[#50] x86机器使用qemu模拟方式安装部署arm版本安装包，当前未精简版，只有简单的node exporter功能，删减日志，GPU指标功能，仍使用Swarm组网
This commit is contained in:
parent
4c45166b44
commit
a6e1bf7fe7
@ -45,8 +45,8 @@ Options:
|
|||||||
--master-offline Build master offline image (requires src/master/offline_wheels.tar.gz)
|
--master-offline Build master offline image (requires src/master/offline_wheels.tar.gz)
|
||||||
--metric Build metric module images (ftp, prometheus, grafana, test nodes)
|
--metric Build metric module images (ftp, prometheus, grafana, test nodes)
|
||||||
--no-cache Build all images without using Docker layer cache
|
--no-cache Build all images without using Docker layer cache
|
||||||
--only LIST Comma-separated targets to build: core,master,metric,web,alert,sys,gpu_bundle,cpu_bundle,server_pkg,client_pkg,all
|
--only LIST Comma-separated targets to build: core,master,metric,web,alert,sys,gpu_bundle,cpu_bundle,server_pkg,client_pkg,arm_server_pkg,arm_client_pkg,all
|
||||||
--version DATE Date tag used by gpu_bundle/server_pkg/client_pkg (e.g. 20251112)
|
--version DATE Date tag used by gpu_bundle/server_pkg/client_pkg/arm_server_pkg/arm_client_pkg (e.g. 20251112)
|
||||||
--client-semver X.Y.Z Override client semver used in all-in-one-full artifact (optional)
|
--client-semver X.Y.Z Override client semver used in all-in-one-full artifact (optional)
|
||||||
--cuda VER CUDA runtime version for NVIDIA base (default: 12.2.2)
|
--cuda VER CUDA runtime version for NVIDIA base (default: 12.2.2)
|
||||||
--tag-latest Also tag bundle image as :latest (for cpu_bundle only; default off)
|
--tag-latest Also tag bundle image as :latest (for cpu_bundle only; default off)
|
||||||
@ -73,6 +73,8 @@ build_gpu_bundle=false
|
|||||||
build_cpu_bundle=false
|
build_cpu_bundle=false
|
||||||
build_server_pkg=false
|
build_server_pkg=false
|
||||||
build_client_pkg=false
|
build_client_pkg=false
|
||||||
|
build_server_pkg_arm=false
|
||||||
|
build_client_pkg_arm=false
|
||||||
no_cache=false
|
no_cache=false
|
||||||
|
|
||||||
bundle_date=""
|
bundle_date=""
|
||||||
@ -110,7 +112,7 @@ while [[ $# -gt 0 ]]; do
|
|||||||
fi
|
fi
|
||||||
sel="$2"; shift 2
|
sel="$2"; shift 2
|
||||||
# reset all, then enable selected
|
# reset all, then enable selected
|
||||||
build_core=false; build_master=false; build_metric=false; build_web=false; build_alert=false; build_sys=false; build_gpu_bundle=false; build_cpu_bundle=false; build_server_pkg=false; build_client_pkg=false
|
build_core=false; build_master=false; build_metric=false; build_web=false; build_alert=false; build_sys=false; build_gpu_bundle=false; build_cpu_bundle=false; build_server_pkg=false; build_client_pkg=false; build_server_pkg_arm=false; build_client_pkg_arm=false
|
||||||
IFS=',' read -ra parts <<< "$sel"
|
IFS=',' read -ra parts <<< "$sel"
|
||||||
for p in "${parts[@]}"; do
|
for p in "${parts[@]}"; do
|
||||||
case "$p" in
|
case "$p" in
|
||||||
@ -122,8 +124,12 @@ while [[ $# -gt 0 ]]; do
|
|||||||
sys) build_sys=true ;;
|
sys) build_sys=true ;;
|
||||||
gpu_bundle) build_gpu_bundle=true ;;
|
gpu_bundle) build_gpu_bundle=true ;;
|
||||||
cpu_bundle) build_cpu_bundle=true ;;
|
cpu_bundle) build_cpu_bundle=true ;;
|
||||||
server_pkg) build_server_pkg=true; build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true ;;
|
# 在 ARM 构建脚本中，server_pkg 视作 arm_server_pkg 的别名，避免误用 x86 打包逻辑
|
||||||
client_pkg) build_client_pkg=true ;;
|
server_pkg) build_server_pkg_arm=true; build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true ;;
|
||||||
|
# 在 ARM 构建脚本中，client_pkg 视作 arm_client_pkg 的别名，避免误用 x86 打包逻辑
|
||||||
|
client_pkg) build_client_pkg_arm=true; build_sys=true ;;
|
||||||
|
arm_server_pkg) build_server_pkg_arm=true; build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true ;;
|
||||||
|
arm_client_pkg) build_client_pkg_arm=true; build_sys=true ;;
|
||||||
all) build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true; build_sys=true ;;
|
all) build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true; build_sys=true ;;
|
||||||
*) echo "Unknown --only target: $p" >&2; exit 1 ;;
|
*) echo "Unknown --only target: $p" >&2; exit 1 ;;
|
||||||
esac
|
esac
|
||||||
@ -169,12 +175,12 @@ fi
|
|||||||
cd "$root"
|
cd "$root"
|
||||||
|
|
||||||
# Set default image tag policy before building
|
# Set default image tag policy before building
|
||||||
if [[ "$build_server_pkg" == true ]]; then
|
if [[ "$build_server_pkg" == true || "$build_client_pkg" == true || "$build_server_pkg_arm" == true || "$build_client_pkg_arm" == true ]]; then
|
||||||
DEFAULT_IMAGE_TAG="${bundle_date:-latest}"
|
DEFAULT_IMAGE_TAG="${bundle_date:-latest}"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# Select build user profile for pkg vs default
|
# Select build user profile for pkg vs default
|
||||||
if [[ "$build_server_pkg" == true || "$build_client_pkg" == true ]]; then
|
if [[ "$build_server_pkg" == true || "$build_client_pkg" == true || "$build_server_pkg_arm" == true || "$build_client_pkg_arm" == true ]]; then
|
||||||
export ARGUS_BUILD_PROFILE=pkg
|
export ARGUS_BUILD_PROFILE=pkg
|
||||||
fi
|
fi
|
||||||
|
|
||||||
@ -902,6 +908,44 @@ if [[ "$build_client_pkg" == true ]]; then
|
|||||||
fi
|
fi
|
||||||
fi
|
fi
|
||||||
|
|
||||||
|
# ARM 专用：Server/Client 部署包
|
||||||
|
if [[ "$build_server_pkg_arm" == true ]]; then
|
||||||
|
if [[ -z "$bundle_date" ]]; then
|
||||||
|
echo "❌ arm_server_pkg requires --version YYYYMMDD" >&2
|
||||||
|
build_failed=true
|
||||||
|
else
|
||||||
|
echo ""
|
||||||
|
echo "🧳 Building ARM Server package..."
