Slashdot Mirror
Windows 7 Hard Drive and SSD Performance Analyzed
bigwophh writes "Despite the fact that Windows 7 is based on many of the same core elements as Vista, Microsoft claims it is a different sort of animal and that it should be looked at in a fresh, new light, especially in terms of performance. With that in mind, this article looks at how various types of disks perform under Windows 7, both the traditional platter-based variety and newer solid state disks. Disk performance between Vista and Win7 is compared using a hard drive and an SSD. SSD performance with and without TRIM enabled is tested. Application performance is also tested on a variety of drives. Looking at the performance data, it seems MS has succeeded in improving Windows 7 disk performance, particularly with regard to solid state drives."
Is is fast enough to get first post?
(Sarcasm guys)
This information is irrelevant to many of us; for a frame of reference, how does HD performance on 7 compare with XP?
This post was made in complete sincere seriousity; as such any attempts to derive humour are doomed to instant failure.
Linux already supports SSD's and other flash media by having a noop scheduler. The basic premise is that devices that don't depend on mechanical movement to access data don't need reordering of requests. This is also the scheduler you use if you have an advanced controller (RAID, etc) that is capable of doing it's own I/O rescheduling.
/dev/sda):
/sys/block/sda/queue/scheduler
/sys/block/sda/queue/scheduler
To see what scheduler you are running (on this case
# cat
noop anticipatory deadline [cfq]
Here the completely fair scheduler is currently running. To swap to the noop scheduler:
# echo noop >
[noop] anticipatory deadline cfq
Platter based hard drives and high-end solid state drives, all run faster on Windows 7. Solid state drives see the largest performance boost, which showed up to a 35% improvement in read performance and up to a 23% boost in write performance
About as much after as Vista was slower than XP. Perhaps a very marginal improvement. At most a third faster reading, and a quarter faster writing than the most hated OS of the millenium so far.
Those who like to bash Microsoft at every turn will have to find some new reasons to hate on Windows 7, as low, machine-halting performance won't likely be a factor when Win7 comes into the mix.
Nope. Same old reason to hate them. They set back operating systems on the majority of the world's PCs by half a decade.
We should be jeering not cheering.
These posts express my own personal views, not those of my employer
They should have also included a benchmark test against Windows XP so that we could see how much it's decreased/increased since then. A majority of people haven't upgraded to Vista yet so it would have been useful to give an idea to those users. And perhaps, benchmarking other OSs to see how they all stand.
"I have never let my schooling interfere with my education." --Mark Twain
Why did they fail to compare performance with Windows XP?
Phoronix has some Linux 2.6.30 Kernel Benchmarks, some on SSD. Not surprisingly they forgot to include comparison with Windows 7, as that HotHardware article forgot to include comparison with Linux. Are they both biased?
Anyhow, SSD is the future.
Sorry, I mistook the "160GB Western Digital WD1600JS-00M SATA 2.0 hard drive" for a SSD.
Still, I don't understand how HotHardware can write: "At this point, everything seems like it's moving in the right direction with this new operating system, and Microsoft is finally showing that it can better compete in terms of usability and user-experience in today's computing environments against OSX and Linux, providing a compelling case why the Windows operating system is such a dominant force." without having compared it with OSX or Linux.
Sorry for the mixup above.
Of course Windows 7 will seem like a completely different OS if you look at it in a "new light" as MS says. OTOH, if you look at it the same way, admitting that Microsoft hasn't changed its customs and see the same bullshit as in 95 - Vista, you can't argue with them, because they can just reply "but it's different this time, just look at it with new eyes." Of course you can't compare it to anything if you try to forget what you've saw before.
I've seen bugs that have been around since Windows 95 in Internet Explorer (since 4.4 until 8.1, there's a limit of 32 <style> tags per page and MS still insists that its only a 4.4 - 6 without saying anything about 7 and that the limit is 31) and in Windows Explorer (when you try to minimize and focus applications, in certain conditions they won't listen. They have changed the way the UI looks, the kernel and added some drivers. Otherwise, I see absolutely no point in trying to analyze Windows 7's performance or compare it to previous versions of Windows. If you look at the bugs, you'll see that there have been bugs around in Windows sincefor 15 years and nobody touched them. I have given them the benefit of the doubt and installed Windows 7 RC1, hoping for a change in attitude from MS, but now I don't want to see anything about Windows again because the only change MS ever made was in the UI.
