#!/bin/bash
# from:www.itpux.com.qq113257174.wx:itpux-com
# web: http://www.fgedu.net.cn
# gg_process_monitor.sh
# from:www.itpux.com.qq113257174.wx:itpux-com
# web: http://www.fgedu.net.cn

# 配置
GG_HOME=”/oracle/goldengate”
LOG_DIR=”$GG_HOME/monitor”
LOG_FILE=”$LOG_DIR/process_$(date +%Y%m%d).log”
ALERT_FILE=”$LOG_DIR/process_alert.log”
PID_FILE=”$LOG_DIR/gg_monitor.pid”

# 进程列表
MANAGER_PID=””
EXTRACT_LIST=”ext01 ext02″
REPLICAT_LIST=”rep01 rep02″

# 检查Manager
check_manager() {
echo “$(date): Checking Manager status” >> $LOG_FILE

# 获取Manager状态
MANAGER_STATUS=$(echo “info mgr” | $GG_HOME/ggsci 2>/dev/null | grep “Manager” | awk ‘{print $2}’)

if [ “$MANAGER_STATUS” != “RUNNING” ]; then
echo “$(date): ALERT – Manager is $MANAGER_STATUS” >> $ALERT_FILE
echo “$(date): Attempting to start Manager” >> $LOG_FILE
echo “start mgr” | $GG_HOME/ggsci
sleep 5

# 再次检查
MANAGER_STATUS=$(echo “info mgr” | $GG_HOME/ggsci 2>/dev/null | grep “Manager” | awk ‘{print $2}’)
if [ “$MANAGER_STATUS” != “RUNNING” ]; then
echo “$(date): CRITICAL – Failed to start Manager” >> $ALERT_FILE
return 2
fi
fi

echo “$(date): Manager is RUNNING” >> $LOG_FILE
return 0
}

# 检查Extract
check_extract() {
EXTRACT=$1
echo “$(date): Checking Extract $EXTRACT status” >> $LOG_FILE

EXTRACT_STATUS=$(echo “info extract $EXTRACT” | $GG_HOME/ggsci 2>/dev/null | grep “EXTRACT” | head -1 | awk ‘{print $2}’)

if [ “$EXTRACT_STATUS” != “RUNNING” ]; then
echo “$(date): ALERT – Extract $EXTRACT is $EXTRACT_STATUS” >> $ALERT_FILE

if [ “$EXTRACT_STATUS” == “ABENDED” ]; then
echo “$(date): Attempting to restart Extract $EXTRACT” >> $LOG_FILE
echo “start extract $EXTRACT” | $GG_HOME/ggsci
sleep 5

# 再次检查
EXTRACT_STATUS=$(echo “info extract $EXTRACT” | $GG_HOME/ggsci 2>/dev/null | grep “EXTRACT” | head -1 | awk ‘{print $2}’)
if [ “$EXTRACT_STATUS” != “RUNNING” ]; then
echo “$(date): CRITICAL – Failed to restart Extract $EXTRACT” >> $ALERT_FILE
return 2
fi
fi
fi

echo “$(date): Extract $EXTRACT is RUNNING” >> $LOG_FILE
return 0
}

# 检查Replicat
check_replicat() {
REPLICAT=$1
echo “$(date): Checking Replicat $REPLICAT status” >> $LOG_FILE

REPLICAT_STATUS=$(echo “info replicat $REPLICAT” | $GG_HOME/ggsci 2>/dev/null | grep “REPLICAT” | head -1 | awk ‘{print $2}’)

if [ “$REPLICAT_STATUS” != “RUNNING” ]; then
echo “$(date): ALERT – Replicat $REPLICAT is $REPLICAT_STATUS” >> $ALERT_FILE

if [ “$REPLICAT_STATUS” == “ABENDED” ]; then
echo “$(date): Attempting to restart Replicat $REPLICAT” >> $LOG_FILE
echo “start replicat $REPLICAT” | $GG_HOME/ggsci
sleep 5

