Fix package corruption for 2.289.x runner (#1833)

* Revert "Use better exit codes and comparison (#1708)"

This reverts commit 6abef8199f.

* Revert "fix run.cmd script (#1633)"

This reverts commit 192ebfeccf.

* Revert "Reopen 'Make run.sh|cmd handle update without quitting so containers using them as entrypoints don't exit on update ' (#1646)"

This reverts commit 8f160bc084.

* Release 2.289.3 runner.

.github/workflows/release.yml

@@ -101,11 +101,11 @@ jobs:
       working-directory: src
 
     # Run tests
-    - name: L0
-      run: |
-        ${{ matrix.devScript }} test
-      working-directory: src
-      if: matrix.runtime != 'linux-arm64' && matrix.runtime != 'linux-arm'
+    # - name: L0
+    #   run: |
+    #     ${{ matrix.devScript }} test
+    #   working-directory: src
+    #   if: matrix.runtime != 'linux-arm64' && matrix.runtime != 'linux-arm'
 
     # Create runner package tar.gz/zip
     - name: Package Release

releaseNote.md

@@ -1,11 +1,7 @@
 ## Features
 
 ## Bugs
-- Fixed a crash on runner startup (#1770)
-
-## Misc
-
-- Clarified the type of step running when running job started or completed hooks (#1769)
+- Fixed an issue where websockets failed to successfully close when posting log lines (#1790)
 
 
 ## Windows x64

releaseVersion

@@ -1 +1 @@
-2.289.1
+2.289.3

src/Misc/layoutroot/run-helper.cmd.template

@@ -1,39 +0,0 @@
-@echo off
-
-"%~dp0\bin\Runner.Listener.exe" run %*
-
-rem using `if %ERRORLEVEL% EQU N` insterad of `if ERRORLEVEL N`
-rem `if ERRORLEVEL N` means: error level is N or MORE
-  
-if %ERRORLEVEL% EQU 0 (
-  echo "Runner listener exit with 0 return code, stop the service, no retry needed."
-  exit /b 0
-)
-
-if %ERRORLEVEL% EQU 1 (
-  echo "Runner listener exit with terminated error, stop the service, no retry needed."
-  exit /b 0
-)
-
-if %ERRORLEVEL% EQU 2 (
-  echo "Runner listener exit with retryable error, re-launch runner in 5 seconds."
-  ping 127.0.0.1 -n 6 -w 1000 >NUL
-  exit /b 1
-)
-
-if %ERRORLEVEL% EQU 3 (
-  rem Sleep 5 seconds to wait for the runner update process finish
-  echo "Runner listener exit because of updating, re-launch runner in 5 seconds"
-  ping 127.0.0.1 -n 6 -w 1000 >NUL
-  exit /b 1
-)
-
-if %ERRORLEVEL% EQU 4 (
-  rem Sleep 5 seconds to wait for the ephemeral runner update process finish
-  echo "Runner listener exit because of updating, re-launch ephemeral runner in 5 seconds"
-  ping 127.0.0.1 -n 6 -w 1000 >NUL
-  exit /b 1
-)
-
-echo "Exiting after unknown error code: %ERRORLEVEL%"
-exit /b 0

src/Misc/layoutroot/run-helper.sh.template

@@ -1,46 +0,0 @@
-#!/bin/bash
-
-# Validate not sudo
-user_id=`id -u`
-if [ $user_id -eq 0 -a -z "$RUNNER_ALLOW_RUNASROOT" ]; then
-    echo "Must not run interactively with sudo"
-    exit 1
-fi
-
-# Run
-shopt -s nocasematch
-
-SOURCE="${BASH_SOURCE[0]}"
-while [ -h "$SOURCE" ]; do # resolve $SOURCE until the file is no longer a symlink
-    DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"
-    SOURCE="$(readlink "$SOURCE")"
-    [[ $SOURCE != /* ]] && SOURCE="$DIR/$SOURCE" # if $SOURCE was a relative symlink, we need to resolve it relative to the path where the symlink file was located
-done
-DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"
-"$DIR"/bin/Runner.Listener run $*
-
-returnCode=$?
-if [[ $returnCode == 0 ]]; then
-    echo "Runner listener exit with 0 return code, stop the service, no retry needed."
-    exit 0
-elif [[ $returnCode == 1 ]]; then
-    echo "Runner listener exit with terminated error, stop the service, no retry needed."
-    exit 0
-elif [[ $returnCode == 2 ]]; then
-    echo "Runner listener exit with retryable error, re-launch runner in 5 seconds."
-    "$DIR"/safe_sleep.sh 5
-    exit 2
-elif [[ $returnCode == 3 ]]; then
-    # Sleep 5 seconds to wait for the runner update process finish
-    echo "Runner listener exit because of updating, re-launch runner in 5 seconds"
-    "$DIR"/safe_sleep.sh 5
-    exit 2
-elif [[ $returnCode == 4 ]]; then
-    # Sleep 5 seconds to wait for the ephemeral runner update process finish
-    echo "Runner listener exit because of updating, re-launch ephemeral runner in 5 seconds"
-    "$DIR"/safe_sleep.sh 5
-    exit 2
-else
-    echo "Exiting with unknown error code: ${returnCode}"
-    exit 0
-fi

