These benchmarks are pretty useless. Sounds like a potentially good idea, but I'll be impressed when I see real benchmarks demonstrating worthwhile improvements.
He starts off by saying that boot times have gotten significantly worse. Reinstalling the OS (not something I want to do) gets startup time back to the same as with a standard HDD. So far so bad.
Secondly, application tests are completely unscientific and show a lack of understanding of how the OS works. After you open an application the OS caches it so that it opens more quickly next time. The startup improvements he's seeing can be entirely attributed to this: Consider that on my MBP with a 5400rpm HDD Pages took ~7 seconds to start the first time and ~1.5 the second time (using the same technique as the videos).
"At this point, we realize that reaching a verdict is not so easy. The new memory management technology is complex and hard to benchmark, as optimizations take place in the background, because we don’t know the performance parameters of the flash memory."
Couldn't these huge speed ups be do to caching or space in inactive memory? For example, you may quit Word or Final Cut, but if nothing else is grabbing for memory aren't a lot of the needed libraries sitting there? I opened, closed, and reopened a few applications on my Macbook Pro with my 500 GB HDD, seems like they are way faster when I open them the second time... For example, iTunes went from taking about 5 seconds to opening almost instantly..
FTA, those are the two things that don't seem to be improved.
"Application results were much more impressive. Because the drive learns, the first time you bring up an app it happens at disk speed. But the 2nd time!"
"Boot performance sucked compared to the old drive’s ~45 second boot"
Boot performance was improved by doing a clean install, however, the best the reviewer got was close to the old HDD speeds (45 seconds) not a Macbook Air's boot times with SDD (15-20 seconds).
If you watch the videos, the speedups being boasted on the review involve opening the application, closing it, and opening it again, without running anything else.
Seems pointless; the flash only works as a read cache. I already have a 4G read cache that's much faster, it's called main memory.
SSDs are nice for lots of random reads/writes; I noticed the biggest improvements on things like "apt-get upgrade"; deleting files, reading tarballs, updating a database. This is where SSDs excel, but the SSD that's part of this disk won't help with any of that. When you download the tarball, it hits the magnetic disk. Then when you extract that, you read from the disk, and write to the disk. Then you read the package database... all from disk. You update the package database... yup, disk write. And so on; this drive will do nothing to help this use case. Anything that could be cached will be invalidated by a write. So you get no speedup on the only workload other than booting that helps a regular user.
If you're thinking of buying this, buy a regular disk instead, and save the $60 premium for a real SSD. Even Intel's "budget" 40G SSD will make your computer noticeably faster... but this thing won't.
Main memory doesn't persist across reboots; this does. Hence, potential increase in boot speed for the main OS, as well as a decrease in start-up time for an application the first time you run it after starting the OS.
And yep, no increase in that use case. Faster in the use case of opening programs (as mentioned in the article), faster in the use case of opening small files, and so forth.
Your last sentence is needless hyperbole, and is contradicted by the last sentence in your middle paragraph. Not that I disagree with your conclusion, though.
The box I'm writing this on has an uptime of 148 days, the last time it went down was to put a second graphic card in it. I really don't see how a 'faster boot' would be of any benefit, in fact any benefit in faster boot time would have to be balanced with how long it took you to install that drive, format it, install your OS and so on in the first time.
Use cases should center around that which happens frequently, optimizing boot time for anything other than a netbook or a laptop that you don't 'sleep' is a case of premature optimization.
For all the other use-cases you sketch main memory is much more effective than a cache in a device at the other end serial link.
Thanks for sharing your personal computing habits with us. I happen to reboot quite often, switching between Ubuntu and Windows. I tried using a VM, but there were too many issues. With an SSD, rebooting from one OS to the other is fast enough to not be annoying, so I can have my dual-boot cake and eat it too. I have paid, and will continue to pay good money for this.
Besides that, it seems that the boot speed increase according to the article is next to non existent, and the comments point out that the application starts were actually done without wiping the OS cache.
> Main memory doesn't persist across reboots; this does. Hence, potential increase in boot speed for the main OS, as well as a decrease in start-up time for an application the first time you run it after starting the OS.
So use system daemons like 'preload' or 'readahead'.
And come to think of it, a daemon can be upgraded and the heuristics & statistics improved. (Even if one can upgrade the hybrid drive's firmware, I'm not sure I would dare do so!)
Yeah, exactly. The reason boot times are long with rotating disks is because our software is really really dumb. Smart software would make "real" boots as fast as un-hibernating. Same for app startup. (/me contemplates cryopid-ing every app that takes a long time to startup, putting the data in a file that is guaranteed to be a single read operation, and enjoying fast speed without a SSD. But I have a SSD already, so meh.)
I boot my machine maybe once or twice a month. All other times, it wakes up from sleep or hibernate (which this drive won't help, of course). Most people, especially mac users, are the same way. Rebooting died with the 90s.