|
||||||
|
if ! "$root/deployment_new/build/make_arm_server_package.sh" --version "$bundle_date"; then
|
||||||
|
build_failed=true
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
|
if [[ "$build_client_pkg_arm" == true ]]; then
|
||||||
|
if [[ -z "$bundle_date" ]]; then
|
||||||
|
echo "❌ arm_client_pkg requires --version YYYYMMDD" >&2
|
||||||
|
build_failed=true
|
||||||
|
else
|
||||||
|
echo ""
|
||||||
|
echo "🧳 Building ARM Client-CPU package..."
|
||||||
|
cpu_repo="argus-sys-metric-test-node-arm64"
|
||||||
|
cpu_image_arg="$cpu_repo:latest"
|
||||||
|
# 若已存在 :<version>，优先使用；否则退回 latest 交由打包脚本打 tag
|
||||||
|
if docker image inspect "${cpu_repo}:${bundle_date}" >/dev/null 2>&1; then
|
||||||
|
cpu_image_arg="${cpu_repo}:${bundle_date}"
|
||||||
|
elif ! docker image inspect "${cpu_repo}:latest" >/dev/null 2>&1; then
|
||||||
|
echo "❌ required CPU node image missing: ${cpu_repo}:{${bundle_date},latest}" >&2
|
||||||
|
build_failed=true
|
||||||
|
fi
|
||||||
|
if [[ "$build_failed" != "true" ]]; then
|
||||||
|
if ! "$root/deployment_new/build/make_arm_client_package.sh" --version "$bundle_date" --image "$cpu_image_arg"; then
|
||||||
|
build_failed=true
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
echo "======================================="
|
echo "======================================="
|
||||||
echo "📦 Build Summary"
|
echo "📦 Build Summary"
|
||||||
echo "======================================="
|
echo "======================================="
|
||||||
|
|||||||
112
deployment_new/build/make_arm_client_package.sh
Executable file
112
deployment_new/build/make_arm_client_package.sh
Executable file
@ -0,0 +1,112 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
# Make ARM Client-CPU package (versioned CPU node image, compose, env, docs)
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
|
||||||
|
TEMPL_DIR="$ROOT_DIR/deployment_new/templates/client_arm"
|
||||||
|
ART_ROOT="$ROOT_DIR/deployment_new/artifact/client_arm"
|
||||||
|
|
||||||
|
COMMON_SH="$ROOT_DIR/deployment_new/build/common.sh"
|
||||||
|
. "$COMMON_SH"
|
||||||
|
|
||||||
|
usage(){ cat <<EOF
|
||||||
|
Build ARM Client-CPU Package (deployment_new)
|
||||||
|
|
||||||
|
Usage: $(basename "$0") --version YYYYMMDD [--image IMAGE[:TAG]]
|
||||||
|
|
||||||
|
Defaults:
|
||||||
|
image = argus-sys-metric-test-node-arm64:latest
|
||||||
|
|
||||||
|
Outputs: deployment_new/artifact/client_arm/<YYYYMMDD>/ and client_arm_YYYYMMDD.tar.gz
|
||||||
|
EOF
|
||||||
|
}
|
||||||
|
|
||||||
|
VERSION=""
|
||||||
|
IMAGE="argus-sys-metric-test-node-arm64:latest"
|
||||||
|
while [[ $# -gt 0 ]]; do
|
||||||
|
case "$1" in
|
||||||
|
--version) VERSION="$2"; shift 2;;
|
||||||
|
--image) IMAGE="$2"; shift 2;;
|
||||||
|
-h|--help) usage; exit 0;;
|
||||||
|
*) err "unknown arg: $1"; usage; exit 1;;
|
||||||
|
esac
|
||||||
|
done
|
||||||
|
if [[ -z "$VERSION" ]]; then VERSION="$(today_version)"; fi
|
||||||
|
|
||||||
|
require_cmd docker tar gzip
|
||||||
|
|
||||||
|
STAGE="$(mktemp -d)"; trap 'rm -rf "$STAGE"' EXIT
|
||||||
|
PKG_DIR="$ART_ROOT/$VERSION"
|
||||||
|
mkdir -p "$PKG_DIR" "$STAGE/images" "$STAGE/compose" "$STAGE/docs" "$STAGE/scripts" "$STAGE/private/argus"
|
||||||
|
|
||||||
|
# 1) Save CPU node image with version tag
|
||||||
|
if ! docker image inspect "$IMAGE" >/dev/null 2>&1; then
|
||||||
|
err "missing image: $IMAGE"; exit 1; fi
|
||||||
|
|
||||||
|
REPO="${IMAGE%%:*}"; TAG_VER="$REPO:$VERSION"
|
||||||
|
docker tag "$IMAGE" "$TAG_VER"
|
||||||
|
out_tar="$STAGE/images/${REPO//\//-}-$VERSION.tar"
|
||||||
|
docker save -o "$out_tar" "$TAG_VER"
|
||||||
|
gzip -f "$out_tar"
|
||||||
|
|
||||||
|
# 2) Compose + env template
|
||||||
|
cp "$TEMPL_DIR/compose/docker-compose.yml" "$STAGE/compose/docker-compose.yml"
|
||||||
|
ENV_EX="$STAGE/compose/.env.example"
|
||||||
|
cat >"$ENV_EX" <<EOF
|
||||||
|
# Generated by make_arm_client_package.sh
|
||||||
|
PKG_VERSION=$VERSION
|
||||||
|
|
||||||
|
NODE_CPU_IMAGE_TAG=${REPO}:${VERSION}
|
||||||
|
|
||||||
|
# Compose project name (isolation from server stack)
|
||||||
|
COMPOSE_PROJECT_NAME=argus-client-arm
|
||||||
|
|
||||||
|
# Required fields（ARM Client 默认通过 overlay alias 访问 master，可按需覆盖 MASTER_ENDPOINT）
|
||||||
|
MASTER_ENDPOINT=http://master.argus.com:3000
|
||||||
|
AGENT_ENV=
|
||||||
|
AGENT_USER=
|
||||||
|
AGENT_INSTANCE=
|
||||||
|
CPU_NODE_HOSTNAME=
|
||||||
|
|
||||||
|
# UID/GID for volume ownership
|
||||||
|
