Re: [PERFORM] A Better External Sort?

On Tue, Oct 04, 2005 at 12:24:54PM +0100, Simon Riggs wrote:
> How did you determine the 1500 figure? Can you give some more info to
> surround that recommendation to allow everybody to evaluate it?

kleptog(at)vali:~/dl/cvs/pgsql-local/src/backend/utils/sort$ gcc -finline-limit-1000 -Winline -O2 -Wall -Wmissing-prototypes -Wpointer-arith -Wendif-labels -fno-strict-aliasing -g -I../../../../src/include -D_GNU_SOURCE -c -o tuplesort.o tuplesort.c
tuplesort.c: In function 'applySortFunction':
tuplesort.c:1833: warning: inlining failed in call to 'inlineApplySortFunction'
tuplesort.c:1906: warning: called from here
tuplesort.c: In function 'comparetup_heap':
tuplesort.c:1833: warning: inlining failed in call to 'inlineApplySortFunction'
tuplesort.c:1937: warning: called from here
tuplesort.c: In function 'comparetup_index':
tuplesort.c:1833: warning: inlining failed in call to 'inlineApplySortFunction'
tuplesort.c:2048: warning: called from here
tuplesort.c: In function 'comparetup_datum':
tuplesort.c:1833: warning: inlining failed in call to 'inlineApplySortFunction'
tuplesort.c:2167: warning: called from here
kleptog(at)vali:~/dl/cvs/pgsql-local/src/backend/utils/sort$ gcc -finline-limit-1500 -Winline -O2 -Wall -Wmissing-prototypes -Wpointer-arith -Wendif-labels -fno-strict-aliasing -g -I../../../../src/include -D_GNU_SOURCE -c -o tuplesort.o tuplesort.c
<no warnings>

A quick binary search puts the cutoff between 1200 and 1300. Given
version variation I picked a nice round number, 1500.

Ugh, that's for -O2, for -O3 and above it needs to be 4100 to work.
Maybe we should go for 5000 or so.

I'm using: gcc (GCC) 3.3.5 (Debian 1:3.3.5-13)

Have a nice day,
--
Martijn van Oosterhout <kleptog(at)svana(dot)org> http://svana.org/kleptog/
> Patent. n. Genius is 5% inspiration and 95% perspiration. A patent is a
> tool for doing 5% of the work and then sitting around waiting for someone
> else to do the other 95% so you can sue them.