I've just noticed a bug with having my scheduler set to 1000Hz (by editing
/usr/src/linux/include/asm/param.h, of course). Although scheduling does,
in fact, seem smoother, ps returns that a process has been running longer
than it really has; in fact, it's by exactly a factor of 10, go figure.
Just to prove this, I ran the following simple script (PID 1097 is,
obviously, rc5des):
while (1)
ps 1097 | tail -1
sleep 1
end
I get results like this:
1097 p0 R N517:34 ./rc5des
1097 p0 R N517:44 ./rc5des
1097 p0 R N517:54 ./rc5des
1097 p0 R N518:04 ./rc5des
1097 p0 R N518:14 ./rc5des
1097 p0 R N518:24 ./rc5des
1097 p0 R N518:34 ./rc5des
1097 p0 R N518:44 ./rc5des
1097 p0 R N518:54 ./rc5des
1097 p0 R N519:04 ./rc5des
1097 p0 R N519:14 ./rc5des
1097 p0 R N519:24 ./rc5des
1097 p0 R N519:34 ./rc5des
1097 p0 R N519:44 ./rc5des
Now, just in case it matters (though I seriously doubt it), I *am* running
my system (a Celeron 300A) overclocked to 450. Also, I'm still running
2.2.0-pre7, so if this bug has been fixed since then, my apologies;
however, I didn't see any mention of this in my quick perusal of the last
couple weeks' worth of the list archives at linuxhq.com.
This isn't really a fatal problem, but it is a bit annoying to have to
worry about, and it dosen't seem like the kind of thing that would take
long to fix.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/