# Hadoop集群日常巡检脚本
LOG_FILE=”/bigdata/logs/daily_check_$(date +%Y%m%d).log”
ALERT_EMAIL=”admin@fgedu.net.cn”

echo “=== Hadoop Cluster Daily Check ===” > ${LOG_FILE}
echo “Date: $(date)” >> ${LOG_FILE}

# 1. HDFS巡检
echo “=== HDFS Check ===” >> ${LOG_FILE}
LIVE_NODES=$(hdfs dfsadmin -report | grep “Live datanodes” | awk ‘{print $3}’)
DEAD_NODES=$(hdfs dfsadmin -report | grep “Dead datanodes” | awk ‘{print $3}’)
MISSING_BLOCKS=$(hdfs dfsadmin -report | grep “Missing blocks” | awk ‘{print $3}’)

echo “Live Nodes: ${LIVE_NODES}” >> ${LOG_FILE}
echo “Dead Nodes: ${DEAD_NODES}” >> ${LOG_FILE}
echo “Missing Blocks: ${MISSING_BLOCKS}” >> ${LOG_FILE}

if [ ${DEAD_NODES} -gt 0 ] || [ ${MISSING_BLOCKS} -gt 0 ]; then
echo “ALERT: HDFS has issues!” >> ${LOG_FILE}
mail -s “HDFS Alert” ${ALERT_EMAIL} < ${LOG_FILE}
fi

# 2. YARN巡检
echo “=== YARN Check ===” >> ${LOG_FILE}
RUNNING_NODES=$(yarn node -list | grep “RUNNING” | wc -l)
UNHEALTHY_NODES=$(yarn node -list -states UNHEALTHY | grep “UNHEALTHY” | wc -l)

echo “Running Nodes: ${RUNNING_NODES}” >> ${LOG_FILE}
echo “Unhealthy Nodes: ${UNHEALTHY_NODES}” >> ${LOG_FILE}

if [ ${UNHEALTHY_NODES} -gt 0 ]; then
echo “ALERT: YARN has unhealthy nodes!” >> ${LOG_FILE}
mail -s “YARN Alert” ${ALERT_EMAIL} < ${LOG_FILE}
fi

# 3. 系统资源巡检
echo “=== System Resource Check ===” >> ${LOG_FILE}
CPU_USAGE=$(top -bn1 | grep “Cpu(s)” | awk ‘{print $2}’)
MEM_USAGE=$(free | grep Mem | awk ‘{printf “%.1f”, $3/$2 * 100.0}’)
DISK_USAGE=$(df -h /bigdata | tail -1 | awk ‘{print $5}’)

echo “CPU Usage: ${CPU_USAGE}%” >> ${LOG_FILE}
echo “Memory Usage: ${MEM_USAGE}%” >> ${LOG_FILE}
echo “Disk Usage: ${DISK_USAGE}” >> ${LOG_FILE}

echo “=== Check Completed ===” >> ${LOG_FILE}