PCIe SSD Performance

I created a Boot Camp partition of around 120GB and ran our client iometer benchmarks to put the new PCIe SSD’s performance in perspective.

Peak random read performance is roughly comparable to the previous-generation Samsung controller. Random write performance took a bit of a hit but it's still more than fast enough for client workloads. Sequential speeds are much improved but the gains are really only visible at high queue depths. Low queue depth sequential transfers can’t be split up enough in order to really require PCIe.

Apple SSD Comparison - 4KB Random Read (QD3)

Apple SSD Comparison - 4KB Random Write (8GB LBA Space - QD3)

Apple SSD Comparison - 128KB Sequential Read (QD1)

Apple SSD Comparison - 128KB Sequential Write (QD1)

What does this mean in the real world? The new SSD is definitely snappier in system use. Wake from sleep is a bit quicker, as are application launches. The funny thing is that with the exception of high-speed Thunderbolt arrays, most external sources aren’t fast enough to even stress the new storage subsystem in the MacBook Air. Large file copies confined to the drive itself benefit a bit as well. I saw roughly 300MB/s reads and 300MB/s writes when copying a large dmg from/to the MacBook Air’s PCIe SSD (compared to roughly 200/200MBps on the old Samsung SATA SSD from the rMBP15).

If you have an external Thunderbolt array with at least a couple of drives, you should have no issues matching the MBA’s internal SSD performance.

Seeing as how this is our first experience with Samsung’s PCIe SSD controller, I wanted to get a feel for how the drive behaved under extended high queue depth random writes. I ran a modified version of our IO consistency test. The test was modified to run in a 91GB space on the MBA’s Boot Camp partition. I made sure to fill the rest of the drive completely, but the random writes were effectively constrained to 91GB of LBAs. When I get back from the UK I’m going to try setting up an external boot drive and will do some more extensive testing on the drive.

The IO consistency results, at least within a somewhat constrained space actually look really good. I have a feeling that Samsung might have improved its IO consistency story with this generation, but I’ll wait on saying for sure until I’ve had a chance to do some more work with the controller. For the vast majority of users however, solid random write performance like this over a 91GB space on a full drive is actually very good news.

A Custom Form Factor PCIe SSD 802.11ac: 533Mbps Over WiFi
Comments Locked

233 Comments

View All Comments

  • lilo777 - Monday, June 24, 2013 - link

    It would help if you disproved something that was so wrong in my post. Perhaps people using OSX in their names are simply incapable of recognizing any Apple bias?
  • akdj - Thursday, June 27, 2013 - link

    In the ultra book market... and this price point....there aren't a lot of excellent choices right now for displays. If you step up to $1500-$1800...yes, one or two of the UltraBook vendors are selling 1080p IPS panels. At this price though...in the 'true' UltraBook sense of the word....go shopping at Best Buy sometime. Take a look at what Dell, Toshiba, Samsung and others are offering....again @ $1099. Asus is honestly the only one, in my opinion...that you can buy odd the shelf that competes. Period. You're right...it's time we get a 'better' panel. Perhaps 2014 will bring IGZO technology and production up to speed...IPS prices drop a bit...and Apple decides to equip a higher quality display. I'm all for it. But the current displays don't suck. They're excellent for what they are and at the current 'price point' you can't get that killer high rez panel from Sony. As well...at this size 11"), unless you double the resolution and pixel double as in the rMBP...raising the default resolution too much and text, icons, etc become to small. I'm always amazed at how much real estate I actually DO have on my 11" Air (2011)....in apps with 'full screen' capability....and until I bought the rMBP 15" last summer...I only used 17" MBPs!
  • TheinsanegamerN - Sunday, June 30, 2013 - link

    everyone overlooks something else with the 13 inch air's display...it's 16:10. which is amazing. i'd gladly take this over 16:9 anyday. wish more oems would go back to 16:10. and having seen the screen, and with a bias against macs...i kinda want one of the new airs.
  • darwinosx - Monday, June 24, 2013 - link

    The display is not glossy. Read the article you are commenting on.
  • lilo777 - Monday, June 24, 2013 - link

    You do not need to read the article to know that all Apple displays are glossy. It seems you do not even know what matte display looks like.
  • Sm0kes - Monday, June 24, 2013 - link

    Apple's Macbook Air lineup, while not as "glossy" in appearance as the Retina Macbook Pro's do still have a glossy coating. As a long time hater of glossy displays on notebooks, I have no issue with my Air.
  • amrs - Tuesday, July 23, 2013 - link

    No WWAN either. I think I'll upgrade my Thinkpad X201 to an X240s when those come out if it's any good. With matte display and 3G/4G inside too. Just the basics for mobile usage really.
  • Strulf - Monday, June 24, 2013 - link

    1920 x 1200 certainly would be nice. I want to upgrade my 2009 MBA but I'm gonna watch for the next revision - hopefully with a higher resolution then.
  • thinkpanda - Monday, June 24, 2013 - link

    I would like to share a few experience regarding to WiFi performance.

    I am using late 2011 MBP 13", which should support 3x3 802.11n. I connect home devices with Asus RT-AC66U router. I have a home server of Ubuntu Server 12.04 LTS, with Realtek 8168 GB Ethernet chip connected to the router. The home server has netatalk service installed to support AFP so that I mount the home server storage from MBP using AFP.

    When I copy file from server to my local SSD (just by dragging the file at Finder), I get file transfer rate of 39MB/s! This is not even an AC network, just N network.

    So I am curious that is it the server size TCP windows size settings affect the performance, and the OS X as client device is not affect at all ?
  • mikk - Monday, June 24, 2013 - link

    "It’s hilarious that Intel refused to give out die photos for anything other than quad-core Haswell GT2, citing competitive concerns, yet at Apple’s WWDC launch of the new MacBook Airs we got to see the first die shot of a dual-core Haswell GT3"

    Anand you are plain wrong here. Bad job! ULT GT3 photos are available from Intel since weeks!!!

    http://download.intel.com/newsroom/kits//core/4thg...
    http://download.intel.com/newsroom/kits//core/4thg...

Log in

Don't have an account? Sign up now