Merge branch 'js/trace2-cap-max-output-files'

The trace2 output, when sending them to files in a designated
directory, can populate the directory with too many files; a
mechanism is introduced to set the maximum number of files and
discard further logs when the maximum is reached.

* js/trace2-cap-max-output-files:
  trace2: write discard message to sentinel files
  trace2: discard new traces if target directory has too many files
  docs: clarify trace2 version invariants
  docs: mention trace2 target-dir mode in git-config

Author: gitster

Documentation/config/trace2.txt

@@ -54,3 +54,9 @@ trace2.destinationDebug::
 	By default, these errors are suppressed and tracing is
 	silently disabled.  May be overridden by the
 	`GIT_TRACE2_DST_DEBUG` environment variable.
+
+trace2.maxFiles::
+	Integer.  When writing trace files to a target directory, do not
+	write additional traces if we would exceed this many files. Instead,
+	write a sentinel file that will block further tracing to this
+	directory. Defaults to 0, which disables this check.

Documentation/technical/api-trace2.txt

@@ -128,7 +128,7 @@ yields
 
 ------------
 $ cat ~/log.event
-{"event":"version","sid":"sid":"20190408T191610.507018Z-H9b68c35f-P000059a8","thread":"main","time":"2019-01-16T17:28:42.620713Z","file":"common-main.c","line":38,"evt":"1","exe":"2.20.1.155.g426c96fcdb"}
+{"event":"version","sid":"sid":"20190408T191610.507018Z-H9b68c35f-P000059a8","thread":"main","time":"2019-01-16T17:28:42.620713Z","file":"common-main.c","line":38,"evt":"2","exe":"2.20.1.155.g426c96fcdb"}
 {"event":"start","sid":"20190408T191610.507018Z-H9b68c35f-P000059a8","thread":"main","time":"2019-01-16T17:28:42.621027Z","file":"common-main.c","line":39,"t_abs":0.001173,"argv":["git","version"]}
 {"event":"cmd_name","sid":"20190408T191610.507018Z-H9b68c35f-P000059a8","thread":"main","time":"2019-01-16T17:28:42.621122Z","file":"git.c","line":432,"name":"version","hierarchy":"version"}
 {"event":"exit","sid":"20190408T191610.507018Z-H9b68c35f-P000059a8","thread":"main","time":"2019-01-16T17:28:42.621236Z","file":"git.c","line":662,"t_abs":0.001227,"code":0}
@@ -142,10 +142,9 @@ system or global config value to one of the following:
 
 include::../trace2-target-values.txt[]
 
-If the target already exists and is a directory, the traces will be
-written to files (one per process) underneath the given directory. They
-will be named according to the last component of the SID (optionally
-followed by a counter to avoid filename collisions).
+When trace files are written to a target directory, they will be named according
+to the last component of the SID (optionally followed by a counter to avoid
+filename collisions).
 
 == Trace2 API
 
@@ -605,17 +604,35 @@ only present on the "start" and "atexit" events.
 ==== Event-Specific Key/Value Pairs
 
 `"version"`::
-	This event gives the version of the executable and the EVENT format.
+	This event gives the version of the executable and the EVENT format. It
+	should always be the first event in a trace session. The EVENT format
+	version will be incremented if new event types are added, if existing
+	fields are removed, or if there are significant changes in
+	interpretation of existing events or fields. Smaller changes, such as
+	adding a new field to an existing event, will not require an increment
+	to the EVENT format version.
 +
 ------------
 {
 	"event":"version",
 	...
-	"evt":"1",		       # EVENT format version
+	"evt":"2",		       # EVENT format version
 	"exe":"2.20.1.155.g426c96fcdb" # git version
 }
 ------------
 
+`"discard"`::
+	This event is written to the git-trace2-discard sentinel file if there
+	are too many files in the target trace directory (see the
+	trace2.maxFiles config option).
++
+------------
+{
+	"event":"discard",
+	...
+}
+------------
+
 `"start"`::
 	This event contains the complete argv received by main().
 +

