Become a fan of Slashdot on Facebook

 


Forgot your password?
Close
typodupeerror
×
Operating Systems Windows Technology

Early Speed Tests For Windows 8 242

Posted by samzenpus from the greased-lightning dept.
adeelarshad82 writes "You often hear in the software industry that performance optimization is one of the last steps in the software development process. That bodes well for Windows 8, considering at the early stage of Developer Preview—even before we've seen an actual beta—the nascent operating system is getting widespread praise for its performance, particularly in startup times. Anecdotal evidence is always encouraging, but PCMag decided to run some very early tests on the OS to see if the reports were wishful thinking or if there was a real, measurable boost in speed. Along with startup and shutdown times, they used several standard industry benchmarks to compare Windows 8 performance with that of Windows 7 running on the same machine."
This discussion has been archived. No new comments can be posted.

Early Speed Tests For Windows 8 More

Early Speed Tests For Windows 8

Comments Filter:

  • Performance (Score:3, Insightful)

    by andresa ( 2485876 ) on Friday October 21, 2011 @02:08AM (#37788210)
    There are actually two kind of performances, which are both important. The real, actual performance, and how well the OS can make the system feel even under load. It's important to have a snappy feel even if the system underneath is working hard, and this is especially true now that the amount of cores in CPUs and multithreading are increasing. Say what you want, but just the feel of speediness is an important factor. This is why the boot up time is looked at so much too - it's great to quickly get to the desktop, and let the OS load up while you're already started working.

    One thing I've noticed with boot up times (and this applies to all operating systems) is that the OS tries to load all programs at once. Usually the limiting factor to this will be hard drive. It's less true with SSD drives, but it's really noticeable with 7200 RPM and slower drives. It usually leads to the whole system crawling for a few minutes after desktop shows up. It would be great if the OS would measure the different loads and UI response times, and actually limit the startup programs. This way you could open your browser and other tools and those would be given priority upon startup process.

    I tested the developer preview version briefly and it sure seemed a lot faster and snappier. The startup time is remarkably faster. And according to this PCMag test, seems like the overall speed has been improved a lot too. Good job MS!

    • Re:Performance (Score:4, Interesting)

      by imess ( 805488 ) on Friday October 21, 2011 @02:24AM (#37788276)

      MS tried to throttle the startup programs in Vista so they don't all hit the disk at once, but reportedly gave up that idea in Windows 7:

      http://blogs.msdn.com/b/oldnewthing/archive/2011/08/17/10196425.aspx [msdn.com]

    • Re:Performance (Score:4, Insightful)

      by MareLooke ( 1003332 ) on Friday October 21, 2011 @03:40AM (#37788592) Homepage
      IMHO the time to desktop means nothing, especially on Windows as you note, the system isn't usable for minutes after the desktop's shown up. Adding in a faster drive (eg, an SSD or a hybrid drive) will cut down on the startup time, but the issue remains. So whether you load everything before showing the desktop or after will only make a difference in perceived bootup time, not in actual "time until the system is actually usable". In other words, it's just a cheap way to appear to boot faster without any actual benefit to the user.

      • Re: (Score:2)

        by Luckyo ( 1726890 )

        This, ten times over. When I swapped from XP to 7, first thing I noticed how fast it went from pressing the power button to seeing the desktop. Second was to notice that said desktop was completely useless for several minutes after becoming visible, and about 30 seconds after all applications have started. 7's caching is utterly retarded in this regard.

        XP was slower to boot to desktop, much faster to get desktop functional and applications started, and most importantly it was HONEST about it. It didn't pret

        • That is quite odd, my desktop is immediately usable. Not sure what the difference is.

        • Re: (Score:2)

          by gmack ( 197796 )

          What happened between 7 an XP was Intel giving MicroSoft a kick by donating a bunch of code to Linux that massively improved the boot times leaving MS to suddenly be far behind in that department.

          It's not he first time I've seen Intel do this and Microsoft reacts the same way every time and suspect that's Intel's new way of dealing with MicroSoft: Anytime they want MS to do something they give the code to Linux that does what they want in Linux.

    • Good job MS!

      Psst, this is Slashdot. You can't say that here.

