Compare commits

..

5 Commits

Author SHA1 Message Date
sundapeng.sdp
68b265624c feat: 基于算力平台的Prometheus镜像改造,supervisor自启应用;调整Prometheus.yml结构;
refs #9
2025-09-23 17:37:59 +08:00
sundapeng.sdp
d9d937f5d6 feat: FTP服务器离线安装及配置;数据采集客户端支持一键部署、版本校验、组件健康检查、失败回滚等功能;
refs #3
2025-09-23 17:37:59 +08:00
sundapeng.sdp
095e8ee32d feat: 提交示例Node-Exporter安装包;
refs #3
2025-09-23 17:37:59 +08:00
sundapeng.sdp
a6c60b2edd feat: 支持all-in-one模式构建、发布安装包;支持各组件健康状态监测;Prometheus相关配置文件;
refs #3
2025-09-23 17:37:59 +08:00
8a38d3d0b2 dev_1.0.0_yuyr 完成 log和bind模块开发部署测试 (#8)
- [x] 完成log模块镜像构建、本地端到端写日志——收集——查询流程;
- [x] 完成bind模块构建;
- [x] 内置域名IP自动更新脚本,使用 /private/argus/etc目录下文件进行同步,容器启动时自动写IP,定时任务刷新更新DNS服务器IP和DNS规则;

Co-authored-by: root <root@curious.host.com>
Reviewed-on: #8
Reviewed-by: sundapeng <sundp@mail.zgclab.edu.cn>
2025-09-22 16:39:38 +08:00
55 changed files with 3004 additions and 2 deletions

138
build/build_images.sh Executable file
View File

@ -0,0 +1,138 @@
#!/usr/bin/env bash
set -euo pipefail
# 帮助信息
show_help() {
cat << EOF
ARGUS Unified Build System - Image Build Tool
Usage: $0 [OPTIONS]
Options:
--intranet Use intranet mirror for Ubuntu 22.04 packages
-h, --help Show this help message
Examples:
$0 # Build with default sources
$0 --intranet # Build with intranet mirror
EOF
}
# 解析命令行参数
use_intranet=false
while [[ $# -gt 0 ]]; do
case $1 in
--intranet)
use_intranet=true
shift
;;
-h|--help)
show_help
exit 0
;;
*)
echo "Unknown option: $1"
show_help
exit 1
;;
esac
done
# 获取项目根目录
root="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
cd "$root"
echo "======================================="
echo "ARGUS Unified Build System"
echo "======================================="
if [[ "$use_intranet" == true ]]; then
echo "🌐 Mode: Intranet (Using internal mirror: 10.68.64.1)"
build_args="--build-arg USE_INTRANET=true"
else
echo "🌐 Mode: Public (Using default package sources)"
build_args=""
fi
echo "📁 Build context: $root"
echo ""
# 构建镜像的函数
build_image() {
local image_name=$1
local dockerfile_path=$2
local tag=$3
echo "🔄 Building $image_name image..."
echo " Dockerfile: $dockerfile_path"
echo " Tag: $tag"
if docker build $build_args -f "$dockerfile_path" -t "$tag" .; then
echo "$image_name image built successfully"
return 0
else
echo "❌ Failed to build $image_name image"
return 1
fi
}
# 构建所有镜像
images_built=()
build_failed=false
# 构建 Elasticsearch 镜像
if build_image "Elasticsearch" "src/log/elasticsearch/build/Dockerfile" "argus-elasticsearch:latest"; then
images_built+=("argus-elasticsearch:latest")
else
build_failed=true
fi
echo ""
# 构建 Kibana 镜像
if build_image "Kibana" "src/log/kibana/build/Dockerfile" "argus-kibana:latest"; then
images_built+=("argus-kibana:latest")
else
build_failed=true
fi
echo ""
# 构建 BIND9 镜像
if build_image "BIND9" "src/bind/build/Dockerfile" "argus-bind9:latest"; then
images_built+=("argus-bind9:latest")
else
build_failed=true
fi
echo ""
echo "======================================="
echo "📦 Build Summary"
echo "======================================="
if [[ ${#images_built[@]} -gt 0 ]]; then
echo "✅ Successfully built images:"
for image in "${images_built[@]}"; do
echo "$image"
done
fi
if [[ "$build_failed" == true ]]; then
echo ""
echo "❌ Some images failed to build. Please check the errors above."
exit 1
fi
if [[ "$use_intranet" == true ]]; then
echo ""
echo "🌐 Built with intranet mirror configuration"
fi
echo ""
echo "🚀 Next steps:"
echo " cd src/log && ./scripts/save_images.sh # Export log images"
echo " cd src/bind && ./scripts/save_images.sh # Export bind images"
echo " cd src/log/tests && ./scripts/02_up.sh # Start log services"
echo ""

222
build/save_images.sh Executable file
View File

@ -0,0 +1,222 @@
#!/usr/bin/env bash
set -euo pipefail
# 帮助信息
show_help() {
cat << EOF
ARGUS Unified Build System - Image Export Tool
Usage: $0 [OPTIONS]
Options:
--compress Compress exported images with gzip
-h, --help Show this help message
Examples:
$0 # Export all images without compression
$0 --compress # Export all images with gzip compression
EOF
}
# 解析命令行参数
use_compression=false
while [[ $# -gt 0 ]]; do
case $1 in
--compress)
use_compression=true
shift
;;
-h|--help)
show_help
exit 0
;;
*)
echo "Unknown option: $1"
show_help
exit 1
;;
esac
done
# 获取项目根目录
root="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
cd "$root"
# 创建镜像输出目录
images_dir="$root/images"
mkdir -p "$images_dir"
echo "======================================="
echo "ARGUS Unified Build System - Image Export"
echo "======================================="
echo ""
if [[ "$use_compression" == true ]]; then
echo "🗜️ Mode: With gzip compression"
else
echo "📦 Mode: No compression"
fi
echo "📁 Output directory: $images_dir"
echo ""
# 定义镜像列表
declare -A images=(
["argus-elasticsearch:latest"]="argus-elasticsearch-latest.tar"
["argus-kibana:latest"]="argus-kibana-latest.tar"
["argus-bind9:latest"]="argus-bind9-latest.tar"
)
# 函数:检查镜像是否存在
check_image() {
local image_name="$1"
if docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^$image_name$"; then
echo "✅ Image found: $image_name"
return 0
else
echo "❌ Image not found: $image_name"
return 1
fi
}
# 函数:显示镜像信息
show_image_info() {
local image_name="$1"
echo "📋 Image info for $image_name:"
docker images "$image_name" --format " Size: {{.Size}}, Created: {{.CreatedSince}}, ID: {{.ID}}"
}
# 函数:保存镜像
save_image() {
local image_name="$1"
local output_file="$2"
local output_path="$images_dir/$output_file"
echo "🔄 Saving $image_name to $output_file..."
# 删除旧的镜像文件(如果存在)
if [[ -f "$output_path" ]]; then
echo " Removing existing file: $output_file"
rm "$output_path"
fi
if [[ "$use_compression" == true && -f "$output_path.gz" ]]; then
echo " Removing existing compressed file: $output_file.gz"
rm "$output_path.gz"
fi
# 保存镜像
docker save "$image_name" -o "$output_path"
if [[ "$use_compression" == true ]]; then
echo " Compressing with gzip..."
gzip "$output_path"
output_path="$output_path.gz"
output_file="$output_file.gz"
fi
# 检查文件大小
local file_size=$(du -h "$output_path" | cut -f1)
echo "✅ Saved successfully: $output_file ($file_size)"
}
echo "🔍 Checking for ARGUS images..."
echo ""
# 检查所有镜像
available_images=()
missing_images=()
for image_name in "${!images[@]}"; do
if check_image "$image_name"; then
show_image_info "$image_name"
available_images+=("$image_name")
else
missing_images+=("$image_name")
fi
echo ""
done
# 如果没有镜像存在,提示构建
if [[ ${#available_images[@]} -eq 0 ]]; then
echo "❌ No ARGUS images found to export."
echo ""
echo "🔧 Please build the images first with:"
echo " ./build/build_images.sh"
exit 1
fi
# 显示缺失的镜像
if [[ ${#missing_images[@]} -gt 0 ]]; then
echo "⚠️ Missing images (will be skipped):"
for image_name in "${missing_images[@]}"; do
echo "$image_name"
done
echo ""
fi
echo "💾 Starting image export process..."
echo ""
# 保存所有可用的镜像
exported_files=()
for image_name in "${available_images[@]}"; do
output_file="${images[$image_name]}"
save_image "$image_name" "$output_file"
if [[ "$use_compression" == true ]]; then
exported_files+=("$output_file.gz")
else
exported_files+=("$output_file")
fi
echo ""
done
echo "======================================="
echo "📦 Export Summary"
echo "======================================="
# 显示导出的文件
echo "📁 Exported files in $images_dir:"
total_size=0
for file in "${exported_files[@]}"; do
full_path="$images_dir/$file"
if [[ -f "$full_path" ]]; then
size=$(du -h "$full_path" | cut -f1)
size_bytes=$(du -b "$full_path" | cut -f1)
total_size=$((total_size + size_bytes))
echo "$file ($size)"
fi
done
# 显示总大小
if [[ $total_size -gt 0 ]]; then
total_size_human=$(numfmt --to=iec --suffix=B $total_size)
echo ""
echo "📊 Total size: $total_size_human"
fi
echo ""
echo "🚀 Usage instructions:"
echo " To load these images on another system:"
if [[ "$use_compression" == true ]]; then
for file in "${exported_files[@]}"; do
if [[ -f "$images_dir/$file" ]]; then
base_name="${file%.gz}"
echo " gunzip $file && docker load -i $base_name"
fi
done
else
for file in "${exported_files[@]}"; do
if [[ -f "$images_dir/$file" ]]; then
echo " docker load -i $file"
fi
done
fi
echo ""
echo "✅ Image export completed successfully!"
echo ""

2
src/bind/.gitignore vendored Normal file
View File

@ -0,0 +1,2 @@
images/

66
src/bind/build/Dockerfile Normal file
View File

@ -0,0 +1,66 @@
FROM ubuntu:22.04
# Set timezone and avoid interactive prompts
ENV DEBIAN_FRONTEND=noninteractive
ENV TZ=Asia/Shanghai
# 设置构建参数
ARG USE_INTRANET=false
# 配置内网 apt 源 (如果指定了内网选项)
RUN if [ "$USE_INTRANET" = "true" ]; then \
echo "Configuring intranet apt sources..." && \
cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
fi
# Update package list and install required packages
RUN apt-get update && \
apt-get install -y \
bind9 \
bind9utils \
bind9-doc \
supervisor \
net-tools \
inetutils-ping \
vim \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
# 配置部署时使用的apt源
RUN if [ "$USE_INTRANET" = "true" ]; then \
echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
fi
# Create supervisor configuration directory
RUN mkdir -p /etc/supervisor/conf.d
# Copy supervisor configuration
COPY src/bind/build/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
# Copy BIND9 configuration files
COPY src/bind/build/named.conf.local /etc/bind/named.conf.local
COPY src/bind/build/db.argus.com /etc/bind/db.argus.com
# Copy startup and reload scripts
COPY src/bind/build/startup.sh /usr/local/bin/startup.sh
COPY src/bind/build/reload-bind9.sh /usr/local/bin/reload-bind9.sh
COPY src/bind/build/argus_dns_sync.sh /usr/local/bin/argus_dns_sync.sh
COPY src/bind/build/update-dns.sh /usr/local/bin/update-dns.sh
# Make scripts executable
RUN chmod +x /usr/local/bin/startup.sh /usr/local/bin/reload-bind9.sh /usr/local/bin/argus_dns_sync.sh /usr/local/bin/update-dns.sh
# Set proper ownership for BIND9 files
RUN chown bind:bind /etc/bind/named.conf.local /etc/bind/db.argus.com
# Expose DNS port
EXPOSE 53/tcp 53/udp
# Use root user as requested
USER root
# Start with startup script
CMD ["/usr/local/bin/startup.sh"]

