The diff below speeds up ld.so library intialisation where the dependency tree is broad and deep, such as samba's smbd which links over 100 libraries.
See for example https://marc.info/?l=openbsd-misc&m=155007285712913&w=2 See https://marc.info/?l=openbsd-tech&m=155637285221396&w=2 for part 1 that speeds up library loading. The timings below are for /usr/local/sbin/smbd --version: Timing without either diff : 6m45.67s real 6m45.65s user 0m00.02s system Timing with part 1 diff only: 4m42.88s real 4m42.85s user 0m00.02s system Timing with part 2 diff only: 2m02.61s real 2m02.60s user 0m00.01s system Timing with both diffs : 0m00.03s real 0m00.03s user 0m00.00s system Note that these timings are for a build of a recent samba master tree (linked with kerberos) which is probably slower than the OpenBSD port. Nathanael Index: libexec/ld.so/loader.c =================================================================== RCS file: /cvs/src/libexec/ld.so/loader.c,v retrieving revision 1.177 diff -u -p -p -u -r1.177 loader.c --- libexec/ld.so/loader.c 3 Dec 2018 05:29:56 -0000 1.177 +++ libexec/ld.so/loader.c 27 Apr 2019 13:24:02 -0000 @@ -749,15 +749,15 @@ _dl_call_init_recurse(elf_object_t *obje { struct dep_node *n; - object->status |= STAT_VISITED; + int visited_flag = initfirst ? STAT_VISITED_1 : STAT_VISITED_2; + + object->status |= visited_flag; TAILQ_FOREACH(n, &object->child_list, next_sib) { - if (n->data->status & STAT_VISITED) + if (n->data->status & visited_flag) continue; _dl_call_init_recurse(n->data, initfirst); } - - object->status &= ~STAT_VISITED; if (object->status & STAT_INIT_DONE) return; Index: libexec/ld.so/resolve.h =================================================================== RCS file: /cvs/src/libexec/ld.so/resolve.h,v retrieving revision 1.90 diff -u -p -p -u -r1.90 resolve.h --- libexec/ld.so/resolve.h 21 Apr 2019 04:11:42 -0000 1.90 +++ libexec/ld.so/resolve.h 27 Apr 2019 13:24:02 -0000 @@ -125,8 +125,9 @@ struct elf_object { #define STAT_FINI_READY 0x10 #define STAT_UNLOADED 0x20 #define STAT_NODELETE 0x40 -#define STAT_VISITED 0x80 +#define STAT_VISITED_1 0x80 #define STAT_GNU_HASH 0x100 +#define STAT_VISITED_2 0x200 Elf_Phdr *phdrp; int phdrc;