ARGUS_BUILD_UID=2133
|
||||||
|
ARGUS_BUILD_GID=2015
|
||||||
|
EOF
|
||||||
|
|
||||||
|
# 3) Docs
|
||||||
|
CLIENT_DOC_SRC="$TEMPL_DIR/docs"
|
||||||
|
if [[ -d "$CLIENT_DOC_SRC" ]]; then
|
||||||
|
copy_tree "$CLIENT_DOC_SRC" "$STAGE/docs"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# 4) Scripts & private skeleton
|
||||||
|
SCRIPTS_SRC="$TEMPL_DIR/scripts"
|
||||||
|
if [[ -d "$SCRIPTS_SRC" ]]; then
|
||||||
|
copy_tree "$SCRIPTS_SRC" "$STAGE/scripts"
|
||||||
|
find "$STAGE/scripts" -type f -name '*.sh' -exec chmod +x {} + 2>/dev/null || true
|
||||||
|
fi
|
||||||
|
|
||||||
|
# x86 专用脚本：用于在 x86_64 主机上运行 ARM Client 包
|
||||||
|
SCRIPTS_X86_SRC="$TEMPL_DIR/scripts_for_x86"
|
||||||
|
if [[ -d "$SCRIPTS_X86_SRC" ]]; then
|
||||||
|
copy_tree "$SCRIPTS_X86_SRC" "$STAGE/scripts_for_x86"
|
||||||
|
find "$STAGE/scripts_for_x86" -type f -name '*.sh' -exec chmod +x {} + 2>/dev/null || true
|
||||||
|
fi
|
||||||
|
|
||||||
|
mkdir -p "$STAGE/private/argus/agent"
|
||||||
|
|
||||||
|
# 5) Manifest & checksums
|
||||||
|
gen_manifest "$STAGE" "$STAGE/manifest.txt"
|
||||||
|
checksum_dir "$STAGE" "$STAGE/checksums.txt"
|
||||||
|
|
||||||
|
# 6) Move to artifact dir and pack
|
||||||
|
mkdir -p "$PKG_DIR"
|
||||||
|
copy_tree "$STAGE" "$PKG_DIR"
|
||||||
|
|
||||||
|
OUT_TAR_DIR="$(dirname "$PKG_DIR")"
|
||||||
|
OUT_TAR="$OUT_TAR_DIR/client_arm_${VERSION}.tar.gz"
|
||||||
|
log "Creating tarball: $OUT_TAR"
|
||||||
|
(cd "$PKG_DIR/.." && tar -czf "$OUT_TAR" "$(basename "$PKG_DIR")")
|
||||||
|
log "Client-ARM package ready: $PKG_DIR"
|
||||||
|
echo "$OUT_TAR"
|
||||||
175
deployment_new/build/make_arm_server_package.sh
Executable file
175
deployment_new/build/make_arm_server_package.sh
Executable file
@ -0,0 +1,175 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
# Make ARM server deployment package (master + prometheus + grafana + alertmanager + web)
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
|
||||||
|
TEMPL_DIR="$ROOT_DIR/deployment_new/templates/server_arm"
|
||||||
|
ART_ROOT="$ROOT_DIR/deployment_new/artifact/server_arm"
|
||||||
|
|
||||||
|
COMMON_SH="$ROOT_DIR/deployment_new/build/common.sh"
|
||||||
|
. "$COMMON_SH"
|
||||||
|
|
||||||
|
usage(){ cat <<EOF
|
||||||
|
Build ARM Server Deployment Package (deployment_new)
|
||||||
|
|
||||||
|
Usage: $(basename "$0") --version YYYYMMDD
|
||||||
|
|
||||||
|
Outputs: deployment_new/artifact/server_arm/<YYYYMMDD>/ and server_arm_YYYYMMDD.tar.gz
|
||||||
|
EOF
|
||||||
|
}
|
||||||
|
|
||||||
|
VERSION=""
|
||||||
|
while [[ $# -gt 0 ]]; do
|
||||||
|
case "$1" in
|
||||||
|
--version) VERSION="$2"; shift 2;;
|
||||||
|
-h|--help) usage; exit 0;;
|
||||||
|
*) err "unknown arg: $1"; usage; exit 1;;
|
||||||
|
esac
|
||||||
|
done
|
||||||
|
if [[ -z "$VERSION" ]]; then VERSION="$(today_version)"; fi
|
||||||
|
|
||||||
|
require_cmd docker tar gzip awk sed
|
||||||
|
|
||||||
|
IMAGES=(
|
||||||
|
argus-master-arm64
|
||||||
|
argus-metric-prometheus-arm64
|
||||||
|
argus-metric-prometheus-targets-updater-arm64
|
||||||
|
argus-metric-grafana-arm64
|
||||||
|
argus-alertmanager-arm64
|
||||||
|
argus-web-frontend-arm64
|
||||||
|
argus-web-proxy-arm64
|
||||||
|
)
|
||||||
|
|
||||||
|
STAGE="$(mktemp -d)"; trap 'rm -rf "$STAGE"' EXIT
|
||||||
|
PKG_DIR="$ART_ROOT/$VERSION"
|
||||||
|
mkdir -p "$PKG_DIR" "$STAGE/images" "$STAGE/compose" "$STAGE/docs" "$STAGE/scripts" "$STAGE/private/argus"
|
||||||
|
|
||||||
|
# 1) Save per-image tars with version tag
|
||||||
|
log "Tagging and saving ARM server images (version=$VERSION)"
|
||||||
|
for repo in "${IMAGES[@]}"; do
|
||||||
|
if ! docker image inspect "$repo:latest" >/dev/null 2>&1 && ! docker image inspect "$repo:$VERSION" >/dev/null 2>&1; then
|
||||||
|
err "missing image: $repo (need :latest or :$VERSION)"; exit 1; fi
|
||||||
|
if docker image inspect "$repo:$VERSION" >/dev/null 2>&1; then
|
||||||
|
tag="$repo:$VERSION"
|
||||||
|
else
|
||||||
|
docker tag "$repo:latest" "$repo:$VERSION"
|
||||||
|
tag="$repo:$VERSION"
|
||||||
|
fi
|
||||||
|
out_tar="$STAGE/images/${repo//\//-}-$VERSION.tar"
|
||||||
|
docker save -o "$out_tar" "$tag"
|
||||||
|
gzip -f "$out_tar"
|
||||||
|
done
|
||||||
|
|
||||||
|
# 1.1) （可选）打包 x86 ARM 测试用基础镜像 ubuntu:22.04（供 scripts_for_x86/install.sh 使用）
|
||||||
|
TEST_BASE="ubuntu:22.04"
|
||||||
|
if docker image inspect "$TEST_BASE" >/dev/null 2>&1 || docker pull "$TEST_BASE" >/dev/null 2>&1; then
|
||||||
|
log "Saving ARM test base image for x86 host: $TEST_BASE"
