Refactor logging setup and simplify Gunicorn configuration

• Move logging setup code to utils.py
• Provide setup_logger for standalone LightRAG logger intialization
This commit is contained in:
yangdx
2025-03-03 23:18:41 +08:00
parent 2d6d0be128
commit 462c27c167
5 changed files with 112 additions and 246 deletions

View File

@@ -2,12 +2,15 @@
import os
import logging
from lightrag.kg.shared_storage import finalize_share_data
from lightrag.api.lightrag_server import LightragPathFilter
from lightrag.utils import setup_logger
# Get log directory path from environment variable
log_dir = os.getenv("LOG_DIR", os.getcwd())
log_file_path = os.path.abspath(os.path.join(log_dir, "lightrag.log"))
# Ensure log directory exists
os.makedirs(os.path.dirname(log_file_path), exist_ok=True)
# Get log file max size and backup count from environment variables
log_max_bytes = int(os.getenv("LOG_MAX_BYTES", 10485760)) # Default 10MB
log_backup_count = int(os.getenv("LOG_BACKUP_COUNT", 5)) # Default 5 backups
@@ -108,6 +111,9 @@ def on_starting(server):
except ImportError:
print("psutil not installed, skipping memory usage reporting")
# Log the location of the LightRAG log file
print(f"LightRAG log file: {log_file_path}\n")
print("Gunicorn initialization complete, forking workers...\n")
@@ -134,51 +140,18 @@ def post_fork(server, worker):
Executed after a worker has been forked.
This is a good place to set up worker-specific configurations.
"""
# Configure formatters
detailed_formatter = logging.Formatter(
"%(asctime)s - %(name)s - %(levelname)s - %(message)s"
)
simple_formatter = logging.Formatter("%(levelname)s: %(message)s")
def setup_logger(logger_name: str, level: str = "INFO", add_filter: bool = False):
"""Set up a logger with console and file handlers"""
logger_instance = logging.getLogger(logger_name)
logger_instance.setLevel(level)
logger_instance.handlers = [] # Clear existing handlers
logger_instance.propagate = False
# Add console handler
console_handler = logging.StreamHandler()
console_handler.setFormatter(simple_formatter)
console_handler.setLevel(level)
logger_instance.addHandler(console_handler)
# Add file handler
file_handler = logging.handlers.RotatingFileHandler(
filename=log_file_path,
maxBytes=log_max_bytes,
backupCount=log_backup_count,
encoding="utf-8",
)
file_handler.setFormatter(detailed_formatter)
file_handler.setLevel(level)
logger_instance.addHandler(file_handler)
# Add path filter if requested
if add_filter:
path_filter = LightragPathFilter()
logger_instance.addFilter(path_filter)
# Set up main loggers
log_level = loglevel.upper() if loglevel else "INFO"
setup_logger("uvicorn", log_level)
setup_logger("uvicorn.access", log_level, add_filter=True)
setup_logger("lightrag", log_level, add_filter=True)
setup_logger("uvicorn", log_level, add_filter=False, log_file_path=log_file_path)
setup_logger(
"uvicorn.access", log_level, add_filter=True, log_file_path=log_file_path
)
setup_logger("lightrag", log_level, add_filter=True, log_file_path=log_file_path)
# Set up lightrag submodule loggers
for name in logging.root.manager.loggerDict:
if name.startswith("lightrag."):
setup_logger(name, log_level, add_filter=True)
setup_logger(name, log_level, add_filter=True, log_file_path=log_file_path)
# Disable uvicorn.error logger
uvicorn_error_logger = logging.getLogger("uvicorn.error")

View File

@@ -437,6 +437,9 @@ def configure_logging():
log_dir = os.getenv("LOG_DIR", os.getcwd())
log_file_path = os.path.abspath(os.path.join(log_dir, "lightrag.log"))
print(f"\nLightRAG log file: {log_file_path}\n")
os.makedirs(os.path.dirname(log_dir), exist_ok=True)
# Get log file max size and backup count from environment variables
log_max_bytes = int(os.getenv("LOG_MAX_BYTES", 10485760)) # Default 10MB
log_backup_count = int(os.getenv("LOG_BACKUP_COUNT", 5)) # Default 5 backups

View File

@@ -266,9 +266,6 @@ class LightRAG:
_storages_status: StoragesStatus = field(default=StoragesStatus.NOT_CREATED)
def __post_init__(self):
os.makedirs(os.path.dirname(self.log_file_path), exist_ok=True)
logger.info(f"Logger initialized for working directory: {self.working_dir}")
from lightrag.kg.shared_storage import (
initialize_share_data,
)

View File

@@ -6,6 +6,7 @@ import io
import csv
import json
import logging
import logging.handlers
import os
import re
from dataclasses import dataclass
@@ -68,6 +69,101 @@ logger.setLevel(logging.INFO)
logging.getLogger("httpx").setLevel(logging.WARNING)
class LightragPathFilter(logging.Filter):
"""Filter for lightrag logger to filter out frequent path access logs"""
def __init__(self):
super().__init__()
# Define paths to be filtered
self.filtered_paths = ["/documents", "/health", "/webui/"]
def filter(self, record):
try:
# Check if record has the required attributes for an access log
if not hasattr(record, "args") or not isinstance(record.args, tuple):
return True
if len(record.args) < 5:
return True
# Extract method, path and status from the record args
method = record.args[1]
path = record.args[2]
status = record.args[4]
# Filter out successful GET requests to filtered paths
if (
method == "GET"
and (status == 200 or status == 304)
and path in self.filtered_paths
):
return False
return True
except Exception:
# In case of any error, let the message through
return True
def setup_logger(
logger_name: str,
level: str = "INFO",
add_filter: bool = False,
log_file_path: str = None,
):
"""Set up a logger with console and file handlers
Args:
logger_name: Name of the logger to set up
level: Log level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
add_filter: Whether to add LightragPathFilter to the logger
log_file_path: Path to the log file. If None, will use current directory/lightrag.log
"""
# Configure formatters
detailed_formatter = logging.Formatter(
"%(asctime)s - %(name)s - %(levelname)s - %(message)s"
)
simple_formatter = logging.Formatter("%(levelname)s: %(message)s")
# Get log file path
if log_file_path is None:
log_dir = os.getenv("LOG_DIR", os.getcwd())
log_file_path = os.path.abspath(os.path.join(log_dir, "lightrag.log"))
# Ensure log directory exists
os.makedirs(os.path.dirname(log_file_path), exist_ok=True)
# Get log file max size and backup count from environment variables
log_max_bytes = int(os.getenv("LOG_MAX_BYTES", 10485760)) # Default 10MB
log_backup_count = int(os.getenv("LOG_BACKUP_COUNT", 5)) # Default 5 backups
logger_instance = logging.getLogger(logger_name)
logger_instance.setLevel(level)
logger_instance.handlers = [] # Clear existing handlers
logger_instance.propagate = False
# Add console handler
console_handler = logging.StreamHandler()
console_handler.setFormatter(simple_formatter)
console_handler.setLevel(level)
logger_instance.addHandler(console_handler)
# Add file handler
file_handler = logging.handlers.RotatingFileHandler(
filename=log_file_path,
maxBytes=log_max_bytes,
backupCount=log_backup_count,
encoding="utf-8",
)
file_handler.setFormatter(detailed_formatter)
file_handler.setLevel(level)
logger_instance.addHandler(file_handler)
# Add path filter if requested
if add_filter:
path_filter = LightragPathFilter()
logger_instance.addFilter(path_filter)
class UnlimitedSemaphore:
"""A context manager that allows unlimited access."""