# 再次检查
REPLICAT_STATUS=$(echo “info replicat $REPLICAT” | $GG_HOME/ggsci 2>/dev/null | grep “REPLICAT” | head -1 | awk ‘{print $2}’)
if [ “$REPLICAT_STATUS” != “RUNNING” ]; then
echo “$(date): CRITICAL – Failed to restart Replicat $REPLICAT” >> $ALERT_FILE
return 2
fi
fi
fi

echo “$(date): Replicat $REPLICAT is RUNNING” >> $LOG_FILE
return 0
}

# 主程序
main() {
# 创建日志目录
mkdir -p $LOG_DIR

# 检查是否已在运行
if [ -f $PID_FILE ]; then
OLD_PID=$(cat $PID_FILE)
if ps -p $OLD_PID > /dev/null 2>&1; then
echo “Monitor is already running with PID $OLD_PID”
exit 1
fi
fi

# 记录PID
echo $$ > $PID_FILE

echo “$(date): Starting GoldenGate process monitor” >> $LOG_FILE

# 检查Manager
check_manager

# 检查Extract
for EXTRACT in $EXTRACT_LIST; do
check_extract $EXTRACT
done

# 检查Replicat
for REPLICAT in $REPLICAT_LIST; do
check_replicat $REPLICAT
done

echo “$(date): GoldenGate process monitor completed” >> $LOG_FILE

# 发送告警
if [ -s $ALERT_FILE ]; then
/oracle/goldengate/monitor/gg_email_alert.sh
/oracle/goldengate/monitor/gg_dingtalk_alert.sh
fi

# 清理PID文件
rm -f $PID_FILE
}

main

#!/bin/bash
# from:www.itpux.com.qq113257174.wx:itpux-com
# web: http://www.fgedu.net.cn
# gg_lag_monitor_advanced.sh
# from:www.itpux.com.qq113257174.wx:itpux-com
# web: http://www.fgedu.net.cn

# 配置
GG_HOME=”/oracle/goldengate”
LOG_DIR=”$GG_HOME/monitor”
LOG_FILE=”$LOG_DIR/lag_$(date +%Y%m%d).log”
ALERT_FILE=”$LOG_DIR/lag_alert.log”
HISTORY_FILE=”$LOG_DIR/lag_history.csv”

# 阈值（秒）
LAG_CRITICAL=1800
LAG_WARNING=600
LAG_INFO=300

# 转换为秒的函数
time_to_seconds() {
TIME_STR=$1
HOURS=$(echo $TIME_STR | cut -d: -f1)
MINUTES=$(echo $TIME_STR | cut -d: -f2)
SECONDS=$(echo $TIME_STR | cut -d: -f3)
echo $((HOURS*3600 + MINUTES*60 + SECONDS))
}

# 监控Extract延迟
monitor_extract_lag() {
EXTRACT=$1
TIMESTAMP=$(date +%Y%m%d%H%M%S)

# 获取延迟信息
LAG_INFO=$(echo “info extract $EXTRACT” | $GG_HOME/ggsci 2>/dev/null | grep “Checkpoint Lag” | awk ‘{print $3}’)

if [ -z “$LAG_INFO” ]; then
echo “$TIMESTAMP,$EXTRACT,EXTRACT,UNKNOWN,-1,ERROR” >> $HISTORY_FILE
echo “$(date): ERROR – Cannot get lag info for Extract $EXTRACT” >> $LOG_FILE
return 1
fi

