1 |
Mark Knecht writes: |
2 |
|
3 |
> On Mon, May 7, 2012 at 5:41 AM, Alex Schuster <wonko@×××××××××.org> |
4 |
> wrote: |
5 |
> > Some while ago, I wrote: |
6 |
> > |
7 |
> > [ |
8 |
> > mplayer stutters when I/O is going on, even hangs for seconds when I |
9 |
> > do a dd if=/dev/zero of=somefile bs=1M |
10 |
> > ] |
11 |
[...] |
12 |
> OK, fire up two terminals. In one run top, hit 1 & z so you see all |
13 |
> your CPUs and then watch CPU usage. In the second terminal su to root |
14 |
> and run iotop -o. Now, watch for a few minutes and get a feel for |
15 |
> what's going on when video is not running. Then start your video and |
16 |
> watch IO usage and CPU usage. Where's the problem? |
17 |
> |
18 |
> Once you get an idea where the bottleneck is we can address what a |
19 |
> solution might be. In general, if the CPUs aren't maxed out and it's |
20 |
> an I/O problem then usually a bit more buffering is a simple solution. |
21 |
> Other more draconian solution might be a real-time kernel with a |
22 |
> player (if there is one) that is set up for real-time playback. |
23 |
> |
24 |
> Looking forward to hearing your test results. |
25 |
|
26 |
Thanks for your support, Mark! |
27 |
|
28 |
I did this already, but sometimes I do not notice anything. I guess it's |
29 |
short I/O operations in that case. CPU load is not the problem, and it |
30 |
happens for both high-quality videos and small ones. |
31 |
Currently iotop shows stuff like kjournald, kworker, kdeinit4, |
32 |
akonadiserver, firefox. And lots of virtuoso-t and nepomuk when I enable |
33 |
indexing again, which I just suspended. |
34 |
And mplayer of course, it shows up in about every 2nd redisplay, which |
35 |
happens every second. |
36 |
|
37 |
Well... but when I do the same in the other window manager, it seems I |
38 |
see fewer processes then. Are they mostly suspended when I am on another |
39 |
display? |
40 |
And I should fire up the same stuff (Firefox, Chromium, maybe KDEPIM |
41 |
stuff) in the other WM and see if this makes things worse. But I'll do |
42 |
this tomorrow. Thanks for the inspiration, though, at least I have |
43 |
something more to try now. |
44 |
|
45 |
The interrupts are very small normally, but noticeable, annoying and |
46 |
somewhat embarrassing. When they just happened I only noticed akonadi and |
47 |
kjournald during that time. I can force larger interrupts by doing my dd |
48 |
command. |
49 |
|
50 |
But anyway - my intention is not so much to find out what all these |
51 |
I/O processes are and how to make them calm down, renice them or whatever. |
52 |
Four cores @ 3.6 GHz just should be able to play movies without any |
53 |
interruption. And it _is_ possible, when I start the playback on another |
54 |
window manager, while KDE is still running on the other display. |
55 |
|
56 |
I could just switch to, um, ummmm.... Gnome maybe... or Xfce4... or |
57 |
something else, but I would not like to do so. Despite by big KDE |
58 |
problems. I hate KDE. But I still want it. I feel mad. |
59 |
|
60 |
Wonko |