Documentation/trace2-target-values.txt

@@ -2,7 +2,9 @@
 * `0` or `false` - Disables the target.
 * `1` or `true` - Writes to `STDERR`.
 * `[2-9]` - Writes to the already opened file descriptor.
-* `<absolute-pathname>` - Writes to the file in append mode.
+* `<absolute-pathname>` - Writes to the file in append mode. If the target
+already exists and is a directory, the traces will be written to files (one
+per process) underneath the given directory.
 * `af_unix:[<socket_type>:]<absolute-pathname>` - Write to a
 Unix DomainSocket (on platforms that support them).  Socket
 type can be either `stream` or `dgram`; if omitted Git will

t/t0212-trace2-event.sh

@@ -265,4 +265,23 @@ test_expect_success JSON_PP 'using global config, event stream, error event' '
 	test_cmp expect actual
 '
 
+test_expect_success 'discard traces when there are too many files' '
+	mkdir trace_target_dir &&
+	test_when_finished "rm -r trace_target_dir" &&
+	(
+		GIT_TRACE2_MAX_FILES=5 &&
+		export GIT_TRACE2_MAX_FILES &&
+		cd trace_target_dir &&
+		test_seq $GIT_TRACE2_MAX_FILES >../expected_filenames.txt &&
+		xargs touch <../expected_filenames.txt &&
+		cd .. &&
+		GIT_TRACE2_EVENT="$(pwd)/trace_target_dir" test-tool trace2 001return 0
+	) &&
+	echo git-trace2-discard >>expected_filenames.txt &&
+	ls trace_target_dir >ls_output.txt &&
+	test_cmp expected_filenames.txt ls_output.txt &&
+	head -n1 trace_target_dir/git-trace2-discard | grep \"event\":\"version\" &&
+	head -n2 trace_target_dir/git-trace2-discard | tail -n1 | grep \"event\":\"too_many_files\"
+'
+
 test_done

trace2/tr2_dst.c

@@ -8,6 +8,19 @@
  */
 #define MAX_AUTO_ATTEMPTS 10
 
+/*
+ * Sentinel file used to detect when we should discard new traces to avoid
+ * writing too many trace files to a directory.
+ */
+#define DISCARD_SENTINEL_NAME "git-trace2-discard"
+
+/*
+ * When set to zero, disables directory file count checks. Otherwise, controls
+ * how many files we can write to a directory before entering discard mode.
+ * This can be overridden via the TR2_SYSENV_MAX_FILES setting.
+ */
+static int tr2env_max_files = 0;
+
 static int tr2_dst_want_warning(void)
 {
 	static int tr2env_dst_debug = -1;
@@ -32,9 +45,75 @@ void tr2_dst_trace_disable(struct tr2_dst *dst)
 	dst->need_close = 0;
 }
 
