How much cheaper is tape than deduped disk?

I’ve often stated that tape is still cheaper than disk, even after dedupe.  I know that many dedupe salespeople try to tell customers that they’re going to save money by moving from tape to their wonderful deduped disk system; I just don’t see how that is possible.  I’m absolutely convinced that tape is still cheaper, for a lot of reasons.  The only question is how much cheaper?

The big reason this is true is that almost no one is getting rid of their tape drives.  While some companies absolutely have, some customers that have tried have stopped trying.  They find it impossible to meet the long term storage requirements of backups and archives, and — much worse — legal hold requirements, without being able to make a pile of tapes and set them on a shelf somewhere.  This means that almost everyone is still keeping at least some of their tape drives.

So if you’re not getting rid of your tape, and instead buying one (or more) additional appliance(s), each of which is going to cost far more in power and cooling than the tape system you’re not getting rid of of, and neither of which is completely self-managing, how is it that you’re saving money again?  You’re tripling the size of your infrastructure, and 2/3 of that tripling is going to be disk that is more expensive than what you already had.  And if you’re going to be replicating your backups, you may need bandwidth you never needed before.  That bandwidth isn’t free.

But that actually wasn’t what I was going to be writing here.  Deduped disk has gotten so hot that some companies are charging way too much for it.  I recently saw a price comparison between a tape unit and a deduped unit where the tape unit was about $6,000 and the equivalent disk unit was $200,000. WOW.

Is the deduped disk unit easier to use?  Absolutely.  Does it enable onsite and offsite backups without touching tape?  You bethcha.  Would I rather have my backups on disk rather than tape if I had to do a lot of restores?  Definitely.

But is it cheaper?  I don’t think so.  And that’s all I wanted to say.


Written by W. Curtis Preston (@wcpreston), four-time O'Reilly author, and host of The Backup Wrap-up podcast. I am now the Technology Evangelist at Sullivan Strickler, which helps companies manage their legacy data

12 comments
  • Well, I am in the biz of selling dedup capable disk products & backup products, and we get this argument all the time. realistically the tapes & related drives do cost less up front. But it is the success rates for both backups AND restores that get increased to a pt to where companies are willing to pay the premium. just had a customer tell me they had 96% backup success rate, but only 33% for restores… they bought disk-based dedup for backups. the other thing is – when push comes to shove, most companies have no idea why they keep data around for so long. retention periods have no legal or governance validity. we generally find that when we can reduce that to “true” needs, that disk is a better fit, and they appreciate that we just reduced the total amt of data they need to manage. setting the expectations around dedup-capable disk often leads to other efficiencies well beyond up front cost. Your argument is absolutely true, just not of great consequence.

  • Ah the endless debate, which is cheaper, backup to disk or tape? Good to see someone is keeping this topic alive.

    The saying “the value of an item is what someone is willing to pay for it” applies here. Improved time-to-recover-data, Improved now-where-did-i-put-that-tape?, improved is-my-data-still-there?, these are all reasons to use disk-based backups. If they are important to you then they should have some value, right?

    DrDedupe

  • The best overall cost position comes when people combine disk and tape, using disk for nearterm backup/restore, replication for stage 1 DR protection, and tape for longer term retention. We’ve seen customers pay for disk systems in a year or so by reducing the amount of removable media they buy, move around, and store–while reducing management time and improving backup/restore. BUT if you try to retain all long term data all on disk, even with dedupe the cost is much higher than if tape is part of the mix.

    Full disclosure: I am with a vendor that sells both disk and tape–which could be seen as making me fairly neutral.

  • i can remember the days when we did direct-to-tape backups. Never again! it was a nightmare, both in managing the backup as well as the restore aspect.
    we then moved to a d2d2t mechanism and this has eased the management of the backup environment to unmeasurable hights. ofcourse, our environment kept growing and growing, and we’re now at a point where the d2d part is so big it’s ridiculous, so we’re looking at dedup to keep the whole disk part under control. less disks, less floorspace, less power/cooling, etc are needed and we can keep almost everything on disk instead of tape.
    it will also help with backup of our remote offices, which are still on tape only and have to be managed by local people, so there’s always something going wrong there.
    we will still have some tapes, for archives and similar purposes, these unique data do take up space on dedup devices with little advantages. dedup only pays of if the data can actually be deduped, otherwise you’re just wasting lots of money.
    no, disks are superiour to me, tapes always cause me problems. they break down more often then disks and even if a disk breaks down, the impact is little or none. not to mention the variable quality of tape cartridges (you can make something high available around tapes to, it’s only 10 times as complicated as a disk array).

  • Here is the conclusion to this debate as it stands today: Tape is cheaper, but disk is more awesomer.

  • As an integrator, I often find that customers want to hold onto their tape technology for long term data retention and use disk to meet short term restore objectives and quicker backup times. I don’t believe target deduplication achieves the latter very well unless your are prepared to fork out a considerable financial investment to provide the infrastructure to feed it fast enough.

    In my opinion, I expect to see more customers using source based deduplication of data before it’s even sent to disk. The reason; data growth is inevitable and backup windows don’t get any bigger.

    Tape has it’s place then to move data from disk for longer term retention requirements and shouldn’t be looked over. As always though, measure the costs of managing your physical media versus technologies like retention lock disk.

  • Does it come down to cost? What’s CHEAPER? I hope customers aren’t penny-wise and pound foolish when it comes to this topic. Hopefully it is balanced between Quality of Service, Cost, Value of Asset. You can publish all the reports, write all the blogs, speak from the highest soapbox but if you’re not helping customers to first understand the value chain of their data the discussion of what’s cheaper becomes a fools debate.

    What’s cheaper? Losing your business or Disk?

    What’s cheaper? spinning you data forEVER or tape?

    Understand the value chain first, then determine the right medium for secondary storage.

    IMHO

    -chapa

  • Cheap plug… we did a podcast on this topic with Curtis and Geoff Barrall: http://bit.ly/bjENdL

    Curtis’ point is about COST, not value, not better, but cost… because dedupe vendors have been falsely claiming that dedupe will save you money. It won’t and that’s all Curtis is saying.

    Which is more valuable? Depends on objective – archive or routine backup? Staging to disk before archiving to tape is a well established best practice for backup.

  • The Infosmack podcast on this topic with Curtis and Geoff Barrall: bit.ly/bjENdL that Greg referenced is on target. Listening now…

    Nicely done.