trace: measure where the time is spent in the index-heavy operations

All the known heavy code blocks are measured (except object database
access). This should help identify if an optimization is effective or
not. An unoptimized git-status would give something like below:

    0.001791141 s: read cache ...
    0.004011363 s: preload index
    0.000516161 s: refresh index
    0.003139257 s: git command: ... 'status' '--porcelain=2'
    0.006788129 s: diff-files
    0.002090267 s: diff-index
    0.001885735 s: initialize name hash
    0.032013138 s: read directory
    0.051781209 s: git command: './git' 'status'

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff-lib.c

@@ -92,6 +92,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 	int diff_unmerged_stage = revs->max_count;
 	unsigned ce_option = ((option & DIFF_RACY_IS_MODIFIED)
 			      ? CE_MATCH_RACY_IS_DIRTY : 0);
+	uint64_t start = getnanotime();
 
 	diff_set_mnemonic_prefix(&revs->diffopt, "i/", "w/");
 
@@ -246,6 +247,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 	}
 	diffcore_std(&revs->diffopt);
 	diff_flush(&revs->diffopt);
+	trace_performance_since(start, "diff-files");
 	return 0;
 }
 
@@ -512,6 +514,7 @@ static int diff_cache(struct rev_info *revs,
 int run_diff_index(struct rev_info *revs, int cached)
 {
 	struct object_array_entry *ent;
+	uint64_t start = getnanotime();
 
 	ent = revs->pending.objects;
 	if (diff_cache(revs, &ent->item->oid, ent->name, cached))
@@ -521,6 +524,7 @@ int run_diff_index(struct rev_info *revs, int cached)
 	diffcore_fix_diff_index(&revs->diffopt);
 	diffcore_std(&revs->diffopt);
 	diff_flush(&revs->diffopt);
+	trace_performance_since(start, "diff-index");
 	return 0;
 }
 

dir.c

@@ -2248,6 +2248,7 @@ int read_directory(struct dir_struct *dir, struct index_state *istate,
 		   const char *path, int len, const struct pathspec *pathspec)
 {
 	struct untracked_cache_dir *untracked;
+	uint64_t start = getnanotime();
 
 	if (has_symlink_leading_path(path, len))
 		return dir->nr;
@@ -2286,6 +2287,7 @@ int read_directory(struct dir_struct *dir, struct index_state *istate,
 		dir->nr = i;
 	}
 
+	trace_performance_since(start, "read directory %.*s", len, path);
 	if (dir->untracked) {
 		static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS);
 		trace_printf_key(&trace_untracked_stats,

name-hash.c

@@ -578,6 +578,8 @@ static void threaded_lazy_init_name_hash(
 
 static void lazy_init_name_hash(struct index_state *istate)
 {
+	uint64_t start = getnanotime();
+
 	if (istate->name_hash_initialized)
 		return;
 	hashmap_init(&istate->name_hash, cache_entry_cmp, NULL, istate->cache_nr);
@@ -600,6 +602,7 @@ static void lazy_init_name_hash(struct index_state *istate)
 	}
 
 	istate->name_hash_initialized = 1;
+	trace_performance_since(start, "initialize name hash");
 }
 
 /*

preload-index.c

@@ -78,6 +78,7 @@ static void preload_index(struct index_state *index,
 {
 	int threads, i, work, offset;
 	struct thread_data data[MAX_PARALLEL];
+	uint64_t start = getnanotime();
 
 	if (!core_preload_index)
 		return;
@@ -108,6 +109,7 @@ static void preload_index(struct index_state *index,
 		if (pthread_join(p->pthread, NULL))
 			die("unable to join threaded lstat");
 	}
+	trace_performance_since(start, "preload index");
 }
 #endif
 

read-cache.c

@@ -1372,6 +1372,7 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 	const char *typechange_fmt;
 	const char *added_fmt;
 	const char *unmerged_fmt;
+	uint64_t start = getnanotime();
 
 	modified_fmt = (in_porcelain ? "M\t%s\n" : "%s: needs update\n");
 	deleted_fmt = (in_porcelain ? "D\t%s\n" : "%s: needs update\n");
@@ -1442,6 +1443,7 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 
 		replace_index_entry(istate, i, new);
 	}
+	trace_performance_since(start, "refresh index");
 	return has_errors;
 }
 
@@ -1873,6 +1875,7 @@ static void freshen_shared_index(char *base_sha1_hex, int warn)
 
 int read_index_from(struct index_state *istate, const char *path)
 {
+	uint64_t start = getnanotime();
 	struct split_index *split_index;
 	int ret;
 	char *base_sha1_hex;
@@ -1883,6 +1886,7 @@ int read_index_from(struct index_state *istate, const char *path)
 		return istate->cache_nr;
 
 	ret = do_read_index(istate, path, 0);
+	trace_performance_since(start, "read cache %s", path);
 
 	split_index = istate->split_index;
 	if (!split_index || is_null_sha1(split_index->base_sha1)) {
@@ -1906,6 +1910,7 @@ int read_index_from(struct index_state *istate, const char *path)
 	freshen_shared_index(base_sha1_hex, 0);
 	merge_base_index(istate);
 	post_read_index_from(istate);
+	trace_performance_since(start, "read cache %s", base_path);
 	return ret;
 }
 
@@ -2234,6 +2239,7 @@ void update_index_if_able(struct index_state *istate, struct lock_file *lockfile
 static int do_write_index(struct index_state *istate, struct tempfile *tempfile,
 			  int strip_extensions)
 {
+	uint64_t start = getnanotime();
 	int newfd = tempfile->fd;
 	git_SHA_CTX c;
 	struct cache_header hdr;
@@ -2374,6 +2380,7 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile,
 		return -1;
 	istate->timestamp.sec = (unsigned int)st.st_mtime;
 	istate->timestamp.nsec = ST_MTIME_NSEC(st);
+	trace_performance_since(start, "write index, changed mask = %x", istate->cache_changed);
 	return 0;
 }