1 |
On 11/19/2010 11:46 PM, Alan McKinnon wrote: |
2 |
> Apparently, though unproven, at 18:03 on Friday 19 November 2010, Nikos |
3 |
> Chantziaras did opine thusly: |
4 |
> |
5 |
>>> Perhaps distros will pick up on this and offer other criteria, maybe |
6 |
>>> something like a profile selectable at boot-time or maybe even runtime. |
7 |
>>> |
8 |
>>> What I would like to see is flash goes into it's own group and gets |
9 |
>>> throttled. Everything else running under KDE is in a different group and |
10 |
>>> left to run full speed |
11 |
>> |
12 |
>> I was kind of hoping this would give results in the same league as the |
13 |
>> BFS patch, but it seems it something that needs tweaking and doesn't |
14 |
>> "just work for everything." It doesn't look like it's for desktop |
15 |
>> users, only for "make -j999" people. |
16 |
> |
17 |
> Maybe I expected more, but I don't seem to feel the improvement in Con's |
18 |
> scheduler. Perhaps it's a perception thing. |
19 |
> |
20 |
> About two months ago I did reboot into a gentoo kernel and things did feel a |
21 |
> little different but not in a way I could put my fingers on. I put it down to |
22 |
> running a huge compile in screen. I *do* feel the incremental improvements in |
23 |
> KDE since about 4.3, mostly because new versions come out rapidly. |
24 |
> |
25 |
> What do you perceive with BFS vs mainline/gentoo/whatever? |
26 |
|
27 |
Less stalls in animations. A classic example is mplayer stalling when I |
28 |
move the mouse over the clock to the right of the system tray in KDE. |
29 |
KDE will fade-in a pop-up that contains details about the current date. |
30 |
For the duration of the fade-in, mplayer will stop playing frames. |
31 |
This is a "stall." It seems that the compositor of KDE gets way more |
32 |
CPU than it should resulting in mplayer starving for CPU. With BFS, |
33 |
this does not happen. |
34 |
|
35 |
Also the reverse happens too. For example, if something is eating CPU, |
36 |
the GUI can stall for a few moments. Like minimizing a window in KDE. |
37 |
This zooms-out the window towards the task bar. Without BFS, the |
38 |
zoom-out animation will sometimes stop in mid-way for a few milliseconds |
39 |
if something else if producing heavy load on the machine. This also |
40 |
happens less often with BFS. |
41 |
|
42 |
Another example is sound latency in audio apps (synths and such.) A |
43 |
realtime kernel is extreme overkill for this use. BFS also helps here. |
44 |
|
45 |
It would seem that this "200 line patch" is not good at solving those |
46 |
issues; it solves them only for stuff launched from the terminal, since |
47 |
they have their own TTY assigned to them. What I like about BFS is that |
48 |
this gets solved automatically in a "run it and forget it" way. There's |
49 |
nothing to set up or tweak. |
50 |
|
51 |
However, it should be mentioned that mainline became much better on the |
52 |
desktop in recent releases. 2.6.36 for example is much closer to BFS |
53 |
than 2.6.31 which kind of totally sucked and was one of the triggers |
54 |
that lead to BFS. |
55 |
|
56 |
(I actually use the whole 2.6.36-ck1 patchset, not just the BFS patch. |
57 |
You can find more info at http://ck-hack.blogspot.com .) |