View File

@ -0,0 +1,100 @@
#!/usr/bin/env bash
set -euo pipefail
WATCH_DIR="/private/argus/etc"
ZONE_DB="/private/argus/bind/db.argus.com"
LOCKFILE="/var/lock/argus_dns_sync.lock"
BACKUP_DIR="/private/argus/bind/.backup"
SLEEP_SECONDS=10
RELOAD_SCRIPT="/usr/local/bin/reload-bind9.sh" # 这里放你已有脚本的路径
mkdir -p "$(dirname "$LOCKFILE")" "$BACKUP_DIR"
is_ipv4() {
local ip="$1"
[[ "$ip" =~ ^([0-9]{1,3}\.){3}[0-9]{1,3}$ ]] || return 1
IFS='.' read -r a b c d <<<"$ip"
for n in "$a" "$b" "$c" "$d"; do
(( n >= 0 && n <= 255 )) || return 1
done
return 0
}
get_current_ip() {
local name="$1"
sed -n -E "s/^${name}[[:space:]]+IN[[:space:]]+A[[:space:]]+([0-9.]+)[[:space:]]*$/\1/p" "$ZONE_DB" | head -n1
}
upsert_record() {
local name="$1"
local new_ip="$2"
local ts
ts="$(date +%Y%m%d-%H%M%S)"
local changed=0
cp -a "$ZONE_DB" "$BACKUP_DIR/db.argus.com.$ts.bak"
local cur_ip
cur_ip="$(get_current_ip "$name" || true)"
if [[ -z "$cur_ip" ]]; then
# Ensure the file ends with a newline before adding new record
if [[ -s "$ZONE_DB" ]] && [[ $(tail -c1 "$ZONE_DB" | wc -l) -eq 0 ]]; then
echo "" >> "$ZONE_DB"
fi
printf "%-20s IN A %s\n" "$name" "$new_ip" >> "$ZONE_DB"
echo "[ADD] ${name} -> ${new_ip}"
changed=1
elif [[ "$cur_ip" != "$new_ip" ]]; then
awk -v n="$name" -v ip="$new_ip" '
{
if ($1==n && $2=="IN" && $3=="A") {
printf "%-20s IN A %s\n", n, ip
} else {
print
}
}
' "$ZONE_DB" > "${ZONE_DB}.tmp" && mv "${ZONE_DB}.tmp" "$ZONE_DB"
echo "[UPDATE] ${name}: ${cur_ip} -> ${new_ip}"
changed=1
else
echo "[SKIP] ${name} unchanged (${new_ip})"
fi
return $changed
}
while true; do
exec 9>"$LOCKFILE"
if flock -n 9; then
shopt -s nullglob
NEED_RELOAD=0
for f in "$WATCH_DIR"/*.argus.com; do
base="$(basename "$f")"
name="${base%.argus.com}"
ip="$(grep -Eo '([0-9]{1,3}\.){3}[0-9]{1,3}' "$f" | tail -n1 || true)"
if [[ -z "$ip" ]] || ! is_ipv4 "$ip"; then
echo "[WARN] $f 未找到有效 IPv4跳过"
continue
fi
if upsert_record "$name" "$ip"; then
NEED_RELOAD=1
fi
done
if [[ $NEED_RELOAD -eq 1 ]]; then
echo "[INFO] 检测到 db.argus.com 变更,执行 reload-bind9.sh"
bash "$RELOAD_SCRIPT"
fi
flock -u 9
else
echo "[INFO] 已有同步任务在运行,跳过本轮"
fi
sleep "$SLEEP_SECONDS"
done

View File

@ -0,0 +1,16 @@
$TTL 604800
@ IN SOA ns1.argus.com. admin.argus.com. (
2 ; Serial
604800 ; Refresh
86400 ; Retry
2419200 ; Expire
604800 ) ; Negative Cache TTL
; 定义 DNS 服务器
@ IN NS ns1.argus.com.
; 定义 ns1 主机
ns1 IN A 127.0.0.1
; 定义 web 指向 12.4.5.6
web IN A 12.4.5.6

View File

@ -0,0 +1,68 @@
#!/bin/bash
# DNS监控脚本 - 每10秒检查dns.conf是否有变化
# 如果有变化则执行update-dns.sh脚本
DNS_CONF="/private/argus/etc/dns.conf"
DNS_BACKUP="/tmp/dns.conf.backup"
UPDATE_SCRIPT="/private/argus/etc/update-dns.sh"
LOG_FILE="/var/log/supervisor/dns-monitor.log"
# 确保日志文件存在
touch "$LOG_FILE"
log_message() {
echo "$(date '+%Y-%m-%d %H:%M:%S') [DNS-Monitor] $1" >> "$LOG_FILE"
}
log_message "DNS监控脚本启动"
while true; do
if [ -f "$DNS_CONF" ]; then
if [ -f "$DNS_BACKUP" ]; then
# 比较文件内容
if ! cmp -s "$DNS_CONF" "$DNS_BACKUP"; then
log_message "检测到DNS配置变化"
# 更新备份文件
cp "$DNS_CONF" "$DNS_BACKUP"
# 执行更新脚本
if [ -x "$UPDATE_SCRIPT" ]; then
log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
"$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
if [ $? -eq 0 ]; then
log_message "DNS更新脚本执行成功"
else
log_message "DNS更新脚本执行失败"
fi
else
log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
fi
fi
else
# 第一次检测到配置文件,执行更新脚本
if [ -x "$UPDATE_SCRIPT" ]; then
log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
"$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
if [ $? -eq 0 ]; then
log_message "DNS更新脚本执行成功"
# 第一次运行,创建备份并执行更新
cp "$DNS_CONF" "$DNS_BACKUP"
log_message "创建DNS配置备份文件"
else
log_message "DNS更新脚本执行失败"
fi
else
log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
fi
fi
else
log_message "警告: DNS配置文件不存在: $DNS_CONF"
fi
sleep 10
done

View File

@ -0,0 +1,4 @@
zone "argus.com" {
type master;
file "/etc/bind/db.argus.com";
};

View File

@ -0,0 +1,27 @@
#!/bin/bash
echo "Reloading BIND9 configuration..."
# Check if configuration files are valid
echo "Checking named.conf.local syntax..."
if ! named-checkconf /etc/bind/named.conf.local; then
echo "ERROR: named.conf.local has syntax errors!"
exit 1
fi
echo "Checking zone file syntax..."
if ! named-checkzone argus.com /etc/bind/db.argus.com; then
echo "ERROR: db.argus.com has syntax errors!"
exit 1
fi
# Reload BIND9 via supervisor
echo "Reloading BIND9 service..."
supervisorctl restart bind9
if [ $? -eq 0 ]; then
echo "BIND9 reloaded successfully!"
else
echo "ERROR: Failed to reload BIND9!"
exit 1
fi

40
src/bind/build/startup.sh Normal file
View File

@ -0,0 +1,40 @@
#!/bin/bash
# Set /private permissions to 777 as requested
chmod 777 /private 2>/dev/null || true
# Create persistent directories for BIND9 configs and DNS sync
mkdir -p /private/argus/bind
mkdir -p /private/argus/etc
# Copy configuration files to persistent storage if they don't exist
if [ ! -f /private/argus/bind/named.conf.local ]; then
cp /etc/bind/named.conf.local /private/argus/bind/named.conf.local
fi
if [ ! -f /private/argus/bind/db.argus.com ]; then
cp /etc/bind/db.argus.com /private/argus/bind/db.argus.com
fi
# Copy update-dns.sh to /private/argus/etc/
cp /usr/local/bin/update-dns.sh /private/argus/etc/update-dns.sh
chown bind:bind /private/argus/etc/update-dns.sh
chmod a+x /private/argus/etc/update-dns.sh
# Create symlinks to use persistent configs
ln -sf /private/argus/bind/named.conf.local /etc/bind/named.conf.local
ln -sf /private/argus/bind/db.argus.com /etc/bind/db.argus.com
# Set proper ownership
chown bind:bind /private/argus/bind/named.conf.local /private/argus/bind/db.argus.com
# 记录容器ip地址更新到dns.conf
IP=`ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}'`
echo current IP: ${IP}
echo ${IP} > /private/argus/etc/dns.conf
# Create supervisor log directory
mkdir -p /var/log/supervisor
# Start supervisor
exec /usr/bin/supervisord -c /etc/supervisor/conf.d/supervisord.conf

View File

@ -0,0 +1,37 @@
[unix_http_server]
file=/var/run/supervisor.sock
chmod=0700
[supervisord]
nodaemon=true
user=root
logfile=/var/log/supervisor/supervisord.log
pidfile=/var/run/supervisord.pid
[rpcinterface:supervisor]
supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface
[supervisorctl]
serverurl=unix:///var/run/supervisor.sock
[program:bind9]
command=/usr/sbin/named -g -c /etc/bind/named.conf -u bind
user=bind
autostart=true
autorestart=true
stderr_logfile=/var/log/supervisor/bind9.err.log
stdout_logfile=/var/log/supervisor/bind9.out.log
priority=10
[program:argus-dns-sync]
command=/usr/local/bin/argus_dns_sync.sh
autostart=true
autorestart=true
startsecs=3
stopsignal=TERM
user=root
stdout_logfile=/var/log/argus_dns_sync.out.log
stderr_logfile=/var/log/argus_dns_sync.err.log
; 根据环境调整环境变量(可选)
; environment=RNDC_RELOAD="yes"

31
src/bind/build/update-dns.sh Executable file
View File

@ -0,0 +1,31 @@
#!/bin/sh
# update-dns.sh
# 从 /private/argus/etc/dns.conf 读取 IP写入 /etc/resolv.conf
DNS_CONF="/private/argus/etc/dns.conf"
RESOLV_CONF="/etc/resolv.conf"
# 检查配置文件是否存在
if [ ! -f "$DNS_CONF" ]; then
echo "配置文件不存在: $DNS_CONF" >&2
exit 1
fi
# 生成 resolv.conf 内容
{
while IFS= read -r ip; do
# 跳过空行和注释
case "$ip" in
\#*) continue ;;
"") continue ;;
esac
echo "nameserver $ip"
done < "$DNS_CONF"
} > "$RESOLV_CONF".tmp
# 替换写入 /etc/resolv.conf
cat "$RESOLV_CONF".tmp > "$RESOLV_CONF"
rm -f "$RESOLV_CONF".tmp
echo "已更新 $RESOLV_CONF"

View File

@ -0,0 +1,16 @@
services:
bind9:
image: argus-bind9:latest
container_name: argus-bind9-test
ports:
- "53:53/tcp"
- "53:53/udp"
volumes:
- ./private:/private
restart: unless-stopped
networks:
- bind-test-network
networks:
bind-test-network:
driver: bridge