Please stop "analyzing" what Windows 7 can do and go after what's more important: what Windows 7 really is.
Going from XP to 7 Beta1 (and now RC), am I the only one who feels that the improved performance issues of Windows 7 may actually work? I installed a copy of the RC on my laptop, and it worked beyond what I expected. The Laptop was "powerful" enough for Vista, and it couldn't even compare to the performance my laptop was giving me currently.
I installed the Beta on my desktop, and only had one issue that isn't worth the words to complain about.
I know Vista may have been a flop to some people, but this just seems like a repeat of about 8-10 years ago. When ME came out, users found it abyssmal. But the solution seemed to be to go from 98SE to XP, and everyone was content.
This just seems like repeated history to me, as everyone jumps the XP ship for 7, because Vista is still taking water.
P.S. It's rather late here, apologies in advance. I'm probably rambling by now.
"I'm a well-wisher, in that I don't wish you any specific harm."
The TRIM spec is not yet final, and most SSD's will not support it until it is. It's also a safe bet that the WIndows 7 RC does not yet issue TRIM commands (for the very same reason). My testing suggests TRIM is *not* yet at play in the 7100 build of 7. The *slight* gain in write performance seen in the linked review is likely due to the fact that they used two different firmwares for the supposed TRIM enabled / disabled testing. TRIM on a Vertex would give you more than the gain they saw.
Allyn Malventano
Storage Editor, PC Perspective
this sig was brought to you by the letter
I believe that in order to have a more global picture about ssd disks performance, the comparison must be made in all OS available today, Windows flavors, Linux flavors, Unix flavors, Mac OS, Solaris and others that I maybe forget.
Until the skies turn blue...
Until the air of freedom strikes us...
I'd like to see some impartial figures to see how disk subsystem performance (regular and raided) compares with FreeBSD. You can even use FreeBSD 2.2.1 if you want.
And them again under heavy load. Not just "oooh, lets try a million database reads".
I'll wait. I use windows. I'm used to it.
Need Mercedes parts ?
The large problem with Windows XP and SSD's is that Windows XP does not properly handle SSDs similar to how Windows Vista does not. You have to go in and manually disable these things to fix performance and increase longevity while it is handled automatically in Windows 7. You cannot expect end users to "tweak" their systems to properly handle these drives, so the real world benefit of paring Windows 7 and an SSD is there that beats out both Vista and XP.
Having struggled with two Vista PCs for many months, I am perpetually on the lookout for a better solution. (I've even considered running XP in a VM under SuSE Linux). I have a pretty powerful desktop machine, with a 2.9MHz 4-core i7, 6GB of fast RAM, two Velociraptors and an SSD. This machine is very sluggish running 64-bit Vista SP2, and I am sick and tired of seeing everyday applications like Firefox flagged "Not Responding" (and living right up to that) for as much as minutes on end - while Task Manager shows the idle process running 85% of the time. My laptop, a ThinkPad T61 with 2GB RAM, shows similar symptoms but (oddly enough) doesn't tend to stay out to lunch quite as often or as long.
So I glommed right on to this review, hoping to see some impressive figures. But it seems to me they aren't. Improvements in disk read performance of around 10% might not change overall user responsiveness enough for you to notice it.
Why can't Microsoft simply produce a scheduler that understands the key principle: when the user wants to do something, everything else must get out of the way? Their trouble is that they just don't agree with what seems to obvious to me. It's MY computer, not theirs. I paid for it, I own it, I use it. So I want it to pay attention to ME, first, last, and foremost. Not some unnecessary housekeeping task that seem Microsoft developer or marketing chum decided to impose on me. It's ironic that an IBM mainframe should be so much more responsive than a supposedly end-user-centric "personal" computer whose OS is completely dominated by its UI.
I am sure that there are many other solipsists out there.
Does windows still abandon file-copying operations when one single file out of a huge directory structure one is trying to copy from one volume to another fails?
This always annoyed me. I would fantasise about paying for my microsoft products thusly "£200? No problem. Here's the first penny, here's the second penny, here's the third penny, Ooops! I dropped the third penny! Well, that is the transaction completed, goodbye."
They whose government reduces their essential liberties for temporary security, receive neither liberty nor security.