You'll be delighted with some of the new kernel patches coming out. There are several patches in arjan's -fastboot git tree on git dot kernel dot org that will improve your kernel boot drastically. Most of it is currently also floating in linux-next as well. Just sit back until those hit mainline and get picked up by your distro, or help out testing;)
With regard to initrd, I assume having support for it configured into the kernel doesn't slow down the boot. Rather it's the actual use of it that does right?
how common is booting from USB devices? you'd probably fall in the 5% of odd cases where you accept an initrd anyway. Still no need to force the other 95% to use initrds....!
and we used the 'stock' SSDs in these systems. from the bootcharts you can see that our SSDs top out at 25-30mb/sec throughput on read, far below what most regular hard discs or server-grade ssd's can do.
it's just a normal linux distro. for the demo we used an auto-login but you can have it start to a password screen as well, so it's just as secure as your base distro is....
actually we do bring up the network daemon (either connmand or network manager) as soon as we can, but we don't stop the entire startup process.
on my test system here it runs dhclient about when X starts up and the network card receives a reply with a few seconds from that, long before I can start firefox:)
so you are saying that you would rather stare at a hung boot in text mode instead of having the possibility of working in offline mode in X?
that does not make sense at all:)
for network-client setups like you describe, we should still start X immediately and if the network fails or is slow, at least provide some interaction with the system (work offline, nudge network with login attempt etc).
We talked with both the fedora and ubuntu developers at the LPC and even they agreed that a LOT more drivers should be compiled into the kernel instead of being modules (c'mon, ext3 as a module? really?).
99% of what we did to make this work in 5 seconds applies straight for generic laptops and even most people's desktop sytems.
The speedups _still_ are relevant with generic spinning media too. Maybe those are not as fast as SSD's, but the principle is still the same (IOW, for instance reading data in the order that you need it, is better than reading it in the order that it is scattered across the hard disk)
speeding up the kernel to boot in 1 second is TOTALLY applicable to generic distros (not only that, it's relatively easy and we basically already did that).
speeding up X startup to be 1.5s is TOTALLY applicable to generic distros.
We've sent a patch to Greg KH making USB initialization go in parallel which reduces usb initialization from [N * 0.1] seconds (where N is the number of usb ports in your system to [0.1]. This patch is currently in linux-next afaik.
I'm wondering why you would even have PCIe HP turned on on an asus 900:)
you'd provide a storage for the VM to put other things into that are less important than the image data, such as other program data that is currently not in use.
if you use images larger than your system memory, all bets are off:)
you actually pointed out the right thing. Linux on itself does work better with a little bit of swap because it gives the VM just the opportunity to page out really old data. This will in the long run result in a few more megabytes of data being available for buffers/cache while it's unlikely that hot items are constantly being swapped out.
it also gives the VM at least ONE alternative to killing a task immediately when it really goes near OOM. Without that alternative the system would immediately grind to a halt.
even on netbooks this story holds. it's still good to have a little bit of swap on them.
these cars have "some" gas engine in it. but the winner had over 200 sqft of solar panels and could as well have just used the RV plane gasoline engine in it to provide as a fresh air fan for the driver.
please remember that there are yearly races through australia where cars driver 3000 miles on NO GASOLINE AT ALL.
the REAL winners in this article are the two models that did 300+ and 160+ mpg (on DIESEL) without any solar panels.
or, a variant after my favorite mountaineer (after the late Edmund Hillary):
Because it's there
Stopping us from dreaming will make humanity dull and suicidal. Even though none of us might actually come to live the day that humans walk on the surface of Mars, doesn't mean that it is wrong to dream about it and start planning humanities future today.
Don't hide in your house from wonderful things that could be. Embrace the future and help make dreams come true!
Slashdot Mirror
one of the main ideas is to put everything + kitchen sink drivers into the kernel
who says we have to?
"slow consumer grade" as in "not one made specifically for high-throughput" :)
seek times on all the existing SSDs are pretty much the same, but throughput is extremely varying.
The used SSDs top out at 30mb/sec throughput (read!), while there are currently SSDs in the market that do over 200mb/sec throughput (read).
You'll be delighted with some of the new kernel patches coming out. There are several patches in arjan's -fastboot git tree on git dot kernel dot org that will improve your kernel boot drastically. Most of it is currently also floating in linux-next as well. Just sit back until those hit mainline and get picked up by your distro, or help out testing ;)
With regard to initrd, I assume having support for it configured into the kernel doesn't slow down the boot. Rather it's the actual use of it that does right?
correct.
we already boot in seconds. the totaly size of the data read from disk at boot is UNDER 100mb total on our 5-second boot systems.
you don't provide a solution to speeding things up, only an alternative that works in limited cases. reinventing hibernate at best.
how common is booting from USB devices? you'd probably fall in the 5% of odd cases where you accept an initrd anyway. Still no need to force the other 95% to use initrds....!
what if you boot in 3 seconds? do you still need to *see* what is going on? :)
and we used the 'stock' SSDs in these systems. from the bootcharts you can see that our SSDs top out at 25-30mb/sec throughput on read, far below what most regular hard discs or server-grade ssd's can do.
