From 750e9be58c7c245d49d6a7227b972bf0fd8c09ab Mon Sep 17 00:00:00 2001
From: Sverker Eriksson <sverker@erlang.org>
Date: Thu, 14 Feb 2019 18:07:15 +0100
Subject: erts: Avoid heart killing a nicely exiting emulator

Symptom:
Heart kills exiting emulator before is has flushed all ports
and with HEART_KILL_SIGNAL=SIGABRT it may also produce
unnecessary core dumps from doing init:reboot() for example.

Problem:
Heart port is closed together with all the others in handle_reap_ports()
which is detected by heart OS process.

Solution 1:
Leave the heart port alone in handle_reap_ports() and let it be closed
by OS when emulator exists. It doesn't need to be flushed anyway.

Solution 2:
When heart OS process gets EOF on connection let it wait max 5 seconds
for emulator process to self terminate before trying to kill it.
---
 erts/emulator/beam/erl_process.c |  7 +++++++
 erts/etc/common/heart.c          | 38 +++++++++++++++++++++++++-------------
 2 files changed, 32 insertions(+), 13 deletions(-)

diff --git a/erts/emulator/beam/erl_process.c b/erts/emulator/beam/erl_process.c
index ffbfbc4e56..a4f312f101 100644
--- a/erts/emulator/beam/erl_process.c
+++ b/erts/emulator/beam/erl_process.c
@@ -2625,6 +2625,13 @@ handle_reap_ports(ErtsAuxWorkData *awdp, erts_aint32_t aux_work, int waiting)
 
 	    erts_smp_port_lock(prt);
 
+            if (prt->common.u.alive.reg &&
+                prt->common.u.alive.reg->name == am_heart_port) {
+                /* Leave heart port to not get killed before flushing is done*/
+                erts_port_release(prt);
+                continue;
+            }
+
 	    state = erts_atomic32_read_nob(&prt->state);
 	    if (!(state & (ERTS_PORT_SFLGS_INVALID_DRIVER_LOOKUP
 			   | ERTS_PORT_SFLG_HALT))) {
diff --git a/erts/etc/common/heart.c b/erts/etc/common/heart.c
index 8f1e89b638..5967fa2543 100644
--- a/erts/etc/common/heart.c
+++ b/erts/etc/common/heart.c
@@ -500,7 +500,7 @@ message_loop(erlin_fd, erlout_fd)
 
 #if defined(__WIN32__)
 static void 
-kill_old_erlang(void){
+kill_old_erlang(int reason){
     HANDLE erlh;
     DWORD exit_code;
     char* envvar = NULL;
@@ -536,7 +536,8 @@ kill_old_erlang(void){
 }
 #else
 static void 
-kill_old_erlang(void){
+kill_old_erlang(int reason)
+{
     pid_t pid;
     int i, res;
     int sig = SIGKILL;
@@ -546,14 +547,25 @@ kill_old_erlang(void){
     if (envvar && strcmp(envvar, "TRUE") == 0)
       return;
 
-    envvar = get_env(HEART_KILL_SIGNAL);
-    if (envvar && strcmp(envvar, "SIGABRT") == 0) {
-        print_error("kill signal SIGABRT requested");
-        sig = SIGABRT;
-    }
-
     if(heart_beat_kill_pid != 0){
-	pid = (pid_t) heart_beat_kill_pid;
+        pid = (pid_t) heart_beat_kill_pid;
+        if (reason == R_CLOSED) {
+            print_error("Wait 5 seconds for Erlang to terminate nicely");
+            for (i=0; i < 5; ++i) {
+                res = kill(pid, 0); /* check if alive */
+                if (res < 0 && errno == ESRCH)
+                    return;
+                sleep(1);
+            }
+            print_error("Erlang still alive, kill it");
+        }
+
+        envvar = get_env(HEART_KILL_SIGNAL);
+        if (envvar && strcmp(envvar, "SIGABRT") == 0) {
+            print_error("kill signal SIGABRT requested");
+            sig = SIGABRT;
+        }
+
 	res = kill(pid,sig);
 	for(i=0; i < 5 && res == 0; ++i){
 	    sleep(1);
@@ -677,7 +689,7 @@ do_terminate(int erlin_fd, int reason) {
 	    if(!command)
 		print_error("Would reboot. Terminating.");
 	    else {
-		kill_old_erlang();
+		kill_old_erlang(reason);
 		/* High prio combined with system() works badly indeed... */
 		SetPriorityClass(GetCurrentProcess(), NORMAL_PRIORITY_CLASS);
 		win_system(command);
@@ -685,7 +697,7 @@ do_terminate(int erlin_fd, int reason) {
 	    }
 	    free_env_val(command);
 	} else {
-	    kill_old_erlang();
+	    kill_old_erlang(reason);
 	    /* High prio combined with system() works badly indeed... */
 	    SetPriorityClass(GetCurrentProcess(), NORMAL_PRIORITY_CLASS);
 	    win_system(&cmd[0]);
@@ -697,13 +709,13 @@ do_terminate(int erlin_fd, int reason) {
 	    if(!command)
 		print_error("Would reboot. Terminating.");
 	    else {
-		kill_old_erlang();
+		kill_old_erlang(reason);
 		ret = system(command);
 		print_error("Executed \"%s\" -> %d. Terminating.",command, ret);
 	    }
 	    free_env_val(command);
 	} else {
-	    kill_old_erlang();
+	    kill_old_erlang(reason);
 	    ret = system((char*)&cmd[0]);
 	    print_error("Executed \"%s\" -> %d. Terminating.",cmd, ret);
 	}
-- 
cgit v1.2.3