|
||||||
|
test_tar="$STAGE/images/ubuntu-22.04-arm-test.tar"
|
||||||
|
docker save -o "$test_tar" "$TEST_BASE"
|
||||||
|
gzip -f "$test_tar"
|
||||||
|
else
|
||||||
|
warn "无法获取 $TEST_BASE，x86 上的 ARM 运行能力将无法使用该镜像做快速自检（可忽略，或在目标机自行拉取）。"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# 1.2) 随包提供 tonistiigi/binfmt 镜像，便于 x86 离线机器安装 binfmt/QEMU
|
||||||
|
BINFMT_IMAGE="tonistiigi/binfmt:latest"
|
||||||
|
if docker image inspect "$BINFMT_IMAGE" >/dev/null 2>&1 || docker pull "$BINFMT_IMAGE" >/dev/null 2>&1; then
|
||||||
|
log "Saving binfmt helper image for x86 host: $BINFMT_IMAGE"
|
||||||
|
binfmt_tar="$STAGE/images/tonistiigi-binfmt.tar"
|
||||||
|
docker save -o "$binfmt_tar" "$BINFMT_IMAGE"
|
||||||
|
gzip -f "$binfmt_tar"
|
||||||
|
else
|
||||||
|
warn "无法获取 $BINFMT_IMAGE，x86 上将无法通过离线方式安装 binfmt（可在目标机上自行 docker pull）。"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# 2) Compose + env template（ARM 专用）
|
||||||
|
cp "$TEMPL_DIR/compose/docker-compose.yml" "$STAGE/compose/docker-compose.yml"
|
||||||
|
ENV_EX="$STAGE/compose/.env.example"
|
||||||
|
cat >"$ENV_EX" <<EOF
|
||||||
|
# Generated by make_arm_server_package.sh
|
||||||
|
PKG_VERSION=$VERSION
|
||||||
|
|
||||||
|
# ARM server image tags
|
||||||
|
MASTER_IMAGE_TAG=argus-master-arm64:${VERSION}
|
||||||
|
PROM_IMAGE_TAG=argus-metric-prometheus-arm64:${VERSION}
|
||||||
|
PROM_UPDATER_IMAGE_TAG=argus-metric-prometheus-targets-updater-arm64:${VERSION}
|
||||||
|
GRAFANA_IMAGE_TAG=argus-metric-grafana-arm64:${VERSION}
|
||||||
|
ALERT_IMAGE_TAG=argus-alertmanager-arm64:${VERSION}
|
||||||
|
FRONT_IMAGE_TAG=argus-web-frontend-arm64:${VERSION}
|
||||||
|
WEB_PROXY_IMAGE_TAG=argus-web-proxy-arm64:${VERSION}
|
||||||
|
|
||||||
|
# Host ports for server compose
|
||||||
|
MASTER_PORT=32300
|
||||||
|
PROMETHEUS_PORT=9090
|
||||||
|
GRAFANA_PORT=3000
|
||||||
|
ALERTMANAGER_PORT=9093
|
||||||
|
WEB_PROXY_PORT_8080=8080
|
||||||
|
WEB_PROXY_PORT_8081=8081
|
||||||
|
WEB_PROXY_PORT_8082=8082
|
||||||
|
WEB_PROXY_PORT_8083=8083
|
||||||
|
WEB_PROXY_PORT_8084=8084
|
||||||
|
WEB_PROXY_PORT_8085=8085
|
||||||
|
|
||||||
|
# Overlay network name
|
||||||
|
ARGUS_OVERLAY_NET=argus-sys-net
|
||||||
|
|
||||||
|
# UID/GID for volume ownership
|
||||||
|
ARGUS_BUILD_UID=2133
|
||||||
|
ARGUS_BUILD_GID=2015
|
||||||
|
|
||||||
|
# Compose project name (isolation from other stacks on same host)
|
||||||
|
COMPOSE_PROJECT_NAME=argus-server-arm
|
||||||
|
EOF
|
||||||
|
|
||||||
|
# 3) Docs & scripts from templates/server_arm
|
||||||
|
DOCS_SRC="$TEMPL_DIR/docs"
|
||||||
|
if [[ -d "$DOCS_SRC" ]]; then
|
||||||
|
copy_tree "$DOCS_SRC" "$STAGE/docs"
|
||||||
|
fi
|
||||||
|
|
||||||
|
SCRIPTS_SRC="$TEMPL_DIR/scripts"
|
||||||
|
if [[ -d "$SCRIPTS_SRC" ]]; then
|
||||||
|
copy_tree "$SCRIPTS_SRC" "$STAGE/scripts"
|
||||||
|
find "$STAGE/scripts" -type f -name '*.sh' -exec chmod +x {} + 2>/dev/null || true
|
||||||
|
fi
|
||||||
|
|
||||||
|
# x86 专用脚本：用于在 x86_64 主机上运行 ARM server 包
|
||||||
|
SCRIPTS_X86_SRC="$TEMPL_DIR/scripts_for_x86"
|
||||||
|
if [[ -d "$SCRIPTS_X86_SRC" ]]; then
|
||||||
|
copy_tree "$SCRIPTS_X86_SRC" "$STAGE/scripts_for_x86"
|
||||||
|
find "$STAGE/scripts_for_x86" -type f -name '*.sh' -exec chmod +x {} + 2>/dev/null || true
|
||||||
|
fi
|
||||||
|
|
||||||
|
# 4) Private skeleton (最小 ARM server 所需目录)
|
||||||
|
mkdir -p \
|
||||||
|
"$STAGE/private/argus/etc" \
|
||||||
|
"$STAGE/private/argus/master" \
|
||||||
|
"$STAGE/private/argus/metric/prometheus" \
|
||||||
|
"$STAGE/private/argus/metric/prometheus/data" \
|
||||||
|
"$STAGE/private/argus/metric/prometheus/rules" \
|
||||||
|
"$STAGE/private/argus/metric/prometheus/targets" \
|
||||||
|
"$STAGE/private/argus/metric/grafana" \
|
||||||
|
"$STAGE/private/argus/metric/grafana/data" \
|
||||||
|
"$STAGE/private/argus/metric/grafana/logs" \
|
||||||
|
"$STAGE/private/argus/metric/grafana/plugins" \
|
||||||
|
"$STAGE/private/argus/metric/grafana/provisioning/datasources" \
|
||||||
|
"$STAGE/private/argus/metric/grafana/provisioning/dashboards" \
|
||||||
|
"$STAGE/private/argus/metric/grafana/data/sessions" \
|
||||||
|
"$STAGE/private/argus/metric/grafana/data/dashboards" \
|
||||||
|
"$STAGE/private/argus/metric/grafana/config"
|
||||||
|
|
||||||
|
# 5) Manifest & checksums
|
||||||
|
gen_manifest "$STAGE" "$STAGE/manifest.txt"
|
||||||
|
checksum_dir "$STAGE" "$STAGE/checksums.txt"
|
||||||
|
|
||||||
|
# 6) Move to artifact dir and pack
|
