Fix "Launching a component with a missing binary can sometimes succeed" (#261)

score/launch_manager/src/daemon/src/process_group_manager/details/graph.cpp

@@ -178,7 +178,7 @@ bool Graph::queueHeadNodes(bool start)
         queueHeadNodesForExecution();
     }
 
-    return (nodes_in_flight_ > 0);
+    return (executing_nodes > 0);
 }
 
 inline uint32_t Graph::countExecutableNodes(bool start)
@@ -223,7 +223,15 @@ inline void Graph::tryQueueNode(const std::shared_ptr<ProcessInfoNode>& node)
         }
         else
         {
-            LM_LOG_WARN() << "Failed to queue node for execution " << push_res.error();
+            // This means the job will never be queued so we'll never get the nodeExecuted() call, we need to call it
+            // here
+            LM_LOG_ERROR() << "Failed to queue node for execution " << push_res.error();
+
+            abort(getLastExecutionError(), ControlClientCode::kSetStateFailed);
+            markNodeInFlight();  // This will be decremented below, avoid it going negative
+            // Also, we need to be careful not to recurse or deadlock here. The below function does not lock any mutex
+            // nor call this function
+            handleNonTransitionExecution(GraphState::kAborting);
             break;
         }
     }

score/launch_manager/src/daemon/src/process_group_manager/details/graph.hpp

@@ -320,7 +320,7 @@ class Graph final {
 
     /// @brief Queue head nodes to start a graph. Return false if there were no head nodes
     /// @param start true if this run of the graph is to start processes, false it it is to stop them
-    /// @return true if one or more head nodes were queued
+    /// @return true if one or more head nodes were found
     bool queueHeadNodes(bool start);
 
     /// @brief Queue the jobs to kick-off a stop process graph

tests/integration/process_wrong_binary_failure/BUILD

@@ -0,0 +1,66 @@
+# *******************************************************************************
+# Copyright (c) 2026 Contributors to the Eclipse Foundation
+#
+# See the NOTICE file(s) distributed with this work for additional
+# information regarding copyright ownership.
+#
+# This program and the accompanying materials are made available under the
+# terms of the Apache License Version 2.0 which is available at
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# SPDX-License-Identifier: Apache-2.0
+# *******************************************************************************
+load("@rules_pkg//pkg:mappings.bzl", "pkg_attributes", "pkg_files")
+load("@rules_pkg//pkg:tar.bzl", "pkg_tar")
+load("//:defs.bzl", "launch_manager_config")
+load("//tests/utils/bazel:integration.bzl", "integration_test")
+
+launch_manager_config(
+    name = "lm_process_wrong_binary_failure_config",
+    config = "//tests/integration/process_wrong_binary_failure:process_wrong_binary_failure.json",
+    flatbuffer_out_dir = "etc",
+)
+
+cc_binary(
+    name = "control_client_mock",
+    srcs = ["control_client_mock.cpp"],
+    deps = [
+        "//score/launch_manager:control_cc",
+        "//score/launch_manager:lifecycle_cc",
+        "//tests/utils/test_helper",
+        "@googletest//:gtest_main",
+    ],
+)
+
+pkg_files(
+    name = "process_wrong_binary_failure_main_files",
+    srcs = [
+        ":control_client_mock",
+        "//score/launch_manager",
+        "//tests/utils/test_helper:verification_process",
+    ],
+    attributes = pkg_attributes(mode = "0755"),
+    prefix = "tests/process_wrong_binary_failure",
+)
+
+pkg_files(
+    name = "process_wrong_binary_failure_etc_files",
+    srcs = [":lm_process_wrong_binary_failure_config"],
+    prefix = "tests/process_wrong_binary_failure",
+)
+
+pkg_tar(
+    name = "process_wrong_binary_failure_binaries",
+    srcs = [
+        ":process_wrong_binary_failure_etc_files",
+        ":process_wrong_binary_failure_main_files",
+    ],
+)
+
+integration_test(
+    name = "process_wrong_binary_failure",
+    srcs = ["process_wrong_binary_failure.py"],
+    tags = ["integration"],
+    test_binaries = ":process_wrong_binary_failure_binaries",
+    deps = ["//tests/utils/testing_utils"],
+)

tests/integration/process_wrong_binary_failure/control_client_mock.cpp

@@ -0,0 +1,52 @@
+/********************************************************************************
+ * Copyright (c) 2026 Contributors to the Eclipse Foundation
+ *
+ * See the NOTICE file(s) distributed with this work for additional
+ * information regarding copyright ownership.
+ *
+ * This program and the accompanying materials are made available under the
+ * terms of the Apache License Version 2.0 which is available at
+ * https://www.apache.org/licenses/LICENSE-2.0
+ *
+ * SPDX-License-Identifier: Apache-2.0
+ ********************************************************************************/
+#include <gtest/gtest.h>
+
+#include "tests/utils/test_helper/test_helper.hpp"
+#include <score/mw/lifecycle/control_client.h>
+#include <score/mw/lifecycle/report_running.h>
+
+TEST(MissingBinaryFailure, ControlClientMock)
+{
+    score::mw::lifecycle::ControlClient client;
+
+    ASSERT_TRUE(check_clean({test_end_location, fallback_file}));
+
+    TEST_STEP("Report kRunning from ControlClientMock")
+    {
+        score::mw::lifecycle::report_running();
+    }
+
+    TEST_STEP("Activate RunTarget containing a component with a missing binary")
+    {
+        score::cpp::stop_token stop_token;
+        auto result = client.ActivateRunTarget("run_target_with_missing_binary").Get(stop_token);
+        EXPECT_FALSE(result.has_value()) << "Activating a run target with a missing binary should fail.";
+    }
+    // Limitation: we cannot wait for the transition to fallback to complete
+    sleep(1);
+    TEST_STEP("Verify fallback run target was activated")
+    {
+        EXPECT_TRUE(std::filesystem::exists(fallback_file)) << "Fallback run target should have been activated";
+    }
+
+    TEST_STEP("Activate RunTarget Off")
+    {
+        client.ActivateRunTarget("Off");
+    }
+}
+
+int main(int argc, char** argv)
+{
+    return TestRunner(__FILE__, TerminationBehavior::kContinue, TerminationNotification::kTestEnd).RunTests();
+}

