本文目录导读：
我来为您提供监控应用响应时间的脚本示例,包含多种方案：
使用 curl 的简单脚本
#!/bin/bash
# 监控应用响应时间脚本
URL="https://your-app.com/api/health"
LOG_FILE="/var/log/response_time.log"
# 获取响应时间（毫秒）
response_time=$(curl -o /dev/null -s -w '%{time_total}' $URL)
# 将时间转换为毫秒
response_time_ms=$(echo "$response_time * 1000" | bc)
# 记录日志
echo "$(date '+%Y-%m-%d %H:%M:%S') Response Time: ${response_time_ms}ms" >> $LOG_FILE
# 阈值告警（超过2秒告警）
if (( $(echo "$response_time > 2" | bc -l) )); then
echo "Warning: Response time too high! ${response_time}s"
# 可以添加发送警报的代码
fi
Python 版本（更详细）
#!/usr/bin/env python3
import requests
import time
import logging
from datetime import datetime
# 配置日志
logging.basicConfig(
filename='response_monitor.log',
level=logging.INFO,
format='%(asctime)s - %(message)s'
)
class ResponseMonitor:
def __init__(self, urls, threshold=2.0):
self.urls = urls
self.threshold = threshold # 阈值（秒）
def check_response_time(self, url):
"""检查单个URL的响应时间"""
try:
start_time = time.time()
response = requests.get(url, timeout=10)
end_time = time.time()
response_time = end_time - start_time
status_code = response.status_code
return {
'url': url,
'response_time': response_time,
'status_code': status_code,
'success': True
}
except requests.exceptions.RequestException as e:
return {
'url': url,
'error': str(e),
'success': False
}
def run_checks(self):
"""执行所有URL的检查"""
results = []
for url in self.urls:
result = self.check_response_time(url)
results.append(result)
# 记录结果
if result['success']:
rt = result['response_time']
log_msg = f"URL: {url} - Response Time: {rt:.3f}s - Status: {result['status_code']}"
if rt > self.threshold:
logging.warning(f"SLOW RESPONSE - {log_msg}")
print(f"[ALERT] {log_msg}")
else:
logging.info(log_msg)
print(f"[OK] {log_msg}")
else:
logging.error(f"ERROR - URL: {url} - {result['error']}")
print(f"[ERROR] {url} - {result['error']}")
return results
# 使用示例
if __name__ == "__main__":
urls_to_check = [
"https://api.example.com/health",
"https://api.example.com/users",
"https://api.example.com/products"
]
monitor = ResponseMonitor(urls_to_check, threshold=2.0)
monitor.run_checks()
持续监控脚本（带统计）
#!/bin/bash
# 持续监控脚本
MONITOR_INTERVAL=5 # 监控间隔（秒）
THRESHOLD_MS=2000 # 阈值（毫秒）
URL="https://your-app.com"
LOG_FILE="response_stats.log"
# 统计变量
total_time=0
count=0
max_time=0
min_time=999999
while true; do
# 获取当前时间
timestamp=$(date '+%Y-%m-%d %H:%M:%S')
# 测量响应时间
start=$(date +%s%N)
response=$(curl -s -o /dev/null -w "%{http_code}" --connect-timeout 5 --max-time 10 "$URL")
end=$(date +%s%N)
# 计算响应时间（毫秒）
response_time=$(( (end - start) / 1000000 ))
# 更新统计
count=$((count + 1))
total_time=$((total_time + response_time))
avg_time=$((total_time / count))
# 更新最大最小值
if [ $response_time -gt $max_time ]; then
max_time=$response_time
fi
if [ $response_time -lt $min_time ]; then
min_time=$response_time
fi
# 输出结果
echo "$timestamp | Response: ${response_time}ms | Status: $response | Avg: ${avg_time}ms | Min: ${min_time}ms | Max: ${max_time}ms"
# 记录到日志文件
echo "$timestamp,${response_time},$response,${avg_time},${min_time},${max_time}" >> $LOG_FILE
# 阈值告警
if [ $response_time -gt $THRESHOLD_MS ]; then
echo "⚠️ ALERT: Response time exceeded threshold! (${response_time}ms > ${THRESHOLD_MS}ms)"
# 这里可以添加发送邮件或Slack通知的代码
fi
sleep $MONITOR_INTERVAL
done
Docker 环境监控
#!/bin/bash
# Docker容器响应时间监控
CONTAINER_NAME="your-app-container"
DOCKER_URL="http://localhost:8080/health"
while true; do
# 检查容器是否运行
if docker ps | grep -q $CONTAINER_NAME; then
# 测试应用响应时间
response_time=$(docker exec $CONTAINER_NAME curl -o /dev/null -s -w '%{time_total}' $DOCKER_URL)
# 检查状态
if [ $? -eq 0 ]; then
echo "$(date) - Container: $CONTAINER_NAME - Response Time: ${response_time}s"
# 检查是否过慢
if (( $(echo "$response_time > 2" | bc -l) )); then
echo "Alert: Container response time high!"
fi
else
echo "$(date) - ERROR: Container not responding"
fi
else
echo "$(date) - ERROR: Container $CONTAINER_NAME not running"
fi
sleep 5
done
使用 Python 的 asyncio 进行异步监控
#!/usr/bin/env python3
import asyncio
import aiohttp
import time
import logging
from datetime import datetime
async def check_url(session, url, timeout=10):
"""异步检查单个URL"""
try:
start_time = time.time()
async with session.get(url, timeout=timeout) as response:
response_time = time.time() - start_time
return {
'url': url,
'response_time': response_time,
'status_code': response.status,
'success': True
}
except Exception as e:
return {
'url': url,
'error': str(e),
'success': False
}
async def monitor_urls(urls, interval=10):
"""持续监控多个URL"""
async with aiohttp.ClientSession() as session:
while True:
tasks = [check_url(session, url) for url in urls]
results = await asyncio.gather(*tasks)
for result in results:
if result['success']:
rt = result['response_time']
print(f"[{datetime.now()}] {result['url']}: {rt:.3f}s")
if rt > 2: # 2秒阈值
logging.warning(f"Slow response: {result['url']} - {rt:.3f}s")
else:
print(f"[{datetime.now()}] ERROR: {result['url']} - {result['error']}")
await asyncio.sleep(interval)
# 使用示例
if __name__ == "__main__":
urls_to_monitor = [
"https://api1.example.com/health",
"https://api2.example.com/health",
"https://api3.example.com/health"
]
try:
asyncio.run(monitor_urls(urls_to_monitor, interval=10))
except KeyboardInterrupt:
print("监控停止")
使用说明
- 基本使用：根据需要选择适合的脚本
- 配置：修改URL、阈值、日志路径
- 运行：
chmod +x monitor.sh ./monitor.sh
高级功能建议
- 告警通知：集成邮件、Slack、钉钉等
- 数据持久化：存储到数据库
- Web界面：使用Flask/Django展示
- 分布式监控：支持多节点
- 性能分析：详细的时间分解（DNS、连接、传输）
根据您的具体需求,可以选择或修改上述脚本，需要更详细的功能说明吗？
