Slashdot Mirror

← Back to Stories (view on slashdot.org)

Embedded Linux Achieves One-Second Boot Time

Posted by timothy on from the all-it-does-is-operate-the-power-button dept.

Sam writes "A new goalpost has been set in the race for faster bootup times. MontaVista Software announced (and demonstrated at the Virtual Freescale Technology Forum) a dashboard application going from cold boot to operational in one second flat on their embedded Linux platform. Although this is unlikely to immediately benefit your average Linux user, previous real-time patches have eventually made their way into the main kernel."

130 of 164 comments (clear)

  1. Nice text color by lpcustom · · Score: 1, Insightful

    That site should just switch to white text. It's like everyone keeps going a shade lighter. Apparently they are racist and have something against black.

    --
    Beer! It's what's for breakfast!
    1. Re:Nice text color by Idiomatick · · Score: 4, Funny

      It isn't the black itself that gets to them it is the black on white action.

    2. Re:Nice text color by sjames · · Score: 5, Funny

      They just want to simulate the effect of printing marketing materials on a worn-out laser printer in need of toner because that looks sooooo professional.

      Nothing says we're professionals and have important information for you like a crooked illegible photocopy except perhaps a grade-school spirit duplicator. Expect funky light purple text next. The holy grail, of course, will be a wrinkled paper background that actually makes it look like they dug the web page back out of the trash and gave it to you.

    3. Re:Nice text color by Chabo · · Score: 1

      Whether or not you like his writing, I think Maddox hit the peak of usable web design: dark background, with large-font bright text. If you don't like the yellow, you could go with old-CLI-style green. Either way, it's the easiest webpage on the internet to read.

      --
      Convert FLACs to a portable format with FlacSquisher
    4. Re:Nice text color by Anonymous Coward · · Score: 2, Informative

      you don't even link to the best page in the universe?

    5. Re:Nice text color by Teun · · Score: 2, Funny

      What are you talking about? On my monitor his site is shown with the same amber colour like any other.

      --
      "The likes of Facebook and WhatsApp are free to those whose privacy is of zero value."
    6. Re:Nice text color by BiggerIsBetter · · Score: 1

      Nothing says we're professionals and have important information for you like a crooked illegible photocopy except perhaps a grade-school spirit duplicator. Expect funky light purple text next. The holy grail, of course, will be a wrinkled paper background that actually makes it look like they dug the web page back out of the trash and gave it to you.

      I won't be impressed until they track your visits and gradually lighten the text in shades of brown, while yellowing the background as time between visits passes. A true old-school professional look akin to yesterday's thermal printers.

      --
      Forget thrust, drag, lift and weight. Airplanes fly because of money.
  2. Finally by 2names · · Score: 4, Funny

    I can post before I log in.

    --
    "I'm just here to regulate funkiness."
    1. Re:Finally by sigxcpu · · Score: 1

      This just shows you, some people will go to great lengths, just to get a first post!

      --
      As of Postgres v6.2, time travel is no longer supported.
    2. Re:Finally by Vandilizer · · Score: 1

      But my computer always POST before I can login...

    3. Re:Finally by poetmatt · · Score: 1

      eh I prefer Honey Bunches of Oats.

  3. Been there, done that by alain94040 · · Score: 3, Informative

    I'm surprised that this is news. I remember working a few years ago on booting Linux (also the MontaVista version) in 600 million cycles flat, which for a CPU running at 600 MHz, is exactly one second as well.

    You can even still: watch a video of this here

    1. Re:Been there, done that by characterZer0 · · Score: 4, Interesting

      How many of those 600 million cycles are performing operations as opposed to waiting for IO and memory access?

      How many operations does it take to boot Linux?

      --
      Go green: turn off your refrigerator.
    2. Re:Been there, done that by jorghis · · Score: 1

      It is not news. I work for an embedded software company and we have operating systems that boot in well under a second. Its not a big deal. Really. Its just a pleasant side effect of the fact that a lot of embedded operating systems don't really have to do a whole lot on boot.

    3. Re:Been there, done that by Jah-Wren+Ryel · · Score: 1

      How many operations does it take to boot Linux?

      As many licks as it takes to get to the center of a tootsie pop.

      --
      When information is power, privacy is freedom.
  4. It's 1980 all over again by JonTurner · · Score: 5, Interesting

    Impressive and would be a huge improvement over the current state of things.

    But then again, my 1Mhz Apple ][ could cold boot in just a couple seconds.Of course, loading Applesoft Basic from tape took an additional two minutes but Integer Basic was in the ROM.

    Michael Abrash wrote a great article about this in Dr. Dobbs magazine in the 90s. His young daughter (5 years old?) asked him why he never used his "fast" computer. Abrash was using a state-of-the-art 266mhz DX2 powerhouse and couldn't figure out what she meant. She was referring to the old Vic-20 in the corner that would boot in just a few seconds. Windows 3.0 took several minutes to load. IIRC, the article was titled "perception is everything"

    1. Re:It's 1980 all over again by fuzzyfuzzyfungus · · Score: 2

      I wonder how much of the boot slowdown has to do with architectural change(loading from slow disk to plentiful RAM vs. small amount of RAM and lots of stuff burned into ROM, the rise of networking as a more or less assumed part of the boot process, increase in the number of highly complex peripherals that need to be negotiated with), and how much has to do with the OS gradually grabbing more of what applications historically had to do(DOS loaded like the wind; but didn't actually load very much).

    2. Re:It's 1980 all over again by noname444 · · Score: 3, Informative

      A DX2, at 266 MHz, in the early 90s? If this is an Intel 486 we're talking about I think you've gotten the numbers a bit wrong. Mine ran at 33 MHz.

    3. Re:It's 1980 all over again by Nethemas+the+Great · · Score: 4, Informative

      FACT NAZI Observation: The 486DX came in 20, 25, 33 or if you were unlucky 50Mhz variants. Consequently a clock doubled (DX2) 486 was not capable of anything close to 266Mhz. That wasn't achieved until the Tillamook-Pentium much later.

