Change launch backend script to handle errors gracefully (infiniflow#…

…3334)

### What problem does this PR solve?

The `launch_backend_service.sh` script enters infinite loops for both
the task executors and the backend server. When an error occurs in any
of these processes, the script continuously restarts them without
properly handling termination signals. This behavior causes the script
to even ignore interrupts, leading to persistent error messages and
making it difficult to exit the script gracefully.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### Explanation of Modifications

1. **Signal Trapping with `trap`:** 
- The `trap cleanup SIGINT SIGTERM` line ensures that when a `SIGINT` or
`SIGTERM` signal is received, the cleanup function is invoked.
- The `cleanup` function sets the `STOP` flag to `true`, iterates
through all child process IDs stored in the `PIDS` array, and sends a
`kill` signal to each process to terminate them gracefully.
2. **Retry Limits:**
- Introduced a `MAX_RETRIES` variable to limit the number of restart
attempts for both `task_executor.py` and `ragflow_server.py`
- The loops now check if the retry count has reached the maximum limit.
If so, they invoke the `cleanup` function to terminate all processes and
exit the script.
3. **Process Tracking with `PIDS` Array:**
- After launching each background process (`task_exe` and `run_server`),
their Process IDs (PIDs) are stored in the `PIDS` array.
- This allows the `cleanup` function to terminate all child processes
effectively when needed.
4. **Graceful Shutdown:**
- When the `cleanup` function is called, it iterates over all child PIDs
and sends a termination signal (`kill`) to each, ensuring that all
subprocesses are stopped before the script exits.
5. **Logging Enhancements:**
- Added `echo` statements to provide clearer logs about the state of
each process, including attempts, successes, failures, and retries.
6. **Exit on Successful Completion:**
- If `ragflow_server.py` or a `task_executor.py` process exits with a
success code (0), the loop breaks, preventing unnecessary retries.

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

docker/launch_backend_service.sh

@@ -1,28 +1,103 @@
 #!/bin/bash
 
-# unset http proxy which maybe set by docker daemon
+# Exit immediately if a command exits with a non-zero status
+set -e
+
+# Unset HTTP proxies that might be set by Docker daemon
 export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
 
 export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu/
 
 PY=python3
+
+# Set default number of workers if WS is not set or less than 1
 if [[ -z "$WS" || $WS -lt 1 ]]; then
   WS=1
 fi
 
-function task_exe(){
-    while [ 1 -eq 1 ];do
-      $PY rag/svr/task_executor.py $1;
+# Maximum number of retries for each task executor and server
+MAX_RETRIES=5
+
+# Flag to control termination
+STOP=false
+
+# Array to keep track of child PIDs
+PIDS=()
+
+# Function to handle termination signals
+cleanup() {
+  echo "Termination signal received. Shutting down..."
+  STOP=true
+  # Terminate all child processes
+  for pid in "${PIDS[@]}"; do
+    if kill -0 "$pid" 2>/dev/null; then
+      echo "Killing process $pid"
+      kill "$pid"
+    fi
+  done
+  exit 0
+}
+
+# Trap SIGINT and SIGTERM to invoke cleanup
+trap cleanup SIGINT SIGTERM
+
+# Function to execute task_executor with retry logic
+task_exe(){
+    local task_id=$1
+    local retry_count=0
+    while ! $STOP && [ $retry_count -lt $MAX_RETRIES ]; do
+        echo "Starting task_executor.py for task $task_id (Attempt $((retry_count+1)))"
+        $PY rag/svr/task_executor.py "$task_id"
+        EXIT_CODE=$?
+        if [ $EXIT_CODE -eq 0 ]; then
+            echo "task_executor.py for task $task_id exited successfully."
+            break
+        else
+            echo "task_executor.py for task $task_id failed with exit code $EXIT_CODE. Retrying..." >&2
+            retry_count=$((retry_count + 1))
+            sleep 2
+        fi
     done
+
+    if [ $retry_count -ge $MAX_RETRIES ]; then
+        echo "task_executor.py for task $task_id failed after $MAX_RETRIES attempts. Exiting..." >&2
+        cleanup
+    fi
 }
 
+# Function to execute ragflow_server with retry logic
+run_server(){
+    local retry_count=0
+    while ! $STOP && [ $retry_count -lt $MAX_RETRIES ]; do
+        echo "Starting ragflow_server.py (Attempt $((retry_count+1)))"
+        $PY api/ragflow_server.py
+        EXIT_CODE=$?
+        if [ $EXIT_CODE -eq 0 ]; then
+            echo "ragflow_server.py exited successfully."
+            break
+        else
+            echo "ragflow_server.py failed with exit code $EXIT_CODE. Retrying..." >&2
+            retry_count=$((retry_count + 1))
+            sleep 2
+        fi
+    done
+
+    if [ $retry_count -ge $MAX_RETRIES ]; then
+        echo "ragflow_server.py failed after $MAX_RETRIES attempts. Exiting..." >&2
+        cleanup
+    fi
+}
+
+# Start task executors
 for ((i=0;i<WS;i++))
 do
-  task_exe  $i &
+  task_exe "$i" &
+  PIDS+=($!)
 done
 
-while [ 1 -eq 1 ];do
-    $PY api/ragflow_server.py
-done
+# Start the main server
+run_server &
+PIDS+=($!)
 
-wait;
+# Wait for all background processes to finish
+wait