The 5-second demo video is of an asus eee pc 901, however the same image boots on an acer aspire 1 also in exactly 5 seconds.
These systems have 512mb of memory, a slow consumer-grade SSD (we used a 4gb partition) and a 1.6GHz atom processor (single core, HT enabled).
this is a _slow_ system compared to any desktop-grade system currently on the shelves.
we don't even need to recompile the kernel, we can just link the modules in as needed. Something most older UNIX systems actually did.
whoops, I meant to say "do not need an initrd".
lol :)
only for systems with full hard disk encryption enabled. all other systems do not need a hard disk.
it's just a normal linux distro. for the demo we used an auto-login but you can have it start to a password screen as well, so it's just as secure as your base distro is....
actually we do bring up the network daemon (either connmand or network manager) as soon as we can, but we don't stop the entire startup process.
on my test system here it runs dhclient about when X starts up and the network card receives a reply with a few seconds from that, long before I can start firefox :)
so you are saying that you would rather stare at a hung boot in text mode instead of having the possibility of working in offline mode in X?
that does not make sense at all :)
for network-client setups like you describe, we should still start X immediately and if the network fails or is slow, at least provide some interaction with the system (work offline, nudge network with login attempt etc).
says who?
We talked with both the fedora and ubuntu developers at the LPC and even they agreed that a LOT more drivers should be compiled into the kernel instead of being modules (c'mon, ext3 as a module? really?).
99% of what we did to make this work in 5 seconds applies straight for generic laptops and even most people's desktop sytems.
The speedups _still_ are relevant with generic spinning media too. Maybe those are not as fast as SSD's, but the principle is still the same (IOW, for instance reading data in the order that you need it, is better than reading it in the order that it is scattered across the hard disk)
speeding up the kernel to boot in 1 second is TOTALLY applicable to generic distros (not only that, it's relatively easy and we basically already did that).
speeding up X startup to be 1.5s is TOTALLY applicable to generic distros.
We've sent a patch to Greg KH making USB initialization go in parallel which reduces usb initialization from [N * 0.1] seconds (where N is the number of usb ports in your system to [0.1]. This patch is currently in linux-next afaik.
I'm wondering why you would even have PCIe HP turned on on an asus 900 :)
you'd provide a storage for the VM to put other things into that are less important than the image data, such as other program data that is currently not in use.
if you use images larger than your system memory, all bets are off :)
you actually pointed out the right thing. Linux on itself does work better with a little bit of swap because it gives the VM just the opportunity to page out really old data. This will in the long run result in a few more megabytes of data being available for buffers/cache while it's unlikely that hot items are constantly being swapped out.
it also gives the VM at least ONE alternative to killing a task immediately when it really goes near OOM. Without that alternative the system would immediately grind to a halt.
even on netbooks this story holds. it's still good to have a little bit of swap on them.
yes, well not entirely
you want a LITTLE BIT of swap in all cases.
- for netbooks (asus eee pc) I recommend 128mb of swap (max).
- for most laptops up to 256mb swap is more than enough.
desktop swap size may be bigger depending on your personal needs. If you gimp gigantic images, use more.
these cars have "some" gas engine in it. but the winner had over 200 sqft of solar panels and could as well have just used the RV plane gasoline engine in it to provide as a fresh air fan for the driver.
please remember that there are yearly races through australia where cars driver 3000 miles on NO GASOLINE AT ALL.
the REAL winners in this article are the two models that did 300+ and 160+ mpg (on DIESEL) without any solar panels.
now THAT should have been the headline.
I've got news for you:
We *are* exploring Mars and we have been doing so for a long time already.
Check your tax return this year and see how much money you paid into extraterrestrial research. You'll be surprised.
"To talk about space exploration and ignore real problems is to talk like a thief and a fool."
I guess all little boys who want to be astronauts on this world are thieves?
this is an absolute troll-like response, you're literally twisting his words around. Grow up.
The real reason we want to explore Mars?
Because we can
or, a variant after my favorite mountaineer (after the late Edmund Hillary):
Because it's there
Stopping us from dreaming will make humanity dull and suicidal. Even though none of us might actually come to live the day that humans walk on the surface of Mars, doesn't mean that it is wrong to dream about it and start planning humanities future today.
Don't hide in your house from wonderful things that could be. Embrace the future and help make dreams come true!
http://en.wikipedia.org/wiki/Stromatolite
Quote:
"The earliest stromatolite of confirmed microbial origin dates to 2,724 million years ago."