[igt-dev] [PATCH i-g-t v3 1/2] runner: Add support for aborting on network failure

* [igt-dev] [PATCH i-g-t v3 1/2] runner: Add support for aborting on network failure
@ 2019-05-20 10:16 Petri Latvala
  2019-05-20 10:16 ` [igt-dev] [PATCH i-g-t 2/2] HAX: Check all conditions to abort Petri Latvala
                   ` (3 more replies)
  0 siblings, 4 replies; 9+ messages in thread
From: Petri Latvala @ 2019-05-20 10:16 UTC (permalink / raw)
  To: igt-dev; +Cc: Tomi Sarvela, Petri Latvala, Daniel Vetter

If the network goes down while testing, CI tends to interpret that as
the device being down, cutting its power after a while. This causes an
incomplete to an innocent test, increasing noise in the results.

A new flag to --abort-on-monitored-error, "ping", uses liboping to
ping a host configured in .igtrc with one ping after each test
execution and aborts the run if there is no reply in a hardcoded
amount of time.

v2:
 - Use a higher timeout
 - Allow hostname configuration from environment
v3:
 - Use runner_c_args for holding c args for runner
 - Handle runner's meson options in runner/meson.build
 - Instead of one ping with 20 second timeout, ping with 1 second timeout
   for a duration of 20 seconds

Signed-off-by: Petri Latvala <petri.latvala@intel.com>
Cc: Arkadiusz Hiler <arkadiusz.hiler@intel.com>
Cc: Martin Peres <martin.peres@linux.intel.com>
Cc: Tomi Sarvela <tomi.p.sarvela@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
---
 meson_options.txt  |   6 ++
 runner/executor.c  | 150 +++++++++++++++++++++++++++++++++++++++++++++
 runner/meson.build |  14 ++++-
 runner/settings.c  |   4 ++
 runner/settings.h  |   5 +-
 5 files changed, 176 insertions(+), 3 deletions(-)

diff --git a/meson_options.txt b/meson_options.txt
index 888efe56..935f883e 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -58,6 +58,12 @@ option('build_runner',
        choices : ['auto', 'true', 'false'],
        description : 'Build test runner')
 
+option('with_oping',
+       type : 'combo',
+       value : 'auto',
+       choices : ['auto', 'true', 'false'],
+       description : 'Build igt_runner with liboping')
+
 option('use_rpath',
        type : 'boolean',
        value : false,
diff --git a/runner/executor.c b/runner/executor.c
index 7e5fbe8f..c07e53fa 100644
--- a/runner/executor.c
+++ b/runner/executor.c
@@ -1,6 +1,10 @@
 #include <errno.h>
 #include <fcntl.h>
+#include <glib.h>
 #include <linux/watchdog.h>
+#if HAVE_OPING
+#include <oping.h>
+#endif
 #include <signal.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -16,6 +20,7 @@
 #include <time.h>
 #include <unistd.h>
 
+#include "igt_aux.h"
 #include "igt_core.h"
 #include "executor.h"
 #include "output_strings.h"
@@ -108,6 +113,147 @@ static void ping_watchdogs(void)
 	}
 }
 
+#if HAVE_OPING
+static pingobj_t *pingobj = NULL;
+
+static bool load_ping_config_from_file(void)
+{
+	char *key_file_env = NULL;
+	char *key_file_loc = NULL;
+	GError *error = NULL;
+	GKeyFile *key_file = NULL;
+	const char *ping_hostname;
+	int ret;
+
+	/* Determine igt config path */
+	key_file_env = getenv("IGT_CONFIG_PATH");
+	if (key_file_env) {
+		key_file_loc = strdup(key_file_env);
+	} else {
+		asprintf(&key_file_loc, "%s/.igtrc", g_get_home_dir());
+	}
+
+	/* Load igt config file */
+	key_file = g_key_file_new();
+	ret = g_key_file_load_from_file(key_file, key_file_loc,
+					G_KEY_FILE_NONE, &error);
+	free(key_file_loc);
+
+	if (!ret) {
+		g_error_free(error);
+		g_key_file_free(key_file);
+		return false;
+	}
+
+	g_clear_error(&error);
+
+	ping_hostname =
+		g_key_file_get_string(key_file, "DUT",
+				      "PingHostName", &error);
+
+	g_clear_error(&error);
+	g_key_file_free(key_file);
+
+	if (!ping_hostname)
+		return false;
+
+	if (ping_host_add(pingobj, ping_hostname)) {
+		fprintf(stderr,
+			"abort on ping: Cannot use hostname from config file\n");
+		return false;
+	}
+
+	return true;
+}
+
+static bool load_ping_config_from_env(void)
+{
+	const char *ping_hostname;
+
+	ping_hostname = getenv("IGT_PING_HOSTNAME");
+	if (!ping_hostname)
+		return false;
+
+	if (ping_host_add(pingobj, ping_hostname)) {
+		fprintf(stderr,
+			"abort on ping: Cannot use hostname from environment\n");
+		return false;
+	}
+
+	return true;
+}
+
+static bool can_ping(void)
+{
+	/*
+	 * On some hosts, getting network back up after suspend takes
+	 * upwards of 10 seconds. 20 seconds should be enough to see
+	 * if network comes back at all, and hopefully not too long to
+	 * make external monitoring freak out.
+	 */
+	igt_until_timeout(20) {
+		pingobj_iter_t *iter;
+
+		ping_send(pingobj);
+
+		for (iter = ping_iterator_get(pingobj);
+		     iter != NULL;
+		     iter = ping_iterator_next(iter)) {
+			double latency;
+			size_t len = sizeof(latency);
+
+			ping_iterator_get_info(iter,
+					       PING_INFO_LATENCY,
+					       &latency,
+					       &len);
+			if (latency >= 0.0)
+				return true;
+		}
+	}
+
+	return false;
+}
+
+#endif
+
+static void ping_config(void)
+{
+#if HAVE_OPING
+	double timeout = 1.0;
+
+	if (pingobj)
+		return;
+
+	pingobj = ping_construct();
+
+	/* Try env first, then config file */
+	if (!load_ping_config_from_env() && !load_ping_config_from_file()) {
+		fprintf(stderr,
+			"abort on ping: No host to ping configured\n");
+		ping_destroy(pingobj);
+		pingobj = NULL;
+		return;
+	}
+
+	ping_setopt(pingobj, PING_OPT_TIMEOUT, &timeout);
+#endif
+}
+
+static char *handle_ping(void)
+{
+#if HAVE_OPING
+	if (pingobj && !can_ping()) {
+		char *reason;
+
+		asprintf(&reason,
+			 "Ping host did not respond to ping, network down");
+		return reason;
+	}
+#endif
+
+	return NULL;
+}
+
 static char *handle_lockdep(void)
 {
 	const char *header = "Lockdep not active\n\n/proc/lockdep_stats contents:\n";
@@ -197,6 +343,7 @@ static const struct {
 } abort_handlers[] = {
 	{ ABORT_LOCKDEP, handle_lockdep },
 	{ ABORT_TAINT, handle_taint },
+	{ ABORT_PING, handle_ping },
 	{ 0, 0 },
 };
 