  • I would have compared the boot-time of Linux to this, but they never state what harddrive they're using, rendering any compare worthless.

    ...on second thought, let's just compare that against my 1.8Ghz Core2Duo, 2GiB RAM Notebook: Debian Wheezy needs 4 seconds to boot. :O

    • I have to agree that this fascination with boot/shutdown time is like some new made up metric. "My machine can boot in 32 seconds." "HA! Mine can boot in 30!" Shut the fuck up. It takes 2 seconds to sneeze, for Chupacabra's sake! And unless you're rebooting, who cares what the shutdown time is? In which case, call it "reboot time." In which case, talk about how often you have to reboot.

      "Long story short: unless the code takes a turn for the worse in the next year or so, we can look forward to some s

      • Re: (Score:2)

        by Targon ( 17348 )

        When you are forced to wait a few minutes before a computer is really ready to be used from the time you turn it on, then yes, the time it takes IS important. Those who get to the desktop but are still forced to wait before doing anything due to the machine still loading tons of garbage want to see an improvement there. I know that between the HP software for my printer and anti-virus, those take a bit of extra time before they are finished loading before my system is properly responsive, and THAT is wh

    • Re: (Score:2)

      by Targon ( 17348 )

      The problem there is that with Linux, you can do a custom install that does not install anything you don't want to be running. Anti-virus on Linux? Nope, and many other things under Linux are also tuned to not start until you actually try to run them. With Debian, yes, you can get to a command line very very quickly, but once you fire up X11(whichever flavor you want), that adds a fair bit to the load time. If you set up for the system to come up with the GUI, your OS load time WILL increase.

      On th

  • From the article

    Benchmark Windows 7 Windows 8 Percent improvement
    Startup time (min:sec) 1:32 0:32 +65
    Shutdown Time 10 11 -10

    Old hobbits die hard.

    • Re:65% improvement but still more than half a minu (Score:4, Interesting)

      by JasterBobaMereel ( 1102861 ) on Friday October 21, 2011 @03:09AM (#37788464)

      Startup time, until login screen, or desktop, or usable system, or fully usable system ....?

      The four are different and most people assume you mean the last, when most are measured to the first .... ...and unless you have a laptop why are you turning the machine on and off enough to worry about boot times (in the real world the difference between 20s and 1 minutes is a vast gulf, the difference between 1 minute and 5 minutes is irrelevant)

      • About year ago, I tuned my linux box (cheap single-core Intel Atom board, 5400rpm HDD, 1GB RAM) to boot into X in 8s (measured between hitting ENTER key and displaying search results for "asdf" on google in Opera browser). Video: http://www.youtube.com/watch?v=zE_QRZwNGOs [youtube.com]

        • So.. you mean it was in suspend and woke up tongue X screen in 8 seconds? My laptop does that faster. Unless you meant it was completely powered down, nothing store in RAM, etc and you pushed the power on button (which may double as an enter key, I have no clue)

      • Even with a laptop, I mostly use hibernate. Amount of time to come out of hibernate, even on Windows 7 is only about 20 seconds after BIOS. And that gives you fully usable system, with all the programs you had open previously. Reboot time is absolutely worthless, because I almost never reboot anymore. Once every couple of weeks for updates.

    • "Old hobbits die hard."
      Was he taking Viagra?

    • Re: (Score:2)

      by Bengie ( 1121981 )

      Actually, they shouldn't be including the BIOS time into the boot time because that has nothing to do with the OS.

      It should read more like

      Benchmark Windows 7 Windows 8 Percent improvement
      Startup time (min:sec) 1:17 0:17 +78

      78% improvement

  • First hammer out the dent, then repaint (Score:3, Insightful)

    by Hognoxious ( 631665 ) on Friday October 21, 2011 @02:29AM (#37788300) Homepage Journal

    You often hear in the software industry that performance optimization is one of the last steps in the software development process. That bodes well for Windows 8, considering at the early stage of Developer Previewâ"even before we've seen an actual betaâ"the nascent operating system is getting widespread praise for its performance

    Not necessarily. It wouldn't be the first time things have been performance tuned before they're actually working properly.

