The Pegasus: Performance

A single 2TB Hitachi Deskstar 7K3000 is good for sequential transfer rates of up to ~150MB/s. With six in a RAID-5 configuration, we should be able to easily hit several Gbps in bandwidth to the Pegasus R6. The problem is, there's no single drive source that can come close to delivering that sort of bandwidth.

Apple sent over a 15-inch MacBook Pro with a 256GB Apple SSD. This was the first MacBook Pro I've ever tested with Apple's own SSD, so I was excited to give it a try. The model number implies a Toshiba controller and I'll get to its performance characteristics in a separate article. But as a relatively modern 3Gbps SSD, this drive should be good for roughly 200MB/s. Copying a large video file from the SSD to the Pegasus R6 over Thunderbolt proved this to be true:

Apple's SSD maxed out at 224MB/s to the Thunderbolt array, likely the peak sequential read speed from the SSD itself. Average performance was around 209MB/s.

That's a peak of nearly 1.8Gbps and we've still got 8.2Gbps left upstream on the PCIe channel. I needed another option.

Without a second Thunderbolt source to copy to the array at closer to the interface's max speed, we had to generate data. I turned to Iometer to perform a 2MB sequential access across the first 1TB of the Pegasus R6's RAID-5 array. I ran the test for 5 minutes, the results are below:

Promise Pegasus R6 12TB (10TB RAID-5) Performance
  Sequential Read Sequential Write 4KB Random Read (QD16) 4KB Random Write (QD16)
Promise Pegasus R6 (RAID-5) 673.7 MB/s 683.9 MB/s 1.24 MB/s 0.98 MB/s

The best performance I saw was 683.9MB/s from our sequential write test, or 5471Mbps. Note that I played with higher queue depths but couldn't get beyond these numbers on the stock configuration. Obviously these are hard drives so random performance is pretty disappointing.

That's best case sequential performance, what about worst case? To find out I wrote a single 10TB file across the entire RAID-5 array then had Iometer measure read/write performance to that file in the last 1TB of the array's capacity:

Promise Pegasus R6 12TB (10TB RAID-5) Performance
  Sequential Read (Beginning) Sequential Write (Beginning) Sequential Read (End) Sequential Write (End)
Promise Pegasus R6 (RAID-5) 673.7 MB/s 683.9 MB/s 422.7 MB/s 463.0 MB/s

Minimum sequential read performance dropped to 422MB/s or 3.3Gbps. This is of course the downside to any platter based storage array. Performance on outer tracks is much better than on the inner tracks, so the more you have written to the drive the slower subsequent writes will be.

At over 5Gbps we're getting decent performance but I still wanted to see how far I could push the interface. I deleted the RAID-5 array and created a 12TB RAID-0 array. I ran the same tests as above:

Promise Pegasus R6 12TB (10TB RAID-5) Performance
  Sequential Read Sequential Write 4KB Random Read (QD16) 4KB Random Write (QD16)
Promise Pegasus R6 (RAID-5) 673.7 MB/s 683.9 MB/s 1.24 MB/s 0.98 MB/s
Promise Pegasus R6 (RAID-0) 782.2 MB/s 757.8 MB/s 1.27 MB/s 5.86 MB/s

Sequential read performance jumped up to 782MB/s or 6257Mbps. We're now operating at just over 60% of the peak theoretical performance of a single upstream Thunderbolt channel. For a HDD based drive array, this is likely the best we'll get.

To see how far we could push things I pulled out all six drives and swapped in four SF-2281 based SSDs. To really test the limits of the interface I created a 4-drive RAID-0 array sized at only 25GB. This would keep drive performance as high as possible and reduce the time required to fill and test the drives.

Unlike the hard drive based arrays, I had to take the queue depth up to 16 in order to get peak performance out of these SSDs. The chart below shows all of my performance attempts:

Promise Pegasus R6 Sequential Read Performance

With highly compressible data, I managed to get just over 1000MB/s (8021Mbps to be exact) to the 4-drive SF-2281 Pegasus R6. Note that this isn't a shipping configuration, but it does show us the limits of the platform. I'm not entirely convinced that we're limited by Thunderbolt here either - it could very well be the Pegasus' internal controller that's limiting performance. Until we get some other Thunderbolt RAID devices in house it's impossible to tell but at around 8Gbps, this is clearly an interface that has legs.

