I'm going to use a block-level backup solution to backup a Hyper-V server running SBS 2008 plus two additional instances of Windows 2008. It's fairly lightweight in terms of relative use. Total file sharing size is only around 100GB. Size of Exchange is 50GB. I'm thinking that the total size of all backed up volumes will be in the neighborhood of 300GB.

I'm not sure how I would collect data on the existing system to estimate this. Storage growth is fairly low; less than 20GB over the past year which includes file storage and Exchange.

What I'm trying to do is estimate how much backup history I can get on 1TB media, backing up in full once every 24 hours, 7 days a week. Again, this is block level backup, not file level. Thus I'm trying to figure out how many blocks might change per day.

While I know there is no clear-cut answer to this, would 1% be too low? Would 10% be too high? Which continent is my ballpark on? Thanks.


I'm not too familiar with Windows, so I can't tell you which tool specifically you'd use for this (I seem to remember there being some built in monitoring / statistics utility in Administrative Tools), but you should be able to get a good idea by simply watching "blocks written" to the device you want to back up.

While some of the writes may not change the data, depending on the snapshot solution these may still be marked as dirty. In any case, it should give you a worst-case estimate of the amount of churn on your device.

  • Duh! Very good suggestion! – Boden Feb 1 '10 at 17:40

If you're running a full, daily, backup, it won't matter how many blocks change per day. You'll be backing up 300gb each time.

Otherwise, the amount of differential that you're looking at depends on the capabilities of the backup software, and the specific amount of churn for your system. There's no good guess in advance without historic knowledge of what the system does day to day.

If you don't have access to system history (not even generic info, such as "15gb of data uploaded daily), I'd recommend making a very relaxed guess (for example, you can take the "last modified" date for all files on the systems, and add up the size of the ones modified in the last couple of days, to give you an upper bound guess on how much is likely to change daily), and then making sure you have enough space for all your needs.

Once the system is up, carefully review it for the first 90 days. The only reliable source of information is the system, while it's running.

  • I'll be doing near-continuous block level incrementals. I can look at past data growth to estimate how much new data is added per day, but not how much data is changed per day. I think you're right, I'll just have to run the new system and see. – Boden Feb 1 '10 at 17:11

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.