+
+
+ Finding non-shared duplicated strings
+
+strings busybox | sort | uniq -c | sort -nr
+
+
+ gcc's data alignment problem
+
+The following attribute added in vi.c:
+
+static int tabstop;
+static struct termios term_orig __attribute__ ((aligned (4)));
+static struct termios term_vi __attribute__ ((aligned (4)));
+
+reduces bss size by 32 bytes, because gcc sometimes aligns structures to
+ridiculously large values. asm output diff for above example:
+
+ tabstop:
+ .zero 4
+ .section .bss.term_orig,"aw",@nobits
+- .align 32
++ .align 4
+ .type term_orig, @object
+ .size term_orig, 60
+ term_orig:
+ .zero 60
+ .section .bss.term_vi,"aw",@nobits
+- .align 32
++ .align 4
+ .type term_vi, @object
+ .size term_vi, 60
+
+gcc doesn't seem to have options for altering this behaviour.
+
+gcc 3.4.3 and 4.1.1 tested:
+char c = 1;
+// gcc aligns to 32 bytes if sizeof(struct) >= 32
+struct {
+ int a,b,c,d;
+ int i1,i2,i3;
+} s28 = { 1 }; // struct will be aligned to 4 bytes
+struct {
+ int a,b,c,d;
+ int i1,i2,i3,i4;
+} s32 = { 1 }; // struct will be aligned to 32 bytes
+// same for arrays
+char vc31[31] = { 1 }; // unaligned
+char vc32[32] = { 1 }; // aligned to 32 bytes
+
+-fpack-struct=1 reduces alignment of s28 to 1 (but probably
+will break layout of many libc structs) but s32 and vc32
+are still aligned to 32 bytes.
+
+I will try to cook up a patch to add a gcc option for disabling it.
+Meanwhile, this is where it can be disabled in gcc source:
+
+gcc/config/i386/i386.c
+int
+ix86_data_alignment (tree type, int align)
+{
+#if 0
+ if (AGGREGATE_TYPE_P (type)
+ && TYPE_SIZE (type)
+ && TREE_CODE (TYPE_SIZE (type)) == INTEGER_CST
+ && (TREE_INT_CST_LOW (TYPE_SIZE (type)) >= 256
+ || TREE_INT_CST_HIGH (TYPE_SIZE (type))) && align < 256)
+ return 256;
+#endif
+
+Result (non-static busybox built against glibc):
+
+# size /usr/srcdevel/bbox/fix/busybox.t0/busybox busybox
+ text data bss dec hex filename
+ 634416 2736 23856 661008 a1610 busybox
+ 632580 2672 22944 658196 a0b14 busybox_noalign
+
+
+
+ Keeping code small
+
+Set CONFIG_EXTRA_CFLAGS="-fno-inline-functions-called-once",
+produce "make bloatcheck", see the biggest auto-inlined functions.
+Now, set CONFIG_EXTRA_CFLAGS back to "", but add NOINLINE
+to some of these functions. In 1.16.x timeframe, the results were
+(annotated "make bloatcheck" output):
+
+function old new delta
+expand_vars_to_list - 1712 +1712 win
+lzo1x_optimize - 1429 +1429 win
+arith_apply - 1326 +1326 win
+read_interfaces - 1163 +1163 loss, leave w/o NOINLINE
+logdir_open - 1148 +1148 win
+check_deps - 1148 +1148 loss
+rewrite - 1039 +1039 win
+run_pipe 358 1396 +1038 win
+write_status_file - 1029 +1029 almost the same, leave w/o NOINLINE
+dump_identity - 987 +987 win
+mainQSort3 - 921 +921 win
+parse_one_line - 916 +916 loss
+summarize - 897 +897 almost the same
+do_shm - 884 +884 win
+cpio_o - 863 +863 win
+subCommand - 841 +841 loss
+receive - 834 +834 loss
+
+855 bytes saved in total.
+
+scripts/mkdiff_obj_bloat may be useful to automate this process: run
+"scripts/mkdiff_obj_bloat NORMALLY_BUILT_TREE FORCED_NOINLINE_TREE"
+and select modules which shrank.