[fedora-arm] Probably The Hardest Task I've Been Assigned At Seneca's CDoT (or at least the one that's taken me the longest...) rasp pi v6hl status

[Gordan Bobic]

On 09/19/2012 03:55 AM, Jon Chiappetta wrote:
> So I *think* I've got a basic start on a general armv6hl hard float root
> fs for Fedora. I just posted probably one of my more complicated blog
> posts this far about bringing up a new arch for Fedora ARM Linux ->
> http://fossjon.wordpress.com/2012/09/18/bootstrapping-fedora-arm-for-a-new-arch-v6hl/
>
>
> Thanks to the help and support from the people on this list and in
> channel, I've been able to get this far. My next step is to patch yum &&
> rpm somehow and turn this basic root fs into a koji builder so we can
> start building for v6hl off to the side for the rasp pi possibly. I
> haven't done any speed tests at all yet and probably wont be able to for
> a while until we get a complete image with all the packages cleanly
> rebuilt -- but were really hoping this thing proves to be much faster
> and a better user experience overall. The text login (multi-user) boot
> up seems pretty good so far though. Anyway, I posted a screenshot up
> above for proof, which is basically me just compiling a v6 binary on the
> pi and running it. It's pretty cool I guess.

Well done.

It raises a couple of questions, though.

1) How much performance difference does this _actually_ make over 
armv5tel targeted binaries? The benchmark results I have seen from a 
similar Debian effort is that with the exception of A/V transcoding, the 
performnce difference is in the low single figure % points which is 
unlikely to be perceivable over and above the placebo effect to the 
average user.

2) Why base the mainline distribution on armv7hl instead of armv6hl if 
armv6hl code will run on both? (Note: I don't consider the argument of 
"That's what all the other distros are doing." to stand up on it's own 
at face value.)

Gordan