Apple's MacBook Pro with 128GB SSD: Performance and Battery Life Investigated
by Anand Lal Shimpi on April 15, 2008 4:20 PM EST- Posted in
- Mac
Better Application Performance? Not Exactly
If battery life didn't improve, surely it must be a sacrifice made in the name of better application performance right? Not exactly.
To understand why, we must first look at the synthetic performance of the drive:
| XBench Disk Test (Sequential) | MacBook Pro (Hitachi 5400RPM) | MacBook Pro (Memoright SSD) |
| Uncached Writes (4K) | 53.5MB/s | 61.7MB/s |
| Uncached Writes (256K) | 48.2MB/s | 73.0MB/s |
| Uncached Reads (4K) | 11.2MB/s | 10.2MB/s |
| Uncached Reads (256K) | 49.8MB/s | 68.2MB/s |
In sequential access, small block reads and writes either don't improve at all or improve by an amount that's not huge (15% for uncached writes, but that's just an improvement in the performance of your disk subsystem - not the entire machine, expect real world performance improvements to be some fraction of that). Larger accesses are a bit more favorable, with reads and writes improving by 37% and 51% respectively.
Most single-application desktop usage models are actually very heavy on sequential disk access, and in these situations you won't see the biggest performance benefits from a SSD - even something as fast as the Memoright.
Looking at the random reads however tells another story:
| XBench Disk Test (Random Access) | MacBook Pro (Hitachi 5400RPM) | MacBook Pro (Memoright SSD) |
| Uncached Writes (4K) | 0.92MB/s | 1.11MB/s |
| Uncached Writes (256K) | 22.4MB/s | 27.9MB/s |
| Uncached Reads (4K) | 0.47MB/s | 9.98MB/s |
| Uncached Reads (256K) | 19.5MB/s | 79.1MB/s |
While random writes offer a ~20% performance improvement, random reads range from 3x - 20x the speed of a mechanical disk. Now since most single-application usage patterns tend to be sequential in nature, we don't see these incredible performance gains in many of our scripted tests - however, in actual usage you can easily feel a bigger difference.
This is where the whole: once you go SSD, it hurts to go back statement from the introduction of this article comes from. Within a single application, performance may not improve a ton, but your day to day usage experience will be a lot smoother.
Let's take a look at some of those application tests:
| Application Tests in Seconds (Lower is Better) | MacBook Pro (Hitachi 5400RPM) | MacBook Pro (Memoright SSD) |
| iPhoto Import | 72.1 seconds | 62.2 seconds |
| iPhoto Export to Web | 116 seconds | 119 seconds |
| Pages Export to Word | 27.4 seconds | 26.9 seconds |
| Keynote Export to PPT | 18.3 seconds | 16.0 seconds |
| Word 2008 - Compare Docs | 69.0 seconds | 62.9 seconds |
| PowerPoint 2008 + Word 2008 - Compare Docs & Print to PDF | 82.8 seconds | 85.8 seconds |
| Adobe Photoshop CS3 - Retouch Artists Speed Test | 44.6 seconds | 42.5 seconds |
The biggest performance increases here are in the iPhoto Import, Keynote Export and Word Compare Documents tests. Performance went down slightly in the iPhoto Export and PowerPoint tests, but the drops were so small that they can be considered insignificant.
The major take-home point here is that performance didn't go up all that much in most of these tests, with the biggest gain being just under 14% that's a marginal improvement given the nearly $4,000 price of admission.
But there is just one more thing...
Facebook
Twitter
RSS
39 Comments
View All Comments
Alexstarfire - Wednesday, April 16, 2008 - link
Efficiency != performance. You know that, right?JarredWalton - Wednesday, April 16, 2008 - link
Yeah. Using a custom IC means you don't have any extra transistors wasting space and power. An FPGA can do the same thing as a custom IC, but you usually have more gates available than you actually need.nubie - Tuesday, April 15, 2008 - link
I was under the impression that SATA used more electricity than PATA, no mention of that?We are going to need a dedicated low power mode for the chipsets and the SSD's
I wouldn't be surprised if these are all switched to a Mini PCIe card when this is mainstream. The added bulk, price and inefficiency of these in a 2.5" form factor is just plain dumb, besides, let it communicate over PCIe, then you wouldn't need to have a PATA-SATA etc interface.
