| 1 |
Speedfreq "dynamic" setting is cool (literally), it saves me from |
| 2 |
burning all my cpu's wattage while my firewall/router/printserver idles |
| 3 |
at 300mhz (on a 2400 p4), and it dials in the mhz required for a |
| 4 |
moderate program to run at .8 idle which leaves room for responsiveness |
| 5 |
to new load. |
| 6 |
|
| 7 |
Every time I emerge it I hack this small tidbit in to solve the |
| 8 |
following author-documented idiosyncracy: |
| 9 |
|
| 10 |
"but some applications may experience erratic performance because of the |
| 11 |
latency in speeding up the CPU." |
| 12 |
|
| 13 |
When I ran vanilla speedfreq I would sometimes rifle through tons of |
| 14 |
diagnostics to locate the lag, before checking speedfreq. slow decay is |
| 15 |
fine but slow response is not as useful. |
| 16 |
|
| 17 |
This one-line patch makes speedfreq perfect imho. it spikes the cpu |
| 18 |
frequency which will adjust itself down stepwise as usual. |
| 19 |
|
| 20 |
Jim |
| 21 |
|
| 22 |
diff -u speedfreq-0.7.2/speedfreqd.c speedfreq-0.7.2b/speedfreqd.c |
| 23 |
--- speedfreq-0.7.2/speedfreqd.c 2003-10-17 21:56:53.000000000 -0700 |
| 24 |
+++ speedfreq-0.7.2b/speedfreqd.c 2005-02-22 18:31:08.173420744 -0800 |
| 25 |
@@ -464,7 +464,7 @@ |
| 26 |
} |
| 27 |
|
| 28 |
if (ratio < FREQ_UP) |
| 29 |
- target += FREQ_STEP; |
| 30 |
+ target += FREQ_STEP*8; |
| 31 |
else if (ratio > FREQ_DOWN) |
| 32 |
target -= FREQ_STEP; |
| 33 |
|
| 34 |
-- |
| 35 |
gentoo-dev@g.o mailing list |
Archives