Re: some profiling info

--MimeMultipartBoundary
Content-Type: text/plain; charset=us-ascii

Julian Anderson wrote:
 
> The counts given below are the number of samples for each
> listed event type.
> ==========================================================
> cycles % cum% imiss % procedure image
> 2976145 10.72% 10.72% 333984 7.88% comm_select
> 2819625 10.16% 20.87% 502885 11.86% _db_print
> 2254499 8.12% 28.99% 4678 0.11% ipcache_compareLastRef
[...]
> The _db_print is of course what is behind all of those debug() calls.
> We are running with debug at ALL,1. Interestingly, I turned all
> debugging of for a couple of days, and it didn't effect the proportion
> of _db_print at all, which suggests that my compiler (gcc 2.7.2.1)
> isn't very good at handling varargs.

Is it time to revisit the modified debug macro in 1.2 (is it there?).

Something along the lines of...

#ifdef SQUID_SYSLOGGING
#define debug(X, Y, Z) { Y ? ((Y <= debugLevels[X]) ? _db_print(Z) : 0)
                           : _db_syslog_printf(Z); }
#else
#define debug(X, Y, Z) { (Y <= debugLevels[X]) ? _db_print(Z) : 0; }
#endif

David.

--MimeMultipartBoundary--
Received on Tue Jul 29 2003 - 13:15:44 MDT