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>

Documentation/technical/api-trace2.txt

@@ -493,6 +493,20 @@ about specific error arguments.
 }
 ------------
 
+`"cmd_ancestry"`::
+	This event contains the text command name for the parent (and earlier
+	generations of parents) of the current process, in an array ordered from
+	nearest parent to furthest great-grandparent. It may not be implemented
+	on all platforms.
++
+------------
+{
+	"event":"cmd_ancestry",
+	...
+	"ancestry":["bash","tmux: server","systemd"]
+}
+------------
+
 `"cmd_name"`::
 	This event contains the command name for this git process
 	and the hierarchy of commands from parent git processes.

compat/linux/procinfo.c

@@ -0,0 +1,55 @@
+#include "cache.h"
+
+#include "strbuf.h"
+#include "strvec.h"
+#include "trace2.h"
+
+static void get_ancestry_names(struct strvec *names)
+{
+	/*
+	 * NEEDSWORK: We could gather the entire pstree into an array to match
+	 * functionality with compat/win32/trace2_win32_process_info.c.
+	 * To do so, we may want to examine /proc/<pid>/stat. For now, just
+	 * gather the immediate parent name which is readily accessible from
+	 * /proc/$(getppid())/comm.
+	 */
+	struct strbuf procfs_path = STRBUF_INIT;
+	struct strbuf name = STRBUF_INIT;
+
+	/* try to use procfs if it's present. */
+	strbuf_addf(&procfs_path, "/proc/%d/comm", getppid());
+	if (strbuf_read_file(&name, procfs_path.buf, 0)) {
+		strbuf_release(&procfs_path);
+		strbuf_trim_trailing_newline(&name);
+		strvec_push(names, strbuf_detach(&name, NULL));
+	}
+
+	return;
+	/* NEEDSWORK: add non-procfs-linux implementations here */
+}
+
+void trace2_collect_process_info(enum trace2_process_info_reason reason)
+{
+	if (!trace2_is_enabled())
+		return;
+
+	/* someday we may want to write something extra here, but not today */
+	if (reason == TRACE2_PROCESS_INFO_EXIT)
+		return;
+
+	if (reason == TRACE2_PROCESS_INFO_STARTUP) {
+		/*
+		 * NEEDSWORK: we could do the entire ptree in an array instead,
+		 * see compat/win32/trace2_win32_process_info.c.
+		 */
+		struct strvec names = STRVEC_INIT;
+
+		get_ancestry_names(&names);
+
+		if (names.nr)
+			trace2_cmd_ancestry(names.v);
+		strvec_clear(&names);
+	}
+
+	return;
+}

config.mak.uname

@@ -58,6 +58,8 @@ ifeq ($(uname_S),Linux)
 	FREAD_READS_DIRECTORIES = UnfortunatelyYes
 	BASIC_CFLAGS += -DHAVE_SYSINFO
 	PROCFS_EXECUTABLE_PATH = /proc/self/exe
+	HAVE_PLATFORM_PROCINFO = YesPlease
+	COMPAT_OBJS += compat/linux/procinfo.o
 endif
 ifeq ($(uname_S),GNU/kFreeBSD)
 	HAVE_ALLOCA_H = YesPlease

t/t0210/scrub_normal.perl

@@ -42,6 +42,12 @@
 	# so just omit it for testing purposes.
 	# print "cmd_path _EXE_\n";
     }
+    elsif ($line =~ m/^cmd_ancestry/) {
+	# 'cmd_ancestry' is not implemented everywhere, so for portability's
+	# sake, skip it when parsing normal.
+	#
+	# print "$line";
+    }
     else {
 	print "$line";
     }

t/t0211/scrub_perf.perl

@@ -44,6 +44,11 @@
 	# $tokens[$col_rest] = "_EXE_";
 	goto SKIP_LINE;
     }
+    elsif ($tokens[$col_event] =~ m/cmd_ancestry/) {
+	# 'cmd_ancestry' is platform-specific and not implemented everywhere,
+	# so skip it.
+	goto SKIP_LINE;
+    }
     elsif ($tokens[$col_event] =~ m/child_exit/) {
 	$tokens[$col_rest] =~ s/ pid:\d* / pid:_PID_ /;
     }

t/t0212/parse_events.perl

@@ -132,7 +132,10 @@
 	# just omit it for testing purposes.
 	# $processes->{$sid}->{'path'} = "_EXE_";
     }
-    
+    elsif ($event eq 'cmd_ancestry') {
+	# 'cmd_ancestry' is platform-specific and not implemented everywhere, so
+	# just skip it for testing purposes.
+    }
     elsif ($event eq 'cmd_name') {
 	$processes->{$sid}->{'name'} = $line->{'name'};
 	$processes->{$sid}->{'hierarchy'} = $line->{'hierarchy'};

trace2.c

@@ -260,6 +260,19 @@ void trace2_cmd_path_fl(const char *file, int line, const char *pathname)
 			tgt_j->pfn_command_path_fl(file, line, pathname);
 }
 
+void trace2_cmd_ancestry_fl(const char *file, int line, const char **parent_names)
+{
+	struct tr2_tgt *tgt_j;
+	int j;
+
+	if (!trace2_enabled)
+		return;
+
+	for_each_wanted_builtin (j, tgt_j)
+		if (tgt_j->pfn_command_ancestry_fl)
+			tgt_j->pfn_command_ancestry_fl(file, line, parent_names);
+}
+
 void trace2_cmd_name_fl(const char *file, int line, const char *name)
 {
 	struct tr2_tgt *tgt_j;

trace2.h

@@ -133,6 +133,16 @@ void trace2_cmd_path_fl(const char *file, int line, const char *pathname);
 
 #define trace2_cmd_path(p) trace2_cmd_path_fl(__FILE__, __LINE__, (p))
 
+/*
+ * Emit an 'ancestry' event with the process name of the current process's
+ * parent process.
+ * This gives post-processors a way to determine what invoked the command and
+ * learn more about usage patterns.
+ */
+void trace2_cmd_ancestry_fl(const char *file, int line, const char **parent_names);
+
+#define trace2_cmd_ancestry(v) trace2_cmd_ancestry_fl(__FILE__, __LINE__, (v))
+
 /*
  * Emit a 'cmd_name' event with the canonical name of the command.
  * This gives post-processors a simple field to identify the command

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;

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,

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,

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,