mindless1 - Friday, April 18, 2008 - link
1) It would be very risky to design a laptop that didn't support 2.5" drives, a lot of the market isn't going to pay $4000 for their hard drive.2) You are obviously wrong about (significant) added bulk, that size is what allows the number of flash chips to reach capacity, the controller to improve performance, and the supporting electronics onboard. Of course there is a bit of space non-electronically *wasted* but so it goes with modular parts. When flash density increases again you could have smaller form factor with same capacity or you could have higher capacity. Also, a well optimized controller should parallelize access to the chips so more chips = better performance.
3) SATA vs PATA power consumption is not necessarily a difference enough to be significant in total device power consumption, although in this case with a PATA SATA bridge chip there is a small (probably under 50mA) consumption by that bridge.
4) You suggest comm over PCIe would be significant, that you wouldn't need PATA to SATA, but you would still need intermediary controller. Remember that SSDs are not developed for only one notebook, the market for a $4000 device is limited enough already so supporting the largest # of systems reasonably possible will help drive down prices.
5) What happens when you keep packing more and more active parts into a smaller space? Power density goes up and you then either need a fan or elaborate heatsinks scattered around and a lifespan degradation of other parts from running at higher temp. Not what people want when paying $5000 plus for a laptop.
In the end, SSD is still in it's infancy, think back to the improvements in mechanical drives made from the beginning until now. Ultimately if space savings becomes priority #1 they will just integrate the controller and flash chips onto the mainboard, forgoing the PCIe mechanical interface and parallel PCBs, that space consumption altogether.
Personally I think we need a new memory format similar to Compact Flash, with robust pin connectors, easily slotted and removable, and native SATA300 support. Next we need a portable Windows, so switching from your laptop environment and files to your desktop is just a matter of pulling card out of slot and plugging into the other system - or any other PC in the world for that matter. The crude precursors of this are already seen in mobile apps on USB thumbdrives but to be truely portable the whole OS environment needs be fully plug-n-play not what MS calls PNP.
quanta - Tuesday, April 15, 2008 - link
Last time I checked, even 8 sticks of Corsair Flash Voyager GT (16GB) flash drive cost less than $1000 total. Even with FPGAs and other extra electronics, the $3,819 price tag is a poor price excuse for extra performance. Considering that the drive doesn't even read and write at 8x the speed of Flash Voyager GT, you are better off using the extra cash to get better laptop options for other components.ltcommanderdata - Tuesday, April 15, 2008 - link
It's interesting that although your article mentions at the bottom of page 2 that and SSD would appear as just another hard drive, the DV Nation website lists the system requirements as OS X 10.5 being required. I guess they are just being conservative.I would like the response time of an SSD, but beyond the price, the storage capacity is still a bit constraining, even at 128GB. Personally, now that Fujitsu has announced 320GB 7200rpm 2.5" drives, I'm waiting on Hitachi to release an equivalent to replace my 160GB 5400 rpm Hitachi in my MacBook Pro. If I'm not mistaken Hitachi drives tend to be faster than Fujitsu.
Timothy123 - Tuesday, April 15, 2008 - link
Honda Civics do not depreciate that much, pretty bad example actually. Honda is known for it's high resale value and continued quality through high mileage and the test of time.You should have picked an American car to use in that metaphor, for instance, any car made by Ford or GM would have been a good choice.
A Ford Focus for instance, loses a lot more of it's value than a Honda Civic, hell for that matter, any American car loses it's value quicker than a Honda Civic.
Really really really bad example. Really bad.
xkon - Saturday, April 19, 2008 - link
lol. well... that kind of makes the statement true nonetheless. if the sdd depreciates in value 40% that means it depreciates a lot faster than a honda civic. if they'd chosen say... a dodge intrepid (my neighbor's '03 sold for $3000) or something like that, the depreciation value would be similar or over 40% defeating the purpose of the comment.Googer - Wednesday, April 16, 2008 - link
Tim,What the hell has that got to do with any thing in the article?
strikeback03 - Wednesday, April 16, 2008 - link
I had the same thought about the lack of depreciation on Civics when I read that line. And the fact that half the comments relate to that one sentence is humorous as well.