tests/integration/process_wrong_binary_failure/process_wrong_binary_failure.json

@@ -0,0 +1,127 @@
+{
+    "schema_version": 1,
+    "defaults": {
+        "deployment_config": {
+            "bin_dir": "/tmp/tests/process_wrong_binary_failure",
+            "ready_timeout": 1.0,
+            "shutdown_timeout": 1.0,
+            "ready_recovery_action": {
+                "restart": {
+                    "number_of_attempts": 0
+                }
+            },
+            "recovery_action": {
+                "switch_run_target": {
+                    "run_target": "fallback_run_target"
+                }
+            },
+            "environmental_variables": {
+                "LD_LIBRARY_PATH": "/opt/lib"
+            },
+            "sandbox": {
+                "uid": 0,
+                "gid": 0,
+                "scheduling_policy": "SCHED_OTHER",
+                "scheduling_priority": 0
+            }
+        },
+        "component_properties": {
+            "application_profile": {
+                "application_type": "Reporting",
+                "is_self_terminating": true,
+                "alive_supervision": {
+                    "reporting_cycle": 0.1,
+                    "min_indications": 1,
+                    "max_indications": 3,
+                    "failed_cycles_tolerance": 1
+                }
+            },
+            "ready_condition": {
+                "process_state": "Running"
+            }
+        }
+    },
+    "components": {
+        "control_client_mock": {
+            "component_properties": {
+                "binary_name": "control_client_mock",
+                "application_profile": {
+                    "application_type": "State_Manager",
+                    "alive_supervision": {
+                        "min_indications": 0
+                    }
+                }
+            },
+            "deployment_config": {
+                "ready_timeout": 1.0,
+                "shutdown_timeout": 1.0,
+                "environmental_variables": {
+                    "PROCESSIDENTIFIER": "control_client_mock"
+                }
+            }
+        },
+        "component_with_missing_binary": {
+            "component_properties": {
+                "binary_name": "abc_complex_reporting_process",
+                "process_arguments": [
+                    "1500.0"
+                ]
+            },
+            "deployment_config": {
+                "ready_timeout": 1.0,
+                "shutdown_timeout": 1.0,
+                "environmental_variables": {
+                    "PROCESSIDENTIFIER": "component_with_missing_binary"
+                }
+            }
+        },
+        "verification_component": {
+            "component_properties": {
+                "binary_name": "verification_process",
+                "application_profile": {
+                    "application_type": "Native",
+                    "is_self_terminating": true
+                },
+                "ready_condition": {
+                    "process_state": "Terminated"
+                }
+            }
+        }
+    },
+    "run_targets": {
+        "Startup": {
+            "depends_on": [
+                "control_client_mock"
+            ],
+            "recovery_action": {
+                "switch_run_target": {
+                    "run_target": "fallback_run_target"
+                }
+            }
+        },
+        "run_target_with_missing_binary": {
+            "depends_on": [
+                "control_client_mock",
+                "component_with_missing_binary"
+            ],
+            "recovery_action": {
+                "switch_run_target": {
+                    "run_target": "fallback_run_target"
+                }
+            }
+        },
+        "Off": {
+            "depends_on": []
+        }
+    },
+    "initial_run_target": "Startup",
+    "alive_supervision": {
+        "evaluation_cycle": 0.05
+    },
+    "fallback_run_target": {
+        "depends_on": [
+            "control_client_mock",
+            "verification_component"
+        ]
+    }
+}

tests/integration/process_wrong_binary_failure/process_wrong_binary_failure.py

@@ -0,0 +1,40 @@
+# *******************************************************************************
+# Copyright (c) 2026 Contributors to the Eclipse Foundation
+#
+# See the NOTICE file(s) distributed with this work for additional
+# information regarding copyright ownership.
+#
+# This program and the accompanying materials are made available under the
+# terms of the Apache License Version 2.0 which is available at
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# SPDX-License-Identifier: Apache-2.0
+# *******************************************************************************
+from tests.utils.testing_utils.run_until_file_deployed import run_until_file_deployed
+from tests.utils.testing_utils.setup_test import setup_test
+from tests.utils.testing_utils.test_results import assert_test_results
+from attribute_plugin import add_test_properties
+
+
+@add_test_properties(
+    partially_verifies=[],
+    test_type="interface-test",
+    derivation_technique="error-guessing",
+)
+def test_process_wrong_binary_failure(
+    target, setup_test, assert_test_results, remote_test_dir
+):
+    """
+    Objective: Verifies that activating a run target containing a component whose binary does not exist
+    results in a failure and triggers the configured recovery action (switch to fallback run target).
+    """
+
+    run_until_file_deployed(
+        target=target,
+        binary_path=str(remote_test_dir / "launch_manager"),
+        file_path=remote_test_dir.parent / "test_end",
+        cwd=str(remote_test_dir),
+        timeout_s=6,
+    )
+
+    assert_test_results({"control_client_mock.xml"})