# 转换为秒
LAG_SECONDS=$(time_to_seconds $LAG_INFO)

# 确定告警级别
ALERT_LEVEL=”NORMAL”
if [ $LAG_SECONDS -gt $LAG_CRITICAL ]; then
ALERT_LEVEL=”CRITICAL”
echo “$(date): CRITICAL – Extract $EXTRACT lag $LAG_INFO exceeds critical threshold” >> $ALERT_FILE
elif [ $LAG_SECONDS -gt $LAG_WARNING ]; then
ALERT_LEVEL=”WARNING”
echo “$(date): WARNING – Extract $EXTRACT lag $LAG_INFO exceeds warning threshold” >> $ALERT_FILE
elif [ $LAG_SECONDS -gt $LAG_INFO ]; then
ALERT_LEVEL=”INFO”
fi

# 记录历史数据
echo “$TIMESTAMP,$EXTRACT,EXTRACT,$LAG_INFO,$LAG_SECONDS,$ALERT_LEVEL” >> $HISTORY_FILE
echo “$(date): Extract $EXTRACT lag is $LAG_INFO ($LAG_SECONDS seconds) – $ALERT_LEVEL” >> $LOG_FILE

return 0
}

# 监控Replicat延迟
monitor_replicat_lag() {
REPLICAT=$1
TIMESTAMP=$(date +%Y%m%d%H%M%S)

# 获取延迟信息
LAG_INFO=$(echo “info replicat $REPLICAT” | $GG_HOME/ggsci 2>/dev/null | grep “Checkpoint Lag” | awk ‘{print $3}’)

if [ -z “$LAG_INFO” ]; then
echo “$TIMESTAMP,$REPLICAT,REPLICAT,UNKNOWN,-1,ERROR” >> $HISTORY_FILE
echo “$(date): ERROR – Cannot get lag info for Replicat $REPLICAT” >> $LOG_FILE
return 1
fi

# 转换为秒
LAG_SECONDS=$(time_to_seconds $LAG_INFO)

# 确定告警级别
ALERT_LEVEL=”NORMAL”
if [ $LAG_SECONDS -gt $LAG_CRITICAL ]; then
ALERT_LEVEL=”CRITICAL”
echo “$(date): CRITICAL – Replicat $REPLICAT lag $LAG_INFO exceeds critical threshold” >> $ALERT_FILE
elif [ $LAG_SECONDS -gt $LAG_WARNING ]; then
ALERT_LEVEL=”WARNING”
echo “$(date): WARNING – Replicat $REPLICAT lag $LAG_INFO exceeds warning threshold” >> $ALERT_FILE
elif [ $LAG_SECONDS -gt $LAG_INFO ]; then
ALERT_LEVEL=”INFO”
fi

# 记录历史数据
echo “$TIMESTAMP,$REPLICAT,REPLICAT,$LAG_INFO,$LAG_SECONDS,$ALERT_LEVEL” >> $HISTORY_FILE
echo “$(date): Replicat $REPLICAT lag is $LAG_INFO ($LAG_SECONDS seconds) – $ALERT_LEVEL” >> $LOG_FILE

return 0
}

# 生成延迟趋势报告
generate_lag_report() {
REPORT_FILE=”$LOG_DIR/lag_report_$(date +%Y%m%d).html”

cat > $REPORT_FILE << EOF

GoldenGate Lag Report – $(date +%Y%m%d)

EOF

tail -100 $HISTORY_FILE | while IFS=, read TIMESTAMP PROCESS TYPE LAG SECONDS LEVEL; do
echo “

” >> $REPORT_FILE
done

echo “

Time	Process	Type	Lag	Seconds	Level
$TIMESTAMP	$PROCESS	$TYPE	$LAG	$SECONDS	$LEVEL