View File

@ -0,0 +1,115 @@
#!/bin/bash
# End-to-end test for BIND9 DNS server
# This script runs all tests in sequence to validate the complete functionality
# Usage: ./00_e2e_test.sh
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
echo "=========================================="
echo "BIND9 DNS Server End-to-End Test Suite"
echo "=========================================="
# Track test results
total_tests=0
passed_tests=0
failed_tests=0
# Function to run a test step
run_test_step() {
local step_name="$1"
local script_name="$2"
local description="$3"
echo ""
echo "[$step_name] $description"
echo "$(printf '=%.0s' {1..50})"
((total_tests++))
if [ ! -f "$SCRIPT_DIR/$script_name" ]; then
echo "✗ Test script not found: $script_name"
((failed_tests++))
return 1
fi
# Make sure script is executable
chmod +x "$SCRIPT_DIR/$script_name"
# Run the test
echo "Executing: $SCRIPT_DIR/$script_name"
if "$SCRIPT_DIR/$script_name"; then
echo "$step_name completed successfully"
((passed_tests++))
return 0
else
echo "$step_name failed"
((failed_tests++))
return 1
fi
}
# Cleanup any previous test environment (but preserve the Docker image)
echo ""
echo "[SETUP] Cleaning up any previous test environment..."
if [ -f "$SCRIPT_DIR/05_cleanup.sh" ]; then
chmod +x "$SCRIPT_DIR/05_cleanup.sh"
"$SCRIPT_DIR/05_cleanup.sh" || true
fi
echo ""
echo "Starting BIND9 DNS server end-to-end test sequence..."
# Test sequence
run_test_step "TEST-01" "01_start_container.sh" "Start BIND9 container" || true
run_test_step "TEST-02" "02_dig_test.sh" "Initial DNS resolution test" || true
run_test_step "TEST-03" "03_reload_test.sh" "Configuration reload with IP modification" || true
run_test_step "TEST-03.5" "03.5_dns_sync_test.sh" "DNS auto-sync functionality test" || true
run_test_step "TEST-04" "04_persistence_test.sh" "Configuration persistence after restart" || true
# Final cleanup (but preserve logs for review)
echo ""
echo "[CLEANUP] Cleaning up test environment..."
run_test_step "CLEANUP" "05_cleanup.sh" "Clean up containers and networks" || true
# Test summary
echo ""
echo "=========================================="
echo "TEST SUMMARY"
echo "=========================================="
echo "Total tests: $total_tests"
echo "Passed: $passed_tests"
echo "Failed: $failed_tests"
if [ $failed_tests -eq 0 ]; then
echo ""
echo "✅ ALL TESTS PASSED!"
echo ""
echo "BIND9 DNS server functionality validated:"
echo " ✓ Container startup and basic functionality"
echo " ✓ DNS resolution for configured domains"
echo " ✓ Configuration modification and reload"
echo " ✓ DNS auto-sync from IP files"
echo " ✓ Configuration persistence across restarts"
echo " ✓ Cleanup and resource management"
echo ""
echo "The BIND9 DNS server is ready for production use."
exit 0
else
echo ""
echo "❌ SOME TESTS FAILED!"
echo ""
echo "Please review the test output above to identify and fix issues."
echo "You may need to:"
echo " - Check Docker installation and permissions"
echo " - Verify network connectivity"
echo " - Review BIND9 configuration files"
echo " - Check system resources and port availability"
exit 1
fi

View File

@ -0,0 +1,38 @@
#!/bin/bash
# Start BIND9 test container
# Usage: ./01_start_container.sh
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(dirname "$SCRIPT_DIR")"
cd "$TEST_DIR"
echo "Starting BIND9 test container..."
# Ensure private directory exists with proper permissions
mkdir -p private
chmod 777 private
# Start the container
docker compose up -d
echo "Waiting for container to be ready..."
sleep 5
# Check if container is running
if docker compose ps | grep -q "Up"; then
echo "✓ Container started successfully"
echo "Container status:"
docker compose ps
else
echo "✗ Failed to start container"
docker compose logs
exit 1
fi
echo ""
echo "BIND9 test environment is ready!"
echo "DNS server listening on localhost:53"

View File

@ -0,0 +1,72 @@
#!/bin/bash
# Test DNS resolution using dig
# Usage: ./02_dig_test.sh
set -e
echo "Testing DNS resolution with dig..."
# Function to test DNS query
test_dns_query() {
local hostname="$1"
local expected_ip="$2"
local description="$3"
echo ""
echo "Testing: $description"
echo "Query: $hostname.argus.com"
echo "Expected IP: $expected_ip"
# Perform dig query
result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
if [ "$result" = "QUERY_FAILED" ]; then
echo "✗ DNS query failed"
return 1
elif [ "$result" = "$expected_ip" ]; then
echo "✓ DNS query successful: $result"
return 0
else
echo "✗ DNS query returned unexpected result: $result"
return 1
fi
}
# Check if dig is available
if ! command -v dig &> /dev/null; then
echo "Installing dig (dnsutils)..."
apt-get update && apt-get install -y dnsutils
fi
# Check if container is running
if ! docker compose ps | grep -q "Up"; then
echo "Error: BIND9 container is not running"
echo "Please start the container first with: ./01_start_container.sh"
exit 1
fi
echo "=== DNS Resolution Tests ==="
# Test cases based on current configuration
failed_tests=0
# Test ns1.argus.com -> 127.0.0.1
if ! test_dns_query "ns1" "127.0.0.1" "Name server resolution"; then
((failed_tests++))
fi
# Test web.argus.com -> 12.4.5.6
if ! test_dns_query "web" "12.4.5.6" "Web server resolution"; then
((failed_tests++))
fi
echo ""
echo "=== Test Summary ==="
if [ $failed_tests -eq 0 ]; then
echo "✓ All DNS tests passed!"
exit 0
else
echo "$failed_tests test(s) failed"
exit 1
fi

View File

@ -0,0 +1,256 @@
#!/bin/bash
# Test DNS auto-sync functionality using argus_dns_sync.sh
# This test validates the automatic DNS record updates from IP files
# Usage: ./03.5_dns_sync_test.sh
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(dirname "$SCRIPT_DIR")"
echo "=== DNS Auto-Sync Functionality Test ==="
# Check if container is running
if ! docker compose ps | grep -q "Up"; then
echo "Error: BIND9 container is not running"
echo "Please start the container first with: ./01_start_container.sh"
exit 1
fi
# Check if dig is available
if ! command -v dig &> /dev/null; then
echo "Installing dig (dnsutils)..."
apt-get update && apt-get install -y dnsutils
fi
# Function to test DNS query
test_dns_query() {
local hostname="$1"
local expected_ip="$2"
local description="$3"
echo "Testing: $description"
echo "Query: $hostname.argus.com -> Expected: $expected_ip"
# Wait a moment for DNS cache
sleep 2
result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
if [ "$result" = "$expected_ip" ]; then
echo "$result"
return 0
else
echo "✗ Got: $result, Expected: $expected_ip"
return 1
fi
}
# Function to wait for sync to complete
wait_for_sync() {
local timeout=15
local elapsed=0
echo "Waiting for DNS sync to complete (max ${timeout}s)..."
while [ $elapsed -lt $timeout ]; do
if docker compose exec bind9 test -f /var/lock/argus_dns_sync.lock; then
echo "Sync process is running..."
else
echo "Sync completed"
sleep 2 # Extra wait for DNS propagation
return 0
fi
sleep 2
elapsed=$((elapsed + 2))
done
echo "Warning: Sync may still be running after ${timeout}s"
return 0
}
echo ""
echo "Step 1: Preparing test environment..."
# Ensure required directories exist
docker compose exec bind9 mkdir -p /private/argus/etc
docker compose exec bind9 mkdir -p /private/argus/bind/.backup
# Backup original configuration if it exists
docker compose exec bind9 test -f /private/argus/bind/db.argus.com && \
docker compose exec bind9 cp /private/argus/bind/db.argus.com /private/argus/bind/db.argus.com.backup.test || true
# Ensure initial configuration is available (may already be symlinked)
docker compose exec bind9 test -f /private/argus/bind/db.argus.com || \
docker compose exec bind9 cp /etc/bind/db.argus.com /private/argus/bind/db.argus.com
echo "✓ Test environment prepared"
echo ""
echo "Step 2: Testing initial DNS configuration..."
# Get current IP for web.argus.com (may have been changed by previous tests)
current_web_ip=$(dig @localhost web.argus.com A +short 2>/dev/null || echo "UNKNOWN")
echo "Current web.argus.com IP: $current_web_ip"
# Test that DNS is working (regardless of specific IP)
if [ "$current_web_ip" = "UNKNOWN" ] || [ -z "$current_web_ip" ]; then
echo "DNS resolution not working for web.argus.com"
exit 1
fi
echo "✓ DNS resolution is working"
echo ""
echo "Step 3: Creating IP files for auto-sync..."
# Create test IP files in the watch directory
echo "Creating test1.argus.com with IP 10.0.0.100"
docker compose exec bind9 bash -c 'echo "10.0.0.100" > /private/argus/etc/test1.argus.com'
echo "Creating test2.argus.com with IP 10.0.0.200"
docker compose exec bind9 bash -c 'echo "test2 service running on 10.0.0.200" > /private/argus/etc/test2.argus.com'
echo "Creating api.argus.com with IP 192.168.1.50"
docker compose exec bind9 bash -c 'echo "API server: 192.168.1.50 port 8080" > /private/argus/etc/api.argus.com'
echo "✓ IP files created"
echo ""
echo "Step 4: Checking DNS sync process..."
# Check if DNS sync process is already running (via supervisord)
if docker compose exec bind9 pgrep -f argus_dns_sync.sh > /dev/null; then
echo "✓ DNS sync process already running (via supervisord)"
else
echo "Starting DNS sync process manually..."
# Start the DNS sync process in background if not running
docker compose exec -d bind9 /usr/local/bin/argus_dns_sync.sh
echo "✓ DNS sync process started manually"
fi
# Wait for first sync cycle
wait_for_sync
echo ""
echo "Step 5: Testing auto-synced DNS records..."
failed_tests=0
# Test new DNS records created by auto-sync
if ! test_dns_query "test1" "10.0.0.100" "Auto-synced test1.argus.com"; then
((failed_tests++))
fi
if ! test_dns_query "test2" "10.0.0.200" "Auto-synced test2.argus.com"; then
((failed_tests++))
fi
if ! test_dns_query "api" "192.168.1.50" "Auto-synced api.argus.com"; then
((failed_tests++))
fi
# Verify original records still work (use current IP from earlier)
if ! test_dns_query "web" "$current_web_ip" "Original web.argus.com still working"; then
((failed_tests++))
fi
if ! test_dns_query "ns1" "127.0.0.1" "Original ns1.argus.com still working"; then
((failed_tests++))
fi
echo ""
echo "Step 6: Testing IP update functionality..."
# Update an existing IP file
echo "Updating test1.argus.com IP from 10.0.0.100 to 10.0.0.150"
docker compose exec bind9 bash -c 'echo "10.0.0.150" > /private/argus/etc/test1.argus.com'
# Wait for sync
wait_for_sync
# Test updated record
if ! test_dns_query "test1" "10.0.0.150" "Updated test1.argus.com IP"; then
((failed_tests++))
fi
echo ""
echo "Step 7: Testing invalid IP handling..."
# Create file with invalid IP
echo "Creating invalid.argus.com with invalid IP"
docker compose exec bind9 bash -c 'echo "this is not an IP address" > /private/argus/etc/invalid.argus.com'
# Wait for sync (should skip invalid IP)
wait_for_sync
# Verify invalid record was not added (should fail to resolve)
result=$(dig @localhost invalid.argus.com A +short 2>/dev/null || echo "NO_RESULT")
if [ "$result" = "NO_RESULT" ] || [ -z "$result" ]; then
echo "✓ Invalid IP correctly ignored"
else
echo "✗ Invalid IP was processed: $result"
((failed_tests++))
fi
echo ""
echo "Step 8: Verifying backup functionality..."
# Check if backups were created
backup_count=$(docker compose exec bind9 ls -1 /private/argus/bind/.backup/ | wc -l || echo "0")
if [ "$backup_count" -gt 0 ]; then
echo "✓ Configuration backups created ($backup_count files)"
# Show latest backup
docker compose exec bind9 ls -la /private/argus/bind/.backup/ | tail -1
else
echo "✗ No backup files found"
((failed_tests++))
fi
echo ""
echo "Step 9: Cleanup..."
# Note: We don't stop the DNS sync process since it's managed by supervisord
echo "Note: DNS sync process will continue running (managed by supervisord)"
# Clean up test files
docker compose exec bind9 rm -f /private/argus/etc/test1.argus.com
docker compose exec bind9 rm -f /private/argus/etc/test2.argus.com
docker compose exec bind9 rm -f /private/argus/etc/api.argus.com
docker compose exec bind9 rm -f /private/argus/etc/invalid.argus.com
# Restore original configuration if backup exists
docker compose exec bind9 test -f /private/argus/bind/db.argus.com.backup.test && \
docker compose exec bind9 cp /private/argus/bind/db.argus.com.backup.test /private/argus/bind/db.argus.com && \
docker compose exec bind9 rm /private/argus/bind/db.argus.com.backup.test || true
# Reload original configuration
docker compose exec bind9 /usr/local/bin/reload-bind9.sh
echo "✓ Cleanup completed"
echo ""
echo "=== DNS Auto-Sync Test Summary ==="
if [ $failed_tests -eq 0 ]; then
echo "✅ All DNS auto-sync tests passed!"
echo ""
echo "Validated functionality:"
echo " ✓ Automatic DNS record creation from IP files"
echo " ✓ IP address extraction from various file formats"
echo " ✓ Dynamic DNS record updates"
echo " ✓ Invalid IP address handling"
echo " ✓ Configuration backup mechanism"
echo " ✓ Preservation of existing DNS records"
echo ""
echo "The DNS auto-sync functionality is working correctly!"
exit 0
else
echo "$failed_tests DNS auto-sync test(s) failed!"
echo ""
echo "Please check:"
echo " - argus_dns_sync.sh script configuration"
echo " - File permissions in /private/argus/etc/"
echo " - BIND9 reload functionality"
echo " - Network connectivity and DNS resolution"
exit 1
fi

