summaryrefslogtreecommitdiff
path: root/read-cache.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-01-21 19:37:38 (GMT)
committerJunio C Hamano <gitster@pobox.com>2010-01-22 01:05:13 (GMT)
commitfb7d3f32b283a3847e6f151a06794abd14ffd81b (patch)
treef9a08d8e688c4200b05c900b3145ff8a035cc5dd /read-cache.c
parent42cfcd20a7e264eb7fc3c42c892ff498cde0542b (diff)
downloadgit-fb7d3f32b283a3847e6f151a06794abd14ffd81b.zip
git-fb7d3f32b283a3847e6f151a06794abd14ffd81b.tar.gz
git-fb7d3f32b283a3847e6f151a06794abd14ffd81b.tar.bz2
Remove diff machinery dependency from read-cache
Exal Sibeaz pointed out that some git files are way too big, and that add_files_to_cache() brings in all the diff machinery to any git binary that needs the basic git SHA1 object operations from read-cache.c. Which is pretty much all of them. It's doubly silly, since add_files_to_cache() is only used by builtin programs (add, checkout and commit), so it's fairly easily fixed by just moving the thing to builtin-add.c, and avoiding the dependency entirely. I initially argued to Exal that it would probably be best to try to depend on smart compilers and linkers, but after spending some time trying to make -ffunction-sections work and giving up, I think Exal was right, and the fix is to just do some trivial cleanups like this. This trivial cleanup results in pretty stunning file size differences. The diff machinery really is mostly used by just the builtin programs, and you have things like these trivial before-and-after numbers: -rwxr-xr-x 1 torvalds torvalds 1727420 2010-01-21 10:53 git-hash-object -rwxrwxr-x 1 torvalds torvalds 940265 2010-01-21 11:16 git-hash-object Now, I'm not saying that 940kB is good either, but that's mostly all the debug information - you can see the real code with 'size': text data bss dec hex filename 418675 3920 127408 550003 86473 git-hash-object (before) 230650 2288 111728 344666 5425a git-hash-object (after) ie we have a nice 24% size reduction from this trivial cleanup. It's not just that one file either. I get: [torvalds@nehalem git]$ du -s /home/torvalds/libexec/git-core 45640 /home/torvalds/libexec/git-core (before) 33508 /home/torvalds/libexec/git-core (after) so we're talking 12MB of diskspace here. (Of course, stripping all the binaries brings the 33MB down to 9MB, so the whole debug information thing is still the bulk of it all, but that's a separate issue entirely) Now, I'm sure there are other things we should do, and changing our compiler flags from -O2 to -Os would bring the text size down by an additional almost 20%, but this thing Exal pointed out seems to be some good low-hanging fruit. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'read-cache.c')
-rw-r--r--read-cache.c78
1 files changed, 0 insertions, 78 deletions
diff --git a/read-cache.c b/read-cache.c
index edd9959..79938bf 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -10,9 +10,6 @@
#include "dir.h"
#include "tree.h"
#include "commit.h"
-#include "diff.h"
-#include "diffcore.h"
-#include "revision.h"
#include "blob.h"
#include "resolve-undo.h"
@@ -1648,81 +1645,6 @@ int read_index_unmerged(struct index_state *istate)
return unmerged;
}
-struct update_callback_data
-{
- int flags;
- int add_errors;
-};
-
-static void update_callback(struct diff_queue_struct *q,
- struct diff_options *opt, void *cbdata)
-{
- int i;
- struct update_callback_data *data = cbdata;
-
- for (i = 0; i < q->nr; i++) {
- struct diff_filepair *p = q->queue[i];
- const char *path = p->one->path;
- switch (p->status) {
- default:
- die("unexpected diff status %c", p->status);
- case DIFF_STATUS_UNMERGED:
- /*
- * ADD_CACHE_IGNORE_REMOVAL is unset if "git
- * add -u" is calling us, In such a case, a
- * missing work tree file needs to be removed
- * if there is an unmerged entry at stage #2,
- * but such a diff record is followed by
- * another with DIFF_STATUS_DELETED (and if
- * there is no stage #2, we won't see DELETED
- * nor MODIFIED). We can simply continue
- * either way.
- */
- if (!(data->flags & ADD_CACHE_IGNORE_REMOVAL))
- continue;
- /*
- * Otherwise, it is "git add path" is asking
- * to explicitly add it; we fall through. A
- * missing work tree file is an error and is
- * caught by add_file_to_index() in such a
- * case.
- */
- case DIFF_STATUS_MODIFIED:
- case DIFF_STATUS_TYPE_CHANGED:
- if (add_file_to_index(&the_index, path, data->flags)) {
- if (!(data->flags & ADD_CACHE_IGNORE_ERRORS))
- die("updating files failed");
- data->add_errors++;
- }
- break;
- case DIFF_STATUS_DELETED:
- if (data->flags & ADD_CACHE_IGNORE_REMOVAL)
- break;
- if (!(data->flags & ADD_CACHE_PRETEND))
- remove_file_from_index(&the_index, path);
- if (data->flags & (ADD_CACHE_PRETEND|ADD_CACHE_VERBOSE))
- printf("remove '%s'\n", path);
- break;
- }
- }
-}
-
-int add_files_to_cache(const char *prefix, const char **pathspec, int flags)
-{
- struct update_callback_data data;
- struct rev_info rev;
- init_revisions(&rev, prefix);
- setup_revisions(0, NULL, &rev, NULL);
- rev.prune_data = pathspec;
- rev.diffopt.output_format = DIFF_FORMAT_CALLBACK;
- rev.diffopt.format_callback = update_callback;
- data.flags = flags;
- data.add_errors = 0;
- rev.diffopt.format_callback_data = &data;
- run_diff_files(&rev, DIFF_RACY_IS_MODIFIED);
- return !!data.add_errors;
-}
-
/*
* Returns 1 if the path is an "other" path with respect to
* the index; that is, the path is not mentioned in the index at all,