New Phoenix BIOS Starts Windows 7 Boot In 1 Second

suraj.sun excerpts from a tantalizing Engadget post: "Phoenix is showing off a few interesting things at IDF, but the real standout is their new Instant Boot BIOS [video here], a highly optimized UEFI implementation that can start loading an OS in just under a second. Combined with Windows 7's optimized startup procedure, that means you're looking at incredibly short boot times — we saw a retrofitted Dell Adamo hit the Windows desktop in 20 seconds, while a Lenovo T400s with a fast SSD got there in under 10."

Comments

BIOS

[sopssa]

That is indeed really fast boot to desktop. I like it how it shows the Windows loading screen almost immediatly too.

This also brings a new friend for F5 hitting. To get to the bios menu you'll be smashing F12 as fast as you can during boot.

But the article is a little low on details of optimizations. As I've understood, BIOS isn't really that complicated nor does it do any heavy calculations. It basically just brings hardware up and tests it, which takes most of the time (not that the 5-6 seconds is so long wait anyway). So have they optimized something else, or are they just skipping those tests?

Re:BIOS

[fuzzyfuzzyfungus]

Could be a while. Given how infrequently most servers are rebooted, and how having at least a backup, better a hot spare, or better still on-line redundancy for servers you actually care about is fairly standard, there probably isn't nearly as much demand.

Also, I suspect, more of the server delays have to do with real needs(notably staggered spin-up of drive arrays) or coordination issues between vendors(your server manufacturer can't do much about how much time a 3rd party RAID controller's option ROM decides to waste once it takes over, and even integrated controllers are usually just 3rd party stuff with some degree of rebadge).

You'll probably actually see fast boot sooner in the cheap seats, which are much more likely to just be a basic business box relabeled as a "pedestal server" or reboxed as a cheap 1/2U and will thus be able to borrow the fast boot stuff directly from the consumer lines. That is also where servers are much less likely to be backed by any serious redundancy, which would make coming up quickly more of a selling point.

Re:BIOS

[dolphinling]

It's not really all that fast. With coreboot there's an option to flash a kernel directly to your bios chip, and skip bios and bootloader entirely. Makes kernel upgrades a pain, of course, but they got wall time from poweron to a working linux shell down to three seconds.

Re:BIOS

[__aamnbm3774]

Computers are lightning fast compare to a few years ago, there should be no need to 'poll hardware, wait 3 seconds, test next piece of hardware'.

If properly parallelized and you remove all the pointless Waits, a BIOS check should be damn-near close to immediate and still manage to check everything.

BIOS writers probably figured, eh, so what if it takes 10 seconds or so, thats still pretty quick, and never rewrote their crappy legacy code.

Re:BIOS

[clone53421]

Nah. I'd tend to agree with GP. If you're a critical service, you want on-line redundancy, so you roll over immediately and it doesn't matter how long the second server takes to reboot. If you're not critical and you don't have redundant servers, 5 minutes of down-time probably isn't much worse than 1... you just have to schedule it at an off-peak time.

Re:BIOS

[pjr.cc]

Actually, how often it boots and fast it boots are often small considerations - depending on where you sit.

Consider a file server that crashes and reboots twice a year and takes 5 minutes to come back up... thats 99.998% availability and from an infrastructure perspective thats pretty dang awesome.
From a helpdesk point of view, they'll suffer one heck of a beeting everytime it goes down and that'll be all they remember of the server.
Same goes for the users, all they'll remember is the 5 minutes it went down when half the company was doing something important.

Consider active directory though (or any kind of multi-master replicated service) - again, your talking about a server thats really not doing anything terribly difficult, but unlike the file server if it goes down no ones likely to notice. On top of that your often more concerned that the server will come up working then how quickly.

As for noise, well the good ol e450 from sun fully stacked with 20 15k disks (not to mention its in-built fans) used to make very amusing noises as it came up and some of the time it went down was because the disks managed to disconnect from the backplane (and you could hear the difference if you were around it during a boot often enough) - a good hard whack and it was sorted. Wondefull little machines those

Re:BIOS

[operagost]

When making claims for availability as a service provider, scheduled maintenance is NOT counted in "the nines". You are making a guarantee of reliability, not uptime per se.

yeah, but...

[jollyreaper]

After you see the desktop it's another minute for all the system tray crap to load. And if you're stuck with corporate antivirus? May as well throw some cinderblocks in the trunk of that nice sportscar and watch it do 0 to 60 like an arthritic Ford Pinto.

I don't understand the obsession...

[IANAAC]

I don't understand the obsession with short boot times.

Most of us keep our machines running all the time. I would think a quicker return from suspend or hibernate would be more useful.

Re:I don't understand the obsession...

[petes_PoV]

And if a PC booted in sub 1-second, more people would switch off and stop wasting power - and then marvel at the savings they make.

The two reasons for ever-on PCs is either when the user doesn't like to wait the (in my case) minutes for the boot sequence to run through: whether that's Linux or Microsoft, it's far too long.
The second reason is when they're running stuff in that background: a server or data collection, or just a long download,. Obviously in this case, faster booting won't help but ignoring these power-users (which is probably a big proportion of the /. base, so there's no need to identify yourselves - I get it), if it gets a few million more PCs turned off then it's a good thing.

Hilarious video

[blind biker]

"Don't take my word for it, take Microsoft's word" !!!

I think I'm going to trust a random schmuck any day rather than Microsoft.

Beeting

[camperdave]

From a helpdesk point of view, they'll suffer one heck of a beeting everytime it goes down...

Arg! Support says the server's down again. Let's throw beets at them!