    Anecdotal evidence is always encouraging

    I heard the opposite.

    Does anyone else detect a whiff of shill in the air?

    • Re: (Score:2)

      by DZign ( 200479 )

      What you often hear is wrong..
      If performance is really important for your product, you have to thikn about it from the beginning and in every step.

      • Re: (Score:2)

        by Hadlock ( 143607 )

        Unless the "product performance" group is headed by some VP's nephew who has no managerial experience, no clout, no budget, and no staff...

      • Re: (Score:2)

        by Locutus ( 9039 )
        you mean like needing the current version of Windows in the same ball park as the competition as far as hardware goes? You don't think this has anything to do with the Apple iPad, Android tablets and various Linux based ARM devices do you? Microsoft can't pull Windows XP out of retirement yet again and also require extra hardware too and consider themselves competitive.

        LoB

    • Re: (Score:3, Insightful)

      by Anonymous Coward

      "Does anyone else detect a whiff of shill in the air?"

      No, I can't smell it due to the overpowering stench of knee-jerk anti-MS zealotry.

      FFS, there'll be plenty of things to hate about 8 when it comes out, attacking it while it's still in the womb is a bit unnecessary, don't you think?

  • Who cares about speed when... (Score:4, Insightful)

    by bmo ( 77928 ) on Friday October 21, 2011 @02:45AM (#37788352)

    ...you boot the bastard on a desktop machine, and then it goes to that horrid Metro screen which makes navigating with a mouse and keyboard painful? It may be fine for touch, but without touch, man....it makes you want to break things.

    Then you talk to a Microsoft turfer, as seen on here and other places, they will bald-faced lie to you and say "well, it's not finished yet, who knows what it will be like?"

    Then you go to the Microsoft fora and ask Microsoft employees about Metro as being standard for the upcoming desktop, they double-down on it.

    Guys, get your friggin' stories straight. All I know for sure is that Metro without touch is a steaming load of bovine excrement backlit by the morning sun so you can see the vapors wafting off it. Fix it.

    --
    BMO

    • What are you using the Metro interface for? The only part of it I see is the Start menu, for the fraction of a second it takes me to type the first few letters of the program name I want and hit Enter. The rest, especially the browser, is un-needed. Just use the desktop (including desktop browser) like you always have, and the Start menu like you have (or should have) been since Vista - as a search interface, nothing more.

      I'll grant you the current version of Metro is crappy with a mouse. Given that there a

      • Re: (Score:2)

        by dbIII ( 701233 )

        What are you using the Metro interface for? The only part of it I see is the Start menu, for the fraction of a second it takes me to type the first few letters of the program name I want and hit Enter

        Remember all the MS Fanboys that argued the Linux is completely broken because you sometimes have to type things in? There used to be hundreds of them here so I'm sure one will read this. What do you have to say now?

        It certainly sounds like a big improvement to me anyway instead of navigating through a const

        • The problem is not exactly the need to type things on Linux... Is more the need to type obscure commands with ever more obscure options to do things that you may can do in a more easy way using a GUI. And in this example remember that:

          1) The average user is not an expert. He just wants to use the computer to do his job and does not want (or are unable to) memorize every single existent Unix command (and their options) to do so. And worst, many MAN pages are sloppy on important details.

          2) The average G

          • Re: (Score:2)

            by dbIII ( 701233 )
            I know that, you know that, but there's a frequent but deluded insistance that linux is broken the second that a key has to be pressed. Remembering a twisty maze of menu options is sometimes just a tricky as remembering a command, it's just different. When MS Windows users encounter a problem you often cannot tell them how to resolve it - you have to show them how to navigate the twisty maze. Sometimes you'll have to show them a few times while the same people would only need to be told the name of a com

    • ICS will be release very soon. We promise. Maybe. I gotta talk to that other guy over there. Once he's done playing Metroid.

  • surely we should bne thinking about time to be usuable once logged in? We all know Windows doesn't start alot of things till after user login (first used in NT4), so this is what we should be measuring, not how quick it gets to login screen. Reading the article they COULD be using this test but it's not clear.

