Linux Kernel Boot Statistics: 2.6.24 To 2.6.39

[jcgeny]

most posters are not carrying about boot time , but if you boot quickly then softwares are running fasters .
i not easy yet with linux booting and mem used . with dos it was very interresting to have a lot of free mem in the 640 ko and use as much as possible upper mem for drivers .

with nt and linux looks the same , no optimization is possible
have a look at this old tool : umbpci

http://www.uwe-sieber.de/umbpci_e.html

http://www.mdgx.com/umb.htm

[jcgeny]

edit time is too short : 1 minute so i add this

with nt and linux , it looks the same , no optimization is possible by editing files to maximize the memory usage according to the pc and cards, it has

[devius]

Realistically anything that is not overly long (minute+ boot) most people are satisfied with.

I was satisfied with the 4MB of ram my first PC came with, until I upgraded it to 16MB. I was satisfied with the SNES until I... nah, I'm still satisfied with the SNES

[deanjo]

I was satisfied with the 4MB of ram my first PC came with, until I upgraded it to 16MB. I was satisfied with the SNES until I... nah, I'm still satisfied with the SNES

At one time "instant on" picture was the rage too on TV's but you don't hear griping how slow the flat panels take before you get a full picture now days.

[deanjo]

If you could reliably cold boot (with or without hibernation) in 3 seconds would you ever choose to sleep instead? Sleep is nothing but a workaround for slow boot times.

Yes I would, here is why. The people that are going to be putting their system in a up/down state the most are laptop users. Now if I have to boot everytime I want to close that lid it also means reopening the applications I had open, remembering what file I had open, getting everything just aligned right again, etc. With a proper working sleep I can resume right where I left off. That is something a reboot doesn't do. In this day and age having to do a full boot should become a rarity not common practice.

[not.sure]

Yes I would, here is why. The people that are going to be putting their system in a up/down state the most are laptop users. Now if I have to boot everytime I want to close that lid it also means reopening the applications I had open, remembering what file I had open, getting everything just aligned right again, etc. With a proper working sleep I can resume right where I left off. That is something a reboot doesn't do. In this day and age having to do a full boot should become a rarity not common practice.

That's why he included hibernation. If that worked within a few seconds you indeed wouldn't need sleep.

Other than that you're right; opening applications and everything after a real boot is mega time consuming and annoying and a real productivity killer. To me it's a mystery why people would really want to reboot and are so obsessed with boot times.

[Ranguvar]

Michael, a suggestion for something Phoronix could create --
a diff tool for bootcharts.

No, I'm not going to stare at eight bootcharts until my eyes bleed trying to find the biggest changes. But that info laid out in +/- ms times for each section, omitting very small differences, would be handy.

Serious suggestion

[jcgeny]

....
now calculate this for an company with 10 000 computers. ....

means shutdown and start speed is business critical.

not for your business? maybe you give a fuck about 200? per year per pc.. but other people care.

200? is the price of windows ;']
10 000 computers running linux ? are you sure there are so many around the world ?

i joke but the more i read the forum , the more i find it too "geeky" .
if you know hl2 game [ that only runs with windows ] linux looks like the Black Mesa Mod http://www.moddb.com/mods/black-mesa

[cyan]

200? is the price of windows ;']
10 000 computers running linux ? are you sure there are so many around the world ?

Well we have around 12000 which we power down overnight and wake up with WOL packets precisely to save power, and it's not a trivial amount.

I did consider renting out the compute power instead during off-peak times, which would probably result in more money, but it's not really core business for a bank

I believe boot times are really important, but not for any silly reasons of productivity (the difference is tiny), but for reasons of user attitudes, especially new users. When the computer is booting, users are typically sitting watching it, not able to do anything. It's the watched-pot effect. Particularly for new users, who are fully focussed on the system and are consciously forming their impressions of the software, it's a big thing. We've found that it is critically important to manage user's impressions of the system when doing a large change like a desktop operating system replacement - a single hostile user in a branch (easy to have - users hate change) can cause the entire branch to actively look for reasons to fault the system. Winning them back from that state is hard

[dnebdal]

One thing that is slightly odd:
If you look at the boot time (seconds) and the bandwidth (MB/sec), you should be able to multiply them and get the amount of data read during the boot process.

Plot that, and you get this:

It's fairly obvious that the time correlates well with the amount of data read, as opposed to with the version number in itself.

That can be shown more clearly:


I'm not sure what's going on on the slower end of the Core2 graph there, but basically the boot time has been the same with varying amounts of data - maybe it's stuck waiting for something else?