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

[Grant Coady]

On Sun, 8 Jan 2006 10:21:01 -0800, Octavio Alvarez Piza <alvarezp@xxxxxxxxxxxxxxxx> wrote:

>On Sun, 08 Jan 2006 22:05:43 +1100
>Grant Coady <gcoady@xxxxxxxxx> wrote:
>
>> On Sun, 8 Jan 2006 10:57:41 +0100, Willy Tarreau <willy@xxxxxxxxx> wrote:
>> 
>> > Could you please retest :
>> >  - without the pipe (remove '| cut ...') to avoid inter-process
>> >    communications
>> 
>> I thought it made a difference, then delay back again, I'll try 
>> again tomorrow when I'm more awake.
>> 
>> >You should be able to find one simple pattern which makes the problem
>> >appear/disappear on 2.6. At least, 'cat x.log >/dev/null' should not
>> >take time or that time should be spent in I/O.
>> 
>> Yes, done that and the time went down by ~five seconds.
>
>Just make sure you first read all the file with cat (I'd retry all from
>the initial tests) so you don't add hd-read time to the first command.

I do notice occasional pauses (just a slight jerkiness) in output 
from log file, perhaps when it is appended to.  As I wrote earlier, 
this one liner is something I do fairly often to see what is hitting 
the web server, the 'cut -c -96' is because I run 96 character 
wide ssh terminals.

Grant.
-
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/