High-resolution user/system times?

[Nadav Har'El]

On Wed, Jul 25, 2012, Valery Reznic wrote about "Re: High-resolution user/system times?":
> If the process that quick why it is of such interest what time it spent in user space and in kernel space?

This is a CGI script, i.e., a tiny program run by a Web server to
generate a page's output. Yes, I know, there have been newer techniques
replacing CGI, but there're actually good reasons why in this case we're
still using CGI (it's a long story).

So if the CGI takes 3ms, it means we can only run 333 of them each
second, and as always, we'd prefer to get 400, or 1000 :-) So we would
like to understand what's taking the time. One of the thing we
suspected is a lot of time in the kernel, and we want to verify this
suspicion.

Nadav.


-- 
Nadav Har'El                        |        Wednesday, Jul 25 2012, 6 Av 5772
nyh at math.technion.ac.il             |-----------------------------------------
Phone +972-523-790466, ICQ 13349191 |A conclusion is simply the place where
http://nadav.harel.org.il           |you got tired of thinking.