As for starting apps, they start when I log in, and most initialization is CPU-bound, not IO-bound. If you do it differently than this, a software or workflow fix seems like a better idea than a very expensive drive.
True enough... but you're underestimating the subjective performance increase. It's astounding (not with this drive, but with a full SSD)
Since switching my mac to a decently quick SSD and doing a few other tweaks to go along with it - I actually shut it down for the night or when I know I won't be using it for a while - because it shuts down in less than 2 seconds and boots to fully-usable in 20 seconds - and apps still start instantly, suddenly rebooting is no longer a thing to work around or avoid. I don't worry about keeping anything running to speed things up, because everything is just that fast.
Plus I can just yank it off the table without waiting for drive spindown if I have to run off to another meeting.
I read the description differently. The article says, "Put those blocks in the flash ... leaving big sequential I/Os to the disk." Sounds to me like the small blocks that are accessed (read or written) often are physically located in the flash---not just cached. If your package database isn't sequential on disk and it's accessed a lot by your system, it will probably be located in the flash.
From the admittedly not very good benchmarks provided - I don't see the appeal. I get the appeal of a potential hybrid - but I don't think this is it.
I replaced my system drive with an 80 gig Intel X25-M G2 a while ago (late-2009 macbook pro) and performed a few other tweaks (which really may or may not matter in the long run...)
My machine shuts down in less than 2 seconds and boots from power off to ready to rock on the desktop in 20 seconds... and while before I used to say "well who cares about boot time, I never reboot"..... I've now realized that I never rebooted because rebooting was something to be avoided, because it took so long. (not that it was long, but it was past that threshold where booting became an event by itself you had to endure).
Now that I can have the thing booted about as fast as I can pour a cup of coffee, and shut it down faster than it used to go into sleep mode (and sleep mode is instant, plus you don't have to wait for spindown before yanking it off the table and running to the next meeting anyway) I'll stick with my solid-state goodness for my portable machine.
Is it really so hard to just put your OS and apps on an SSD drive and keep your big media files on a regular HDD? Unlike a disk, I can predict with 100% accuracy what data seek times will matter for.
I bought a $2,000 laptop from Dell a few months ago with a 128 GB SSD and 500 GB Big Dumb Drive. Guess which one had Windows installed on it when it arrived. grumble grumble Scratch one day.
SSDs come in form factors other than 2.5" laptop drives. Most of that space is just air. My eeepc had one in a mini-PCI-E form factor. If you can fit a 3G card in something, you can fit a pretty big SSD in, too.
Thats exacty what I did. But my SSD is an older one, so doing disk intensive things like Windows Update can make the whole system sluggish (mainly the system restore points I guess).
This seems a bit like electric lights and horn on my horse-drawn buggy. Nice, but making my buggy like an actual automobile is not the answer. I don't see much of a future for these, even in large corporate applications. They can simply mix HDDs with SSDs more efficiently.
No, but I would guess this hybrid drive isn't 50% better than a regular old 500GB hard drive even though it's 150% the price. Value-wise, HDD > HDD-SSD > SSD.
What do people think of Seagate's reliability, these days? I've switched to Western Digital for this reason, but the performance gains of these Seagate models are tempting.
Of course, I'm a bit gun-shy about being an early adopter of a new product line.
BTW, Amazon shows them available for pre-order. 500 GB is listed for US$138.
I've setup about 3000 seagate drives in 2008 and 2009 (90% are 1TB Barracuda ES2). In the second half of 2009, the quality dropped sharply. The number of disk failures went through the ceiling (from about 1 to 3% per year to 5 to 8% per year) and we switched to Hitachi.
I still don't have enough data to evaluate Hitachi drives reliability. Come back next year :)
Interesting. The most recent OEM drive I purchased has a three year warranty, I think. (Their web site shows a bit less, probably because I haven't registered it, along with the sale date, yet.)
I should search to check this, but my vague recollection is reading about a backlash to the warranty reduction, which they subsequently at least partially reversed. Is that what ultimately happened?
They have most likely changed the practice - but any changes were really irrelevant to me when my 160Gb WD Drive died at 16months and was "out of warranty" completely.
I'm less concerned with warranty lengths these days because I have a larger budget for computer hardware - but Seagate has been very good for me since 2004 when I stopped purchasing WD (Which I'd been using almost exclusively since 1997.)
I have a 150 GB Seagate external drive that has performed just fine. I held them in good regard and considered them a first choice, until recent incidents such as "the click of death" accumulated to cause me concern.
I'd really be tempted by this new line of hybrid notebook drives, particularly to extend the effective lifespan of some older notebooks I and friends and family have. But I would like to know that they've taken good measures to eliminate the underlying conditions that allowed for some of the recent problems to enter into and persist in shipping products.
I take your point with regard to the particular situation you describe. I have similar "relationships" with a few companies; they may be "sliced bread" these days, but they screwed me, once, and I'm still voting with my feet.
