tr2: log parent process name

It can be useful to tell who invoked Git - was it invoked manually by a
user via CLI or script? By an IDE?  In some cases - like 'repo' tool -
we can influence the source code and set the GIT_TRACE2_PARENT_SID
environment variable from the caller process. In 'repo''s case, that
parent SID is manipulated to include the string "repo", which means we
can positively identify when Git was invoked by 'repo' tool. However,
identifying parents that way requires both that we know which tools
invoke Git and that we have the ability to modify the source code of
those tools. It cannot scale to keep up with the various IDEs and
wrappers which use Git, most of which we don't know about. Learning
which tools and wrappers invoke Git, and how, would give us insight to
decide where to improve Git's usability and performance.

Unfortunately, there's no cross-platform reliable way to gather the name
of the parent process. If procfs is present, we can use that; otherwise
we will need to discover the name another way. However, the process ID
should be sufficient to look up the process name on most platforms, so
that code may be shareable.

Git for Windows gathers similar information and logs it as a "data_json"
event. However, since "data_json" has a variable format, it is difficult
to parse effectively in some languages; instead, let's pursue a
dedicated "cmd_ancestry" event to record information about the ancestry
of the current process and a consistent, parseable way.

Git for Windows also gathers information about more than one generation
of parent. In Linux further ancestry info can be gathered with procfs,
but it's unwieldy to do so. In the interest of later moving Git for
Windows ancestry logging to the 'cmd_ancestry' event, and in the
interest of later adding more ancestry to the Linux implementation - or
of adding this functionality to other platforms which have an easier
time walking the process tree - let's make 'cmd_ancestry' accept an
array of parentage.

Signed-off-by: Emily Shaffer <emilyshaffer@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

4 files changed, 59 insertions, 0 deletions

diff --git a/trace2/tr2_tgt.h b/trace2/tr2_tgt.h
index 7b90469212..1f66fd6573 100644
--- a/trace2/tr2_tgt.h
+++ b/trace2/tr2_tgt.h
@@ -27,6 +27,8 @@ typedef void(tr2_tgt_evt_error_va_fl_t)(const char *file, int line,
 
 typedef void(tr2_tgt_evt_command_path_fl_t)(const char *file, int line,
 					    const char *command_path);
+typedef void(tr2_tgt_evt_command_ancestry_fl_t)(const char *file, int line,
+						const char **parent_names);
 typedef void(tr2_tgt_evt_command_name_fl_t)(const char *file, int line,
 					    const char *name,
 					    const char *hierarchy);
@@ -108,6 +110,7 @@ struct tr2_tgt {
 	tr2_tgt_evt_atexit_t                    *pfn_atexit;
 	tr2_tgt_evt_error_va_fl_t               *pfn_error_va_fl;
 	tr2_tgt_evt_command_path_fl_t           *pfn_command_path_fl;
+	tr2_tgt_evt_command_ancestry_fl_t	*pfn_command_ancestry_fl;
 	tr2_tgt_evt_command_name_fl_t           *pfn_command_name_fl;
 	tr2_tgt_evt_command_mode_fl_t           *pfn_command_mode_fl;
 	tr2_tgt_evt_alias_fl_t                  *pfn_alias_fl;
diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c
index 6353e8ad91..578a9a5287 100644
--- a/trace2/tr2_tgt_event.c
+++ b/trace2/tr2_tgt_event.c
@@ -261,6 +261,26 @@ static void fn_command_path_fl(const char *file, int line, const char *pathname)
 	jw_release(&jw);
 }
 
+static void fn_command_ancestry_fl(const char *file, int line, const char **parent_names)
+{
+	const char *event_name = "cmd_ancestry";
+	const char *parent_name = NULL;
+	struct json_writer jw = JSON_WRITER_INIT;
+
+	jw_object_begin(&jw, 0);
+	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	jw_object_inline_begin_array(&jw, "ancestry");
+
+	while ((parent_name = *parent_names++))
+		jw_array_string(&jw, parent_name);
+
+	jw_end(&jw); /* 'ancestry' array */
+	jw_end(&jw); /* event object */
+
+	tr2_dst_write_line(&tr2dst_event, &jw.json);
+	jw_release(&jw);
+}
+
 static void fn_command_name_fl(const char *file, int line, const char *name,
 			       const char *hierarchy)
 {
@@ -584,6 +604,7 @@ struct tr2_tgt tr2_tgt_event = {
 	fn_atexit,
 	fn_error_va_fl,
 	fn_command_path_fl,
+	fn_command_ancestry_fl,
 	fn_command_name_fl,
 	fn_command_mode_fl,
 	fn_alias_fl,
diff --git a/trace2/tr2_tgt_normal.c b/trace2/tr2_tgt_normal.c
index 31b602c171..a5751c8864 100644
--- a/trace2/tr2_tgt_normal.c
+++ b/trace2/tr2_tgt_normal.c
@@ -160,6 +160,24 @@ static void fn_command_path_fl(const char *file, int line, const char *pathname)
 	strbuf_release(&buf_payload);
 }
 
+static void fn_command_ancestry_fl(const char *file, int line, const char **parent_names)
+{
+	const char *parent_name = NULL;
+	struct strbuf buf_payload = STRBUF_INIT;
+
+	/* cmd_ancestry parent <- grandparent <- great-grandparent */
+	strbuf_addstr(&buf_payload, "cmd_ancestry ");
+	while ((parent_name = *parent_names++)) {
+		strbuf_addstr(&buf_payload, parent_name);
+		/* if we'll write another one after this, add a delimiter */
+		if (parent_names && *parent_names)
+			strbuf_addstr(&buf_payload, " <- ");
+	}
+
+	normal_io_write_fl(file, line, &buf_payload);
+	strbuf_release(&buf_payload);
+}
+
 static void fn_command_name_fl(const char *file, int line, const char *name,
 			       const char *hierarchy)
 {
@@ -306,6 +324,7 @@ struct tr2_tgt tr2_tgt_normal = {
 	fn_atexit,
 	fn_error_va_fl,
 	fn_command_path_fl,
+	fn_command_ancestry_fl,
 	fn_command_name_fl,
 	fn_command_mode_fl,
 	fn_alias_fl,
diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c
index a8018f18cc..af4d65a0a5 100644
--- a/trace2/tr2_tgt_perf.c
+++ b/trace2/tr2_tgt_perf.c
@@ -253,6 +253,21 @@ static void fn_command_path_fl(const char *file, int line, const char *pathname)
 	strbuf_release(&buf_payload);
 }
 
+static void fn_command_ancestry_fl(const char *file, int line, const char **parent_names)
+{
+	const char *event_name = "cmd_ancestry";
+	struct strbuf buf_payload = STRBUF_INIT;
+
+	strbuf_addstr(&buf_payload, "ancestry:[");
+	/* It's not an argv but the rules are basically the same. */
+	sq_append_quote_argv_pretty(&buf_payload, parent_names);
+	strbuf_addch(&buf_payload, ']');
+
+	perf_io_write_fl(file, line, event_name, NULL, NULL, NULL, NULL,
+			 &buf_payload);
+	strbuf_release(&buf_payload);
+}
+
 static void fn_command_name_fl(const char *file, int line, const char *name,
 			       const char *hierarchy)
 {
@@ -532,6 +547,7 @@ struct tr2_tgt tr2_tgt_perf = {
 	fn_atexit,
 	fn_error_va_fl,
 	fn_command_path_fl,
+	fn_command_ancestry_fl,
 	fn_command_name_fl,
 	fn_command_mode_fl,
 	fn_alias_fl,