” >> $REPORT_FILE

echo “$(date): Lag report generated: $REPORT_FILE” >> $LOG_FILE
}

# 主程序
main() {
mkdir -p $LOG_DIR

echo “$(date): Starting GoldenGate lag monitor” >> $LOG_FILE

# 监控Extract
monitor_extract_lag “ext01”
monitor_extract_lag “ext02”

# 监控Replicat
monitor_replicat_lag “rep01”
monitor_replicat_lag “rep02”

# 生成报告
generate_lag_report

echo “$(date): GoldenGate lag monitor completed” >> $LOG_FILE

# 发送告警
if [ -s $ALERT_FILE ]; then
/oracle/goldengate/monitor/gg_email_alert.sh
fi
}

main

#!/bin/bash
# from:www.itpux.com.qq113257174.wx:itpux-com
# web: http://www.fgedu.net.cn
# gg_monitor_platform.sh
# from:www.itpux.com.qq113257174.wx:itpux-com
# web: http://www.fgedu.net.cn

# 综合监控平台主控脚本
# 整合进程监控、延迟监控、资源监控、告警通知等功能

# 配置
GG_HOME=”/oracle/goldengate”
LOG_DIR=”$GG_HOME/monitor”
CONFIG_FILE=”$GG_HOME/monitor/monitor.conf”

# 加载配置
source $CONFIG_FILE

# 初始化日志目录
init_log_dir() {
mkdir -p $LOG_DIR/{status,lag,resource,alert,report}

# 创建历史数据目录
mkdir -p $LOG_DIR/history/{daily,hourly}
}

# 进程状态监控模块
module_process() {
echo “$(date): Running process monitoring module”

LOG_FILE=”$LOG_DIR/status/process_$(date +%Y%m%d%H).log”

# 获取所有进程状态
echo “info all” | $GG_HOME/ggsci > $LOG_DIR/status/current_status.txt

# 分析状态
while read LINE; do
if echo “$LINE” | grep -q “EXTRACT\|REPLICAT”; then
PROCESS=$(echo $LINE | awk ‘{print $1}’)
STATUS=$(echo $LINE | awk ‘{print $2}’)
GROUP=$(echo $LINE | awk ‘{print $3}’)
LAG=$(echo $LINE | awk ‘{print $4}’)

TIMESTAMP=$(date +%Y%m%d%H%M%S)
echo “$TIMESTAMP,$PROCESS,$GROUP,$STATUS,$LAG” >> $LOG_DIR/history/process_history.csv

# 检查异常状态
if [ “$STATUS” != “RUNNING” ]; then
echo “$TIMESTAMP,$PROCESS,$GROUP,$STATUS,ALERT” >> $LOG_DIR/alert/process_alert.csv
fi
fi
done < $LOG_DIR/status/current_status.txt } # 延迟监控模块 module_lag() { echo "$(date): Running lag monitoring module" # 获取所有Extract和Replicat列表 EXTRACT_LIST=$(echo "info all" | $GG_HOME/ggsci | grep "EXTRACT" | awk '{print $3}') REPLICAT_LIST=$(echo "info all" | $GG_HOME/ggsci | grep "REPLICAT" | awk '{print $3}') # 监控Extract延迟 for EXTRACT in $EXTRACT_LIST; do LAG_INFO=$(echo "info extract $EXTRACT" | $GG_HOME/ggsci | grep "Checkpoint Lag" | awk '{print $3}') TIMESTAMP=$(date +%Y%m%d%H%M%S) echo "$TIMESTAMP,$EXTRACT,EXTRACT,$LAG_INFO" >> $LOG_DIR/history/lag_history.csv
done

# 监控Replicat延迟
for REPLICAT in $REPLICAT_LIST; do
LAG_INFO=$(echo “info replicat $REPLICAT” | $GG_HOME/ggsci | grep “Checkpoint Lag” | awk ‘{print $3}’)
TIMESTAMP=$(date +%Y%m%d%H%M%S)
echo “$TIMESTAMP,$REPLICAT,REPLICAT,$LAG_INFO” >> $LOG_DIR/history/lag_history.csv
done
}

# 资源监控模块
module_resource() {
echo “$(date): Running resource monitoring module”

TIMESTAMP=$(date +%Y%m%d%H%M%S)