||||||
|
mkdir -p "$PKG_DIR"
|
||||||
|
copy_tree "$STAGE" "$PKG_DIR"
|
||||||
|
|
||||||
|
OUT_TAR_DIR="$(dirname "$PKG_DIR")"
|
||||||
|
OUT_TAR="$OUT_TAR_DIR/server_arm_${VERSION}.tar.gz"
|
||||||
|
log "Creating tarball: $OUT_TAR"
|
||||||
|
(cd "$PKG_DIR/.." && tar -czf "$OUT_TAR" "$(basename "$PKG_DIR")")
|
||||||
|
log "ARM Server package ready: $PKG_DIR"
|
||||||
|
echo "$OUT_TAR"
|
||||||
@ -0,0 +1,29 @@
|
|||||||
|
version: "3.8"
|
||||||
|
|
||||||
|
networks:
|
||||||
|
argus-sys-net:
|
||||||
|
external: true
|
||||||
|
|
||||||
|
services:
|
||||||
|
metric-cpu-node:
|
||||||
|
image: ${NODE_CPU_IMAGE_TAG:-argus-sys-metric-test-node-arm64:${PKG_VERSION}}
|
||||||
|
platform: linux/arm64
|
||||||
|
container_name: argus-metric-cpu-node
|
||||||
|
hostname: ${CPU_NODE_HOSTNAME}
|
||||||
|
restart: unless-stopped
|
||||||
|
environment:
|
||||||
|
- TZ=Asia/Shanghai
|
||||||
|
- DEBIAN_FRONTEND=noninteractive
|
||||||
|
- MASTER_ENDPOINT=${MASTER_ENDPOINT}
|
||||||
|
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
|
||||||
|
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
|
||||||
|
- AGENT_ENV=${AGENT_ENV}
|
||||||
|
- AGENT_USER=${AGENT_USER}
|
||||||
|
- AGENT_INSTANCE=${AGENT_INSTANCE}
|
||||||
|
networks:
|
||||||
|
argus-sys-net:
|
||||||
|
aliases:
|
||||||
|
- ${AGENT_INSTANCE}.node.argus.com
|
||||||
|
volumes:
|
||||||
|
- ../private/argus/agent:/private/argus/agent
|
||||||
|
|
||||||
@ -0,0 +1,154 @@
|
|||||||
|
# ARM Client-CPU 安装指南（client_arm）
|
||||||
|
|
||||||
|
本包用于在 ARM64 CPU 节点上部署 Argus 的最小客户端：
|
||||||
|
|
||||||
|
- `argus-agent`（负责注册/上报状态到 master）
|
||||||
|
- `node-exporter`（暴露该节点的系统指标）
|
||||||
|
|
||||||
|
> 注意：本 ARM 客户端包 **不包含 GPU/DCGM exporter 和 Fluent Bit**，仅用于 CPU 节点 metrics。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 1. 前置条件
|
||||||
|
|
||||||
|
- 目标机器为 ARM64（例如：aarch64 服务器 / 节点）；
|
||||||
|
- 已安装 Docker 和 docker compose（v2，支持 `docker compose` 命令）；
|
||||||
|
- 能访问 master 所在网络，或已经通过 overlay 网络加入到与 server 相同的 `argus-sys-net` 中。
|
||||||
|
|
||||||
|
如采用 overlay 网络（Swarm 模式），需提前创建 `argus-sys-net`：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker network create --driver overlay argus-sys-net || true
|
||||||
|
```
|
||||||
|
|
||||||
|
如仅使用本地 bridge 网络，可将 compose 中 `networks: argus-sys-net` 调整为本地自定义 network。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 2. 解压和加载镜像
|
||||||
|
|
||||||
|
假设你已经将 `client_arm_YYYYMMDD.tar.gz` 拷贝到 ARM 节点：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
tar -xzf client_arm_YYYYMMDD.tar.gz
|
||||||
|
cd client_arm/YYYYMMDD
|
||||||
|
```
|
||||||
|
|
||||||
|
加载 CPU node 镜像：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
for f in images/*.tar.gz; do
|
||||||
|
gunzip -c "$f" | docker load
|
||||||
|
done
|
||||||
|
```
|
||||||
|
|
||||||
|
可以通过：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker images | grep 'argus-sys-metric-test-node-arm64'
|
||||||
|
```
|
||||||
|
|
||||||
|
确认镜像已加载。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 3. 配置 .env
|
||||||
|
|
||||||
|
进入 compose 目录：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd compose
|
||||||
|
cp .env.example .env
|
||||||
|
```
|
||||||
|
|
||||||
|
需要填写的关键字段：
|
||||||
|
|
||||||
|
- `MASTER_ENDPOINT`
|
||||||
|
- 例如：`http://master.argus.com:3000` 或 `http://<Server-IP>:32300`
|
||||||
|
- `AGENT_ENV` / `AGENT_USER` / `AGENT_INSTANCE`
|
||||||
|
- 用于识别环境、用户和实例，在 UI 中区分节点：
|
||||||
|
- 示例：`AGENT_ENV=prod`, `AGENT_USER=ops`, `AGENT_INSTANCE=node001`
|
||||||
|
- `CPU_NODE_HOSTNAME`
|
||||||
|
- 节点在配置中的 hostname，一般与宿主 `hostname` 一致，例如 `swarm-metric-node-001`。
|
||||||
|
- `ARGUS_BUILD_UID` / `ARGUS_BUILD_GID`
|
||||||
|
- 用于挂载目录 `/private/argus/agent` 的权限映射。
|
||||||
|
|
||||||
|
例如：
|
||||||
|
|
||||||
|
```env
|
||||||
|
PKG_VERSION=20251124
|
||||||
|
NODE_CPU_IMAGE_TAG=argus-sys-metric-test-node-arm64:20251124
|
||||||
|
|
||||||
|
COMPOSE_PROJECT_NAME=argus-client-arm
|
||||||
|
|
||||||
|
MASTER_ENDPOINT=http://master.argus.com:3000
|
||||||
|
AGENT_ENV=dev2
|
||||||
|
AGENT_USER=yuyr
|
||||||
|
AGENT_INSTANCE=node001sX
|
||||||
|
CPU_NODE_HOSTNAME=swarm-metric-node-001
|
||||||
|
|
||||||
|
ARGUS_BUILD_UID=1000
|
||||||
|
ARGUS_BUILD_GID=1000
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 4. 准备挂载目录
|
||||||
|
|
||||||
|
包中已经预创建 `private/argus/agent` 目录：
|
||||||
|
|
||||||
|
- `../private/argus/agent`
|
||||||
|
|
||||||
|
可以根据需要设置所有者和权限：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd ..