View File

@ -0,0 +1,112 @@
#!/bin/bash
# Test DNS configuration reload with IP modification
# Usage: ./03_reload_test.sh
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(dirname "$SCRIPT_DIR")"
echo "=== DNS Configuration Reload Test ==="
# Check if container is running
if ! docker compose ps | grep -q "Up"; then
echo "Error: BIND9 container is not running"
echo "Please start the container first with: ./01_start_container.sh"
exit 1
fi
# Check if dig is available
if ! command -v dig &> /dev/null; then
echo "Installing dig (dnsutils)..."
apt-get update && apt-get install -y dnsutils
fi
# Function to test DNS query
test_dns_query() {
local hostname="$1"
local expected_ip="$2"
local description="$3"
echo "Testing: $description"
echo "Query: $hostname.argus.com -> Expected: $expected_ip"
result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
if [ "$result" = "$expected_ip" ]; then
echo "$result"
return 0
else
echo "✗ Got: $result, Expected: $expected_ip"
return 1
fi
}
echo ""
echo "Step 1: Testing initial DNS configuration..."
# Test initial configuration
if ! test_dns_query "web" "12.4.5.6" "Initial web.argus.com resolution"; then
echo "Initial DNS test failed"
exit 1
fi
echo ""
echo "Step 2: Modifying DNS configuration..."
# Backup original configuration
cp "$TEST_DIR/private/argus/bind/db.argus.com" "$TEST_DIR/private/argus/bind/db.argus.com.backup" 2>/dev/null || true
# Create new configuration with modified IP
DB_FILE="$TEST_DIR/private/argus/bind/db.argus.com"
# Check if persistent config exists, if not use from container
if [ ! -f "$DB_FILE" ]; then
echo "Persistent config not found, copying from container..."
docker compose exec bind9 cp /etc/bind/db.argus.com /private/argus/bind/db.argus.com
docker compose exec bind9 chown bind:bind /private/argus/bind/db.argus.com
fi
# Modify the IP address (12.4.5.6 -> 192.168.1.100)
sed -i 's/12\.4\.5\.6/192.168.1.100/g' "$DB_FILE"
# Increment serial number for DNS cache invalidation
current_serial=$(grep -o "2[[:space:]]*;" "$DB_FILE" | grep -o "2")
new_serial=$((current_serial + 1))
sed -i "s/2[[:space:]]*;/${new_serial} ;/" "$DB_FILE"
echo "Modified configuration:"
echo "- Changed web.argus.com IP: 12.4.5.6 -> 192.168.1.100"
echo "- Updated serial number: $current_serial -> $new_serial"
echo ""
echo "Step 3: Reloading BIND9 configuration..."
# Reload BIND9 configuration
docker compose exec bind9 /usr/local/bin/reload-bind9.sh
echo "Configuration reloaded"
# Wait a moment for changes to take effect
sleep 3
echo ""
echo "Step 4: Testing modified DNS configuration..."
# Test modified configuration
if ! test_dns_query "web" "192.168.1.100" "Modified web.argus.com resolution"; then
echo "Modified DNS test failed"
exit 1
fi
# Also verify ns1 still works
if ! test_dns_query "ns1" "127.0.0.1" "ns1.argus.com still working"; then
echo "ns1 DNS test failed after reload"
exit 1
fi
echo ""
echo "✓ DNS configuration reload test completed successfully!"
echo "✓ IP address changed from 12.4.5.6 to 192.168.1.100"
echo "✓ Configuration persisted and reloaded correctly"

View File

@ -0,0 +1,115 @@
#!/bin/bash
# Test configuration persistence after container restart
# Usage: ./04_persistence_test.sh
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(dirname "$SCRIPT_DIR")"
echo "=== Configuration Persistence Test ==="
# Check if dig is available
if ! command -v dig &> /dev/null; then
echo "Installing dig (dnsutils)..."
apt-get update && apt-get install -y dnsutils
fi
# Function to test DNS query
test_dns_query() {
local hostname="$1"
local expected_ip="$2"
local description="$3"
echo "Testing: $description"
echo "Query: $hostname.argus.com -> Expected: $expected_ip"
result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
if [ "$result" = "$expected_ip" ]; then
echo "$result"
return 0
else
echo "✗ Got: $result, Expected: $expected_ip"
return 1
fi
}
echo ""
echo "Step 1: Stopping current container..."
# Stop the container
docker compose down
echo "Container stopped"
echo ""
echo "Step 2: Verifying persistent configuration exists..."
# Check if modified configuration exists
DB_FILE="$TEST_DIR/private/argus/bind/db.argus.com"
if [ ! -f "$DB_FILE" ]; then
echo "✗ Persistent configuration file not found: $DB_FILE"
exit 1
fi
# Check if the modified IP is in the configuration
if grep -q "192.168.1.100" "$DB_FILE"; then
echo "✓ Modified IP (192.168.1.100) found in persistent configuration"
else
echo "✗ Modified IP not found in persistent configuration"
echo "Configuration content:"
cat "$DB_FILE"
exit 1
fi
echo ""
echo "Step 3: Restarting container with persistent configuration..."
# Start the container again
docker compose up -d
echo "Waiting for container to be ready..."
sleep 5
# Check if container is running
if ! docker compose ps | grep -q "Up"; then
echo "✗ Failed to restart container"
docker compose logs
exit 1
fi
echo "✓ Container restarted successfully"
echo ""
echo "Step 4: Testing DNS resolution after restart..."
# Wait a bit more for DNS to be fully ready
sleep 5
# Test that the modified configuration is still active
if ! test_dns_query "web" "192.168.1.100" "Persistent web.argus.com resolution"; then
echo "✗ Persistent configuration test failed"
exit 1
fi
# Also verify ns1 still works
if ! test_dns_query "ns1" "127.0.0.1" "ns1.argus.com still working"; then
echo "✗ ns1 DNS test failed after restart"
exit 1
fi
echo ""
echo "Step 5: Verifying configuration files are linked correctly..."
# Check that the persistent files are properly linked
echo "Checking file links in container:"
docker compose exec bind9 ls -la /etc/bind/named.conf.local /etc/bind/db.argus.com
echo ""
echo "✓ Configuration persistence test completed successfully!"
echo "✓ Modified IP (192.168.1.100) persisted after container restart"
echo "✓ Configuration files properly linked to persistent storage"
echo "✓ DNS resolution working correctly with persisted configuration"

View File

@ -0,0 +1,87 @@
#!/bin/bash
# Clean up test environment and containers
# Usage: ./05_cleanup.sh [--full]
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(dirname "$SCRIPT_DIR")"
# Parse command line arguments
FULL_CLEANUP=true
while [[ $# -gt 0 ]]; do
case $1 in
--full)
FULL_CLEANUP=true
shift
;;
*)
echo "Unknown option: $1"
echo "Usage: $0 [--full]"
echo " --full: Also remove persistent data "
exit 1
;;
esac
done
cd "$TEST_DIR"
echo "=== Cleaning up BIND9 test environment ==="
echo ""
echo "Step 1: Stopping and removing containers..."
# Stop and remove containers
docker compose down -v
echo "✓ Containers stopped and removed"
echo ""
echo "Step 2: Removing Docker networks..."
# Clean up networks
docker network prune -f > /dev/null 2>&1 || true
echo "✓ Docker networks cleaned"
if [ "$FULL_CLEANUP" = true ]; then
echo ""
echo "Step 3: Removing persistent data..."
# Remove persistent data directory
if [ -d "private" ]; then
rm -rf private
echo "✓ Persistent data directory removed"
else
echo "✓ No persistent data directory found"
fi
else
echo ""
echo "Step 3: Preserving persistent data and Docker image..."
echo "✓ Persistent data preserved in: private/"
echo "✓ Docker image 'argus-bind9:latest' preserved"
echo ""
echo "To perform full cleanup including persistent data and image, run:"
echo " $0 --full"
fi
echo ""
echo "=== Cleanup Summary ==="
echo "✓ Containers stopped and removed"
echo "✓ Docker networks cleaned"
if [ "$FULL_CLEANUP" = true ]; then
echo "✓ Persistent data removed"
echo ""
echo "Full cleanup completed! Test environment completely removed."
else
echo "✓ Persistent data preserved"
echo "✓ Docker image preserved"
echo ""
echo "Basic cleanup completed! Run './01_start_container.sh' to restart testing."
fi
echo ""
echo "Test environment cleanup finished."

5
src/log/.gitignore vendored Normal file
View File

@ -0,0 +1,5 @@
private/
images/

View File

@ -0,0 +1,8 @@
测试log模块开发
elasticsearch: 部署镜像构建及启动脚本解决账号问题、挂载目录、使用supervisor守护
kibana: 镜像构建
fluent-bit: 安装包,脚本准备, 交付给大鹏统一组织客户端侧安装流程
init: EK初始化脚本数据视图创建脚本等

View File

@ -0,0 +1,56 @@
FROM docker.elastic.co/elasticsearch/elasticsearch:8.13.4
# 切换到 root 用户进行系统级安装
USER root
# 修改elasticsearch用户的UID和GID
RUN usermod -u 2133 elasticsearch && \
groupmod -g 2015 elasticsearch && \
chown -R elasticsearch:elasticsearch /usr/share/elasticsearch
# 设置构建参数
ARG USE_INTRANET=false
# 配置内网 apt 源 (如果指定了内网选项)
RUN if [ "$USE_INTRANET" = "true" ]; then \
echo "Configuring intranet apt sources..." && \
cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
fi
# 安装 supervisor, net-tools, vim
RUN apt-get update && \
apt-get install -y supervisor net-tools inetutils-ping vim && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
# 配置部署时使用的apt源
RUN if [ "$USE_INTRANET" = "true" ]; then \
echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
fi
# 创建 supervisor 日志目录
RUN mkdir -p /var/log/supervisor
# 复制 supervisor 配置文件
COPY src/log/elasticsearch/build/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
# 复制启动脚本
COPY src/log/elasticsearch/build/start-es-supervised.sh /usr/local/bin/start-es-supervised.sh
RUN chmod +x /usr/local/bin/start-es-supervised.sh
# 复制DNS监控脚本
COPY src/log/elasticsearch/build/dns-monitor.sh /usr/local/bin/dns-monitor.sh
RUN chmod +x /usr/local/bin/dns-monitor.sh
# 保持 root 用户,由 supervisor 管理用户切换
USER root
# 暴露端口
EXPOSE 9200 9300
# 使用 supervisor 作为入口点
CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