      --
      Two of my imaginary friends reproduced once ... with negative results.
    4. Re:It's 1980 all over again by schon · · Score: 1

      I wonder how much of the boot slowdown has to do with architectural change

      None of it - at least not the architecture you're meaning (ROM vs. HD loading)

      The post above yours talked about an A1200 that booted in 3 seconds - from hard drive.

      I had an A3000 that booted from HD in 6 seconds - and it was only that slow because it loaded up drivers for my network card, set up TCP/IP, initialized the (additional) display card, and a bunch of other things (desktop customization.)

      Loading off disk isn't the issue.

    5. Re:It's 1980 all over again by JonTurner · · Score: 1

      good catch -- indeed, that was a goof. meant to write 66 but my fingers had other ideas. Sorry. But at any rate, I don't think the specific numbers are that important. The point was the new machine was computationally hundreds of times faster. But in actual use, it was slower in some areas that really matter, to the degree that even a young child noticed!
      BTW, It's been a few years since I read it, but I believe this story is included in Abrash's book titled "Michael Abrash's Graphics Programming Black Book" since it's largely a compilation of his DDJ "Mode X" articles and a few others.

      Yep, the early 486 with the clock-doubled processor. I had a DX2-80 *I think* (with a VESA local-bus video card so I could play Aces Of The Pacific in 256 color 800x600 mode -- woot!) and thought it was the cat's whiskers. Couldn't believe how fast it was compared to my lowly 33MHz machine @ work. And it only cost me $2300, what a great deal! And to think, now a $99 iPod Touch could run a PC emulator faster than that machine. That's serious progress.

    6. Re:It's 1980 all over again by SirStiff · · Score: 1

      My bet is he had 486DX266 in his head.. meaning 486 DX2 66MHz, and then transcribed it wrong.

    7. Re:It's 1980 all over again by DocSavage64109 · · Score: 1

      Not only that, but Win 3.1 took about .2 seconds to load from a dos prompt on my old pentium 90. I'd be afraid to see the machine that took 2 minutes to boot Win 3.1!

  5. That's pretty cool... by MrCrassic · · Score: 1

    Though the fact that this is an embedded device with, most likely, a REALLY stripped down version of Linux is kind of cheating a bit.

    1. Re:That's pretty cool... by jd · · Score: 5, Informative

      CoreBoot (formerly known as LinuxBIOS) will boot a full Linux kernel on a general-purpose machine in 3 seconds. Ok, it's two seconds longer, but it ain't bad.

      --
      It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
    2. Re:That's pretty cool... by sjames · · Score: 1

      Embedded apps often run on a stripped down embedded system, so for that context, the test is fair.

    3. Re:That's pretty cool... by C18H27NO3+ · · Score: 1

      _Only_ 2 seconds longer??! That's a 300% increase in boot time! Nobody has the time to wait for that.

    4. Re:That's pretty cool... by maxwell+demon · · Score: 2, Informative

      No, it's a 200% increase.

      --
      The Tao of math: The numbers you can count are not the real numbers.
    5. Re:That's pretty cool... by ezzzD55J · · Score: 2, Informative

      It's 300% of the old boottime, which is a 200% increase.

    6. Re:That's pretty cool... by C18H27NO3+ · · Score: 1

      Yeah, I fat-fingered the number and didn't notice it on preview.

    7. Re:That's pretty cool... by jd · · Score: 1

      So what you're saying is that your message booted too quickly.

      --
      It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
    8. Re:That's pretty cool... by Anonymous Coward · · Score: 1, Informative

      The thing with an embedded device is that the hardware is known. The boot sequence can skip hardware detection and it can be customized to only deal with what is specifically installed.

    9. Re:That's pretty cool... by BobMcD · · Score: 1

      Premature encapsulation?

    10. Re:That's pretty cool... by arndawg · · Score: 1

      No. It just passed POST to quickly

  6. Does it matter all that much? by 93+Escort+Wagon · · Score: 3, Interesting

    Okay, I haven't been using desktop Linux on a day to day basis since around 2003; but even then, sleeping and hibernating worked reasonably well - so I didn't reboot all that often. On my Mac, the only time I reboot is when an update forces me to. So (serious question) why is faster boot times all that important? I wouldn't think devices w/ embedded Linux would shut down regularly, but maybe I'm wrong...

    --
    #DeleteChrome
    1. Re:Does it matter all that much? by kent_eh · · Score: 1

      I wouldn't think devices w/ embedded Linux would shut down regularly, but maybe I'm wrong...

      Certainly you don't want them to shut down regularly, but if it does spontaneously shut down for some reason (power interruption comes to mind) then getting your embedded device back online fast may be very important, depending on the importance of the embedded device in your system.

      --

      ---
      "I can't complain, but sometimes still do..." Joe Walsh
    2. Re:Does it matter all that much? by fuzzyfuzzyfungus · · Score: 1

      Depends on the type of embedded device, I suspect.

      In extremely broad terms, there is "embedded" as in "essentially always on" which covers things like routers, NAS boxes, LOM cards, and watches; and "embedded" as in "should turn on and off as fast as the device it is embedded in" which covers things like TV electronic program guide systems, car engine computers, and the like. The line between the two can be rather blurry(my cellphone is on most of the day, to receive work calls; but waiting 40ish seconds when I just need a single phone number after hours annoys me, so it could fall in either category. And computers fall in one or the other largely depending on how you use them); but, depending on your taste, you can come up with one.

      For the first class; boot time isn't a giant deal. All else being equal, I'd rather have my router reboot in 2 seconds rather than 90 seconds; but I wouldn't pay much money for such a feature(and the sort of people who would pay any nontrivial amount would likely be better off with a redundant router instead). For the second class, though, the faster the better(especially since embedded systems often don't have any good way of signalling progress to the outside world, they are either visibly working or not, and having no progress indicator makes waits seem much longer).

