1 |
Qiangning Hong wrote: |
2 |
|
3 |
>Hardware: Thinkpad R52, pentium-m 1.73G, |
4 |
>Host: suspend2-sources-2.6.13-r4, vmware-workstation-4.5.2.8848-r7 |
5 |
>Guest OS: Windows 2000 professional |
6 |
> |
7 |
>The windows guest os is extemely slow. After double-click the date at |
8 |
>bottom-right corner and show the second hand of the clock, I find that |
9 |
>it cost more than 10 seconds for the guest os to increase *one* second. |
10 |
> That is, the timer in the guest os is 10 times slower than the host. |
11 |
>How can I resolve this? |
12 |
> |
13 |
> |
14 |
> |
15 |
|
16 |
The problem is probably because VMWare uses the processor TSC counter |
17 |
for timing, the rate of which varies with the processor frequency. |
18 |
|
19 |
The following works for me on a pentium-m 2.13ghz system: |
20 |
|
21 |
1. Add "processor.max_cstate=1" to your kernel boot options. |
22 |
2. If you are running cpufreqd, stop it with "/etc/init.d/cpufreqd stop" |
23 |
3. Do "echo performance |
24 |
>/sys/devices/system/cpu/cpu0/cpufreq/scaling_governor" |
25 |
4. Run VMWare. |
26 |
|
27 |
When you are done with VMWare, you can restart cpufreqd to get the |
28 |
frequency scaling back. |
29 |
|
30 |
Actually, #2 isn't strictly necessary, but you have to add a rule to |
31 |
/etc/cpufreqd.conf to use the performance governor when VMWare is being |
32 |
run. For example, mine contains the following: |
33 |
|
34 |
... |
35 |
[Profile] |
36 |
name=Performance High |
37 |
minfreq=100% |
38 |
maxfreq=100% |
39 |
policy=performance |
40 |
[/Profile] |
41 |
... |
42 |
## |
43 |
# VMWare |
44 |
[Rule] |
45 |
name=VMWare |
46 |
programs=vmware-vmx |
47 |
battery_interval=0-100 |
48 |
profile=Performance High |
49 |
[/Rule] |
50 |
|
51 |
The above rule is the very first rule in my configuration. With this, I |
52 |
do not have to do steps 2 or 3 above. |
53 |
|
54 |
HTH, |
55 |
|
56 |
-Richard |
57 |
|
58 |
-- |
59 |
gentoo-user@g.o mailing list |