View File

@ -0,0 +1 @@
../../../bind/build/dns-monitor.sh

View File

@ -0,0 +1,32 @@
#!/bin/bash
set -euo pipefail
echo "[INFO] Starting Elasticsearch under supervisor..."
# 创建数据目录并设置权限(如果不存在)
mkdir -p /private/argus/log/elasticsearch
# 创建软链接到Elasticsearch预期的数据目录
if [ -L /usr/share/elasticsearch/data ]; then
rm /usr/share/elasticsearch/data
elif [ -d /usr/share/elasticsearch/data ]; then
rm -rf /usr/share/elasticsearch/data
fi
ln -sf /private/argus/log/elasticsearch /usr/share/elasticsearch/data
# 记录容器ip地址
DOMAIN=es.log.argus.com
IP=`ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}'`
echo current IP: ${IP}
echo ${IP} > /private/argus/etc/${DOMAIN}
echo "[INFO] Data directory linked: /usr/share/elasticsearch/data -> /private/argus/log/elasticsearch"
# 设置环境变量ES配置通过docker-compose传递
export ES_JAVA_OPTS="${ES_JAVA_OPTS:-"-Xms512m -Xmx512m"}"
echo "[INFO] Starting Elasticsearch process..."
# 启动原始的Elasticsearch entrypoint
exec /usr/local/bin/docker-entrypoint.sh elasticsearch

View File

@ -0,0 +1,39 @@
[supervisord]
nodaemon=true
logfile=/var/log/supervisor/supervisord.log
pidfile=/var/run/supervisord.pid
user=root
[program:elasticsearch]
command=/usr/local/bin/start-es-supervised.sh
user=elasticsearch
stdout_logfile=/var/log/supervisor/elasticsearch.log
stderr_logfile=/var/log/supervisor/elasticsearch_error.log
autorestart=true
startretries=3
startsecs=30
stopwaitsecs=30
killasgroup=true
stopasgroup=true
[program:dns-monitor]
command=/usr/local/bin/dns-monitor.sh
user=root
stdout_logfile=/var/log/supervisor/dns-monitor.log
stderr_logfile=/var/log/supervisor/dns-monitor_error.log
autorestart=true
startretries=3
startsecs=5
stopwaitsecs=10
killasgroup=true
stopasgroup=true
[unix_http_server]
file=/var/run/supervisor.sock
chmod=0700
[supervisorctl]
serverurl=unix:///var/run/supervisor.sock
[rpcinterface:supervisor]
supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface

View File

@ -0,0 +1,37 @@
[SERVICE]
Daemon Off
Parsers_File parsers.conf
HTTP_Server On
HTTP_Listen 0.0.0.0
HTTP_Port 2020
storage.path /buffers
storage.sync normal
storage.checksum on
storage.backlog.mem_limit 128M
# 备注:该镜像默认未开启 Hot Reload修改配置后请重启容器。
@INCLUDE inputs.d/*.conf
[FILTER]
Name parser
Match app.*
Key_Name log
Parser timestamp_parser
Reserve_Data On
Preserve_Key On
Unescape_Key On
[FILTER]
Name record_modifier
Match *
Record cluster ${CLUSTER}
Record rack ${RACK}
Record host ${HOSTNAME}
[FILTER]
Name lua
Match app.*
script inject_labels.lua
call add_labels
@INCLUDE outputs.d/*.conf

View File

@ -0,0 +1,15 @@
function add_labels(tag, ts, record)
record["job_id"] = os.getenv("FB_JOB_ID") or record["job_id"] or "unknown"
record["user"] = os.getenv("FB_USER") or record["user"] or "unknown"
record["model"] = os.getenv("FB_MODEL") or record["model"] or "unknown"
record["gpu_id"] = os.getenv("FB_GPU_ID") or record["gpu_id"] or "na"
local p = record["log_path"] or ""
if string.find(p, "/logs/infer/") then
record["role"] = "infer"
elseif string.find(p, "/logs/train/") then
record["role"] = "train"
else
record["role"] = record["role"] or "app"
end
return 1, ts, record
end

View File

@ -0,0 +1,10 @@
[INPUT]
Name tail
Path /logs/train/*.log
Tag app.train
Path_Key log_path
Refresh_Interval 5
DB /buffers/train.db
Skip_Long_Lines On
storage.type filesystem
multiline.parser python,go,java

View File

@ -0,0 +1,10 @@
[INPUT]
Name tail
Path /logs/infer/*.log
Tag app.infer
Path_Key log_path
Refresh_Interval 5
DB /buffers/infer.db
Skip_Long_Lines On
storage.type filesystem
multiline.parser python,go,java

View File

@ -0,0 +1,24 @@
# 重要:使用 Logstash_Format + Logstash_Prefix生成 train-*/infer-* 索引
[OUTPUT]
Name es
Match app.train
Host ${ES_HOST}
Port ${ES_PORT}
Logstash_Format On
Logstash_Prefix train
Replace_Dots On
Generate_ID On
Retry_Limit False
Suppress_Type_Name On
[OUTPUT]
Name es
Match app.infer
Host ${ES_HOST}
Port ${ES_PORT}
Logstash_Format On
Logstash_Prefix infer
Replace_Dots On
Generate_ID On
Retry_Limit False
Suppress_Type_Name On

View File

@ -0,0 +1,27 @@
[MULTILINE_PARSER]
Name python
Type regex
Flush 2
Rule "start_state" "/^\d{4}-\d{2}-\d{2}[\sT]/" "cont"
Rule "cont" "/^\s+|^Traceback|^\tat\s+/" "cont"
[MULTILINE_PARSER]
Name go
Type regex
Flush 2
Rule "start_state" "/^[0-9]{4}\/[0-9]{2}\/[0-9]{2}/" "cont"
Rule "cont" "/^\s+|^\t/" "cont"
[MULTILINE_PARSER]
Name java
Type regex
Flush 2
Rule "start_state" "/^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}/" "cont"
Rule "cont" "/^\s+at\s+|^\t.../" "cont"
[PARSER]
Name timestamp_parser
Format regex
Regex ^(?<timestamp>\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})\s+(?<level>\w+)\s+(?<message>.*)$
Time_Key timestamp
Time_Format %Y-%m-%d %H:%M:%S

View File

@ -0,0 +1,47 @@
#!/bin/bash
set -euo pipefail
echo "[INFO] Starting Fluent Bit setup in Ubuntu container..."
# 安装必要的工具
echo "[INFO] Installing required packages..."
export DEBIAN_FRONTEND=noninteractive
apt-get update -qq
apt-get install -y -qq curl
# 解压bundle到/tmp
echo "[INFO] Extracting fluent-bit bundle..."
cp -r /private/etc /tmp
cp -r /private/packages /tmp
cd /tmp
# 安装 Fluent Bit 从 deb 包
echo "[INFO] Installing Fluent Bit from deb package..."
dpkg -i /tmp/packages/fluent-bit_3.1.9_amd64.deb || true
apt-get install -f -y -qq # 解决依赖问题
# 验证 Fluent Bit 可以运行
echo "[INFO] Fluent Bit version:"
/opt/fluent-bit/bin/fluent-bit --version
# 创建配置目录
mkdir -p /etc/fluent-bit
cp -r /tmp/etc/* /etc/fluent-bit/
# 创建日志和缓冲区目录
mkdir -p /logs/train /logs/infer /buffers
chmod 755 /logs/train /logs/infer /buffers
# 等待 Elasticsearch 就绪
echo "[INFO] Waiting for Elasticsearch to be ready..."
while ! curl -fs http://${ES_HOST}:${ES_PORT}/_cluster/health >/dev/null 2>&1; do
echo " Waiting for ES at ${ES_HOST}:${ES_PORT}..."
sleep 5
done
echo "[INFO] Elasticsearch is ready"
# 启动 Fluent Bit
echo "[INFO] Starting Fluent Bit with configuration from /etc/fluent-bit/"
echo "[INFO] Command: /opt/fluent-bit/bin/fluent-bit --config=/etc/fluent-bit/fluent-bit.conf"
exec /opt/fluent-bit/bin/fluent-bit \
--config=/etc/fluent-bit/fluent-bit.conf

View File

@ -0,0 +1,60 @@
FROM docker.elastic.co/kibana/kibana:8.13.4
# 切换到 root 用户进行系统级安装
USER root
# 修改kibana用户的UID和GID
RUN usermod -u 2133 kibana && \
groupmod -g 2015 kibana && \
chown -R kibana:kibana /usr/share/kibana
# 设置构建参数
ARG USE_INTRANET=false
# 配置内网 apt 源 (如果指定了内网选项)
RUN if [ "$USE_INTRANET" = "true" ]; then \
echo "Configuring intranet apt sources..." && \
cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
fi
# 安装 supervisor, net-tools, vim
RUN apt-get update && \
apt-get install -y supervisor net-tools inetutils-ping vim && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
# 配置部署时使用的apt源
RUN if [ "$USE_INTRANET" = "true" ]; then \
echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
fi
# 创建 supervisor 日志目录
RUN mkdir -p /var/log/supervisor
# 复制 supervisor 配置文件
COPY src/log/kibana/build/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
# 复制启动脚本
COPY src/log/kibana/build/start-kibana-supervised.sh /usr/local/bin/start-kibana-supervised.sh
COPY src/log/kibana/build/kibana-post-start.sh /usr/local/bin/kibana-post-start.sh
RUN chmod +x /usr/local/bin/start-kibana-supervised.sh /usr/local/bin/kibana-post-start.sh
# 复制DNS监控脚本
COPY src/log/kibana/build/dns-monitor.sh /usr/local/bin/dns-monitor.sh
RUN chmod +x /usr/local/bin/dns-monitor.sh
# kibana需要用到 /root/.config/puppeteer 路径
RUN chmod 777 /root
# 保持 root 用户,由 supervisor 管理用户切换
USER root
# 暴露端口
EXPOSE 5601
# 使用 supervisor 作为入口点
CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