+/*
+ * Check to make sure we're not overloading the target directory with too many
+ * files. First get the threshold (if present) from the config or envvar. If
+ * it's zero or unset, disable this check. Next check for the presence of a
+ * sentinel file, then check file count.
+ *
+ * Returns 0 if tracing should proceed as normal. Returns 1 if the sentinel file
+ * already exists, which means tracing should be disabled. Returns -1 if there
+ * are too many files but there was no sentinel file, which means we have
+ * created and should write traces to the sentinel file.
+ *
+ * We expect that some trace processing system is gradually collecting files
+ * from the target directory; after it removes the sentinel file we'll start
+ * writing traces again.
+ */
+static int tr2_dst_too_many_files(struct tr2_dst *dst, const char *tgt_prefix)
+{
+	int file_count = 0, max_files = 0, ret = 0;
+	const char *max_files_var;
+	DIR *dirp;
+	struct strbuf path = STRBUF_INIT, sentinel_path = STRBUF_INIT;
+	struct stat statbuf;
+
+	/* Get the config or envvar and decide if we should continue this check */
+	max_files_var = tr2_sysenv_get(TR2_SYSENV_MAX_FILES);
+	if (max_files_var && *max_files_var && ((max_files = atoi(max_files_var)) >= 0))
+		tr2env_max_files = max_files;
+
+	if (!tr2env_max_files) {
+		ret = 0;
+		goto cleanup;
+	}
+
+	strbuf_addstr(&path, tgt_prefix);
+	if (!is_dir_sep(path.buf[path.len - 1])) {
+		strbuf_addch(&path, '/');
+	}
+
+	/* check sentinel */
+	strbuf_addbuf(&sentinel_path, &path);
+	strbuf_addstr(&sentinel_path, DISCARD_SENTINEL_NAME);
+	if (!stat(sentinel_path.buf, &statbuf)) {
+		ret = 1;
+		goto cleanup;
+	}
+
+	/* check file count */
+	dirp = opendir(path.buf);
+	while (file_count < tr2env_max_files && dirp && readdir(dirp))
+		file_count++;
+	if (dirp)
+		closedir(dirp);
+
+	if (file_count >= tr2env_max_files) {
+		dst->too_many_files = 1;
+		dst->fd = open(sentinel_path.buf, O_WRONLY | O_CREAT | O_EXCL, 0666);
+		ret = -1;
+		goto cleanup;
+	}
+
+cleanup:
+	strbuf_release(&path);
+	strbuf_release(&sentinel_path);
+	return ret;
+}
+
 static int tr2_dst_try_auto_path(struct tr2_dst *dst, const char *tgt_prefix)
 {
-	int fd;
+	int too_many_files;
 	const char *last_slash, *sid = tr2_sid_get();
 	struct strbuf path = STRBUF_INIT;
 	size_t base_path_len;
@@ -50,18 +129,29 @@ static int tr2_dst_try_auto_path(struct tr2_dst *dst, const char *tgt_prefix)
 	strbuf_addstr(&path, sid);
 	base_path_len = path.len;
 
-	for (attempt_count = 0; attempt_count < MAX_AUTO_ATTEMPTS; attempt_count++) {
-		if (attempt_count > 0) {
-			strbuf_setlen(&path, base_path_len);
-			strbuf_addf(&path, ".%d", attempt_count);
+	too_many_files = tr2_dst_too_many_files(dst, tgt_prefix);
+	if (!too_many_files) {
+		for (attempt_count = 0; attempt_count < MAX_AUTO_ATTEMPTS; attempt_count++) {
+			if (attempt_count > 0) {
+				strbuf_setlen(&path, base_path_len);
+				strbuf_addf(&path, ".%d", attempt_count);
+			}
+
+			dst->fd = open(path.buf, O_WRONLY | O_CREAT | O_EXCL, 0666);
+			if (dst->fd != -1)
+				break;
 		}
-
-		fd = open(path.buf, O_WRONLY | O_CREAT | O_EXCL, 0666);
-		if (fd != -1)
-			break;
+	} else if (too_many_files == 1) {
+		strbuf_release(&path);
+		if (tr2_dst_want_warning())
+			warning("trace2: not opening %s trace file due to too "
+				"many files in target directory %s",
+				tr2_sysenv_display_name(dst->sysenv_var),
+				tgt_prefix);
+		return 0;
 	}
 
-	if (fd == -1) {
+	if (dst->fd == -1) {
 		if (tr2_dst_want_warning())
 			warning("trace2: could not open '%.*s' for '%s' tracing: %s",
 				(int) base_path_len, path.buf,
@@ -75,7 +165,6 @@ static int tr2_dst_try_auto_path(struct tr2_dst *dst, const char *tgt_prefix)
 
 	strbuf_release(&path);
 
-	dst->fd = fd;
 	dst->need_close = 1;
 	dst->initialized = 1;
 

trace2/tr2_dst.h

@@ -9,6 +9,7 @@ struct tr2_dst {
 	int fd;
 	unsigned int initialized : 1;
 	unsigned int need_close : 1;
+	unsigned int too_many_files : 1;
 };
 