|
||||||
|
sudo chown -R $UID:$GID private/argus
|
||||||
|
```
|
||||||
|
|
||||||
|
确保与 `.env` 中的 `ARGUS_BUILD_UID/GID` 一致。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 5. 启动客户端容器
|
||||||
|
|
||||||
|
在 `compose/` 目录执行：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker compose --env-file .env up -d
|
||||||
|
```
|
||||||
|
|
||||||
|
查看状态：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker compose ps
|
||||||
|
```
|
||||||
|
|
||||||
|
预期看到：
|
||||||
|
|
||||||
|
- `argus-metric-cpu-node` 处于 `Up` 状态。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 6. 在 server 端验证
|
||||||
|
|
||||||
|
在 server 侧（master + Prometheus + Grafana 已经通过 ARM server 包部署）：
|
||||||
|
|
||||||
|
1. 在 master 的 UI 或 API 中：
|
||||||
|
- `GET /api/v1/master/nodes` 应能看到新节点，`name=CPU_NODE_HOSTNAME`；
|
||||||
|
2. 在 Prometheus 中：
|
||||||
|
- `up{job="node"}` 中应有当前节点记录，且 `value=1`；
|
||||||
|
- 可以通过 `node_load1{hostname="swarm-metric-node-001"}` 等表达式查看指标；
|
||||||
|
3. 在 Web 门户 / Grafana：
|
||||||
|
- 节点列表页面中能看到该节点；
|
||||||
|
- 通过“按 hostname 的节点面板”查看对应指标。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 7. 注意事项
|
||||||
|
|
||||||
|
- ARM 客户端包只负责“CPU 节点 metrics”，不包含 GPU/DCGM 或 Fluent Bit；
|
||||||
|
- 如需要 GPU 支持，请继续使用 `client_gpu` 包，并部署在 x86_64 + NVIDIA GPU 节点上；
|
||||||
|
- ARM 节点的网络连通性（到 master / Prometheus）需要运维侧提前规划；
|
||||||
|
本包不做网络路由/防火墙配置，仅假定可以直接访问 `MASTER_ENDPOINT`。
|
||||||
|
|
||||||
105
deployment_new/templates/client_arm/scripts/config.sh
Normal file
105
deployment_new/templates/client_arm/scripts/config.sh
Normal file
@ -0,0 +1,105 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
# ARM Client-CPU 配置脚本：
|
||||||
|
# - 读取 server 侧生成的 cluster-info.env（包含 SWARM_MANAGER_ADDR / SWARM_JOIN_TOKEN_WORKER）
|
||||||
|
# - 加入 Swarm（worker）
|
||||||
|
# - 预热 overlay 网络，确保能通过 master.argus.com 访问 server
|
||||||
|
# - 生成/更新 compose/.env（填充 Swarm 相关字段，保留人工填写的 AGENT_*、CPU_NODE_HOSTNAME 等）
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
PKG_ROOT="$ROOT_DIR"
|
||||||
|
ENV_EX="$PKG_ROOT/compose/.env.example"
|
||||||
|
ENV_OUT="$PKG_ROOT/compose/.env"
|
||||||
|
|
||||||
|
info(){ echo -e "\033[34m[CONFIG-ARM-CLIENT]\033[0m $*"; }
|
||||||
|
err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
|
||||||
|
|
||||||
|
# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
|
||||||
|
require_compose(){
|
||||||
|
if docker compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
|
||||||
|
}
|
||||||
|
|
||||||
|
require docker curl jq awk sed tar gzip
|
||||||
|
require_compose
|
||||||
|
|
||||||
|
[[ -f "$ENV_EX" ]] || { err "缺少模板文件: $ENV_EX"; exit 1; }
|
||||||
|
|
||||||
|
# 磁盘空间检查（MB）
|
||||||
|
check_disk(){ local p="$1"; local need=5120; local free
|
||||||
|
free=$(df -Pm "$p" | awk 'NR==2{print $4+0}')
|
||||||
|
if [[ -z "$free" || "$free" -lt "$need" ]]; then err "磁盘空间不足: $p 剩余 ${free:-0}MB (<${need}MB)"; fi
|
||||||
|
}
|
||||||
|
check_disk "$PKG_ROOT" || true
|
||||||
|
check_disk "/var/lib/docker" || true
|
||||||
|
|
||||||
|
# 导入 cluster-info.env（默认取当前包根，也可用 CLUSTER_INFO 指定路径）
|
||||||
|
CI_IN="${CLUSTER_INFO:-$PKG_ROOT/cluster-info.env}"
|
||||||
|
info "读取 cluster-info.env: $CI_IN"
|
||||||
|
[[ -f "$CI_IN" ]] || { err "找不到 cluster-info.env（默认当前包根，或设置环境变量 CLUSTER_INFO 指定绝对路径）"; exit 1; }
|
||||||
|
set -a; source "$CI_IN"; set +a
|
||||||
|
[[ -n "${SWARM_MANAGER_ADDR:-}" && -n "${SWARM_JOIN_TOKEN_WORKER:-}" ]] || { err "cluster-info.env 缺少 SWARM 信息（SWARM_MANAGER_ADDR/SWARM_JOIN_TOKEN_WORKER）"; exit 1; }
|
||||||
|
|
||||||
|
# 加入 Swarm（幂等）
|
||||||
|
info "加入 Swarm（幂等）：$SWARM_MANAGER_ADDR"
|
||||||
|
docker swarm join --token "$SWARM_JOIN_TOKEN_WORKER" "$SWARM_MANAGER_ADDR":2377 >/dev/null 2>&1 || true
|
||||||
|
|
||||||
|
# 导入 busybox 并做 overlay 预热与连通性
|
||||||
|
NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
|
||||||
|
if ! docker image inspect busybox:latest >/dev/null 2>&1; then
|
||||||
|
if [[ -f "$PKG_ROOT/images/busybox.tar" ]]; then
|
||||||
|
info "加载 busybox.tar 以预热 overlay"
|
||||||
|
docker load -i "$PKG_ROOT/images/busybox.tar" >/dev/null
|
||||||
|
else
|
||||||
|
err "缺少 busybox 镜像（包内 images/busybox.tar 或本地 busybox:latest），无法预热 overlay $NET_NAME"; exit 1
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
|
# 预热容器（worker 侧加入 overlay 以便本地可见）
|
||||||
|
docker rm -f argus-net-warmup >/dev/null 2>&1 || true
|
||||||
|
info "启动 warmup 容器加入 overlay: $NET_NAME"
|
||||||
|
