: logging: default disable log forwarding

hyperactor_mesh/src/bootstrap.rs

@@ -99,7 +99,7 @@ declare_attrs! {
         env_name: Some("HYPERACTOR_MESH_ENABLE_LOG_FORWARDING".to_string()),
         py_name: None,
     })
-    pub attr MESH_ENABLE_LOG_FORWARDING: bool = true;
+    pub attr MESH_ENABLE_LOG_FORWARDING: bool = false;
 
     /// When `true`: if stdio is piped, each child's `StreamFwder`
     /// also forwards lines to a host-scoped `FileAppender` managed by
@@ -124,7 +124,7 @@ declare_attrs! {
         env_name: Some("HYPERACTOR_MESH_ENABLE_FILE_CAPTURE".to_string()),
         py_name: None,
     })
-    pub attr MESH_ENABLE_FILE_CAPTURE: bool = true;
+    pub attr MESH_ENABLE_FILE_CAPTURE: bool = false;
 
     /// Maximum number of log lines retained in a proc's stderr/stdout
     /// tail buffer. Used by [`StreamFwder`] when wiring child
@@ -133,7 +133,7 @@ declare_attrs! {
         env_name: Some("HYPERACTOR_MESH_TAIL_LOG_LINES".to_string()),
         py_name: None,
     })
-    pub attr MESH_TAIL_LOG_LINES: usize = 100;
+    pub attr MESH_TAIL_LOG_LINES: usize = 0;
 
     /// If enabled (default), bootstrap child processes install
     /// `PR_SET_PDEATHSIG(SIGKILL)` so the kernel reaps them if the
@@ -3692,6 +3692,10 @@ mod tests {
     #[tokio::test]
     async fn exit_tail_is_attached_and_logged() {
         hyperactor_telemetry::initialize_logging_for_test();
+
+        let lock = hyperactor::config::global::lock();
+        let _guard = lock.override_key(MESH_TAIL_LOG_LINES, 100);
+
         // Spawn a child that writes to stderr then exits 7.
         let mut cmd = Command::new("sh");
         cmd.arg("-c")

hyperactor_mesh/src/v1/host_mesh.rs

@@ -1125,6 +1125,7 @@ mod tests {
 
     use super::*;
     use crate::Bootstrap;
+    use crate::bootstrap::MESH_TAIL_LOG_LINES;
     use crate::resource::Status;
     use crate::v1::ActorMesh;
     use crate::v1::testactor;
@@ -1321,6 +1322,9 @@ mod tests {
     #[tokio::test]
     #[cfg(fbcode_build)]
     async fn test_failing_proc_allocation() {
+        let lock = hyperactor::config::global::lock();
+        let _guard = lock.override_key(MESH_TAIL_LOG_LINES, 100);
+
         let program = crate::testresource::get("monarch/hyperactor_mesh/bootstrap");
 
         let hosts = vec![free_localhost_addr(), free_localhost_addr()];

monarch_hyperactor/src/v1/logging.rs

@@ -310,9 +310,9 @@ impl LoggingMeshClient {
             // re-spawning infra, which we deliberately don't do at
             // runtime.
             (None, true) => {
-                return Err(PyErr::new::<pyo3::exceptions::PyRuntimeError, _>(
-                    "log forwarding disabled by config at startup; cannot enable streaming_to_client",
-                ));
+                // return Err(PyErr::new::<pyo3::exceptions::PyRuntimeError, _>(
+                //     "log forwarding disabled by config at startup; cannot enable streaming_to_client",
+                // ));
             }
         }
 
@@ -592,6 +592,9 @@ mod tests {
                     );
                 }
 
+                /*
+                // Update (SF: 2025, 11, 13): We now ignore stream to client requests if
+                // log forwarding is enabled.
                 // (c) stream_to_client = true when forwarding was
                 //     never spawned -> Err
                 let res = client_ref.set_mode(&py_instance, true, None, 10);
@@ -606,6 +609,7 @@ mod tests {
                         "unexpected err when enabling streaming with no forwarders: {msg}"
                     );
                 }
+                */
             });
 
             drop(client_py); // See note "NOTE ON LIFECYCLE / CLEANUP"

python/monarch/_src/actor/v1/proc_mesh.py

@@ -365,8 +365,8 @@ def rank_tensors(self) -> Dict[str, "Tensor"]:
 
     async def logging_option(
         self,
-        stream_to_client: bool = True,
-        aggregate_window_sec: int | None = 3,
+        stream_to_client: bool = False,
+        aggregate_window_sec: int | None = None,
         level: int = logging.INFO,
     ) -> None:
         """

python/tests/test_allocator.py

@@ -254,9 +254,19 @@ async def test_allocate_failure_message(self) -> None:
             r"exited with code 1: Traceback \(most recent call last\).*",
         ):
             with remote_process_allocator(
-                envs={"MONARCH_ERROR_DURING_BOOTSTRAP_FOR_TESTING": "1"}
+                envs={
+                    "MONARCH_ERROR_DURING_BOOTSTRAP_FOR_TESTING": "1",
+                    "HYPERACTOR_MESH_ENABLE_LOG_FORWARDING": "true",
+                    "HYPERACTOR_MESH_ENABLE_FILE_CAPTURE": "true",
+                    "HYPERACTOR_MESH_TAIL_LOG_LINES": "100",
+                }
             ) as host1, remote_process_allocator(
-                envs={"MONARCH_ERROR_DURING_BOOTSTRAP_FOR_TESTING": "1"}
+                envs={
+                    "MONARCH_ERROR_DURING_BOOTSTRAP_FOR_TESTING": "1",
+                    "HYPERACTOR_MESH_ENABLE_LOG_FORWARDING": "true",
+                    "HYPERACTOR_MESH_ENABLE_FILE_CAPTURE": "true",
+                    "HYPERACTOR_MESH_TAIL_LOG_LINES": "100",
+                }
             ) as host2:
                 allocator = RemoteAllocator(
                     world_id="test_remote_allocator",