Search:

So, what about those power/performance benchmarks, Michael?

Sandy bridge: 0x2A, 0x2D
Ivy bridge: 0x3A, 0x3E
Haswell: 0x3c, 0x45

according to cpu_idle.c

EDIT:

case 0x2a: /* Sandy Bridge Core */
case 0x2d: /* Sandy Bridge Xeon */

Can't wait to see the benchmarks.

Also, what about those power regressions from older kernel versions? I saw different articles here in the past but I've never heard about these issues again.

But we can still choose CONFIG_NO_HZ_IDLE over CONFIG_NO_HZ_FULL, right?
Where can I find more information about those regressions?

Released? Good. So that means we can finally see a more recent gnome version (3.8...) in Sid sooner or later?

Woohoo! Only 14 bugs left... http://udd.debian.org/bugs.cgi?release=wheezy&merged=ign&rc=1

It would be interesting to see how BFS compares to the latest CFS now that the fixes & io patches have been added in 3.9. The only benchmark I could find @ Phoronix is dated Sep 2009.

configs here... http://liquorix.net/sources/3.8/

i never used liquorix, but if it shares code from zen-kernel (same author) then it also uses extra code/patches

yep, BFQ (http://groups.google.com/group/bfq-iosched)... CONFIG_DEFAULT_BFQ=y

there's also BFS in the config but apparently it's not enabled

Great, in 3.9 the new code has been merged for all codecs: http://mailman.alsa-project.org/pipermail/alsa-devel/2013-January/058883.html

What did you expect, he's a troll :rolleyes:

Michael, it would be nice to have updates once in a while about the current status of all these regressions you talk about in your articles. Browsing through a high-volume mailing list like LKML is...

Any news about that regression in kernel 3.8 ?

Have you reported this to the devs?

compressio and postgres results... ouch :(

Agreed. Many comments can be summed up as either "I love Windoze-like interfaces, don't innovate, keep Gnome 2", or "nyah nyah, XXX is a better desktop". And then the inevitable morons ("let it die",...

AND, you lose power savings on Intel GPUs. You forgot about this... feature.

Perhaps 3.8 can save RAM in specific situations, but I don't like the massive power cost for Intel video introduced in xf86-video-intel 2.20.12 -- i.e. keeping the GPU out of power-saving mode,...

I wonder if these bug fixes (not new features, just fixes) are propagated to stable (e.g. the current mainline, 3.7) ?

Ok, I'll bite, troll. Complaining about ad revenues and repeating post after post that Larabel is <insert insult here>, spamming about your little distro and your websites, and resorting to personal...