    Also things like with WIndows you NEED some sort of anti-virus installed as well so again not that real world, but looking encouraging and we'll see how many of the extra features not yet implemented i

    • Re: (Score:2)

      by Bengie ( 1121981 )

      The BUILD conference showed a laptop that booted and was usable within 4-5 seconds of pressing the power button. Not suspended.

      BTW, in the Win8 boot sequence, the antivirus is loaded just after the driver and before any user apps, so a good portion of that 4-5 seconds included scanning.

      Overall, I think that's a lot better than prior Windows OSs.

      • Re: (Score:2)

        by jedidiah ( 1196 )

        The missus chuckles any time she sees the "startup laptop during skydive" commercial as she has the laptop in question running the OS in question and it doesn't behave anything like the one in the commercial. It's a fairly new machine that's not modified too heavily from it's stock configuration.

        +...this is just like "minimum system requirements".

        There are probably a lot of details left out, a lot of overly optimistic assumptions made and it's probably not a stock configuration as you're going to see it fro

    • Re: (Score:2)

      by PJ6 ( 1151747 )

      Also things like with WIndows you NEED some sort of anti-virus installed as well

      No, you don't.

  • Development process knowledge fail (Score:5, Insightful)

    by Knuckles ( 8964 ) <knucklesNO@SPAMdantian.org> on Friday October 21, 2011 @03:08AM (#37788458)

    You often hear in the software industry that performance optimization is one of the last steps in the software development process.

    No you don't, not among sane people. You don't do performance optimization as "one of the last steps" shortly before shipping.

    What you hear is that "premature optimization is the root of all evil" (quoting Donald Knuth). What he meant is that you should not bother with complicated performance optimizations when designing the code. Rather, create and implement a good clean design, then test performance and optimize where needed. On the other hand, algorithm choice is one of the biggest performance contributors and initial choices will often be made quite early, so one cannot apply this quote blindly. Read here: http://en.wikipedia.org/wiki/Program_optimization [wikipedia.org]

    • As a note: premature != early.

    • In Penguin Antarctica, Microsoft optimizes you!

    • Re: (Score:2)

      by MobyDisk ( 75490 )

      You often hear in the software industry that performance optimization is one of the last steps in the software development process.

      No you don't, not among sane people. You don't do performance optimization as "one of the last steps" shortly before shipping.

      I suspect that the misunderstanding comes from the fact that Microsoft releases checked builds initially, with lots of debugging code some compiler optimizations disabled. So the perception is that they don't "optimize" the code until the final release.

  • Startup time is not a useful metric (Score:5, Interesting)

    by Coward Anonymous ( 110649 ) on Friday October 21, 2011 @03:21AM (#37788504)

    Ideally, a modern desktop OS should be booted once. The rest of the time it should be slipping in and out of sleep.

    In practice it seems that a few months between reboots (for OS updates) is easily attainable on some platforms.
    When a reboot occurs once every few months, boot time is not terribly important.

    I can't help but think that people who marvel at improved boot times are rebooting their machines too much.

    • I can't help but think that people who marvel at improved boot times are rebooting their machines too much.

      Either that or they're journalists.

      Boot times are something that's easy to measure and they generate lots of pretty graphs to fill those column inches with.

    • Ideally, a modern desktop OS should be booted once. The rest of the time it should be slipping in and out of sleep.

      I know anecdotal evidence is frowned upon here, but my laptop with 4GB of ram and a 5400rpm disk takes about the same time to wake from hibernation as to boot*. Pair that with KDE's ability to restore sessions after a shutdown**, there is almost no advantage in putting it to sleep. I do suspend frequently, but that's more of a short-term solution with battery being used and lights blinking. And I can't sleep next to a running computer, I like silence in my room.

      * It's probably a buggy driver problem too. St

      • * It's probably a buggy driver problem too.

        Why? Do the math...

        a) How many megabytes per second can your hard drive read?
        b) How much RAM have you got?
        c) Divide (b) by (a)

        With 4Gb it's not really shocking that it takes quite a while to come back from hibernation. 8Gb probably takes longer than booting on most hard drives.

