Date: Fri, 5 Feb 2010 15:03:43 +0000 (UTC) From: Robert Watson <rwatson@FreeBSD.org> To: src-committers@freebsd.org, svn-src-projects@freebsd.org Subject: svn commit: r203526 - projects/capabilities8/tools/tools/syscall_timing Message-ID: <201002051503.o15F3hQJ072301@svn.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: rwatson Date: Fri Feb 5 15:03:43 2010 New Revision: 203526 URL: http://svn.freebsd.org/changeset/base/203526 Log: Merge c174286 by rwatson@rwatson_vimage_client on 2010/02/03 22:52:48 Always do one "warmup" run of every test before the measured loops. Modified: projects/capabilities8/tools/tools/syscall_timing/syscall_timing.c Modified: projects/capabilities8/tools/tools/syscall_timing/syscall_timing.c ============================================================================== --- projects/capabilities8/tools/tools/syscall_timing/syscall_timing.c Fri Feb 5 14:41:18 2010 (r203525) +++ projects/capabilities8/tools/tools/syscall_timing/syscall_timing.c Fri Feb 5 15:03:43 2010 (r203526) @@ -860,6 +860,10 @@ main(int argc, char *argv[]) if (the_test == NULL) usage(); + /* + * Run one warmup, then do the real thing (loops) times. + */ + the_test->t_func(iterations); for (k = 0; k < loops; k++) { the_test->t_func(iterations); timespecsub(&ts_end, &ts_start);
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201002051503.o15F3hQJ072301>