    3. Re:Does it matter all that much? by Tubal-Cain · · Score: 1

      My phone gets no reception at work, so I turn it off. I turn it on again when I leave, and I usually need to use it at that time. It's frustrating that it takes longer to boot my phone than to actually make the phone call.

    4. Re:Does it matter all that much? by Stray7Xi · · Score: 1

      Outside consumer devices it could be even more important, such as solar-powered wireless sensors. For example, every hour it powers on an embedded device which transmits the data back to a server then powers down. The boot time has real effects on power requirements. Which is either solved by larger solar panel ($$$) or fewer updates.

    5. Re:Does it matter all that much? by elgaard · · Score: 1

      Can it wake up from sleeping and hibernating in a second?

      If you have a full-disc encrypted computer you want to turn if off when you are not sitting in front of it.

    6. Re:Does it matter all that much? by putzin · · Score: 1

      Yeah, that's exactly it. In my business, we try to design for 0 failures, but that's unrealistic. So we also design in restarts that are fast enough that the outage isn't as noticeable to whoever is using the services. The less our customers customers have to deal with outage, the less our customers have to yell at us, or do bad things with contract clauses. If my PPC embedded controller comes back to life and working in 1 second, then my peripheral services can come back that much faster, and the network is up that much faster. Right now, with our high end boards, reboots using WindRiver Linux cycle completely in about 30 seconds and the environment is completely restored in about 2 minutes. Taking 29 seconds off of two minutes would be a 25% improvement almost, and a huge selling point.

      --
      Bah
    7. Re:Does it matter all that much? by RiotingPacifist · · Score: 1

      It depends what you are doing. shutdown != hibernate/suspend.
      suspend is used as a workaround for slow boot,
      hibernate is also used but even that can only be so fast ~2.5s per gig of ram in use when hibernated.
      But both are just ways to save power while and allow you to continue your current task later and should not be considered replacements for shutdown/startup when your done.

      I wouldn't think devices w/ embedded Linux would shut down regularly,

      Embedded linux can go everywhere, in this specific case its a car system that
      1) has very low power usage requirements (no suspend)
      2) has no permanent storage (no hdd or battery backed ram)

      --
      IranAir Flight 655 never forget!
    8. Re:Does it matter all that much? by tepples · · Score: 1

      Okay, I haven't been using desktop Linux on a day to day basis since around 2003; but even then, sleeping and hibernating worked reasonably well

      It doesn't for everyone, in part because several notable hardware makers decline to cooperate with the developers of Linux and the developers of user-space driver frameworks designed to run on Linux.

    9. Re:Does it matter all that much? by selven · · Score: 1

      What if you're carrying a laptop on a trip where you won't have a power socket for a long time and you want to conserve energy? Hibernate isn't 100% effective.

    10. Re:Does it matter all that much? by fia · · Score: 1

      Yes, it matters. Read the customer design challenges: "system needs to provide real-time data in 1sec from power-on" "can not use suspend/resume due to a very limited power budget and temperature range - no battery to backup RAM." "must be resilient to power loss at any time - to prevent data corruption"

  7. Re:Not needed by Niris · · Score: 1

    Some people (including myself) are kind of anal about turning things off when they're not being used. On the other hand, a lot of people also just turn on their computer and walk away to get something to eat/drink/use the restroom while the machine boots, so it isn't really a big problem.

  8. Re:Not needed by maxwell+demon · · Score: 2, Insightful

    A computer sitting idle needlessly consumes power. A computer switched off doesn't.

    --
    The Tao of math: The numbers you can count are not the real numbers.
  9. Re:Not needed by Abreu · · Score: 5, Insightful

    I'll bite.

    Some of us want to run laptops, netbooks and other devices where the ability to shut down completely and then turn on quickly, using zero battery in the meantime would be very useful.

    --
    No sig for the moment.
  10. Surf internet in 1 second? by odin84gk · · Score: 2

    Give me a call when they can go from off to Google in less than 1 second. (OS boot, wireless initialization, browser start, google reply). Shoot, I would be impressed with 10 seconds.

    1. Re:Surf internet in 1 second? by Flea+of+Pain · · Score: 1

      I wonder what Google's OS boot time is...

      --
      Do not argue with an idiot. He will drag you down to his level and beat you with experience.
    2. Re:Surf internet in 1 second? by Culture20 · · Score: 1

      My gaming workstation at home goes from off to Windows XP desktop in 9 seconds. Minimal POST, no pagefile, auto-login, 4-HDDs striped, yadda yadda. If I put FF in the startup folder, your 10 second requirement would be met. Of course, it's a bad disk just waiting to happen, but it loads games faster than my wii or xbox.

    3. Re:Surf internet in 1 second? by Tubal-Cain · · Score: 1

      Here. Though the latency and bandwidth suck.

    4. Re:Surf internet in 1 second? by HeronBlademaster · · Score: 1

      That might be kinda hard, considering that in my experience it takes no less than five seconds, and sometimes as long as twenty seconds, for the wireless card to complete a connection with the router, especially if there's encryption involved.

      You're also assuming that latency is trivial. That's probably an invalid assumption in the most common use case for the sort of machine where this would be useful (i.e. netbooks getting online via 3G or similar).

    5. Re:Surf internet in 1 second? by HeronBlademaster · · Score: 1

      Somewhat off-topic, but related to your post... my gaming machine takes forever to boot. Part of the problem is that when it's powered off, and I push the power button, it spends ten seconds just spinning the fans before the BIOS POST screen shows up. I have minimal POST enabled, but I suspect the issue is my video card's initialization (which, presumably, must finish before the BIOS can initialize and display its POST screen). My machine has a Core i7 920, an MSI X58 Platinum motherboard, 12GB RAM, and a GeForce GTX 285. Any ideas?

    6. Re:Surf internet in 1 second? by HeronBlademaster · · Score: 1

      What power supply do you have? I've got a 750W Thermaltake. I'm wondering if maybe the power supply itself is taking a long time to stabilize, causing the long boot delay.

