Improve handling of exceptions during distributor startup

Remove call to requestShutdown which could try to use components
that weren't properly set up yet. Only used for _maybe_ being able
to scream an error to the cluster controller, but this has very
limited usefulness in practice.

Since exceptions are categorized and logged with backtrace at the
root application main level, remove redundant logging. Also enforce
component shutdown for network setup exceptions (not sure why this
wasn't there to start with).

1 files changed, 2 insertions, 2 deletions

diff --git a/storageserver/src/apps/storaged/storage.cpp b/storageserver/src/apps/storaged/storage.cpp
index 428067e3059..8fbeeb836da 100644
--- a/storageserver/src/apps/storaged/storage.cpp
+++ b/storageserver/src/apps/storaged/storage.cpp
@@ -187,7 +187,7 @@ int StorageApp::Main()
     // main loop - wait for termination signal
     while (!_process->getNode().attemptedStopped()) {
         if (_process->configUpdated()) {
-            LOG(debug, "Config updated. Progagating config updates");
+            LOG(debug, "Config updated. Propagating config updates");
             ResumeGuard guard(_process->getNode().pause());
             _process->updateConfig();
         }
@@ -197,7 +197,7 @@ int StorageApp::Main()
         handleSignals();
     }
     LOG(debug, "Server was attempted stopped, shutting down");
-    // Create guard that will forcifully kill storage if destruction takes longer
+    // Create guard that will forcefully kill storage if destruction takes longer
     // time than given timeout.
     vespalib::ShutdownGuard shutdownGuard(getMaxShutDownTime());
     LOG(debug, "Attempting proper shutdown");