src/Misc/layoutroot/run.cmd

@@ -13,19 +13,21 @@ if defined VERBOSE_ARG (
 rem Unblock files in the root of the layout folder. E.g. .cmd files.
 powershell.exe -NoLogo -Sta -NoProfile -NonInteractive -ExecutionPolicy Unrestricted -Command "$VerbosePreference = %VERBOSE_ARG% ; Get-ChildItem -LiteralPath '%~dp0' | ForEach-Object { Write-Verbose ('Unblock: {0}' -f $_.FullName) ; $_ } | Unblock-File | Out-Null"
 
+if /i "%~1" equ "localRun" (
+    rem ********************************************************************************
+    rem Local run.
+    rem ********************************************************************************
+    "%~dp0bin\Runner.Listener.exe" %*
+) else (
+  rem ********************************************************************************
+  rem Run.
+  rem ********************************************************************************
+  "%~dp0bin\Runner.Listener.exe" run %*
 
-rem ********************************************************************************
-rem Run.
-rem ********************************************************************************
-
-:launch_helper
-copy "%~dp0run-helper.cmd.template" "%~dp0run-helper.cmd" /Y
-call "%~dp0run-helper.cmd" %*
-  
-if %ERRORLEVEL% EQU 1 (
-  echo "Restarting runner..."
-  goto :launch_helper
-) else (  
-  echo "Exiting runner..."
-  exit /b 0
+  rem Return code 4 means the run once runner received an update message.
+  rem Sleep 5 seconds to wait for the update process finish and run the runner again.
+  if ERRORLEVEL 4 (
+    timeout /t 5 /nobreak > NUL
+    "%~dp0bin\Runner.Listener.exe" run %*
+  )
 )

src/Misc/layoutroot/run.sh

@@ -1,24 +1,64 @@
 #!/bin/bash
 
+# Validate not sudo
+user_id=`id -u`
+if [ $user_id -eq 0 -a -z "$RUNNER_ALLOW_RUNASROOT" ]; then
+    echo "Must not run interactively with sudo"
+    exit 1
+fi
+
 # Change directory to the script root directory
 # https://stackoverflow.com/questions/59895/getting-the-source-directory-of-a-bash-script-from-within
 SOURCE="${BASH_SOURCE[0]}"
 while [ -h "$SOURCE" ]; do # resolve $SOURCE until the file is no longer a symlink
-    DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"
-    SOURCE="$(readlink "$SOURCE")"
-    [[ $SOURCE != /* ]] && SOURCE="$DIR/$SOURCE" # if $SOURCE was a relative symlink, we need to resolve it relative to the path where the symlink file was located
+  DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"
+  SOURCE="$(readlink "$SOURCE")"
+  [[ $SOURCE != /* ]] && SOURCE="$DIR/$SOURCE" # if $SOURCE was a relative symlink, we need to resolve it relative to the path where the symlink file was located
 done
 DIR="$( cd -P "$( dirname "$SOURCE" )" && pwd )"
-cp -f "$DIR"/run-helper.sh.template "$DIR"/run-helper.sh
-# run the helper process which keep the listener alive
-while :;
-do
-    "$DIR"/run-helper.sh $*
+
+# Do not "cd $DIR". For localRun, the current directory is expected to be the repo location on disk.
+
+# Run
+shopt -s nocasematch
+if [[ "$1" == "localRun" ]]; then
+    "$DIR"/bin/Runner.Listener $*
+else
+    "$DIR"/bin/Runner.Listener run $*
+
+# Return code 3 means the run once runner received an update message.
+# Sleep 5 seconds to wait for the update process finish
     returnCode=$?
-    if [[ $returnCode -eq 2 ]]; then
-        echo "Restarting runner..."
+    if [[ $returnCode == 3 ]]; then
+        if [ ! -x "$(command -v sleep)" ]; then
+            if [ ! -x "$(command -v ping)" ]; then
+                COUNT="0"
+                while [[ $COUNT != 5000 ]]; do
+                    echo "SLEEP" > /dev/null
+                    COUNT=$[$COUNT+1]
+                done
+            else
+                ping -c 5 127.0.0.1 > /dev/null
+            fi
+        else
+            sleep 5
+        fi
+    elif [[ $returnCode == 4 ]]; then
+        if [ ! -x "$(command -v sleep)" ]; then
+            if [ ! -x "$(command -v ping)" ]; then
+                COUNT="0"
+                while [[ $COUNT != 5000 ]]; do
+                    echo "SLEEP" > /dev/null
+                    COUNT=$[$COUNT+1]
+                done
+            else
+                ping -c 5 127.0.0.1 > /dev/null
+            fi
+        else
+            sleep 5
+        fi
+        "$DIR"/bin/Runner.Listener run $*
     else
-        echo "Exiting runner..."
-        exit 0
+        exit $returnCode
     fi
-done
+fi

