The SATA 3Gbps vs. 1.5Gbps Issue

All unibody MacBook/MacBook Pros use NVIDIA’s GeForce 9400M chipset. The chipset includes native support for up to six SATA ports running at 3.0Gbps (300MB/s max transfer rate). Here’s a copy of OS X’s system profiler showing 3.0Gbps as the interface speed on the previous generation MacBook Pro:


3 Gigabit...only on the first unibody MacBook Pro

Unfortunately, the current version of the MacBook Pro appears to only support 1.5Gbps SATA. I’m not sure whether this is an OS, drive or hardware problem, but your drive is limited to transfer rates of 150MB/s. For most laptop drives, this isn’t a problem. Your 5400RPM SATA drive just isn’t going to be moving anything at 150MB/s. The real problem lies with high performance SSDs.

Let’s look at the read/write performance of the three top SSDs on the market today: the Intel X25-M, the OCZ Vertex and the Corsair P256:

New 15-inch MacBook Pro (73WHr battery) 4KB Random Read 4KB Random Write 2MB Sequential Read 2MB Sequential Write
Intel X25-M 54.2 MB/s 22.2 MB/s 230 MB/s 71 MB/s
OCZ Vertex (Indilinx) 34.9 MB/s 6.55 MB/s 256 MB/s 137 MB/s
Corsair P256 (Samsung) 29.1 MB/s 0.78 MB/s 207 MB/s 178 MB/s

 

You’ll see four categories of performance: random read, random write, sequential read and sequential write speed. All four categories matter to the performance of your hard drive but some are more noticeable than others depending on what you do.

Random read/write performance actually contributes to your system feeling fast more than anything else. These are the sorts of transactions that happen when you’re launching applications or searching for files. Sequential read/write transactions happen when you’re copying large files to/from your drive. The latter is less common than the former for most users but that’s why you don’t see the 1.5Gbps issue really impacting real world performance on the new MacBook Pro.

All three of the SSDs in the table above would be interface limited on the new MBP because of their high sequential read speeds. If you were copying large files from the SSD in your MacBook to a similarly fast device, the transfers could take longer. I doubt the performance difference would be significant or noticeable in real world notebook usage, but it doesn’t change that there’s no reason to take a step backwards like that. In the coming years we’ll see more drives that can consistently break 150MB/s; Apple artificially limiting performance today would just hinder progress.

I’m not sure what the issue is since the 9400M does support 3Gbps SATA. Perhaps it could be one of the mystery optimizations Apple did to increase battery life well beyond reasonable expectations? Or perhaps it’s just an issue with the firmware and something that will be corrected in the near future. It's worth noting that the version of OS X 10.5.7 that ships with the new MacBook Pro is a different build than the one everyone else gets to download.

It’s something to keep an eye on and I’ve already sent out some probes trying to gather more on the issue.

Index
POST A COMMENT

81 Comments

View All Comments

  • Narcofis - Tuesday, June 16, 2009 - link

    In an earlier article you mentionned optimization with the System Managment Controller chip that helps the battery life. I wonder if OS X turns it on and off when it starts.

    Just wondering.

    Reply
  • thorgal73 - Tuesday, June 16, 2009 - link

    I remember OCZ slowing down its Mac version of the Vertex drive, so went to look up a news post about it :

    http://www.brightsideofnews.com/news/2009/4/9/ocz-...">http://www.brightsideofnews.com/news/20...use-mac-...

    On the other hand I'd still like to know which mobile chipsets do offer speeds higher than SATA150, in practice. Here's a post about that :

    http://www.madshrimps.be/vbulletin/f22/mobile-chip...">http://www.madshrimps.be/vbulletin/f22/...e-ssds-f...

    Maybe you guys can figure this out ?
    Reply
  • pmonti80 - Tuesday, June 16, 2009 - link

    Acer Aspire Timeline series is also capable of delivering "8 hours" of battery life at a low price. It's a CULV notebook, but it is quite interesting if you need so much battery life. Reply
  • abs0lut3 - Tuesday, June 16, 2009 - link

    Hi Anand,

    Would it be possible if the reason OS X has longer battery life compared to Vista was because of Apple "capped" the HD bandwith through software at 1.5Gb/s while Vista and Windows 7 are both running at 3.0Gb/s?
    Reply
  • unfalliblekrutch - Tuesday, June 16, 2009 - link

    Perhaps there are legal issues with doing this, but for curiousity's sake, perhaps installing OSX on a "windows" notebook and testing to see if that causes it to have a longer battery life than running windows will determine if OSX uses less power or if OSX has hardware specific trickery going on to make the battery last longer. Reply
  • Methodical - Monday, June 15, 2009 - link

    Stupid thought, but have you considered, almost just for giggles, running your battery bench in a VM'ed copy of windows?