      (See this post which reminded me of this possibility.)

  11. Direct link to MontaVista Video on YouTube by Qubit · · Score: 5, Informative

    The video was hard to find on the given links. One of them even had the audacity to ask me to log in to view it. Yeah, as if.

    One Second Linux Boot Demonstration (new version)

    Also, kudos on the music choice. The wah-wah pedal in the opening music really gives the tech demo that "porn soundtrack" feel I know you were going for.

    --

    coding is life /* the rest is */
  12. Re:Not needed by Flea+of+Pain · · Score: 1

    A computer which is frequently powered on and off wears through components much more quickly (thermal stress). A computer that is running 24/7 does not. Better yet, a computer that is off 24/7 has no issues at all.

    --
    Do not argue with an idiot. He will drag you down to his level and beat you with experience.
  13. Re:Awesome! by ezzzD55J · · Score: 1

    well, there is an open source bios project, so that doesn't have to be the problem.

  14. Re:Awesome! by BrokenHalo · · Score: 3, Insightful

    Yeah, but you know you're really cool when you have no idea how long it takes to boot your machine. After all, you only do it once. ;-)

  15. Re:Windows 7 And OS X both do this already. by ezzzD55J · · Score: 1

    Poor attempt at trolling. Get your facts straight at least.

  16. Re:Not needed by Chabo · · Score: 1

    I can't wait until I get a powerful desktop machine that has an idle power draw low enough that I'd get no noticeable benefit to my electric bill by turning the machine off.

    --
    Convert FLACs to a portable format with FlacSquisher
  17. Re:Not needed by sjames · · Score: 1

    It wasn't done for desktop machines and servers. It was meant for embedded devices. Think pocket mp3 players and industrial control devices.

  18. Re:Not needed by Psyborgue · · Score: 1

    It would still take considerable amounts of time to write all the ram to disk and read it back again.

  19. Re:Awesome! by Sun.Jedi · · Score: 1

    Probably they should. I have never seen one single credible justification for over 1 second boot time for any desktop operating system.

    I don't think the eventual target is desktops.

    From TFA:

    For industrial automation and other similar applications, fast boot and response time is critical to successful operation. Applications must be fully operational at power on and cannot be delayed due to the volatile nature of the platform and environment. Variables such as power fluctuation, network failure, device availability, and memory management must be responded to with no loss of performance and functionality. These same demanding requirements are found not just in Industrial Automation applications, but automotive, aerospace, and military applications as well.

    I can see other reasons for linux based kernel devices like web/net appliances, game consoles, cell phones, etc... to have really low boot times.

  20. Re:Windows 7 And OS X both do this already. by jedidiah · · Score: 1

    If XP is supposed to be how power management is done, I will pass.

    It's faster to just reboot the box into Linux.

    --
    A Pirate and a Puritan look the same on a balance sheet.
  21. Re:Not needed by pz · · Score: 1

    Linux has insane uptime. I can usually keep my box on indefinitely. I'll only turn it off when I accidentally pull out the cord when I'm reaching behind my desk or when I blow a fuse by running the microwave, toaster, and dishwasher at the same time.

    Why have such a quick boot time when you hardly need to boot in the first place?

    Because, in my experience, laptops are far less well-supported and far less reliable. My desktop machine currently has 100+ days of uptime, and the last power cycle was because of a scheduled power outage in the building. That uptime is typical for my desktops. In contrast, my laptop rarely goes more than a couple of days without needing a reboot because some driver or another gets into a fubar state. I use my desktop 8-10 hours per day, and my laptop 1-2 hours per day, so factor that in as well.

    Couple that experience (which has been repeated over a number of desktops and a number of laptops, so I don't think is exceptional) with the fact that laptops are, I believe, outselling desktops and you have a need for quick boot times.

    Also, Linux coming out of hibernation is dog slow. Doooooooooooggggggggg slow. It's far faster to boot up from scratch, for my laptop at least, and have to re-initialize my workspace than it is to wait for the RAM image to load from disk.

    --

    Put my fist through my alarm clock with its ding-dong death inside my ear. - The Blackjacks.
  22. I had 4 second boot with uClinux in 2001. by cellurl · · Score: 1

    At the time, I bragged 4 seconds (real application running) was the industry fastest with out gizmo, Blabbermouth

    What I want to see is 0seconds using Flash. eg. run out of flash and just stop the clock! Then resume it. That has to work, right?

  23. Re:Linux makes airplanes faster by Psyborgue · · Score: 1

    I fly a *lot* and I haven't had to do that in a very long time (it's in suspend all the time just in case).

  24. Re:Windows 7 And OS X both do this already. by gigabites2 · · Score: 1

    I don't know about everyone else, but my Kubuntu installation suspends/sleeps perfectly. The Windows 7 RC installation on the other hand... Yeah, yeah; something about anecdotes meaning nothing in the grand scheme of things.

  25. Re:Awesome! by HeronBlademaster · · Score: 1

    The BIOS isn't always the problem... if it takes three seconds for the video card to become usable (fans running, memory initialized, etc), you're not going to get less than a three-second perceived boot time, no matter how fast you make everything else happen. The same goes for other hardware. If they happen in series (or worse, if they have to happen in series), then that can add up - that can be mitigated by the BIOS, of course, but I can see why boot times might get longer.

    I've also heard that it can take a few seconds for modern CPUs just to stabilize to a usable state when they're powered on. This may or may not be true; I'm not a hardware engineer. However, if it is true, then between this and other hardware initialization time we may not ever see sub-ten-second boot times.

    I'd settle for a sub-60-second boot time... and I'm running the latest and greatest (i7 920, 12GB RAM, GTX 285...), so discounting hardware initialization time, the hardware is certainly *capable* of quick boot times. As it is, my computer takes nearly two minutes to get to a logon screen (whether that's Gentoo or Windows 7).