# CPU使用率
CPU_USAGE=$(top -bn1 | grep “Cpu(s)” | awk ‘{print $2}’ | cut -d’%’ -f1)

# 内存使用率
MEM_USAGE=$(free | grep Mem | awk ‘{printf “%.2f”, $3/$2 * 100.0}’)

# 磁盘使用率
DISK_USAGE=$(df -h $GG_HOME | tail -1 | awk ‘{print $5}’ | cut -d’%’ -f1)

# GoldenGate进程资源使用
GG_CPU=$(ps -eo pid,comm,pcpu | grep “extract\|replicat” | awk ‘{sum+=$3} END {print sum}’)
GG_MEM=$(ps -eo pid,comm,pmem | grep “extract\|replicat” | awk ‘{sum+=$3} END {print sum}’)

# 记录数据
echo “$TIMESTAMP,$CPU_USAGE,$MEM_USAGE,$DISK_USAGE,$GG_CPU,$GG_MEM” >> $LOG_DIR/history/resource_history.csv

# 检查阈值
if [ ${DISK_USAGE%.*} -gt 80 ]; then
echo “$TIMESTAMP,DISK,$DISK_USAGE%,WARNING” >> $LOG_DIR/alert/resource_alert.csv
fi
}

# 告警处理模块
module_alert() {
echo “$(date): Running alert processing module”

ALERT_FILE=”$LOG_DIR/alert/all_alerts_$(date +%Y%m%d).log”

# 合并所有告警
cat $LOG_DIR/alert/*.csv > $ALERT_FILE 2>/dev/null

# 发送告警通知
if [ -s $ALERT_FILE ]; then
# 邮件告警
if [ “$EMAIL_ALERT” == “Y” ]; then
/oracle/goldengate/monitor/gg_email_alert.sh
fi

# 钉钉告警
if [ “$DINGTALK_ALERT” == “Y” ]; then
/oracle/goldengate/monitor/gg_dingtalk_alert.sh
fi

# 短信告警（严重告警）
if [ “$SMS_ALERT” == “Y” ] && grep -q “CRITICAL” $ALERT_FILE; then
/oracle/goldengate/monitor/gg_sms_alert.sh
fi
fi
}

# 报告生成模块
module_report() {
echo “$(date): Running report generation module”

REPORT_FILE=”$LOG_DIR/report/daily_report_$(date +%Y%m%d).html”

# 生成HTML报告
cat > $REPORT_FILE << 'EOF'

GoldenGate Daily Report – $(date +%Y-%m-%d)

Process Status

EOF

# 添加进程状态数据
tail -20 $LOG_DIR/history/process_history.csv | while IFS=, read TIMESTAMP PROCESS GROUP STATUS LAG; do
CSS_CLASS=”normal”
if [ “$STATUS” != “RUNNING” ]; then
CSS_CLASS=”alert”
fi
echo “

” >> $REPORT_FILE
done

cat >> $REPORT_FILE << 'EOF'

Process	Group	Status	Lag
$PROCESS	$GROUP	$STATUS	$LAG

Performance Metrics

EOF

# 添加性能数据
tail -10 $LOG_DIR/history/resource_history.csv | while IFS=, read TIMESTAMP CPU MEM DISK GGCPU GGMEM; do
echo “

” >> $REPORT_FILE
done

echo “

Time	CPU%	Memory%	Disk%	GG CPU%	GG Mem%
$TIMESTAMP	$CPU	$MEM	$DISK	$GGCPU	$GGMEM

” >> $REPORT_FILE

echo “$(date): Report generated: $REPORT_FILE”
}

# 主程序
main() {
echo “$(date): Starting GoldenGate Monitor Platform”

# 初始化
init_log_dir

# 运行各监控模块
module_process
module_lag
module_resource

# 处理告警
module_alert

# 生成报告（每小时执行一次）
if [ $(date +%M) == “00” ]; then
module_report
fi

echo “$(date): GoldenGate Monitor Platform completed”
}

main