    Most likely the battery life will be even lower..... but there's an ever so slight chance that os x is doing something tricky under the hood, and if so your battery life could increase. Even staying the same could be an indicator, with the VM overhead and such.
    Reply
  • gcor - Monday, June 15, 2009 - link

    One reason Vista MAY have a shorter battery life is Microsoft's business model of backward compatibility. As I understand it, in order for MS to support the multitude of old software on it's new operating systems, MS codes and tests specifically for legacy applications. For example, if you want to run the original SIMS on Vista, the OS detects that SIMS is running and performs code specifically so that SIMS works.

    The need for specific handling is two fold. The original OS function calls may not have behaved exactly as per the spec, so application developers coded for the actual behaviour provided by the OS. On the flip side, application developers may have developed code that functioned correctly, but were misusing the intended purpose of the OS function calls.

    I remember reading that when Vista development was running late, that over 95% of the Vista code base was dedicated to supporting backward compatibility and that it was the biggest cause for delivery delay and restriction of functionality.

    If my understanding is correct, then for any given call to the OS, a number of checks are being run for legacy software even when running current applications. This is a backward compatibility tax that we all pay, all the time. With every new release of MS operating system, this problem gets bigger and more complex, requiring more resources at design, code, test and run time. This MAY explain why battery life has reduced in Windows 7 more than Vista, which is intern worse than XP.

    Apple reduces these problems in two ways. Firstly, they occasionally break backward compatibility support (e.g. OS-9 to OS-X in 2002). Also, their licensing and testing model for third party applications reduces the amount of "bad but functioning" applications that misuse the OS function calls.

    Mind you, I'm not criticising MS for their backward compatibility support. It's what consumers and business have demanded from them and has made them very successful. It's just that the backward compatibility support back to DOS days has a cost for all of us, including MS.
    Reply
  • CompOne - Tuesday, June 16, 2009 - link

    Among the many flaws of Vista, and a major reason it was never widely adopted, is the fact that it wasn't backward compatible. I did buy a Vista laptop, but when fewer than half my applications would run on it, I returned it and bought an XP system. Try not making excuses for Micro$oft. They're a multi-billion dollar big boy and can defend themselves. When Micro$oft releases their new buggier, incompatible, operating systems we should instead ask 1)What does this offer thats worth the upfront cost, the time to install it, the time to install all my applications, 2) the cost to replace all my expensive applications that no longer work, 3) the time to find, purchase, and install all the applications that no longer work, 3) the time to learn yet another buggy and unintuitive interface, 4) the cost of new hardware and lower productiviity due to the poorer performance of the bloated and underperforming OS. 5) Does this OS perform the basic functions of an OS well such as disk storage management - Micro$oft has yet to get Windows explorer to work well.

    The conclusion is that Micro$oft is not backward compatible, and their self-serving goal of making money hand over fist clashes with my desire for value for my money.
    Reply
  • gcor - Wednesday, June 17, 2009 - link

    Interesting you think I'm defending MS. I'm not an MS fan. Far from it. In fact, after working as a developer for 20 years, MS was one of the big reasons I recently threw in the towel and have jumped ship into a brand new career, starting with 4 years back in University.

    However, about Vista backwards compatibility... I'm not surprised not everything worked for you. On the whole, I imagine MS got quite a lot of things to work, but frankly they don't have a chance of getting all the 3rd party apps AND hardware combinations to work all the time. The permutations and combinations of the problem they are trying to solve is patently ridiculous beyond belief. Trying to get it to work is just silly and believing they can do it is gullible.

    Having worked as a master engineer developing telecoms network software for the major firm in the indudtry for over 7 years, I've seen the rod built for it's back by one company where that company controlled every application and every hardware release. In addition, the required quality of all the releases was far beyond a consumer ALT-CTRL-DEL OS like Windows. The problems we had with backward compatibility were enormous. I think MS has NO chance, they don't control all the parts and don't have access to majority of application code or hardware designs. Frankly I think it's futile, BUT, we all expect it of them and they keep promising it.
    Reply
  • PhreePhly - Tuesday, June 16, 2009 - link

    What software didn't work? Pretty much everything I had running on XP ran in Vista. I say pretty much, because, while I can't think of a single program that didn't run, it's been over 2 years since I installed Vista.

    I don't run Industrial CADD/CAM software, so that might be it, but those programs were always problematic with an OS change. They are typically certified on a specific hardware/software combo. Other than that, Vista was (I run Win 7 RC at the moment) amazingly backwards compatible as well as stable. After SP1, even better. The "Vista is teh suxor" FUD is getting real old now.

    PhreePhly
    Reply

Log in

Don't have an account? Sign up now