  26. Re:Moot by Chabo · · Score: 1

    During the summer I shut down my desktop daily. Besides the electricity used directly, it also means my AC has to work harder to keep a certain temperature.

    I'd love to have a reasonably powerful desktop machine that idles at 20W or less, but for now it idles at 100W, and that's quite a bit of heat to be needlessly generated in a small apartment in the summer.

    --
    Convert FLACs to a portable format with FlacSquisher
  27. Re:32Bit Amigas. by localman57 · · Score: 1

    That's nothing. My Atari 2600 booted into COMBAT before my finger left the POWER lever. And a few seconds later my 3 little green planes were beating the shit out of poor sap flying the big pink plane.

  28. Re:Not needed by HeronBlademaster · · Score: 1

    If you dual boot between Linux and Windows, like I do, quick boot times are important. I often find myself just staying in Windows to do things I would be better off doing in Linux because I don't want to wait for the computer to reboot. Waiting for Windows to shut down and then waiting for Linux to boot up takes a while (in terms of attention span). I already have a hard enough time motivating myself to be productive at home ;)

    On an unrelated note... why are your microwave, toaster, dishwasher, and computer all on the same circuit? Do you plug your computer in in your kitchen? :P

  29. Re:Not needed by HeronBlademaster · · Score: 1

    The simple solution, of course, is to add in, say, 4GB of flash storage to laptop motherboards for exclusive use in hibernation. It could also double as swap space during normal usage.

    Even as it is, my laptop comes out of hibernation in five seconds or so (in Windows); it doesn't take very long for your average hard drive to spam your data back into RAM (assuming I had a lot running when I went into hibernation).

  30. Re:Not needed by HeronBlademaster · · Score: 1

    Whoops, that last parenthetical comment was from my first draft ^_^

  31. Re:Awesome! by Em+Emalb · · Score: 1

    Meh. My macbook pro is so damned cool I don't boot it. I just think "I'd like to check slashdot" and in the blink of an eye, slashdot it open, I'm logged in, and sitting at preview for a +5 funny comment.

    It's truly amazing.

    --
    Sent from your iPad.
  32. i wanna see! by FudRucker · · Score: 1

    i want to see what the kernel .config and rc.xxx files that load at boot time look like

    --
    Politics is Treachery, Religion is Brainwashing
  33. Re:Awesome! by Em+Emalb · · Score: 1

    sadly, my macbook pro doesn't check grammar or proper sentence structure. ;-/

    woah, slow down there cowboy, it's been 69 (Dude!) seconds since you last posted. You're likely to be eaten by a grue.

    --
    Sent from your iPad.
  34. Re:Not needed by Psyborgue · · Score: 1

    It sort of already exists, but it's not used as you suggest (yet). It would be nice if it were one drive with two virtual drives, separately accessible. MSI has a netbook with both SSD and HDD (seperate). Provided you could select where windows stores it's hibernate data (don't know, don't use windows), you could probably accomplish what you suggest fairly easily.

  35. Re:Not needed by TooMuchToDo · · Score: 1

    You can indeed select the location/drive for the hibernation data (which is just a file on the filesystem).

  36. Re:Moot by Abalamahalamatandra · · Score: 1

    Depends on your definition of "reasonably powered", but this has a dual-core 1.6 gHz Atom processor and nVidia graphics, certainly pulls less than 30w in idle, and has no fans so coupled with SSD storage would be completely silent. Also has a kit to hang it on the back of an LCD so it would be pretty invisible as well.

  37. Re:Not needed by TooMuchToDo · · Score: 1

    Google for Pico ITX. I believe full-tilt consumption is something like 30 watts, which is about double the power consumption of a compact fluorescent bulb. Assuming you leave it running all the time, and your electricity is 7 cents/kwH, your power bill every month for it would be $1.50 (assuming 30watt draw). $1.50 is not really noticeable on an electric bill when you take into account delivery charges and taxes.

  38. Re:Not needed by TooMuchToDo · · Score: 1

    My bad, you said *powerful* desktop. What I mentioned would take care of most day to day tasks, but probably not re-encoding video or playing high end games.

  39. Re:Not needed by Psyborgue · · Score: 1

    I guess the only thing to worry about then is the limited amount of writes on an SSD disk, it's one critical weakness.

  40. Re:Moot by TooMuchToDo · · Score: 1

    http://www.via.com.tw/en/products/embedded/ProductSeries.jsp?serialNo=6

  41. Re:Moot by karnal · · Score: 1

    Depends on what kind of $$ you have, but you could do what I do in my house:

    The wife and I share a laptop. 90% of our activity revolves around using the laptop to browse and chat with friends. The other 10% I can walk over and use my desktop - or, if I'm particularly lazy but need the raw HP for something, I can turn it on using WOL and VNC/RDP to it. My desktop PC generally remains off then, and the laptop (when full on battery) only uses 15-20 watts. And it's not a particularly new laptop, either.

    --
    Karnal
  42. Re:Not needed by TooMuchToDo · · Score: 1

    With how quickly the price of SSDs are coming down, I wouldn't worry about it. You'd just replace the drive. And if cost is a concern, someone wouldn't be considering the idea in the first place.

  43. Re:Awesome! by MeatBag+PussRocket · · Score: 1

    Probably they should. I have never seen one single credible justification for over 1 second boot time for any desktop operating system.

    I don't think the eventual target is desktops.

    From TFA:

    For industrial automation and other similar applications, fast boot and response time is critical to successful operation. Applications must be fully operational at power on and cannot be delayed due to the volatile nature of the platform and environment. Variables such as power fluctuation, network failure, device availability, and memory management must be responded to with no loss of performance and functionality. These same demanding requirements are found not just in Industrial Automation applications, but automotive, aerospace, and military applications as well.