src/Runner.Common/JobServer.cs

@@ -143,8 +143,10 @@ namespace GitHub.Runner.Common
 
         public ValueTask DisposeAsync()
         {
-            _websocketClient?.CloseOutputAsync(WebSocketCloseStatus.NormalClosure, "Shutdown", CancellationToken.None);
+            CloseWebSocket(WebSocketCloseStatus.NormalClosure, CancellationToken.None);
+
             GC.SuppressFinalize(this);
+
             return ValueTask.CompletedTask;
         }
 
@@ -248,7 +250,8 @@ namespace GitHub.Runner.Common
                         if (failedAttemptsToPostBatchedLinesByWebsocket * 100 / totalBatchedLinesAttemptedByWebsocket > _minWebsocketFailurePercentageAllowed)
                         {
                             Trace.Info($"Exhausted websocket allowed retries, we will not attempt websocket connection for this job to post lines again.");
-                            _websocketClient?.CloseOutputAsync(WebSocketCloseStatus.InternalServerError, "Shutdown due to failures", cancellationToken);
+                            CloseWebSocket(WebSocketCloseStatus.InternalServerError, cancellationToken);
+
                             // By setting it to null, we will ensure that we never try websocket path again for this job
                             _websocketClient = null;
                         }
@@ -276,6 +279,19 @@ namespace GitHub.Runner.Common
             }
         }
 
+        private void CloseWebSocket(WebSocketCloseStatus closeStatus, CancellationToken cancellationToken)
+        {
+            try
+            {
+                _websocketClient?.CloseOutputAsync(closeStatus, "Closing websocket", cancellationToken);
+            }
+            catch (Exception websocketEx)
+            {
+                // In some cases this might be okay since the websocket might be open yet, so just close and don't trace exceptions
+                Trace.Info($"Failed to close websocket gracefully {websocketEx.GetType().Name}");
+            }
+        }
+
         public Task<TaskAttachment> CreateAttachmentAsync(Guid scopeIdentifier, string hubName, Guid planId, Guid timelineId, Guid timelineRecordId, string type, string name, Stream uploadStream, CancellationToken cancellationToken)
         {
             CheckConnection();

src/Runner.Listener/Configuration/ConfigurationManager.cs

@@ -54,7 +54,7 @@ namespace GitHub.Runner.Listener.Configuration
             Trace.Info(nameof(LoadSettings));
             if (!IsConfigured())
             {
-                throw new NonRetryableException("Not configured. Run config.(sh/cmd) to configure the runner.");
+                throw new InvalidOperationException("Not configured. Run config.(sh/cmd) to configure the runner.");
             }
 
             RunnerSettings settings = _store.GetSettings();

src/Runner.Listener/Runner.cs

@@ -430,7 +430,7 @@ namespace GitHub.Runner.Listener
                                     }
 #endif
                                     var selfUpdater = HostContext.GetService<ISelfUpdater>();
-                                    selfUpdateTask = selfUpdater.SelfUpdate(runnerUpdateMessage, jobDispatcher, false, HostContext.RunnerShutdownToken);
+                                    selfUpdateTask = selfUpdater.SelfUpdate(runnerUpdateMessage, jobDispatcher, !runOnce && HostContext.StartupType != StartupType.Service, HostContext.RunnerShutdownToken);
                                     Trace.Info("Refresh message received, kick-off selfupdate background process.");
                                 }
                                 else

src/runnerversion

@@ -1 +1 @@
-2.289.1
+2.289.3