View File

@ -0,0 +1 @@
../../../bind/build/dns-monitor.sh

View File

@ -0,0 +1,146 @@
#!/bin/bash
set -euo pipefail
ES_HOST="${ELASTICSEARCH_HOSTS:-http://es:9200}"
KB_HOST="http://localhost:5601"
echo "[INFO] Starting Kibana post-start configuration..."
# 等待 Elasticsearch 可用
wait_for_elasticsearch() {
echo "[INFO] Waiting for Elasticsearch..."
local max_attempts=60
local attempt=1
while [ $attempt -le $max_attempts ]; do
if curl -fs "$ES_HOST/_cluster/health" >/dev/null 2>&1; then
echo "[OK] Elasticsearch is available"
return 0
fi
echo " Waiting for ES... ($attempt/$max_attempts)"
sleep 5
((attempt++))
done
echo "[ERROR] Elasticsearch timeout"
return 1
}
# 等待 Kibana 可用
wait_for_kibana() {
echo "[INFO] Waiting for Kibana..."
local max_attempts=120
local attempt=1
while [ $attempt -le $max_attempts ]; do
if curl -fs "$KB_HOST/api/status" >/dev/null 2>&1; then
local status=$(curl -s "$KB_HOST/api/status" | grep -o '"level":"available"' || echo "")
if [ -n "$status" ]; then
echo "[OK] Kibana is available"
return 0
fi
echo " Waiting for Kibana... ($attempt/$max_attempts, status: $status)"
else
echo " Waiting for Kibana... ($attempt/$max_attempts, connection failed)"
fi
sleep 5
((attempt++))
done
echo "[ERROR] Kibana timeout"
return 1
}
# 幂等设置索引副本数为0
fix_replicas_idempotent() {
echo "[INFO] Checking and fixing index replicas..."
# 获取所有 train-* 和 infer-* 索引
local indices=$(curl -s "$ES_HOST/_cat/indices/train-*,infer-*?h=index" 2>/dev/null || echo "")
if [ -z "$indices" ]; then
echo "[INFO] No train-*/infer-* indices found, skipping replica adjustment"
return 0
fi
for idx in $indices; do
# 检查当前副本数
local current_replicas=$(curl -s "$ES_HOST/$idx/_settings" | grep -o '"number_of_replicas":"[^"]*"' | cut -d'"' -f4 || echo "")
if [ "$current_replicas" != "0" ]; then
echo "[INFO] Setting replicas to 0 for index: $idx (current: $current_replicas)"
curl -fsS -X PUT "$ES_HOST/$idx/_settings" \
-H 'Content-Type: application/json' \
-d '{"index":{"number_of_replicas":0}}' >/dev/null || {
echo "[WARN] Failed to set replicas for $idx"
continue
}
echo "[OK] Updated replicas for $idx"
else
echo "[INFO] Index $idx already has 0 replicas, skipping"
fi
done
}
# 幂等创建数据视图
create_data_views_idempotent() {
echo "[INFO] Checking and creating data views..."
# 检查是否存在匹配的索引
local train_indices=$(curl -s "$ES_HOST/_cat/indices/train-*?h=index" 2>/dev/null | wc -l || echo "0")
local infer_indices=$(curl -s "$ES_HOST/_cat/indices/infer-*?h=index" 2>/dev/null | wc -l || echo "0")
# 创建 train 数据视图
if [ "$train_indices" -gt 0 ]; then
# 检查数据视图是否已存在
local train_exists=$(curl -s "$KB_HOST/api/data_views" -H 'kbn-xsrf: true' 2>/dev/null | grep '"title":"train-\*"' | wc -l )
if [ "$train_exists" -eq 0 ]; then
echo "[INFO] Creating data view for train-* indices"
curl -fsS -X POST "$KB_HOST/api/data_views/data_view" \
-H 'kbn-xsrf: true' \
-H 'Content-Type: application/json' \
-d '{"data_view":{"name":"train","title":"train-*","timeFieldName":"@timestamp"}}' \
>/dev/null && echo "[OK] Created train data view" || echo "[WARN] Failed to create train data view"
else
echo "[INFO] Train data view already exists, skipping"
fi
else
echo "[INFO] No train-* indices found, skipping train data view creation"
fi
# 创建 infer 数据视图
if [ "$infer_indices" -gt 0 ]; then
# 检查数据视图是否已存在
local infer_exists=$(curl -s "$KB_HOST/api/data_views" -H 'kbn-xsrf: true' 2>/dev/null | grep '"title":"infer-\*"' | wc -l )
if [ "$infer_exists" -eq 0 ]; then
echo "[INFO] Creating data view for infer-* indices"
curl -fsS -X POST "$KB_HOST/api/data_views/data_view" \
-H 'kbn-xsrf: true' \
-H 'Content-Type: application/json' \
-d '{"data_view":{"name":"infer","title":"infer-*","timeFieldName":"@timestamp"}}' \
>/dev/null && echo "[OK] Created infer data view" || echo "[WARN] Failed to create infer data view"
else
echo "[INFO] Infer data view already exists, skipping"
fi
else
echo "[INFO] No infer-* indices found, skipping infer data view creation"
fi
}
# 主逻辑
main() {
# 等待服务可用
wait_for_elasticsearch || exit 1
wait_for_kibana || exit 1
# 执行幂等配置
fix_replicas_idempotent
create_data_views_idempotent
echo "[INFO] Kibana post-start configuration completed"
}
# 运行主逻辑
main

View File

@ -0,0 +1,37 @@
#!/bin/bash
set -euo pipefail
echo "[INFO] Starting Kibana under supervisor..."
mkdir -p /private/argus/log/kibana
# 创建软链接到Kibana预期的数据目录
if [ -L /usr/share/kibana/data ]; then
rm /usr/share/kibana/data
elif [ -d /usr/share/kibana/data ]; then
rm -rf /usr/share/kibana/data
fi
ln -sf /private/argus/log/kibana /usr/share/kibana/data
echo "[INFO] Data directory linked: /usr/share/kibana/data -> /private/argus/log/kibana"
# 记录容器ip地址
DOMAIN=kibana.log.argus.com
IP=`ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}'`
echo current IP: ${IP}
echo ${IP} > /private/argus/etc/${DOMAIN}
# 设置环境变量
export ELASTICSEARCH_HOSTS="${ELASTICSEARCH_HOSTS:-"http://es:9200"}"
echo "[INFO] Connecting to Elasticsearch at: $ELASTICSEARCH_HOSTS"
# 启动后台配置任务
echo "[INFO] Starting background post-start configuration..."
/usr/local/bin/kibana-post-start.sh &
echo "[INFO] Starting Kibana process..."
# 启动原始的Kibana entrypoint
exec /usr/local/bin/kibana-docker

View File

@ -0,0 +1,39 @@
[supervisord]
nodaemon=true
logfile=/var/log/supervisor/supervisord.log
pidfile=/var/run/supervisord.pid
user=root
[program:kibana]
command=/usr/local/bin/start-kibana-supervised.sh
user=kibana
stdout_logfile=/var/log/supervisor/kibana.log
stderr_logfile=/var/log/supervisor/kibana_error.log
autorestart=true
startretries=3
startsecs=30
stopwaitsecs=30
killasgroup=true
stopasgroup=true
[program:dns-monitor]
command=/usr/local/bin/dns-monitor.sh
user=root
stdout_logfile=/var/log/supervisor/dns-monitor.log
stderr_logfile=/var/log/supervisor/dns-monitor_error.log
autorestart=true
startretries=3
startsecs=5
stopwaitsecs=10
killasgroup=true
stopasgroup=true
[unix_http_server]
file=/var/run/supervisor.sock
chmod=0700
[supervisorctl]
serverurl=unix:///var/run/supervisor.sock
[rpcinterface:supervisor]
supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface

View File

@ -0,0 +1,85 @@
version: "3.8"
services:
es:
build:
context: ../elasticsearch/build
dockerfile: Dockerfile
image: argus-elasticsearch:latest
environment:
- discovery.type=single-node
- xpack.security.enabled=false
- ES_JAVA_OPTS=-Xms512m -Xmx512m
volumes:
- ./private/argus/:/private/argus/
ports: ["9200:9200"]
healthcheck:
test: ["CMD-SHELL", "curl -fs http://localhost:9200 >/dev/null || exit 1"]
interval: 10s
timeout: 5s
retries: 30
kibana:
build:
context: ../kibana/build
dockerfile: Dockerfile
image: argus-kibana:latest
environment:
- ELASTICSEARCH_HOSTS=http://es.log.argus.com:9200
volumes:
- ./private/argus/:/private/argus/
ports: ["5601:5601"]
depends_on:
es:
condition: service_healthy
fluent-bit-host01:
image: ubuntu:22.04
environment:
- CLUSTER=local
- RACK=dev
- HOSTNAME=host01
- ES_HOST=es
- ES_PORT=9200
volumes:
- ../fluent-bit/build:/private/
ports: ["2020:2020"]
depends_on:
es:
condition: service_healthy
command: /private/start-fluent-bit.sh
healthcheck:
test: ["CMD-SHELL", "curl -fs http://localhost:2020/api/v2/metrics >/dev/null || exit 1"]
interval: 15s
timeout: 10s
retries: 30
fluent-bit-host02:
image: ubuntu:22.04
environment:
- CLUSTER=local
- RACK=dev
- HOSTNAME=host02
- ES_HOST=es
- ES_PORT=9200
volumes:
- ../fluent-bit/build:/private/
ports: ["2021:2020"]
depends_on:
es:
condition: service_healthy
command: /private/start-fluent-bit.sh
healthcheck:
test: ["CMD-SHELL", "curl -fs http://localhost:2020/api/v2/metrics >/dev/null || exit 1"]
interval: 15s
timeout: 10s
retries: 30
bind9:
image: argus-bind9:latest
ports:
- "53:53/tcp"
- "53:53/udp"
volumes:
- ./private/argus:/private/argus/
restart: unless-stopped

View File

@ -0,0 +1,30 @@
#!/usr/bin/env bash
set -euo pipefail
root="$(cd "$(dirname "${BASH_SOURCE[0]}")/../" && pwd)"
# 创建新的private目录结构 (基于argus目录结构)
echo "[INFO] Creating private directory structure for supervisor-based containers..."
mkdir -p "$root/private/argus/log/elasticsearch"
mkdir -p "$root/private/argus/log/kibana"
mkdir -p "$root/private/argus/etc/"
# 设置数据目录权限ES 和 Kibana 容器都使用 UID 1000
echo "[INFO] Setting permissions for data directories..."
sudo chown -R 2133:2015 "$root/private/argus/log/elasticsearch" 2>/dev/null || true
sudo chown -R 2133:2015 "$root/private/argus/log/kibana" 2>/dev/null || true
sudo chown -R 2133:2015 "$root/private/argus/etc" 2>/dev/null || true
echo "[INFO] Supervisor-based containers will manage their own scripts and configurations"
# 检查fluent-bit相关文件是否存在
if [[ ! -f "$root/../fluent-bit/fluent-bit-bundle.tar.gz" ]]; then
echo "[WARN] fluent-bit/fluent-bit-bundle.tar.gz 不存在,请确保已创建该文件"
fi
if [[ ! -f "$root/../fluent-bit/start-fluent-bit.sh" ]]; then
echo "[WARN] fluent-bit/start-fluent-bit.sh 不存在,请确保已创建该启动脚本"
fi
echo "[OK] 初始化完成: private/argus/log/{elasticsearch,kibana}"
echo "[INFO] Fluent-bit files should be in fluent-bit/ directory"

10
src/log/tests/scripts/02_up.sh Executable file
View File

@ -0,0 +1,10 @@
#!/usr/bin/env bash
set -euo pipefail
cd "$(dirname "$0")/.."
compose_cmd="docker compose"
if ! $compose_cmd version >/dev/null 2>&1; then
if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
echo "需要 Docker Compose请安装后重试" >&2; exit 1; fi
fi
$compose_cmd -p logging-mvp up -d --remove-orphans
echo "[OK] 服务已启动ES http://localhost:9200 Kibana http://localhost:5601 Fluent-Bit host01 http://localhost:2020 Fluent-Bit host02 http://localhost:2021"

View File

@ -0,0 +1,31 @@
#!/usr/bin/env bash
set -euo pipefail
# 获取fluent-bit-host01容器名称
container_name="logging-mvp-fluent-bit-host01-1"
# 检查容器是否存在并运行
if ! docker ps | grep -q "$container_name"; then
echo "[ERROR] Fluent Bit容器 $container_name 未运行"
exit 1
fi
# 创建日志目录
docker exec "$container_name" mkdir -p /logs/train /logs/infer
# 写入训练日志 (host01)
docker exec "$container_name" sh -c "printf '%s INFO [host01] training step=1 loss=1.23 model=bert\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
docker exec "$container_name" sh -c "printf '%s INFO [host01] training step=2 loss=1.15 model=bert\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
# 写入推理日志 (host01)
docker exec "$container_name" sh -c "printf '%s ERROR [host01] inference failed on batch=1\n' \"\$(date '+%F %T')\" >> /logs/infer/infer-demo.log"
docker exec "$container_name" sh -c "cat <<'STACK' >> /logs/infer/infer-demo.log
Traceback (most recent call last):
File \"inference.py\", line 15, in <module>
raise RuntimeError(\"CUDA out of memory on host01\")
RuntimeError: CUDA out of memory on host01
STACK"
echo "[OK] 已通过docker exec写入测试日志到 host01 容器内:"
echo " - /logs/train/train-demo.log"
echo " - /logs/infer/infer-demo.log"