    I can see other reasons for linux based kernel devices like web/net appliances, game consoles, cell phones, etc... to have really low boot times.

    add to that list automobiles, GPS systems, and the like. IIRC the Bugatti Veron has win CE

    --
    i wage a holy war against the apostrophe.
  44. Re:Not needed by je+ne+sais+quoi · · Score: 1

    Even desktop users who use linux often have to dual boot into windows. Sometimes virtual machines or wine is good enough for what you want, but for something like games or software that couples closely to hardware (e.g. AnyDVD or most games), this doesn't work. Having a faster boot on linux makes switching between OSes nicer. On my machine my Debian it's already faster than Vista (I forgot by how much, I'll have to remeasure it), and that's including running some slow services at startup for linux like uploading firmware for an HD card and starting the smartd.

    --
    Gentlemen! You can't fight in here, this is the war room!
  45. Re:Awesome! by Jeremy+Erwin · · Score: 1

    1 second boot will never be possible on this shitty hardware until you rewrite the bios.

    So rewrite the bios. Fastboot BIOS:An Investigation of BIOS Speed Enhancement Featuring the Intel Atom Processor

    On the other hand, perhaps the authors cheated.

    During the boot process, the BIOS provides an opportunity for the user to hit a hot key that
    terminates the boot process and instead displays a menu used to modify various platform settings.
    This includes settings such as boot order, disabling various processor or chipset features, modifying
    media parameters, etc. On an embedded device, BIOS setup (and any similar settings provided by
    an operating system loader) is more of a liability since it gives the end-user access to BIOS
    features that are potentially untested on the device. It is better to have a set of setup options that
    may be chosen at BIOS build time. Removal of BIOS setup also saves significant BIOS post time.

  46. Completely overrated and someone else did it first by synthesizerpatel · · Score: 3, Insightful

    I'm working as an embedded driver software engineer and setup our company's OpenEmbedded build system to provide an end-to-end build environment for our embedded offering and while I can't find the link at the moment -- the one second boot time has been done before and was posted on TI's OMAP developer site a while ago. If I remember correctly it's mostly about U-Boot and how it copies the kernel into memory (byte by byte as opposed to streaming it) which is where you get the majority of your time decrease.

    Either way, MontaVista is not the first on this one and it's a shame they're pretending they are.

    The one second boot time is also never going to benefit regular PCs as they achieve it due to the nature of embedded systems -- you build a distro for your specific hardware which means no probing, none of that BIOS junk. No looking for the 'first' boot device.. U-Boot can be configured to automatically jump to the booting phase so you're already faster there. Beyond that, load and decompress your kernel (it'd be faster if your kernel wasn't compressed too wouldn't it?)..

    So, chalk this up to having a kernel built specifically for your hardware and a boot-loader that is set to only boot one way, ever.

  47. Re:Awesome! by B00KER · · Score: 1

    Macbook PRO could be Magic, but an instantaneous +5 funny comment on /. Come on. You must be new here.

  48. Re:Not needed by ShadowRangerRIT · · Score: 1

    That limitation is effectively irrelevant. And that article is from 2006. And it accounts for the case of constant, high speed writing; hibernating out to disk happens a few times a day, and as such is barely noticeable.

    Think about it. Lets say you've got a crappy flash drive: Only 1 million writes per sector. And it's exactly the size of your main RAM, so no wear leveling algorithm will help. If woke up and hibernate that machine 100 times per day, it would still last 10,000 days, or 27.4 years. That's slightly longer than I've been alive; I think I could live with a hard drive that "only" lasted that long.

    --
    $_ = "wftedskaebjgdpjgidbsmnjgcdwatb"; tr/a-z/oh, turtleneck Phrase Jar!/; print
  49. Re:Completely overrated and someone else did it fi by synthesizerpatel · · Score: 5, Informative

    Found it.

    Originally posted by 'Mohanky' June 2008:

    http://wiki.davincidsp.com/index.php/All_This_For_1_Second_Boot

  50. Re:Not needed by afidel · · Score: 1

    HDD's break MUCH more often if power cycled frequently, as do power supplies and fans.

    --
    There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  51. Re:Not needed by afidel · · Score: 1

    Dual boot? Didn't that go away when free virtualization became available?

    --
    There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  52. Re:Not needed by HeronBlademaster · · Score: 1

    Some of us like playing Windows games (and not via Wine).

  53. Re:Linux makes airplanes faster by kent_eh · · Score: 1

    I fly a *lot* and I haven't had to do that in a very long time (it's in suspend all the time just in case).

    I flew with 4 co-workers last week, and 3 of us had to boot our laptops. All had our laptops and/or laptop cases swabbed.
    One of us had to take off his shoes and socks, and submit to having the waistband of his pants searched by hand.

    I love the theater...

    --

    ---
    "I can't complain, but sometimes still do..." Joe Walsh
  54. Re:Moot by ground.zero.612 · · Score: 1

    Maybe as a developer I have a warped sense of the word "workstation," as I do not consider a "desktop" PC to be in the same class.

    I agree that desktops in general do not need to remain fully powered up 24x7x365. There's gotta be some other guys/gals out there reading this that have a similar scenario to mine: workstation at the office is on 24x7x365 with the monitor off when I'm not there, desktop at home to connect to the office VPN, laptop on the go to connect to the office VPN.

    I haven't bothered to check my workstation's actual uptime yet. However I can tell you that I didn't configure it, it was powered on the day I started employment and hasn't been turned off (that I am aware of) since.

    --
    "Be prepared, son. That's my motto. Be prepared." --Joe Hallenbeck
  55. Re:Not needed by Rakishi · · Score: 1

    Virtulization sucks at games. The main reason someone using linux would boot into windows is games. I'm sure you see the dilemma.

  56. Re:Awesome! by Bakkster · · Score: 2, Informative

    The BIOS isn't always the problem... if it takes three seconds for the video card to become usable (fans running, memory initialized, etc), you're not going to get less than a three-second perceived boot time, no matter how fast you make everything else happen. The same goes for other hardware. If they happen in series (or worse, if they have to happen in series), then that can add up - that can be mitigated by the BIOS, of course, but I can see why boot times might get longer.