The Pegasus: Quirks It's Bootable & Power/Thermals/Noise


View All Comments

  • takumsawsherman - Saturday, July 9, 2011 - link

    You mean like booting from a CD or USB flash drive and copying files to a very small, hideable storage container?

    Perfectly possible, and in fact I find myself doing this frequently (though copying the data in the other direction typically) when disinfecting PCs. I do this multiple times per week, removing data stealing trojans and rootkits.

    Compare with Thunderbolt, where you will "sneak in with only a laptop and a cable and reboot and press T, and ZOMG yor datas are hax0red! Ha HA ha stupid Apple!!!111oneonewonwon"

    Leaves obvious traces? Exactly what traces did the Boot CD leave?
  • Penti - Wednesday, July 13, 2011 - link

    As you can password protect (which can be bypassed with physical access any way) the firmware it doesn't matter if it is Firewire/Thunderbolt-target or USB-stick/HDD that access and or copies the files or simply a CD that changes your password so you can just log in an access everything without any effort at all. If you don't have limits on the firmware/bios any way you can just set up whatever, and access anything without any effort, less so then using slow target disk mode, even through network boot is possible which might be on in a corporate/university environment any way.

    Just disable the good damn features you don't like, it don't make your computer safe but I'm sure it will quit you whining for nothing.

    You will just access everything by running the system rescue tools on the install CD for OS X any how. Windows computers are essentially unprotected any way. So I really don't see how it's any worse then plugging in a USB stick to access everything or change the password (SAM) to blank/whateveryoulike. Screaming about a ten year old feature is just dumb. Just set up a firmware password and it stops people from simply booting a CD, USB-drive, HDD-drive, using target disk mode and network boot any way. It's simply not more vulnerable then PCs any way. It's quite easy to restore the firmware-password thus bypassing it on say an iMac any way, I could easily do it on older macs without taking the entire computer apart. And on a PC of course resetting CMOS password is often troubleless and manufacturers often has master passwords you get by calling the support any way. Later macs has got better protection from resetting the firmware password though. So just set the damn password.
  • Penti - Friday, July 8, 2011 - link

    They are not driving the screen with a separate control-board. That's why target display is so awkward. You can expect third party stuff (and older macs) will work when Atlona has designed and released an Thunderbolt-compatible adapter/switch/converter/scaler though. It a integrated solution not a screen and a computer separate. The screen is when used normally connected directly to the ATi/AMD 6000M GPU. That's why you can't adjust the screen in Bootcamp/Windows without their software tool too. Reply
  • HW_mee - Friday, July 8, 2011 - link

    That makes sense, not much you can do to separate the two things if the screen is "merged" with the computer. I expected the computer part and screen part was seperate and the display input could be used in the same way as with most multiple input screens.
    If that was the case, a simple power circuit could control the screen and computer separately.
  • youngjimmy - Friday, July 8, 2011 - link

    'Failing to do so will give you this all-*to*-familiar error' (bottom, The Pegasus: Software) Reply
  • Kimbie - Friday, July 8, 2011 - link

    You made mention about connecting up a monitor to the last port on the chain, by plugging in a thunderbolt cable into the imac and used it as a second screen.

    Does this still work if you use a mini-display port to DVI adaptor and into a bog standard DVI monitor?

  • Focher - Saturday, July 9, 2011 - link

    Just to clarify, the last connection in the chain to a mini DisplayPort monitor does not require a Thunderbolt cable. You would just use a mini DP cable. Reply
  • André - Friday, July 8, 2011 - link

    Does it support JBOD?

    Would be really great for us using ZFS+ arrays, although I would have preferred at least 8 bays.
  • Exodite - Friday, July 8, 2011 - link

    The performance is impressive, though nothing like what you'd get transfering a large number of smaller files obviously.

    That said, for 2000 USD why wouldn't I simply build a high-end desktop /with/ 12TB of storage?

    It'd still be cheaper and I could put the remainder towards a gilded sticker for the case saying 'cheap-ass NAS'.
  • André - Friday, July 8, 2011 - link

    It would appear that is the solution for you, building your own NAS.

    This enclosure is, however, not a NAS.

    It enable users that need high disk performance to get easy access to precisely that in a mobile package you can take on the road with you and edit in the field.

    Think large Final Cut Pro (or any other NLE), Logic Studio and Photoshop projects.

Log in

Don't have an account? Sign up now