[igt-dev] [PATCH i-g-t 1/2] runner: Introduce a way to stop testing without marking tests incomplete

[Petri Latvala]

Killing igt_runner with SIGHUP will now still kill the currently
running test, but it will mark that test as being "notrun" instead of
"incomplete". This allows for external tools to interrupt the testing
without messing the results.

Incidentally, Intel CI's testing procedures occasionally falsely
determine that the machine being tested is unreachable and as its next
step, will ssh in and issue a reboot in preparation for the next round
of testing, causing igt_runner to be killed with a SIGHUP...

v2:
 - Fix typo SIGUP -> SIGHUP
 - Make runner print that a graceful exit will be done
 - Explain the code flow regarding handling of signals to the runner process
 - Use GRACEFUL_EXITCODE instead of -SIGHUP directly

Signed-off-by: Petri Latvala <petri.latvala at intel.com>
Cc: Tomi Sarvela <tomi.p.sarvela at intel.com>
Cc: Arkadiusz Hiler <arek at hiler.eu>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
---
 runner/executor.c  | 31 +++++++++++++++++++++++++++++++
 runner/resultgen.c | 10 +++++++---
 2 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/runner/executor.c b/runner/executor.c
index c1a0545a..3ca2d20a 100644
--- a/runner/executor.c
+++ b/runner/executor.c
@@ -1008,6 +1008,37 @@ static int monitor_output(pid_t child,
 					     get_cmdline(siginfo.ssi_pid, comm, sizeof(comm)),
 					     siginfo.ssi_pid,
 					     strsignal(siginfo.ssi_signo));
+
+					if (siginfo.ssi_signo == SIGHUP) {
+						/*
+						 * If taken down with
+						 * SIGHUP, arrange the
+						 * current test to be
+						 * marked as notrun
+						 * instead of
+						 * incomplete. For
+						 * other signals we
+						 * don't need to do
+						 * anything, the lack
+						 * of a completion
+						 * marker of any kind
+						 * in the logs will
+						 * mark those tests as
+						 * incomplete. Note
+						 * that since we set
+						 * 'aborting' to true
+						 * we're going to skip
+						 * all other journal
+						 * writes later.
+						 */
+
+						outf("Exiting gracefully, currently running test will have a 'notrun' result\n");
+						dprintf(outputs[_F_JOURNAL], "%s%d (%.3fs)\n",
+							EXECUTOR_EXIT,
+							-SIGHUP, 0.0);
+						if (settings->sync)
+							fdatasync(outputs[_F_JOURNAL]);
+					}
 				}
 
 				aborting = true;
diff --git a/runner/resultgen.c b/runner/resultgen.c
index 46007803..8d0c6249 100644
--- a/runner/resultgen.c
+++ b/runner/resultgen.c
@@ -17,11 +17,13 @@
 #include "executor.h"
 #include "output_strings.h"
 
-#define INCOMPLETE_EXITCODE -1
+#define INCOMPLETE_EXITCODE -1234
+#define GRACEFUL_EXITCODE -SIGHUP
 
 _Static_assert(INCOMPLETE_EXITCODE != IGT_EXIT_SKIP, "exit code clash");
 _Static_assert(INCOMPLETE_EXITCODE != IGT_EXIT_SUCCESS, "exit code clash");
 _Static_assert(INCOMPLETE_EXITCODE != IGT_EXIT_INVALID, "exit code clash");
+_Static_assert(INCOMPLETE_EXITCODE != GRACEFUL_EXITCODE, "exit code clash");
 
 struct subtest
 {
@@ -1106,6 +1108,8 @@ static const char *result_from_exitcode(int exitcode)
 		return "abort";
 	case INCOMPLETE_EXITCODE:
 		return "incomplete";
+	case GRACEFUL_EXITCODE:
+		return "notrun";
 	default:
 		return "fail";
 	}
@@ -1180,7 +1184,7 @@ static void fill_from_journal(int fd,
 		}
 	}
 
-	if (subtests->size && exitcode == IGT_EXIT_ABORT) {
+	if (subtests->size && (exitcode == IGT_EXIT_ABORT || exitcode == GRACEFUL_EXITCODE)) {
 		char *last_subtest = subtests->subs[subtests->size - 1].name;
 		char subtest_piglit_name[256];
 		struct json_object *subtest_obj;
@@ -1188,7 +1192,7 @@ static void fill_from_journal(int fd,
 		generate_piglit_name(entry->binary, last_subtest, subtest_piglit_name, sizeof(subtest_piglit_name));
 		subtest_obj = get_or_create_json_object(tests, subtest_piglit_name);
 
-		set_result(subtest_obj, "abort");
+		set_result(subtest_obj, exitcode == IGT_EXIT_ABORT ? "abort" : "notrun");
 	}
 
 	if (subtests->size == 0) {
-- 
2.29.2