I'm not a zealot. I had some unfortunate experiences with Ford products, but I still drive one (the best option at the time of purchase) and would pick Ford over the other U.S. brands. (Still, if I ever find the engineers and/or quality control who allowed unground, sharp metal edges on my driver's seat frame to destroy the seat's foam and support, for example...)
"Microsoft Word startup went from about 12 seconds to less than 3."
What is it about OSX that makes applications to launch so slowly? Microsoft Word always starts in under 5 seconds on Windows, almost regardless of the hardware, and has been for as long as I can remember. Sluggish application launch was #1 impression after getting an MBP - nothing on it starts like Notepad/Wordpad/Mspaint on Pentium III winbox circa 99.
My gut feeling is that it's dynamic linking. How wrong am I?
Doesn't MS Office offload some of that load time to startup by running a helper app on login that preloads some stuff? So your tradeoff is boot time vs app launch time.
I usually kill Office Start and all the other "fast startup" applications that various bits and pieces install, but Word is damn fast to start. I've had occasion to use Word 97 on modern machines - it starts about as fast as Notepad.
I don't own Word 2007. I actually use OpenOffice for all office-like tasks; they're somewhat slower, relatively glitchy, but they get the minimum amount of work I need there done.
I don't think microsoft mac apps are a fair test of how fast mac apps start. native apps are better, in general. and for Word in particular, I bet microsoft optimized the hell out of the startup on windows.
Word is a native app in osx. Word on the Mac is a completely different piece of software and not a bad port. I read a blog from one of the team members on the word.app team and it showed me that they are very committed to a good product. I doubt they would intentionally slow down the startup of the app just because it's on osx.
They rolled their own interface (which means buttons, events, accessibility tools, text boxes...), dictionary, spell check, grammar check, API, scripting interface, damn near everything. And it integrates extremely poorly with other Mac applications, even screwing up basics.
By that logic, Flash apps are native too. So are Java, GTK (on non-GTK-unixes), etc etc until anything that runs on the machine can be considered "native", unless you're remote-controlling another machine through something like SSH/VNC/Remote Desktop.
I doubt the developers would intentionally slow down the startup. But I also doubt Microsoft would invest their better/best programmers in optimizing it. But isn't that the same thing as intentionally slowing it down, but from the business's standpoint instead of the developers?
i've used word on mac, and it kinda sucks (even has data corruption problems). even if microsoft is trying, it doesn't mean they are nearly as good at making mac apps as windows apps (let alone fast mac apps, which is not their area of expertise).
and there's a world of difference between "intentionally slow down" (that's crazy) and neglecting to put a ton of work into optimization of startup.
I can't say I've noticed that myself. Pages starts instantly on my SSD. Logic, which is a boat of a program, opens along with a project file in about 5 seconds. Word 2008 takes about 5 seconds and also takes an awkward amount of time to close too. Maybe it has something to do with universal binaries? I've always stripped the PPC code out to save some disk space on my (relatively) small SSD. 10.6 ships without the PPC code for all the bundled applications.
So does the SSD portion effectively become a cache for the traditional platter HDD portion? Seems similar to an L1 cache for a HDD. Of course, as the article states, the caching algorithm will be application-specific. At 4GB however, it wouldn't be hard at all to keep a significant portion of the OS and any oft-used apps like browsers directly in the SSD portion.
That's the idea, but 4GB for a 500GB disk seems extremely small, especially considering the price. The other problem I see with this is that the 4GB are probably only one flash chip. Fast SSDs manage to sustain high transfer rates by effectively arranging flash chips in a RAID-0; the 80/160GB Intel X25-M SSDs use 10 chips in parallel if I remember correctly.
"By blurring the performance difference between disk and SSD, these drives will ensure that hard drives dominate for at least another decade" - I would say 18 months at the most. A decade is a long time in solid-state hardware!
Does anyone know where I can buy a nice desktop computer with an SSD drive? I feel like I looked on Dell recently and didn't see any. (But then again I'm an online shopping moran)
Buy the nice desktop computer and then install your own SSD and re-install the system on it - then use the mechanical drive for bulk storage, compiling, video streaming, etc.....
Is this similar to ReadyBoost in Windows? I haven't seen any benchmarks that demonstrate significant performance. Why would it work better if the flash is built into the hard drive?
He starts off by saying that boot times have gotten significantly worse. Reinstalling the OS (not something I want to do) gets startup time back to the same as with a standard HDD. So far so bad.
Secondly, application tests are completely unscientific and show a lack of understanding of how the OS works. After you open an application the OS caches it so that it opens more quickly next time. The startup improvements he's seeing can be entirely attributed to this: Consider that on my MBP with a 5400rpm HDD Pages took ~7 seconds to start the first time and ~1.5 the second time (using the same technique as the videos).
This is a better benchmark of the same drive, but I still think the conclusion is too favorable without more thorough real-world tests: http://www.overclockersclub.com/reviews/seagate_momentus_xt_...
Edit: Spelling and slightly overzealous language.