[v5,2/9] dir: report number of visited directories and paths with trace2

Commit Message

Elijah Newren May 12, 2021, 5:28 p.m. UTC

From: Elijah Newren <[e-mail]>

Provide more statistics in trace2 output that include the number of
directories and total paths visited by the directory traversal logic.
Subsequent patches will take advantage of this to ensure we do not
unnecessarily traverse into ignored directories.

Signed-off-by: Elijah Newren <[e-mail]>
---
 dir.c                             | 9 +++++++++
 dir.h                             | 4 ++++
 t/t7063-status-untracked-cache.sh | 3 ++-
 3 files changed, 15 insertions(+), 1 deletion(-)

Patch

diff --git a/dir.c b/dir.c
index cf19a83d3e2c..f6dec5fd4a78 100644
--- a/dir.c
+++ b/dir.c
@@ -2440,6 +2440,7 @@  static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 
 	if (open_cached_dir(&cdir, dir, untracked, istate, &path, check_only))
 		goto out;
+	dir->visited_directories++;
 
 	if (untracked)
 		untracked->check_only = !!check_only;
@@ -2448,6 +2449,7 @@  static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 		/* check how the file or directory should be treated */
 		state = treat_path(dir, untracked, &cdir, istate, &path,
 				   baselen, pathspec);
+		dir->visited_paths++;
 
 		if (state > dir_state)
 			dir_state = state;
@@ -2777,6 +2779,11 @@  static void emit_traversal_statistics(struct dir_struct *dir,
 		strbuf_release(&tmp);
 	}
 
+	trace2_data_intmax("read_directory", repo,
+			   "directories-visited", dir->visited_directories);
+	trace2_data_intmax("read_directory", repo,
+			   "paths-visited", dir->visited_paths);
+
 	if (!dir->untracked)
 		return;
 	trace2_data_intmax("read_directory", repo,
@@ -2797,6 +2804,8 @@  int read_directory(struct dir_struct *dir, struct index_state *istate,
 	struct untracked_cache_dir *untracked;
 
 	trace2_region_enter("dir", "read_directory", istate->repo);
+	dir->visited_paths = 0;
+	dir->visited_directories = 0;
 
 	if (has_symlink_leading_path(path, len)) {
 		trace2_region_leave("dir", "read_directory", istate->repo);
diff --git a/dir.h b/dir.h
index 04d886cfce75..22c67907f689 100644
--- a/dir.h
+++ b/dir.h
@@ -336,6 +336,10 @@  struct dir_struct {
 	struct oid_stat ss_info_exclude;
 	struct oid_stat ss_excludes_file;
 	unsigned unmanaged_exclude_files;
+
+	/* Stats about the traversal */
+	unsigned visited_paths;
+	unsigned visited_directories;
 };
 
 /*Count the number of slashes for string s*/
diff --git a/t/t7063-status-untracked-cache.sh b/t/t7063-status-untracked-cache.sh
index 9710d33b3cd6..a0c123b0a77a 100755
--- a/t/t7063-status-untracked-cache.sh
+++ b/t/t7063-status-untracked-cache.sh
@@ -65,7 +65,8 @@  get_relevant_traces () {
 	INPUT_FILE=$1
 	OUTPUT_FILE=$2
 	grep data.*read_directo $INPUT_FILE |
-	    cut -d "|" -f 9 \
+	    cut -d "|" -f 9 |
+	    grep -v visited \
 	    >"$OUTPUT_FILE"
 }