mgr, qa: clarify module checks in DaemonServer

The current check groups modules not being
enabled with failing to initialize. In this commit,
we reorder the checks:

1: Screen for a module being enabled. If it's not,
   issue an EOPNOTSUPP with instructions on how
   to enable it.

2. Screen for if a module is active. If a module
   is enabled, then the cluster expects it to
   be active to support commands. If the module
   took too long to initialize though, we will
   catch this and issue an ETIMEDOUT error with
   a link for troubleshooting.

Now, these two separate issues are not grouped
together, and they are checked in the right order.

Fixes: https://tracker.ceph.com/issues/71631
Signed-off-by: Laura Flores <lflores@ibm.com>

diff --git a/qa/workunits/mgr/test_mgr_module_loading_time.sh b/qa/workunits/mgr/test_mgr_module_loading_time.sh
index 0f7cccf2515552355c93f023d0915689ae80226c..9901e73ec29ca58c1a33dc98a84b53441390b008 100755 (executable)
--- a/qa/workunits/mgr/test_mgr_module_loading_time.sh
+++ b/qa/workunits/mgr/test_mgr_module_loading_time.sh
@@ -136,7 +136,7 @@ echo "Test 3: Inject large delay (10000000000 ms) that exceeds max loading expir
 orch_status_output=$("$ceph" orch status 2>&1)
 
 echo "$orch_status_output"
-if [[ "$orch_status_output" == *"Error ENOTSUP: Module 'orchestrator' is not enabled/loaded"* ]]; then
+if [[ "$orch_status_output" == *"Error ETIMEDOUT: Module 'orchestrator' did not initialize in time"* ]]; then
     echo "PASS: orch command failed during large delay as expected."
 else
     echo "FAIL: Unexpected error in orch command during large delay."

diff --git a/src/mgr/DaemonServer.cc b/src/mgr/DaemonServer.cc
index f5a356f7e1dc01b25290d82d7b2f1d078a778ca3..a4d15b515106e39327ce12246b2b44202e1cbbc9 100644 (file)
--- a/src/mgr/DaemonServer.cc
+++ b/src/mgr/DaemonServer.cc
@@ -3045,14 +3045,27 @@ bool DaemonServer::_handle_command(
     return true;
   }
 
+  // Validate that the module is enabled
+  auto& py_handler_name = py_command.module_name;
+  PyModuleRef module = py_modules.get_module(py_handler_name);
+  ceph_assert(module);
+  if (!module->is_enabled()) {
+    ss << "Module '" << py_handler_name << "' is not enabled (required by "
+          "command '" << prefix << "'): use `ceph mgr module enable "
+          << py_handler_name << "` to enable it";
+    dout(4) << ss.str() << dendl;
+    cmdctx->reply(-EOPNOTSUPP, ss);
+    return true;
+  }
+
   // Validate that the module is active
   auto& mod_name = py_command.module_name;
   if (!py_modules.is_module_active(mod_name)) {
-    ss << "Module '" << mod_name << "' is not enabled/loaded (required by "
-          "command '" << prefix << "'): use `ceph mgr module enable "
-          << mod_name << "` to enable it";
+    ss << "Module '" << mod_name << "' did not initialize in time (required by "
+          "command '" << prefix << "'): see https://docs.ceph.com/en/latest/rados/operations/health-checks/#mgr-module-error "
+         "for troubleshooting tips.";
     dout(4) << ss.str() << dendl;
-    cmdctx->reply(-EOPNOTSUPP, ss);
+    cmdctx->reply(-ETIMEDOUT, ss);
     return true;
   }
 
@@ -3061,25 +3074,12 @@ bool DaemonServer::_handle_command(
   dout(10) << "passing through command '" << prefix << "' size " << cmdctx->cmdmap.size() << dendl;
   Finisher& mod_finisher = py_modules.get_active_module_finisher(mod_name);
 
-  mod_finisher.queue(new LambdaContext([this, cmdctx, session, py_command, prefix, op]
+  mod_finisher.queue(new LambdaContext([this, cmdctx, session, py_command, prefix, op, py_handler_name, module]
                                        (int r_) mutable {
     std::stringstream ss;
 
     dout(10) << "dispatching command '" << prefix << "' size " << cmdctx->cmdmap.size() << dendl;
 
-    // Validate that the module is enabled
-    auto& py_handler_name = py_command.module_name;
-    PyModuleRef module = py_modules.get_module(py_handler_name);
-    ceph_assert(module);
-    if (!module->is_enabled()) {
-      ss << "Module '" << py_handler_name << "' is not enabled (required by "
-            "command '" << prefix << "'): use `ceph mgr module enable "
-            << py_handler_name << "` to enable it";
-      dout(4) << ss.str() << dendl;
-      cmdctx->reply(-EOPNOTSUPP, ss);
-      return;
-    }
-
     // Hack: allow the self-test method to run on unhealthy modules.
     // Fix this in future by creating a special path for self test rather
     // than having the hook be a normal module command.