@@ -1288,6 +1435,9 @@ bool execute(struct execute_state *state,
 
 	init_watchdogs(settings);
 
+	if (settings->abort_mask & ABORT_PING)
+		ping_config();
+
 	if (!uname(&unamebuf)) {
 		dprintf(unamefd, "%s %s %s %s %s\n",
 			unamebuf.sysname,
diff --git a/runner/meson.build b/runner/meson.build
index b658f1d2..6d60c530 100644
--- a/runner/meson.build
+++ b/runner/meson.build
@@ -1,4 +1,15 @@
 jsonc = dependency('json-c', required: _runner_required)
+runner_deps = [jsonc, glib]
+runner_c_args = []
+
+with_oping = get_option('with_oping')
+if with_oping != 'false'
+	oping = dependency('liboping', required: with_oping == 'true')
+	if oping.found()
+		runner_deps += oping
+		runner_c_args += '-DHAVE_OPING=1'
+	endif
+endif
 
 runnerlib_sources = [ 'settings.c',
 		      'job_list.c',
@@ -21,7 +32,8 @@ if _build_runner and _build_tests and jsonc.found()
 
 	runnerlib = static_library('igt_runner', runnerlib_sources,
 				   include_directories : inc,
-				   dependencies : [jsonc, glib])
+				   c_args : runner_c_args,
+				   dependencies : runner_deps)
 
 	runner = executable('igt_runner', runner_sources,
 			    link_with : runnerlib,
diff --git a/runner/settings.c b/runner/settings.c
index ad38ae8d..b57d1a6a 100644
--- a/runner/settings.c
+++ b/runner/settings.c
@@ -48,6 +48,7 @@ static struct {
 } abort_conditions[] = {
 	{ ABORT_TAINT, "taint" },
 	{ ABORT_LOCKDEP, "lockdep" },
+	{ ABORT_PING, "ping" },
 	{ ABORT_ALL, "all" },
 	{ 0, 0 },
 };
@@ -136,6 +137,9 @@ static const char *usage_str =
 	"                        Possible conditions:\n"
 	"                         lockdep - abort when kernel lockdep has been angered.\n"
 	"                         taint   - abort when kernel becomes fatally tainted.\n"
+	"                         ping    - abort when a host configured in .igtrc or\n"
+	"                                   environment variable IGT_PING_HOSTNAME does\n"
+	"                                   not respond to ping.\n"
 	"                         all     - abort for all of the above.\n"
 	"  -s, --sync            Sync results to disk after every test\n"
 	"  -l {quiet,verbose,dummy}, --log-level {quiet,verbose,dummy}\n"
diff --git a/runner/settings.h b/runner/settings.h
index 0a1ee08d..2b6e65d0 100644
--- a/runner/settings.h
+++ b/runner/settings.h
@@ -15,9 +15,10 @@ enum {
 
 #define ABORT_TAINT   (1 << 0)
 #define ABORT_LOCKDEP (1 << 1)
-#define ABORT_ALL     (ABORT_TAINT | ABORT_LOCKDEP)
+#define ABORT_PING    (1 << 2)
+#define ABORT_ALL     (ABORT_TAINT | ABORT_LOCKDEP | ABORT_PING)
 
-_Static_assert(ABORT_ALL == (ABORT_TAINT | ABORT_LOCKDEP), "ABORT_ALL must be all conditions bitwise or'd");
+_Static_assert(ABORT_ALL == (ABORT_TAINT | ABORT_LOCKDEP | ABORT_PING), "ABORT_ALL must be all conditions bitwise or'd");
 
 struct regex_list {
 	char **regex_strings;
-- 
2.19.1

_______________________________________________
igt-dev mailing list
igt-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/igt-dev

^ permalink raw reply related	[flat|nested] 9+ messages in thread