    This is absolutely part of the problem. The power supply needs to turn on its fans and generate stable voltage, then the case fans and mobo power conditioning needs to stabilize. Then you get to touch the BIOS, which probably does a staggered startup of most devices to prevent power supply droop. As stated, all of this hardware then needs to reach a usable state, both mechanically and electrically.

    In a car, the power supply is DC to start with, the hardware is smaller and simpler (requiring fewer moving parts to wait for), the BIOS has mostly sensors to startup (If not done within the OS), and the OS needs only to load the basics and a few drivers from ROM. One second startups are common for small embedded systems, including to embedded versions of Linux. Just don't expect it on a desktop.

    --
    Write your representatives! Repeal the 2nd Law of Thermodynamics!
  57. Re:Not needed by afidel · · Score: 1

    Boot to windows and run linux in the VM then. It's certainly not going to give you less uptime than constantly rebooting to the other OS.

    --
    There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  58. Re:Moot by afidel · · Score: 1

    I have a Athlon 64 4200+ low power machine with a no fan motherboard and a underclocked (when not running games) Geforec 9600 GSO. It idles at about 50w with 2x7200 HDD's and maxes at ~150W. It plays most games at 1080p30 or close enough that I don't care.

    --
    There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  59. Re:Awesome! by thatkid_2002 · · Score: 1

    While your point about the video card is interesting and seems correct, I cannot help wondering why you do not get a sub 30 second boot time on both Windows 7 AND especially Gentoo.

    I have hardware only half as powerful and under half of the amount of RAM you have, and I easily achieve these with just about any distro (I regularly run a pretty heavy Fedora install). My old 1.4GHz 512MB RAM laptop boots Debian to X in under 40 seconds.

  60. Re:Awesome! by HeronBlademaster · · Score: 1

    I think Bakkster's comment (sibling to yours) has the idea. To wit: my power supply has to stabilize first, and given that it's a 750W, I wouldn't be surprised to find it take several seconds by itself.

    I'll reboot when I get home and time it from off to the BIOS screen being displayed, from there to grub, and from grub to the login screen in each OS. I may be overestimating the OS boot time; I just know that the time between pressing the power button and the screen showing the BIOS startup info is like one of those long, awkward silences during dates. I shouldn't have to deal with that anymore, I'm married!

  61. Re:Not needed by TinBromide · · Score: 1

    provided that the SSD is used only for hibernation data, the cost of the drive is more than the cost of the data, meaning that you can replace the drive for cost of drive + nada. If, however, you wish to rely on the drive for anything more than hibernation, you run into a case where the data is more valuable than the drive and additional measures should be taken to protect that data. Knowing most people though, they'll just curse and turn purple when their report is gone and the drive is dead.

    --
    Is it sad that I am more likely to recognize you and your posts by your sig than your name or UID?
  62. Re:Not needed by CAIMLAS · · Score: 1

    Not needed? What about on mobile platforms?

    Put a true embedded system in a car, for instance. While it's off, it uses zero power, but by the time you're backing up your driveway, it's already doing it's thing.

    --
    ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
  63. Re:Nice text color ... If Tux gets that down and by davidsyes · · Score: 1

    Dirty, on ice (or, in bed) with his girl (or, with his male) would he be a quickshot from cold to boot-topping? (Yeh, i realize this is a ... heady topic...)

    --
    Previously: "Linux... Toward the Sunrise..." Now: "Linux... Toward the-- No, now, part of Every Sunrise"
  64. Re:It's 1980 all over again Maybe that "Lexus" was by davidsyes · · Score: 1

    Too expensive to drive (out of the corner)? (Perception is EVERYthing, hehehehe...)...

    --
    Previously: "Linux... Toward the Sunrise..." Now: "Linux... Toward the-- No, now, part of Every Sunrise"
  65. Re:Not needed As for me... by davidsyes · · Score: 1

    I only RECENTLY (as in, say after Dec 2008) began to enjoy fully functional suspend to RAM on my laptop, partly IIRC, with PCLOS, and then Mandriva 2009.0 and currently with 2009.1. However, if i yank the USB broadband device out, I get streams of IOCTL and other errors, KPPP, and pppd won't die, even when as root i try to kill them, and reinserting the device doesn't satisfy it. On suspend attempts, i get to the BLACK display, then the backlight resumes, then i get "Resuming tasks". I end up having to reboot.

    Point? If some devices hose up the system, rebooting will be necessary, so instant on is (for some here, but not necessarily me, hehehe) better than sex. Sex is ZERO, but rebooting in near-zero is nervvv..hahahaahh...nah....

    It would be nice if the mobo's contained chips that would allow the owners to load their OS of choice into, and then powering on is just a split second of waiting. It would be nice if Runlevel 1 actually purged 100% of any hosed up /dev connections and a full reboot weren't necessary. But, it's nice to have my laptop behave for 28 or 29 days without rebooting. I don't need 6 months or a year -- I'm not THAT demanding.

    --
    Previously: "Linux... Toward the Sunrise..." Now: "Linux... Toward the-- No, now, part of Every Sunrise"
  66. Re:Awesome! by dotgain · · Score: 1

    There's been an open source BIOS project for years. I'm not holding out much hope of getting anything useful out of it, I just switched to a platform that already had it right. x86 Mac with EFI, of course.

  67. Murky definition of "general-purpose" by tepples · · Score: 1

    CoreBoot (formerly known as LinuxBIOS) will boot a full Linux kernel on a general-purpose machine in 3 seconds.

    Except one can't easily install coreboot on a random PC because as I understand it, most motherboard makers have declined to cooperate. Therefore, any machine to run coreboot would need to be purpose built. So if a machine is advertised as compatible with coreboot, is it really "general-purpose"?

