior engineering -- merely the fact that fewer users are using it.
So the moral of the story is, if you are Facebook and wish to remain so, you will either strive to find a way to keep the random access time for everything down below 2000ms -- or die.
And also, Facebook would be wise to heed the following:
once / forgotten by tourists / a bicycle joined a herd of mountain goats /// with its splendidly turned horns / it became / their leader /// with its bell / it warned them / of danger /// with them / it partook / in romps / on the snow covered / glade /// the bicycle / gazed from above / on people walking; / with the goats /// it fought / over a goat, / with a bearded buck /// it reared up at eagles / enraged / on its back wheel /// it was happy / though it never / nibbled at grass /// or drank from a stream /// until once / a poacher / shot it /// tempted / by the silver trophy / of its horns /// and then / above the Tatras was seen / against the sparkling / January sky /// the angel of death erect / slowly / riding to heaven / holding the bicycle's / dead horns //////~Jerzy Harasymowicz
Re: (Score:2)
Since they are disk packs I bet they will be RAIDed which will help protect from bitrot.
Re: (Score:2)
Or is the stuff already not really important to keep more than one copy around
It's Facebook. I doubt it's of any importantce even to the op. At any rate, the NSA has a copy for backup.
Re: (Score:2)
If they only keep one copy, how do they detect and recover from bitrot?
Or is the stuff already not really important to keep more than one copy around
Data replication is an honest question. What if a copy was kept on spinning disks
and the Blue-Ray media was backing store for spinning media.
A RAID design for the future need not have equal access times for ECC, voting
and redundancy. It only needs to be reliable and the net sum of the parts
inexpensive. Data rates on and off a single Blu-Ray are consistent with very long
distance optical fibre data rates.
If I allow myself to think of this as heterogeneous RAID hardware design it makes sense.
If I allow m
Re: (Score:2)
Ideally you'd have two different types of media so they would degrade at different rates (which doesn't completely eliminate the possibility of synchronous degradation of any particular bit of information, of course. But helps)
Re: (Score:2)
That's not what the summary is saying.
Re: (Score:3)
Couldn't get all the way to the 7th sentence of the summary?
Re: (Score:2)
Not clear why LTO5 wouldnt be about 5 times better in every regard other than the red herring of water proof-ness.
Re: (Score:2)
You either need a giant bank of HDDs to store a snapshot of the data before it's written to tape, or a system that can handle large inconsistencies in data caused by the slow write speed.
You'd still need some inconsistency handling for Blu-ray, but it's a lot faster than tape so there's a lot less to handle.
Re: (Score:2)
5 Blu-ray drives, autoloader with thousands of disks. When not operating, you are powering the SATA-or-similar interface for 5 drives and 1 autoloader.
2000 HDDs. When not operating, you are powering the SATA-or-similar interface for 2000 drives.
2000 > 5 + 1.
I know! Let's pay people to go unplug the 2000 drives. That'll make it cheaper!!!
Or we'll kill pow
Re: (Score:2)
No. You're not. I can see why you are confused. You seem to think that there would be no engineering involved in the HDD based system, and that people are proposing that we simply stack a bunch of servers together and call it a day.
I'm sorry. What was the MTBF on the robot aga
BD is Less per GB (Score:2)
BD also cost more per-GB than a HDD.
fifty "25GB 4x BD-R Hard Coating" for $35 about 1250GB about 36GB a $
A 3TB drive (I would say the sweet spot) would be $100 about 30GB to a $
So blue ray is slightly cheaper per GB for me. I suspect in bulk the differences are bigger.
Re: (Score:2)
BD-Rs are write once, which is going to be terribly limited and not give you the full amount of space if you reuse them (ie UDF deletes). Tape hits ~75/150GB per $ (1.5/3.0TB tape for $20), and all of it is reusable.
Re: (Score:2)
Tape is cheaper. LTO5 tapes are $20 each on newegg, LTO6 is $65 (for ~6TB of space).
Re: (Score:3, Insightful)
Re: (Score:2)
what does that cost? Compare 64TB per $300 (Score:2)
What does that TS4500 cost? I'm curious how it compares to a stack of dumb 16-bay SAS enclosures at $300 each.
http://www.ebay.com/itm/like/1... [ebay.com]
A general purpose FreeBSD or Linux system with four raid cards can control 1024 drives mounted in such enclosures, so about $2 per drive for the intelligent bit.
Re: (Score:2)
How big a stack do you need to match a 1320 tape library? Even using 4TB disks you're talking 825 disks, which means 51 enclosures. And then four racks to hold those enclosures. And enough floor space to hold those racks. And enough circuits to power those racks.
At that level of scale, tape is simply a better option for archival storage.