Re: Why is 2.4.32 four times faster than 2.6.14.6??

[Grant Coady]

On Sun, 08 Jan 2006 08:18:40 +0100, be-news06@xxxxxxxxxxxx (Bernd Eckenfels) wrote:

>Markus Rechberger <mrechberger@xxxxxxxxx> wrote:
>> Hi,
>> 
>> what does hdparm show up?
>> Were there any other processes running during the test?
>> what does "vmstat 1" show up during the test?
>
>also also retry with redirection to /dev/null, this could be a console
>problem since there is 5 minutes wait time.

Excuse me?  there is no 5 minutes wait time ;)

grant@deltree:~$ uname -r
2.4.32-hf32.1
grant@deltree:~$ time grep -v 192\.168\. /var/log/apache/access_log |cut -c-96

real    0m1.671s
user    0m0.550s
sys     0m0.300s
grant@deltree:~$ time grep -v 192\.168\. /var/log/apache/access_log |cut -c-96 >/dev/null

real    0m0.510s
user    0m0.420s
sys     0m0.080s

grant@deltree:~$ uname -r
2.6.14.6a
grant@deltree:~$ time grep -v 192\.168\. /var/log/apache/access_log |cut -c-96 >/dev/null
real    0m6.463s
user    0m0.770s
sys     0m0.990s
grant@deltree:~$ time grep -v 192\.168\. /var/log/apache/access_log |cut -c-96 >/dev/null

real    0m0.524s
user    0m0.400s
sys     0m0.130s

Yes, the delay is in the console, that's what I'm talking about ;)
A very perceivable, measurable sluggishness in 2.6 CLI over ssh.

Same thing on 2.6.14.6 screen console is (copy by hand):
real 0m1.374s
user 0m0.510s
sys  0m0.960s

-- 
Thanks,
Grant.
http://bugsplatter.mine.nu/
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/