    1. Re:Murky definition of "general-purpose" by jd · · Score: 1

      Coreboot actually works on a very wide range of motherboards, in much the same way that Linux had drivers for hardware where the vendors weren't cooperating (reverse-engineering). I maintain (when I have time) the Freshmeat record for Coreboot and just about every entry I've done for it has had vast numbers of new drivers.

      --
      It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
  68. How fast can you type 5w0rdf1s#? by tepples · · Score: 1

    Give me a call when they can go from off to Google in less than 1 second. (OS boot, wireless initialization, browser start, google reply).

    That would depend on two things: 1. how fast you can type in the passphrase to unlock the keyring that holds your WEP/WPA/WPA2 keys, and 2. how fast your router (whose operating system you usually do not control) responds.

  69. Re:Not needed by mldi · · Score: 1

    To be fair, a typical machine idling uses about the same energy as 1 incandescent light bulb (60w - 75w). A typical machine under load is even comparable to the 100w bulbs. I'd imagine laptops to be less than that. So, I guess if you're playing Quake, turn the light off in the room and make up the difference.

    --
    If you aren't suspicious of your government's actions, you aren't doing your job as a responsible citizen.
  70. Re:Completely overrated and someone else did it fi by drinkypoo · · Score: 1

    All you have to do to gain the same benefits on your PC (besides throw away the BIOS and replace it with Coreboot) is compile the kernel for your system. There's no reason this can't be done on every system. Gentoo has proved that. Everyone compiles kernel modules on-demand these days... might as well recompile the kernel.

    Now, if only kexec would work on more platforms... or for that matter, work reliably on x86.

    --
    "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  71. Re:Not needed by drinkypoo · · Score: 1

    Dual boot? Didn't that go away when free virtualization became available?

    3d graphics in virtual hosts still bite ass.

    --
    "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  72. Re:Not needed by maxwell+demon · · Score: 1

    I also tend to switch off incandescent light bulbs when I don't need them.

    --
    The Tao of math: The numbers you can count are not the real numbers.
  73. Re:Awesome! by HeronBlademaster · · Score: 1

    pre-POST: 20s
    POST to grub: 10s
    grub to Win7 logon screen: 20s

    Odd that the numbers turned out so round, but there you have it. I guess my two minute figure was a bit exaggerated, but my pre-POST period was too low.

    Seriously, twenty seconds doing nothing before the POST? Something has to be messed up.

  74. Re:Canon Cameras by ettlz · · Score: 1

    Until recently, VxWorks. Newer models (DIG!C 3 onwards?) use something Canon developed in-house.

  75. DIY by Crossmire · · Score: 1

    I've recently become interested in this area myself, so I was surprised to see an article on fast booting. I was hoping the comments would by chance happen to answer some of the questions I have regarding the topic, but they have not, so my next best bet is to ask. I know plenty of you will say that fast booting is not important. I'll admit do care a little bit about boot times, but I'm mainly interested from an academic point of view and am using this to try to learn a little more about how Linux works.

    I'd like to put together a very fast booting Linux system, composed of just the bare minimum needed to be able to run something like BusyBox. I've googled this topic and have found things like Linux From Scratch, but as far as I can tell these seem to have their own software on which you base whatever you're building. I was under the impression that all you need to boot is a file system, the Linux kernel, an initrd and then userland software for whatever you want to run. I've read that initrd isn't even needed if you compile SATA drivers into the kernel and maybe some other things. In fact I would say that another aim is to boot without using initrd at all, I only intend to use this on my computer for a bit of fun.

    Are there any websites that contain a minimal list of things required to get Linux to boot? I could be horribly wrong on a lot of this, in which case I look forward to being corrected.

    1. Re:DIY by Tangent128 · · Score: 1

      I haven't had much luck finding such sites, but from my limited experience you're right.

      In fact, if you have sufficiently small software to run, you could just put that in the initrd and skip the main filesystem completely...

  76. Re:Completely overrated and someone else did it fi by Ren+Hoak · · Score: 1

    According to the manufacturer, http://www.embeddedarm.com/products/board-detail.php?product=TS-7800 boots to Linux in 0.69 second. It's a 500MHz ARM-9 based system. I haven't used this board, but I've used others from the same manufacturer; the Linux they provide is Debian-based on the boards I've used.

  77. Re:Awesome! by ezzzD55J · · Score: 1

    oh, i thought linuxbios (nowadays coreboot?) actually worked?

  78. Re:32Bit Amigas. by ciderVisor · · Score: 1

    flying the big pink plane

    Is this another example of teh "ghey slang" I've been hearing so much about ?

    --
    Squirrel!
  79. Re:Awesome! by Bakkster · · Score: 1

    Seriously, twenty seconds doing nothing before the POST? Something has to be messed up.

    Doing nothing? No. You're starting up the hardware, which shouldn't take 20s on most systems. Perhaps your hardware configuration is bad? Weak power supply, clogged fans, etc?

    --
    Write your representatives! Repeal the 2nd Law of Thermodynamics!
  80. What I want for Christmas... by RogueWarrior65 · · Score: 1

    This is great but I also want a completely power-loss tolerant file system that doesn't need any fscking on restart. If I'm building a true Linux-based appliance, not a general purpose computer, laptop or netbook, basic criteria would be fast boot and the ability to turn it off by disconnecting the power without telling it to shut down gracefully. Basic toggle switch control and no fancy hardware to keep power available while it's shutting down. This would be battery powered and an end-user should be able to pull the batteries and put in new ones without ill effects.

  81. Re:Awesome! by HeronBlademaster · · Score: 1

    All the hardware was purchased brand new just one month ago, and appears to work perfectly once it's started up. I don't know how to verify whether something is wrong with the hardware during startup but not any other time.

  82. Read TFA, but... by Bootarn · · Score: 1

    ...the marketspeak made my ears bleed. The word "kernel" was mentioned *once* in the article linked to by the second link.

  83. Re:Awesome! by dotgain · · Score: 1

    Oh, it works (by FOSS definition). Now got and look at the supported motherboards/chipsets page.