View File

@ -0,0 +1,27 @@
#!/usr/bin/env bash
set -euo pipefail
# 获取fluent-bit-host02容器名称
container_name="logging-mvp-fluent-bit-host02-1"
# 检查容器是否存在并运行
if ! docker ps | grep -q "$container_name"; then
echo "[ERROR] Fluent Bit容器 $container_name 未运行"
exit 1
fi
# 创建日志目录
docker exec "$container_name" mkdir -p /logs/train /logs/infer
# 写入训练日志 (host02)
docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=1 loss=1.45 model=gpt\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=2 loss=1.38 model=gpt\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=3 loss=1.32 model=gpt\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
# 写入推理日志 (host02)
docker exec "$container_name" sh -c "printf '%s WARN [host02] inference slow on batch=5 latency=2.3s\n' \"\$(date '+%F %T')\" >> /logs/infer/infer-demo.log"
docker exec "$container_name" sh -c "printf '%s INFO [host02] inference completed batch=6 latency=0.8s\n' \"\$(date '+%F %T')\" >> /logs/infer/infer-demo.log"
echo "[OK] 已通过docker exec写入测试日志到 host02 容器内:"
echo " - /logs/train/train-demo.log"
echo " - /logs/infer/infer-demo.log"

View File

@ -0,0 +1,7 @@
#!/usr/bin/env bash
set -euo pipefail
ES="${ES:-http://localhost:9200}"
echo "[i] 查询 ES 端点:$ES"
curl -fsS "$ES/_cat/indices?v" | egrep 'train-|infer-|logstash' || true
printf "train-* 计数:"; curl -fsS "$ES/train-*/_count" | sed -E 's/.*"count":([0-9]+).*/\1/'; echo
printf "infer-* 计数:"; curl -fsS "$ES/infer-*/_count" | sed -E 's/.*"count":([0-9]+).*/\1/'; echo

View File

@ -0,0 +1,21 @@
#!/usr/bin/env bash
set -euo pipefail
cd "$(dirname "$0")/.."
compose_cmd="docker compose"
if ! $compose_cmd version >/dev/null 2>&1; then
if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
echo "需要 Docker Compose请安装后重试" >&2; exit 1; fi
fi
$compose_cmd -p logging-mvp down
echo "[OK] 已停止所有容器"
# 清理private目录内容
echo "[INFO] 清理private目录内容..."
cd "$(dirname "$0")/.."
if [ -d "private" ]; then
# 删除private目录及其所有内容
rm -rf private
echo "[OK] 已清理private目录"
else
echo "[INFO] private目录不存在无需清理"
fi

View File

@ -0,0 +1,208 @@
#!/usr/bin/env bash
set -euo pipefail
echo "======================================="
echo "ARGUS DNS监控功能测试"
echo "======================================="
echo ""
# 记录测试开始时间
test_start_time=$(date +%s)
# 函数:显示测试步骤
show_step() {
echo ""
echo "🔄 Step $1: $2"
echo "----------------------------------------"
}
# 函数:验证步骤结果
verify_step() {
if [ $? -eq 0 ]; then
echo "$1 - SUCCESS"
else
echo "$1 - FAILED"
exit 1
fi
}
# 函数:等待服务就绪
wait_for_services() {
echo "[INFO] Waiting for services to be ready..."
local max_attempts=60
local attempt=1
while [ $attempt -le $max_attempts ]; do
if curl -fs http://localhost:9200/_cluster/health >/dev/null 2>&1 && \
curl -fs http://localhost:5601/api/status >/dev/null 2>&1; then
echo "[OK] Services are ready!"
return 0
fi
echo " Waiting for services... ($attempt/$max_attempts)"
sleep 5
((attempt++))
done
echo "[ERROR] Services not ready after $max_attempts attempts"
return 1
}
# 函数:检查容器中的/etc/resolv.conf
check_resolv_conf() {
local service_name=$1
local expected_dns=$2
echo "[INFO] 检查 $service_name 容器的 /etc/resolv.conf..."
local resolv_content=$(docker exec "${service_name}" cat /etc/resolv.conf 2>/dev/null || echo "")
if echo "$resolv_content" | grep -q "nameserver $expected_dns"; then
echo "$service_name resolv.conf contains nameserver $expected_dns"
return 0
else
echo "$service_name resolv.conf does not contain nameserver $expected_dns"
echo "实际内容:"
echo "$resolv_content"
return 1
fi
}
# 函数检查DNS监控日志
check_dns_monitor_logs() {
local service_name=$1
echo "[INFO] 检查 $service_name 的DNS监控日志..."
local dns_logs=$(docker exec "$service_name" tail -n 20 /var/log/supervisor/dns-monitor.log 2>/dev/null || echo "")
if [ -n "$dns_logs" ]; then
echo "$service_name DNS监控日志存在"
echo "最近的日志:"
echo "$dns_logs"
return 0
else
echo "$service_name DNS监控日志为空或不存在"
return 1
fi
}
# 函数:确保目录结构存在
ensure_directories() {
echo "[INFO] 确保目录结构存在..."
# 确保目录存在
mkdir -p ./private/argus/etc/
echo "✅ 目录结构准备完成使用真实的update-dns.sh脚本"
}
# 开始DNS监控测试
show_step "1" "Bootstrap - Initialize environment"
./scripts/01_bootstrap.sh
verify_step "Bootstrap"
# 确保目录结构
ensure_directories
show_step "2" "Startup - Start all services"
./scripts/02_up.sh
verify_step "Service startup"
# 等待服务完全就绪
wait_for_services || exit 1
show_step "3" "Create initial DNS configuration"
# 创建初始的DNS配置文件 - 只有一个IP
echo "[INFO] 创建初始的dns.conf文件 (8.8.8.8)..."
cat > ./private/argus/etc/dns.conf << 'EOF'
8.8.8.8
EOF
echo "✅ 初始dns.conf文件创建成功 (8.8.8.8)"
verify_step "Initial DNS configuration creation"
# 等待DNS监控检测到配置文件
echo "[INFO] 等待DNS监控检测并处理初始配置..."
sleep 15
show_step "4" "Verify initial DNS configuration processing"
# 检查两个容器的DNS监控日志
check_dns_monitor_logs "logging-mvp-es-1"
verify_step "Elasticsearch DNS monitor logs"
check_dns_monitor_logs "logging-mvp-kibana-1"
verify_step "Kibana DNS monitor logs"
# 检查resolv.conf是否包含新的DNS服务器
check_resolv_conf "logging-mvp-es-1" "8.8.8.8"
verify_step "Elasticsearch resolv.conf initial check"
check_resolv_conf "logging-mvp-kibana-1" "8.8.8.8"
verify_step "Kibana resolv.conf initial check"
show_step "5" "Modify DNS configuration and test auto-update"
# 修改DNS配置文件 - 改为另一个IP
echo "[INFO] 修改dns.conf文件改为1.1.1.1..."
cat > ./private/argus/etc/dns.conf << 'EOF'
1.1.1.1
EOF
echo "✅ dns.conf文件更新成功改为1.1.1.1"
# 等待DNS监控检测到配置变化
echo "[INFO] 等待DNS监控检测配置变化并执行更新..."
sleep 15
show_step "6" "Verify DNS configuration auto-update"
# 再次检查DNS监控日志应该看到配置变化检测
echo "[INFO] 检查DNS监控是否检测到配置变化..."
# 检查elasticsearch容器
echo "[INFO] 检查elasticsearch容器的DNS监控日志最近30行..."
docker exec logging-mvp-es-1 tail -n 30 /var/log/supervisor/dns-monitor.log || true
# 检查kibana容器
echo "[INFO] 检查kibana容器的DNS监控日志最近30行..."
docker exec logging-mvp-kibana-1 tail -n 30 /var/log/supervisor/dns-monitor.log || true
# 验证新的DNS服务器是否被添加到resolv.conf
check_resolv_conf "logging-mvp-es-1" "1.1.1.1"
verify_step "Elasticsearch resolv.conf after update"
check_resolv_conf "logging-mvp-kibana-1" "1.1.1.1"
verify_step "Kibana resolv.conf after update"
show_step "7" "Final verification - Check DNS configuration"
# 最终验证DNS配置
echo "[INFO] 最终验证elasticsearch容器的resolv.conf..."
docker exec logging-mvp-es-1 cat /etc/resolv.conf
echo "[INFO] 最终验证kibana容器的resolv.conf..."
docker exec logging-mvp-kibana-1 cat /etc/resolv.conf
echo "[INFO] 最终dns.conf内容:"
cat ./private/argus/etc/dns.conf
verify_step "Final DNS configuration verification"
show_step "8" "Cleanup - Stop all services"
./scripts/05_down.sh
verify_step "Service cleanup"
# 清理测试文件
rm -f ./private/argus/etc/dns.conf
# 注不删除update-dns.sh因为这是真实的脚本
# 计算总测试时间
test_end_time=$(date +%s)
total_time=$((test_end_time - test_start_time))
echo ""
echo "======================================="
echo "🎉 DNS监控功能测试完成!"
echo "======================================="
echo "📊 测试总结:"
echo " • 总耗时: ${total_time}"
echo " • 初始DNS配置: 8.8.8.8"
echo " • 更新DNS配置: 1.1.1.1"
echo " • DNS监控脚本正常工作"
echo " • 容器resolv.conf自动覆盖更新成功"
echo ""
echo "✅ DNS自动更新功能测试通过!"
echo ""