 /*

trace2/tr2_sysenv.c

@@ -49,6 +49,9 @@ static struct tr2_sysenv_entry tr2_sysenv_settings[] = {
 				       "trace2.perftarget" },
 	[TR2_SYSENV_PERF_BRIEF]    = { "GIT_TRACE2_PERF_BRIEF",
 				       "trace2.perfbrief" },
+
+	[TR2_SYSENV_MAX_FILES]     = { "GIT_TRACE2_MAX_FILES",
+				       "trace2.maxfiles" },
 };
 /* clang-format on */
 

trace2/tr2_sysenv.h

@@ -24,6 +24,8 @@ enum tr2_sysenv_variable {
 	TR2_SYSENV_PERF,
 	TR2_SYSENV_PERF_BRIEF,
 
+	TR2_SYSENV_MAX_FILES,
+
 	TR2_SYSENV_MUST_BE_LAST
 };
 

trace2/tr2_tgt_event.c

@@ -10,16 +10,17 @@
 #include "trace2/tr2_tgt.h"
 #include "trace2/tr2_tls.h"
 
-static struct tr2_dst tr2dst_event = { TR2_SYSENV_EVENT, 0, 0, 0 };
+static struct tr2_dst tr2dst_event = { TR2_SYSENV_EVENT, 0, 0, 0, 0 };
 
 /*
- * The version number of the JSON data generated by the EVENT target
- * in this source file.  Update this if you make a significant change
- * to the JSON fields or message structure.  You probably do not need
- * to update this if you just add another call to one of the existing
- * TRACE2 API methods.
+ * The version number of the JSON data generated by the EVENT target in this
+ * source file. The version should be incremented if new event types are added,
+ * if existing fields are removed, or if there are significant changes in
+ * interpretation of existing events or fields. Smaller changes, such as adding
+ * a new field to an existing event, do not require an increment to the EVENT
+ * format version.
  */
-#define TR2_EVENT_VERSION "1"
+#define TR2_EVENT_VERSION "2"
 
 /*
  * Region nesting limit for messages written to the event target.
@@ -107,6 +108,19 @@ static void event_fmt_prepare(const char *event_name, const char *file,
 		jw_object_intmax(jw, "repo", repo->trace2_repo_id);
 }
 
+static void fn_too_many_files_fl(const char *file, int line)
+{
+	const char *event_name = "too_many_files";
+	struct json_writer jw = JSON_WRITER_INIT;
+
+	jw_object_begin(&jw, 0);
+	event_fmt_prepare(event_name, file, line, NULL, &jw);
+	jw_end(&jw);
+
+	tr2_dst_write_line(&tr2dst_event, &jw.json);
+	jw_release(&jw);
+}
+
 static void fn_version_fl(const char *file, int line)
 {
 	const char *event_name = "version";
@@ -120,6 +134,9 @@ static void fn_version_fl(const char *file, int line)
 
 	tr2_dst_write_line(&tr2dst_event, &jw.json);
 	jw_release(&jw);
+
+	if (tr2dst_event.too_many_files)
+		fn_too_many_files_fl(file, line);
 }
 
 static void fn_start_fl(const char *file, int line,

trace2/tr2_tgt_normal.c

@@ -9,7 +9,7 @@
 #include "trace2/tr2_tgt.h"
 #include "trace2/tr2_tls.h"
 
-static struct tr2_dst tr2dst_normal = { TR2_SYSENV_NORMAL, 0, 0, 0 };
+static struct tr2_dst tr2dst_normal = { TR2_SYSENV_NORMAL, 0, 0, 0, 0 };
 
 /*
  * Use the TR2_SYSENV_NORMAL_BRIEF setting to omit the "<time> <file>:<line>"

trace2/tr2_tgt_perf.c

@@ -11,7 +11,7 @@
 #include "trace2/tr2_tgt.h"
 #include "trace2/tr2_tls.h"
 
-static struct tr2_dst tr2dst_perf = { TR2_SYSENV_PERF, 0, 0, 0 };
+static struct tr2_dst tr2dst_perf = { TR2_SYSENV_PERF, 0, 0, 0, 0 };
 
 /*
  * Use TR2_SYSENV_PERF_BRIEF to omit the "<time> <file>:<line>"