Improve testing around using SIGKILL (#127)

* Add test for SIGKILL of process
* silent TestProxyManager_RunningEndpoint debug output
* Ref #125

proxy/helpers_test.go

@@ -48,14 +48,18 @@ func getSimpleResponderPath() string {
 	return filepath.Join("..", "build", fmt.Sprintf("simple-responder_%s_%s", goos, goarch))
 }
 
-func getTestSimpleResponderConfig(expectedMessage string) ModelConfig {
+func getTestPort() int {
 	portMutex.Lock()
 	defer portMutex.Unlock()
 
 	port := nextTestPort
 	nextTestPort++
 
-	return getTestSimpleResponderConfigPort(expectedMessage, port)
+	return port
+}
+
+func getTestSimpleResponderConfig(expectedMessage string) ModelConfig {
+	return getTestSimpleResponderConfigPort(expectedMessage, getTestPort())
 }
 
 func getTestSimpleResponderConfigPort(expectedMessage string, port int) ModelConfig {

proxy/process.go

@@ -67,6 +67,9 @@ type Process struct {
 
 	// for managing concurrency limits
 	concurrencyLimitSemaphore chan struct{}
+
+	// stop timeout waiting for graceful shutdown
+	gracefulStopTimeout time.Duration
 }
 
 func NewProcess(ID string, healthCheckTimeout int, config ModelConfig, processLogger *LogMonitor, proxyLogger *LogMonitor) *Process {
@@ -92,6 +95,9 @@ func NewProcess(ID string, healthCheckTimeout int, config ModelConfig, processLo
 
 		// concurrency limit
 		concurrencyLimitSemaphore: make(chan struct{}, concurrentLimit),
+
+		// stop timeout
+		gracefulStopTimeout: 5 * time.Second,
 	}
 }
 
@@ -348,7 +354,7 @@ func (p *Process) StopImmediately() {
 	}
 
 	// stop the process with a graceful exit timeout
-	p.stopCommand(5 * time.Second)
+	p.stopCommand(p.gracefulStopTimeout)
 
 	if curState, err := p.swapState(StateStopping, StateStopped); err != nil {
 		p.proxyLogger.Infof("<%s> Stop() StateStopping -> StateStopped err: %v, current state: %v", p.ID, err, curState)
@@ -361,7 +367,7 @@ func (p *Process) StopImmediately() {
 // the StateShutdown state, it can not be started again.
 func (p *Process) Shutdown() {
 	p.shutdownCancel()
-	p.stopCommand(5 * time.Second)
+	p.stopCommand(p.gracefulStopTimeout)
 	p.state = StateShutdown
 }
 

proxy/process_test.go

@@ -393,3 +393,53 @@ func TestProcess_StopImmediately(t *testing.T) {
 	process.StopImmediately()
 	assert.Equal(t, process.CurrentState(), StateStopped)
 }
+
+// Test that SIGKILL is sent when gracefulStopTimeout is reached and properly terminates
+// the upstream command
+func TestProcess_ForceStopWithKill(t *testing.T) {
+
+	expectedMessage := "test_sigkill"
+	binaryPath := getSimpleResponderPath()
+	port := getTestPort()
+
+	config := ModelConfig{
+		// note --ignore-sig-term which ignores the SIGTERM signal so a SIGKILL must be sent
+		// to force the process to exit
+		Cmd:           fmt.Sprintf("%s --port %d --respond %s --silent --ignore-sig-term", binaryPath, port, expectedMessage),
+		Proxy:         fmt.Sprintf("http://127.0.0.1:%d", port),
+		CheckEndpoint: "/health",
+	}
+
+	process := NewProcess("stop_immediate", 2, config, debugLogger, debugLogger)
+	defer process.Stop()
+
+	// reduce to make testing go faster
+	process.gracefulStopTimeout = time.Second
+
+	err := process.start()
+	assert.Nil(t, err)
+	assert.Equal(t, process.CurrentState(), StateReady)
+
+	waitChan := make(chan struct{})
+	go func() {
+		// slow, but will get killed by StopImmediate
+		req := httptest.NewRequest("GET", "/slow-respond?echo=12345&delay=2s", nil)
+		w := httptest.NewRecorder()
+		process.ProxyRequest(w, req)
+
+		// StatusOK because that was already sent before the kill
+		assert.Equal(t, http.StatusOK, w.Code)
+
+		// unexpected EOF because the kill happened, the "1" is sent before the kill
+		// then the unexpected EOF is sent after the kill
+		assert.Equal(t, "1unexpected EOF\n", w.Body.String())
+		close(waitChan)
+	}()
+
+	<-time.After(time.Millisecond)
+	process.StopImmediately()
+	assert.Equal(t, process.CurrentState(), StateStopped)
+
+	// the request should have been interrupted by SIGKILL
+	<-waitChan
+}

proxy/proxymanager_test.go

@@ -339,7 +339,7 @@ func TestProxyManager_RunningEndpoint(t *testing.T) {
 			"model1": getTestSimpleResponderConfig("model1"),
 			"model2": getTestSimpleResponderConfig("model2"),
 		},
-		LogLevel: "debug",
+		LogLevel: "warn",
 	})
 
 	// Define a helper struct to parse the JSON response.