169
src/log/tests/scripts/e2e_test.sh Executable file
View File

@ -0,0 +1,169 @@
#!/usr/bin/env bash
set -euo pipefail
echo "======================================="
echo "ARGUS Log System End-to-End Test"
echo "======================================="
echo ""
# 记录测试开始时间
test_start_time=$(date +%s)
# 函数获取ES中的日志计数
get_log_count() {
local train_count=$(curl -s "http://localhost:9200/train-*/_count" 2>/dev/null | grep -o '"count":[0-9]*' | cut -d':' -f2 || echo "0")
local infer_count=$(curl -s "http://localhost:9200/infer-*/_count" 2>/dev/null | grep -o '"count":[0-9]*' | cut -d':' -f2 || echo "0")
echo "$((train_count + infer_count))"
}
# 函数:等待服务就绪
wait_for_services() {
echo "[INFO] Waiting for all services to be ready..."
local max_attempts=60
local attempt=1
while [ $attempt -le $max_attempts ]; do
if curl -fs http://localhost:9200/_cluster/health >/dev/null 2>&1 && \
curl -fs http://localhost:5601/api/status >/dev/null 2>&1 && \
curl -fs http://localhost:2020/api/v2/metrics >/dev/null 2>&1 && \
curl -fs http://localhost:2021/api/v2/metrics >/dev/null 2>&1; then
echo "[OK] All services are ready!"
return 0
fi
echo " Waiting for services... ($attempt/$max_attempts)"
sleep 5
((attempt++))
done
echo "[ERROR] Services not ready after $max_attempts attempts"
return 1
}
# 函数:显示测试步骤
show_step() {
echo ""
echo "🔄 Step $1: $2"
echo "----------------------------------------"
}
# 函数:验证步骤结果
verify_step() {
if [ $? -eq 0 ]; then
echo "$1 - SUCCESS"
else
echo "$1 - FAILED"
exit 1
fi
}
# 开始端到端测试
show_step "1" "Bootstrap - Initialize environment"
./scripts/01_bootstrap.sh
verify_step "Bootstrap"
show_step "2" "Startup - Start all services"
./scripts/02_up.sh
verify_step "Service startup"
# 等待服务完全就绪
wait_for_services || exit 1
# 记录发送测试数据前的日志计数
initial_count=$(get_log_count)
echo "[INFO] Initial log count: $initial_count"
show_step "3a" "Send test data - Host01"
./scripts/03_send_test_host01.sh
verify_step "Test data sending (host01)"
show_step "3b" "Send test data - Host02"
./scripts/03_send_test_host02.sh
verify_step "Test data sending (host02)"
# 等待数据被处理
echo "[INFO] Waiting for data to be processed..."
sleep 10
show_step "4" "Verify data - Query Elasticsearch"
./scripts/04_query_es.sh
verify_step "Data verification"
# 记录发送测试数据后的日志计数
final_count=$(get_log_count)
echo "[INFO] Final log count: $final_count"
# 验证日志数量是否增加
if [ "$final_count" -gt "$initial_count" ]; then
added_logs=$((final_count - initial_count))
echo "✅ Log count verification - SUCCESS: Added $added_logs logs (from $initial_count to $final_count)"
else
echo "❌ Log count verification - FAILED: Expected count to increase, but got $initial_count -> $final_count"
exit 1
fi
# 验证预期的最小日志数量(每个主机应该发送一些日志)
expected_min_logs=4 # 至少应该有几条日志
if [ "$final_count" -ge "$expected_min_logs" ]; then
echo "✅ Minimum log threshold - SUCCESS: $final_count logs (>= $expected_min_logs expected)"
else
echo "❌ Minimum log threshold - FAILED: Only $final_count logs (>= $expected_min_logs expected)"
exit 1
fi
# 检查服务健康状态
show_step "Health" "Check service health"
echo "[INFO] Checking service health..."
# 检查 Elasticsearch 健康状态
es_health=$(curl -s "http://localhost:9200/_cluster/health" | grep -o '"status":"[^"]*"' | cut -d'"' -f4)
if [ "$es_health" = "green" ] || [ "$es_health" = "yellow" ]; then
echo "✅ Elasticsearch health: $es_health"
else
echo "❌ Elasticsearch health: $es_health"
fi
# 检查 Kibana 状态
if curl -fs "http://localhost:5601/api/status" >/dev/null 2>&1; then
kb_status="available"
echo "✅ Kibana status: $kb_status"
else
kb_status="unavailable"
echo "⚠️ Kibana status: $kb_status"
fi
# 检查 Fluent-Bit 指标
fb_host01_uptime=$(curl -s "http://localhost:2020/api/v2/metrics" | grep "fluentbit_uptime" | head -1 | grep -o "[0-9]\+$" || echo "0")
fb_host02_uptime=$(curl -s "http://localhost:2021/api/v2/metrics" | grep "fluentbit_uptime" | head -1 | grep -o "[0-9]\+$" || echo "0")
if [ "$fb_host01_uptime" -gt 0 ] && [ "$fb_host02_uptime" -gt 0 ]; then
echo "✅ Fluent-Bit services: host01 uptime=${fb_host01_uptime}s, host02 uptime=${fb_host02_uptime}s"
else
echo "⚠️ Fluent-Bit services: host01 uptime=${fb_host01_uptime}s, host02 uptime=${fb_host02_uptime}s"
fi
verify_step "Service health check"
show_step "5" "Cleanup - Stop all services"
./scripts/05_down.sh
verify_step "Service cleanup"
# 计算总测试时间
test_end_time=$(date +%s)
total_time=$((test_end_time - test_start_time))
echo ""
echo "======================================="
echo "🎉 END-TO-END TEST COMPLETED SUCCESSFULLY!"
echo "======================================="
echo "📊 Test Summary:"
echo " • Initial logs: $initial_count"
echo " • Final logs: $final_count"
echo " • Added logs: $added_logs"
echo " • Total time: ${total_time}s"
echo " • ES health: $es_health"
echo " • Kibana status: $kb_status"
echo " • DNS resolv: ✅ Passed (ES domain verified)"
echo " • All services started and stopped successfully"
echo ""
echo "✅ The ARGUS log system is working correctly!"
echo ""

View File

@ -0,0 +1,67 @@
FROM ubuntu/prometheus:3-24.04_stable
USER root
ARG USE_INTRANET=false
# 内网 apt 源配置
RUN if [ "$USE_INTRANET" = "true" ]; then \
echo "Configuring intranet apt sources..." && \
cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
fi
# 常用工具
RUN apt-get update && \
apt-get install -y supervisor net-tools inetutils-ping vim && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
# 如果是部署环境替换 apt 源
RUN if [ "$USE_INTRANET" = "true" ]; then \
echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
fi
# supervisor 日志目录
RUN mkdir -p /var/log/supervisor
# 设置 Prometheus 基础路径环境变量
ENV PROMETHEUS_BASE_PATH=/private/argus/metric/prometheus
# 设置用户和组ID环境变量
ARG PROMETHEUS_UID=2133
ARG PROMETHEUS_GID=2015
ENV PROMETHEUS_UID=${PROMETHEUS_UID}
ENV PROMETHEUS_GID=${PROMETHEUS_GID}
# 创建目录结构
RUN mkdir -p ${PROMETHEUS_BASE_PATH}/rules \
&& mkdir -p ${PROMETHEUS_BASE_PATH}/targets \
&& mkdir -p /private/argus/etc \
&& rm -rf /prometheus \
&& ln -s ${PROMETHEUS_BASE_PATH} /prometheus
# 修改 Prometheus 用户 UID/GID 并授权
RUN usermod -u ${PROMETHEUS_UID} nobody && \
groupmod -g ${PROMETHEUS_GID} nogroup && \
chown -h nobody:nogroup /prometheus && \
chown -R nobody:nogroup /private/argus/metric /etc/prometheus && \
chown -R nobody:nogroup ${PROMETHEUS_BASE_PATH}
# supervisor 配置
COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
# 启动脚本
COPY start-prometheus-supervised.sh /usr/local/bin/start-prometheus-supervised.sh
RUN chmod +x /usr/local/bin/start-prometheus-supervised.sh
# 自定义 prometheus 配置文件
COPY prometheus.yml /etc/prometheus/prometheus.yml
USER root
EXPOSE 9090
ENTRYPOINT ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf", "-n"]

View File

@ -0,0 +1,126 @@
# Prometheus Docker 镜像配置
## 环境变量配置
### PROMETHEUS_BASE_PATH
设置 Prometheus 配置和数据的基础路径。
**默认值**: `/private/argus/metric/prometheus`
**用途**:
- 配置文件存储路径: `${PROMETHEUS_BASE_PATH}/prometheus.yml`
- 规则文件路径: `${PROMETHEUS_BASE_PATH}/rules/*.yml`
- 监控目标文件路径: `${PROMETHEUS_BASE_PATH}/targets/`
## 使用示例
### 1. 使用默认路径
```bash
docker run -d \
--name prometheus \
-p 9090:9090 \
-v /host/prometheus/data:/private/argus/metric/prometheus \
prometheus:latest
```
### 2. 自定义基础路径
```bash
docker run -d \
--name prometheus \
-p 9090:9090 \
-e PROMETHEUS_BASE_PATH=/custom/prometheus/path \
-v /host/prometheus/data:/custom/prometheus/path \
prometheus:latest
```
### 3. Kubernetes 部署示例
```yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: prometheus
spec:
replicas: 1
selector:
matchLabels:
app: prometheus
template:
metadata:
labels:
app: prometheus
spec:
containers:
- name: prometheus
image: prometheus:latest
env:
- name: PROMETHEUS_BASE_PATH
value: "/data/prometheus"
ports:
- containerPort: 9090
volumeMounts:
- name: prometheus-data
mountPath: /data/prometheus
volumes:
- name: prometheus-data
persistentVolumeClaim:
claimName: prometheus-pvc
```
## 目录结构
容器启动后会在 `${PROMETHEUS_BASE_PATH}` 下创建以下目录结构:
```
${PROMETHEUS_BASE_PATH}/
├── prometheus.yml # 主配置文件
├── rules/ # 告警规则目录
│ └── *.yml
└── targets/ # 监控目标目录
├── node_exporter.json
└── dcgm_exporter.json
```
## 动态配置
- **规则文件**: 在 `rules/` 目录下添加 `.yml` 文件即可自动加载
- **监控目标**: 修改 `targets/` 目录下的 JSON 文件即可动态更新监控目标
- **主配置**: 修改 `prometheus.yml` 后可通过 Prometheus 的 `/-/reload` 端点重新加载配置
## 权限管理
### 默认路径权限
- 默认路径 `/private/argus/metric/prometheus` 在 Dockerfile 中已设置正确的权限
- nobody 用户UID: 2133, GID: 2015拥有完全读写权限
### 自定义路径权限
- 当使用自定义 `PROMETHEUS_BASE_PATH` 时,启动脚本会自动创建目录并设置权限
- 确保 nobody 用户对自定义路径有读写权限
### 挂载卷注意事项
1. **主机目录权限**: 确保挂载的主机目录对 nobody 用户UID: 2133可写
2. **SELinux**: 如果使用 SELinux可能需要设置适当的上下文
3. **Docker 用户映射**: 确保容器内的 nobody 用户与主机用户权限匹配
## 故障排除
### 权限问题
如果遇到权限错误,可以检查:
```bash
# 检查目录权限
ls -la /path/to/prometheus/data
# 检查用户映射
id nobody
# 手动修复权限
chown -R 2133:2015 /path/to/prometheus/data
chmod -R 755 /path/to/prometheus/data
```
## 注意事项
1. 确保挂载的目录有适当的读写权限
2. 配置文件会在容器启动时自动生成,无需手动创建
3. 可以通过修改环境变量 `PROMETHEUS_BASE_PATH` 来改变所有相关路径,无需重新构建镜像
4. 自定义路径的目录会在启动时自动创建并设置权限

View File

@ -1,15 +1,27 @@
global: global:
scrape_interval: 15s scrape_interval: 15s
evaluation_interval: 15s
scrape_timeout: 10s
# 对接 AlertManager
alerting:
alertmanagers:
- static_configs:
- targets: []
# 规则目录
rule_files:
- "${PROMETHEUS_BASE_PATH}/rules/*.yml"
scrape_configs: scrape_configs:
- job_name: "node" - job_name: "node"
file_sd_configs: file_sd_configs:
- files: - files:
- "targets/node_exporter.json" - "${PROMETHEUS_BASE_PATH}/targets/node_exporter.json"
refresh_interval: 30s refresh_interval: 30s
- job_name: "dcgm" - job_name: "dcgm"
file_sd_configs: file_sd_configs:
- files: - files:
- "targets/dcgm_exporter.json" - "${PROMETHEUS_BASE_PATH}/targets/dcgm_exporter.json"
refresh_interval: 30s refresh_interval: 30s

View File

@ -0,0 +1,26 @@
#!/bin/bash
set -euo pipefail
echo "[INFO] Starting Prometheus under supervisor..."
PROMETHEUS_BASE_PATH=${PROMETHEUS_BASE_PATH:-/private/argus/metric/prometheus}
DOMAIN=prom.metric.argus.com
echo "[INFO] Prometheus base path: ${PROMETHEUS_BASE_PATH}"
# 生成配置文件
echo "[INFO] Generating prometheus.yml with base path: ${PROMETHEUS_BASE_PATH}"
sed "s|\${PROMETHEUS_BASE_PATH}|${PROMETHEUS_BASE_PATH}|g" \
/etc/prometheus/prometheus.yml > ${PROMETHEUS_BASE_PATH}/prometheus.yml
# 记录容器 IP
IP=$(ifconfig eth0 | awk '/inet /{print $2}')
echo "current IP: ${IP}"
echo "${IP}" > /private/argus/etc/${DOMAIN}
exec /bin/prometheus \
--config.file=${PROMETHEUS_BASE_PATH}/prometheus.yml \
--storage.tsdb.path=/prometheus \
--web.enable-lifecycle \
--web.console.libraries=/usr/share/prometheus/console_libraries \
--web.console.templates=/usr/share/prometheus/consoles

View File

@ -0,0 +1,27 @@
[supervisord]
nodaemon=true
logfile=/var/log/supervisor/supervisord.log
pidfile=/var/run/supervisord.pid
user=root
[program:prometheus]
command=/usr/local/bin/start-prometheus-supervised.sh
user=nobody
stdout_logfile=/var/log/supervisor/prometheus.log
stderr_logfile=/var/log/supervisor/prometheus_error.log
autorestart=true
startretries=3
startsecs=30
stopwaitsecs=30
killasgroup=true
stopasgroup=true
[unix_http_server]
file=/var/run/supervisor.sock
chmod=0700
[supervisorctl]
serverurl=unix:///var/run/supervisor.sock
[rpcinterface:supervisor]
supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface