1 |
2007/8/5, Joshua Hoblitt <jhoblitt@××××××××××.edu>: |
2 |
> |
3 |
> Your statement was that the on-demand governor is "very bad" for amd |
4 |
> CPUs. I don't see how you have qualified that statement in any way. |
5 |
> Yes, it behaves differently then the conservative governor but that |
6 |
> doesn't make it "bad", "harmful", or even inefficient with power usage. |
7 |
|
8 |
|
9 |
i never intended that it was harmful or bad in the way you think. i was |
10 |
only saying that it is a bad governor for an amd processor. or at least it |
11 |
is for my turion 64 and for my athlon x2. when i used it on these processors |
12 |
i had a bad feeling, cpu lags about it. so i switched to the conservative |
13 |
wich is smoother. |
14 |
|
15 |
I use the ondemand govern on a large number of production Opteron |
16 |
> machines with great results. According to my empirical measurements |
17 |
> with an ammeter it saves an average of ~35w per socket in systems with |
18 |
> dual core CPUs (not per core). As you can imagine, this is a pretty use |
19 |
> full savings for the 8-socket system that I have. |
20 |
> |
21 |
> Cheers, |
22 |
> |
23 |
> -J |
24 |
> |
25 |
> on my turion 64 it does not behave as you say, and just step from 800mhz |
26 |
to 2ghz, and it doesn't save anything when compared to conservative and |
27 |
userspace with powernowd/powerthend. and i assure you that the overall |
28 |
system energy consumption is of very great importance to me, specially when |
29 |
i'm on battery. |