Apple Fusion Drive – What is it and what the *#%@ do we do with it? [CONFIRMED]

[Update november 27th; DiY FusionDrive confirmed!, see last page]

[Update november 9th; Do-it-yourself FusionDrive available!, see last page]

Hi all.

For a change, a regular blog post, not a how-to or a script to share, just some info on a “new” technology “invented” by Apple; Fusion Drive.

First of all; what is it?

Well, that’s a difficult question, since only Apple really knows and there probably isn’t a Mac outside of Apple HQ that runs on it. But based on the information presented by Apple and discussed by many techfora, like arstechnica and ubergizmo, already discussed Fusion Drive in depth and here’s the scuttlebutt;

1. Apple Fusion Drive combines a regular HDD with a fast SSD so files accessed often are available at high speeds, others are on the large capacity storage. All seamless and even so that certain files of one project can be on the SSD (the files you use) and others on the HDD (the documentation). It’s file-based (actually block-based), it’s seamless, it’s automatic. It fits the Apple philosophy perfectly; it’s dead-easy to use.

2. Apple Fusion Drive is NOT a cache; A cache is typically a volatile data storage with very high speed. Caching has been around for ages; VGA-ROM and BIOS were cached in RAM as early as the 90’s. CPU’s have L1 and L2 cache, L1 being insanely fast, L2 slower but still faster than most RAM. Your HDD has a cache; it’s usually about 32 or 64 MB, not much, but it’s there. High-traffic websites do caching as well, and although different in nature, the effect is the same; Varnish, for example, is a cache for Apache; the original website still is there underneath, but you get a fast copy served instead.

Common denominator of all these is this; The data exists in both the original location (be it a CPU register, a block of Data in RAM or on your Harddisk) AND the cache. That’s what caching is; a far far faster accessible copy of your data. If the cache is destroyed? nothing to worry about; just get the data from the slower medium and you’re done.

3. Apple Fusion Drive does not take away capacity (actually, it does, about 4 GB is reserved, but the big picture is; no; you don’t loose capacity, not in the way that is “lost” with caching); With Apple Fusion Drive, the capacity of both the HDD and the SSD (minus 4 GB or so) is combined to form one big logical volume. If you have a 1 TB HDD and a 128 GB SSD, you will end up with a 1.12 TB Fusion Drive. Of course, capacity isn’t lost with caching, but when adding a 128 GB SSD to a 1 TB HDD and still ending up with 1 TB of storage, well, you could say, you lost 128 GB of capacity, right?

This technology used by Apple Fusion Drive is called Data Tiering.
(read on…)

Data Tiering.
It has been around for a while now, but Apple – as with a lot of other technology – is the first to offer it to the consumers, and not to enterprises alone. You can – for example – get Data Tiering in “BeyondRaid” data storage solutions, like Drobo.

So what’s the diff? 

With Data Tiering, the data is never in more than one location – it’s fundamentally different from caching that way. If you loose the cache, no big deal, but if you loose a tier, you’re in trouble. (All the more reason to keep Time Machine running, ey?)

This is both a Pro and a Con; data-caching does not get you higher capacity, only higher speed, data-Tiering gets you both, but data-Tiering does not give you a fallback in case the high-speed tier drops out. Data-caching does.

Now then, what do we do with it, and why do we care?

Well, we want speed. Incredible speed. Waiting 2 minutes for an App to start is so 1999. We want it fast and we want it 20 seconds ago! But we also want more and more, we can’t live with “just” 128 or 256 GB of storage, we desperately need those terabytes.

We could get a Seagate Momentus XT Solid State Hybrid drive (damn, what a name); that would give you 750GB of storage with 8GB of SSD cache. Total storage is 750GB.

For desktop computers (not Apple at the moment) there is the Intel Smart Response Technology which gives us the same effect in separate components; 1 HDD + 1 SSD + the correct main board and we’re done. But combining the 1 TB with a 64 GB (supposedly the maximum size) still gets you 1 TB of storage. Nothing more, nothing less.

Microsoft ReadyBoost provides similar technology by utilizing an USB flash drive as a cache.
(read on, only one more page of ranting :P)

Apple Fusion Drive

Again, Apple Fusion Drive is fundamentally different. With Fusion Drive – driven by OSX itself, data is moved from the HDD to the SSD when it’s accessed more often, and moved back to the HDD when not. This way, those every-day-use applications are super fast and apps that are there ‘Just in case’, are available at HDD speeds.

So is it all good?

Well, we don’t know. It’s not a new technology, but it is the first time it’s applied to consumer level electronics. In a RAID or BeyondRAID setup, there’s always built-in data protection. When one disk fails, and is replaced, data is rebuilt using the remainder of the array. With Fusion Drive; when one drive failed; it’s over. Time will tell if Time Machine offers ample protection.

So how about a real-world example?

I have my MBP set-up with 750 GB of harddisk space and a 256 GB SSD. This is done by removing the optical drive, moving the HDD to the optical-drive-space using a bracket and placing the SSD in the HDD spot. But instead of choosing where to put the data, sim-linking back and forth to allow software to run transparently, I was pleasantly surprised when Apple announced FusionDrive and after a few weeks of googling and waiting, the answer was presented.

I ordered myself a LaCie Rugged ThunderBolt hard disk, an ugly-orange, bus-powered (industry first!), 1 TB harddisk. Backed-up my system to it (if you remember; I had two separate volumes, one SSD, one HDD). All symlinks to the HDD needed to be removed and data moved to the original location. That took about 2 hours (thank God for Thunderbolt otherwise I would have had to wait about 7 hours over USB). Then set-up the Fusion Drive as described below, then reinstalled OSX from the recovery; took 2 hours because of slow internet. Yes, I know, I should have realised earlier that my OSX 10.8.0 USB drive would not recognise the volume, its 10.8.2 and up!!. Finally, after installing, copy back the data using the Migration Tool (which is slow of it’s own, but it did the job in 3.5 hours.)

Setting up Fusion Drive with an after-market SSD

With Mountain Lion 10.8.2 (and up, presumably) FusionDrive can be used on ANY Mac with two drives. Apparently the only thing to do is to create a logical volume across those drives. This video explains it quite clearly (this is NOT my video and I am in no way responsible for it’s content).

The commands used in this video are;

1. Read the disk identifiers

This will create output like this;

Note the identifiers of the two main drives. In my case disk0 and disk1

2. Create the logical volume

The disk order is (probably) important; SSD first, HDD second. Also; ‘Fusion’ is the LV name, this could be any name, I called mine “FusionDrive”. I don’t have example output from my own system, but here’s some example I found on the web;

3. Create the filesystem.

Now, before just copying and pasting this, please note the variables;
first, the VolumeUUID, copy this from the output of the previous command.
second, the size. Not sure why the person in the video chose 300g while his total storage would approximate 310g. According to the manual, we can input a percentage. So why not state 100%?? Also, why the ambiguous instructions? the command ‘coreStorage’ and ‘cs’ are the same, so just choose one and use it. I used this:

Now, we are done!

Final notes:

1. This WILL destroy ANY and ALL information on both drives. BACKUP FIRST!
2. This will have to be done from the installer (create a flash drive installer or use the recovery mode) or booted from a USB, FireWire or Thunderbolt hard drive.

Right now I’m the proud user of a Fusion Drive. Now the main question, other than my eyes telling me it’s fast; how do I know the usage of both drives…. That’s the next step; getting statistics… :)

Thanks for reading :)