    • And in the UK its not cheap so yes, I shut my desktop down when I'm not using it and fully switch off the monitor. Aside from that it has an enviromental benefit downstream at the power station. Sleep mode might not use much power but it still uses some and with all the computers in the world that probably adds up to a lot of CO2 for nothing.

      • A decent PC will use about 2 watts in sleep mode. You'll be lucky if you save enough in a year for a single pint of beer.

        • I believe mine takes somewhere between 7 and 12 watts, and that's everything I have plugged into my UPS. My tower, external drives, cable modem, router, monitor, etc. Basically everything I need to keep my computer running, and the internet up.

    • "Ideally, a modern desktop OS should be booted once."
      What! And remove another dick-measurement metric from the field. You blasphemer! And other stuff.

      "I can't help but think that people who marvel at improved boot times are rebooting their machines too much."
      Yeppers, I said that somewhere else in this thread. (You beat me too it, though. You win boot-posting death match! [yes, I'm just joking around] )

      • They might have notebooks. I have a macbook and an asus g series for windows stuff (translation: gaming).

        I don't travel much with the asus so it tends to sit plugged in and go in and out of hibernation. The macbook, I carry around a lot. When i do, i shut it down.

        Just shutting the lid and letting it sleep still draws enough power that the battery is somewhat depleted later that day. I don't tune it to start up fast*, but a speedy boot is desirable and one of the reasons i have a macbook and not a very p

    • Re: (Score:2)

      by Targon ( 17348 )

      This assumes the user is running software without memory leaks. You want to play some games on your computer(something most Mac and Linux users just don't do), you have to expect memory leaks, and the idea of sleep/hibernation to let the machine run for months at a time without a full shutdown/restart just doesn't work. I've run Linux setups where I would run them six months or more between reboots, but the software for Linux generally doesn't have the memory leaks you see under Windows.

      When Apple is t

      • Re: (Score:2)

        by clodney ( 778910 )

        This assumes the user is running software without memory leaks. You want to play some games on your computer(something most Mac and Linux users just don't do), you have to expect memory leaks, and the idea of sleep/hibernation to let the machine run for months at a time without a full shutdown/restart just doesn't work.

        I will admit that there are ways that system resources can be consumed and leaked, but in general it is hard for a user mode process to leak anything past process termination. Microsoft took that lesson to heart starting back in Win 95, and the system is very aggressive about keeping track of what process allocated what, and cleaning it all up when the process terminates. I play a lot of games, and and I can't think of the last time I had to do a reboot to address something like memory allocation or file

        • Re: (Score:2)

          by Targon ( 17348 )

          Try playing a modern game for six hours straight and doing that daily without doing a reboot. Windows 7 will let me go a week or more, which is better than the 3-4 days of Vista, and the 1-2 days under XP, but it is still needed.

          It may be driver related that is causing it, but it's still an issue.

    • Re: (Score:2)

      by Chemisor ( 97276 )

      Since all the games I want to play crash wine and only run on Windows, I have to reboot whenever I want some entertainment. I don't expect companies to start developing Linux games anytime soon, seeing how the driver situation is, so I expect to continue rebooting frequently for a long time yet.

  • Making Windows more optimal might signal a turn of focus toward phones and tablets.

  • They aren't done yet (Score:3)

    by Charliemopps ( 1157495 ) on Friday October 21, 2011 @06:55AM (#37789468)
    Give Microsoft time to stick some horribly designed bells and whistles on to destroy any performance gains you're seeing now.

  • Just wait to install updates (Score:3)

    by 1800maxim ( 702377 ) on Friday October 21, 2011 @01:14PM (#37795960)
    Just wait to install updates, service packs, .NET frameworks (or their future equivalent), etc, etc... A fresh XP installation books in less than 20 seconds on my machine, more like 15. Install updates, drivers, .NET frameworks...

    And it's nearly 2 minutes on my, relatively lean, machine (nothing in startup), with decent modern hardware (Intel 9550 Quado Core CPU, 4 GB RAM, 10K RPM hard disk). That's all the way past the login process until I can USE the machine. This thing should fly. Ubuntu loads in 30 seconds, fully ready to be used.

Slashdot Top Deals

As you will see, I told them, in no uncertain terms, to see Figure one. -- Dave "First Strike" Pare

Close