docker run -d --rm --name argus-net-warmup --network "$NET_NAME" busybox:latest sleep 600 >/dev/null 2>&1 || true
|
||||||
|
for i in {1..60}; do docker network inspect "$NET_NAME" >/dev/null 2>&1 && { info "overlay 可见 (t=${i}s)"; break; }; sleep 1; done
|
||||||
|
docker network inspect "$NET_NAME" >/dev/null 2>&1 || { err "预热后仍未看到 overlay: $NET_NAME；请确认 server 侧 overlay 已创建且可达"; exit 1; }
|
||||||
|
|
||||||
|
# 通过 warmup 容器测试实际数据通路（alias → master）
|
||||||
|
if ! docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 master.argus.com >/dev/null 2>&1"; then
|
||||||
|
err "warmup 容器内无法通过别名访问 master.argus.com；请确认 server compose 已启动并加入 overlay $NET_NAME"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
info "warmup 容器内可达 master.argus.com（Docker DNS + alias 正常）"
|
||||||
|
|
||||||
|
# 生成/更新 .env（保留人工填写项，不覆盖已有键）
|
||||||
|
if [[ ! -f "$ENV_OUT" ]]; then
|
||||||
|
cp "$ENV_EX" "$ENV_OUT"
|
||||||
|
fi
|
||||||
|
|
||||||
|
set_kv(){ local k="$1" v="$2"; if grep -q "^${k}=" "$ENV_OUT"; then sed -i -E "s#^${k}=.*#${k}=${v}#" "$ENV_OUT"; else echo "${k}=${v}" >> "$ENV_OUT"; fi }
|
||||||
|
|
||||||
|
# 写入与 Swarm 相关的字段，便于后续诊断
|
||||||
|
set_kv SWARM_MANAGER_ADDR "${SWARM_MANAGER_ADDR:-}"
|
||||||
|
set_kv SWARM_JOIN_TOKEN_WORKER "${SWARM_JOIN_TOKEN_WORKER:-}"
|
||||||
|
set_kv SWARM_JOIN_TOKEN_MANAGER "${SWARM_JOIN_TOKEN_MANAGER:-}"
|
||||||
|
|
||||||
|
# 若未显式设置 MASTER_ENDPOINT，则默认走 overlay 别名
|
||||||
|
if ! grep -q '^MASTER_ENDPOINT=' "$ENV_OUT"; then
|
||||||
|
echo "MASTER_ENDPOINT=http://master.argus.com:3000" >> "$ENV_OUT"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# 检查用户必须填写的字段
|
||||||
|
REQ_VARS=(AGENT_ENV AGENT_USER AGENT_INSTANCE CPU_NODE_HOSTNAME)
|
||||||
|
missing=()
|
||||||
|
for v in "${REQ_VARS[@]}"; do
|
||||||
|
val=$(grep -E "^$v=" "$ENV_OUT" | head -1 | cut -d= -f2-)
|
||||||
|
if [[ -z "$val" ]]; then missing+=("$v"); fi
|
||||||
|
done
|
||||||
|
if [[ ${#missing[@]} -gt 0 ]]; then
|
||||||
|
err "以下变量必须在 compose/.env 中填写：${missing[*]}（已保留你现有的内容，不会被覆盖）"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
info "已生成 compose/.env；可执行 scripts/install.sh 启动 ARM Client-CPU"
|
||||||
48
deployment_new/templates/client_arm/scripts/install.sh
Normal file
48
deployment_new/templates/client_arm/scripts/install.sh
Normal file
@ -0,0 +1,48 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
# ARM Client-CPU 安装脚本：
|
||||||
|
# - 导入 ARM CPU node 镜像
|
||||||
|
# - 启动 compose 中的 metric-cpu-node 服务
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
PKG_ROOT="$ROOT_DIR"
|
||||||
|
ENV_FILE="$PKG_ROOT/compose/.env"
|
||||||
|
COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
|
||||||
|
|
||||||
|
info(){ echo -e "\033[34m[INSTALL-ARM-CLIENT]\033[0m $*"; }
|
||||||
|
err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
|
||||||
|
|
||||||
|
require_compose(){
|
||||||
|
if docker compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
|
||||||
|
}
|
||||||
|
|
||||||
|
require docker
|
||||||
|
require_compose
|
||||||
|
|
||||||
|
[[ -f "$ENV_FILE" ]] || { err "缺少 compose/.env，请先运行 scripts/config.sh"; exit 1; }
|
||||||
|
info "使用环境文件: $ENV_FILE"
|
||||||
|
|
||||||
|
set -a; source "$ENV_FILE"; set +a
|
||||||
|
|
||||||
|
# 导入 ARM CPU node 镜像
|
||||||
|
IMG_TGZ=$(ls -1 "$PKG_ROOT"/images/argus-sys-metric-test-node-arm64-*.tar.gz 2>/dev/null | head -1 || true)
|
||||||
|
[[ -n "$IMG_TGZ" ]] || { err "找不到 ARM CPU node 镜像 tar.gz（argus-sys-metric-test-node-arm64-*.tar.gz）"; exit 1; }
|
||||||
|
info "导入 ARM CPU node 镜像: $(basename "$IMG_TGZ")"
|
||||||
|
tmp=$(mktemp); gunzip -c "$IMG_TGZ" > "$tmp"; docker load -i "$tmp" >/dev/null; rm -f "$tmp"
|
||||||
|
|
||||||
|
# 确保 agent 挂载目录存在
|
||||||
|
mkdir -p "$PKG_ROOT/private/argus/agent"
|
||||||
|
|
||||||
|
# 启动 compose
|
||||||
|
PROJECT="${COMPOSE_PROJECT_NAME:-argus-client-arm}"
|
||||||
|
info "启动 ARM CPU 节点 (docker compose -p $PROJECT up -d)"
|
||||||
|
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" up -d
|
||||||
|
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps
|
||||||
|
|
||||||
|
info "ARM Client-CPU 安装完成。可通过 docker logs -f argus-metric-cpu-node 查看节点容器日志。"
|
||||||
|
|
||||||
28
deployment_new/templates/client_arm/scripts/uninstall.sh
Normal file
28
deployment_new/templates/client_arm/scripts/uninstall.sh
Normal file
@ -0,0 +1,28 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
PKG_ROOT="$ROOT_DIR"
|
||||||
|
ENV_FILE="$PKG_ROOT/compose/.env"
|
||||||
|
COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
|
||||||
|
|
||||||
|
if [[ -f "$ENV_FILE" ]]; then
|
||||||
|
set -a; source "$ENV_FILE"; set +a
|
||||||
|
fi
|
||||||
|
|
||||||
|
PROJECT="${COMPOSE_PROJECT_NAME:-argus-client-arm}"
|
||||||
|
|
||||||
|
err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
require_compose(){
|
||||||
|
if docker compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
|
||||||
|
}
|
||||||
|
|
||||||
|
require_compose
|
||||||
|
|
||||||
|
echo "[UNINSTALL-ARM-CLIENT] stopping compose (project=$PROJECT)"
|
||||||
|
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" down --remove-orphans || true
|
||||||
|
echo "[UNINSTALL-ARM-CLIENT] done"
|
||||||
|
|
||||||
@ -0,0 +1,96 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
# x86 上安装 ARM Client-CPU 的配置脚本：
|
||||||
|
# 逻辑与 ARM 版基本一致（读取 cluster-info、加入 Swarm、预热 overlay、生成 .env），只是日志前缀不同。
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
PKG_ROOT="$ROOT_DIR"
|
||||||
|
ENV_EX="$PKG_ROOT/compose/.env.example"
|
||||||
|
ENV_OUT="$PKG_ROOT/compose/.env"
|
||||||
|
|
||||||
|
info(){ echo -e "\033[34m[CONFIG-ARM-CLIENT-X86]\033[0m $*"; }
|
||||||
|
err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
|
||||||
|
|
||||||
|
require_compose(){
|
||||||
|
if docker compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
|
||||||
|
}
|
||||||
|
|
||||||
|
require docker curl jq awk sed tar gzip
|
||||||
|
require_compose
|
||||||
|
|
||||||
|
[[ -f "$ENV_EX" ]] || { err "缺少模板文件: $ENV_EX"; exit 1; }
|
||||||
|
|
||||||
|
# 磁盘空间检查
|
||||||
|
check_disk(){ local p="$1"; local need=5120; local free
|
||||||
|
free=$(df -Pm "$p" | awk 'NR==2{print $4+0}')
|
||||||
|
if [[ -z "$free" || "$free" -lt "$need" ]]; then err "磁盘空间不足: $p 剩余 ${free:-0}MB (<${need}MB)"; fi
|
||||||
|
}
|
||||||
|
check_disk "$PKG_ROOT" || true
|
||||||
|
check_disk "/var/lib/docker" || true
|
||||||
|
|
||||||
|
# 导入 cluster-info.env
|
||||||
|
CI_IN="${CLUSTER_INFO:-$PKG_ROOT/cluster-info.env}"
|
||||||
|
info "读取 cluster-info.env: $CI_IN"
|
||||||
|
[[ -f "$CI_IN" ]] || { err "找不到 cluster-info.env（默认当前包根，或设置环境变量 CLUSTER_INFO 指定绝对路径）"; exit 1; }
|
||||||
|
set -a; source "$CI_IN"; set +a
|
||||||
|
[[ -n "${SWARM_MANAGER_ADDR:-}" && -n "${SWARM_JOIN_TOKEN_WORKER:-}" ]] || { err "cluster-info.env 缺少 SWARM 信息（SWARM_MANAGER_ADDR/SWARM_JOIN_TOKEN_WORKER）"; exit 1; }
|
||||||
|
|
||||||
|
# 加入 Swarm（幂等）
|
||||||
|
info "加入 Swarm（幂等）：$SWARM_MANAGER_ADDR"
|
||||||
|
docker swarm join --token "$SWARM_JOIN_TOKEN_WORKER" "$SWARM_MANAGER_ADDR":2377 >/dev/null 2>&1 || true
|
||||||
|
|
||||||
|
# 导入 busybox 并做 overlay 预热与连通性
|
||||||
|
NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
|
||||||
|
if ! docker image inspect busybox:latest >/dev/null 2>&1; then
|
||||||
|
if [[ -f "$PKG_ROOT/images/busybox.tar" ]]; then
|
||||||
|
info "加载 busybox.tar 以预热 overlay"
|
||||||
|
docker load -i "$PKG_ROOT/images/busybox.tar" >/dev/null
|
||||||
|
else
|
||||||
|
err "缺少 busybox 镜像（包内 images/busybox.tar 或本地 busybox:latest），无法预热 overlay $NET_NAME"; exit 1
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
|
docker rm -f argus-net-warmup >/dev/null 2>&1 || true
|
||||||
|
info "启动 warmup 容器加入 overlay: $NET_NAME"
|
||||||
|
docker run -d --rm --name argus-net-warmup --network "$NET_NAME" busybox:latest sleep 600 >/dev/null 2>&1 || true
|
||||||
|
for i in {1..60}; do docker network inspect "$NET_NAME" >/dev/null 2>&1 && { info "overlay 可见 (t=${i}s)"; break; }; sleep 1; done
|
||||||
|
docker network inspect "$NET_NAME" >/dev/null 2>&1 || { err "预热后仍未看到 overlay: $NET_NAME；请确认 server 侧 overlay 已创建且可达"; exit 1; }
|
||||||
|
|
||||||
|
if ! docker exec argus-net-warmup sh -lc "ping -c 1 -W 2 master.argus.com >/dev/null 2>&1"; then
|
||||||
|
err "warmup 容器内无法通过别名访问 master.argus.com；请确认 server compose 已启动并加入 overlay $NET_NAME"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
info "warmup 容器内可达 master.argus.com（Docker DNS + alias 正常）"
|
||||||
|
|
||||||
|
if [[ ! -f "$ENV_OUT" ]]; then
|
||||||
|
cp "$ENV_EX" "$ENV_OUT"
|
||||||
|
fi
|
||||||
|
|
||||||
|
set_kv(){ local k="$1" v="$2"; if grep -q "^${k}=" "$ENV_OUT"; then sed -i -E "s#^${k}=.*#${k}=${v}#" "$ENV_OUT"; else echo "${k}=${v}" >> "$ENV_OUT"; fi }
|
||||||
|
|
||||||
|
set_kv SWARM_MANAGER_ADDR "${SWARM_MANAGER_ADDR:-}"
|
||||||
|
set_kv SWARM_JOIN_TOKEN_WORKER "${SWARM_JOIN_TOKEN_WORKER:-}"
|
||||||
|
set_kv SWARM_JOIN_TOKEN_MANAGER "${SWARM_JOIN_TOKEN_MANAGER:-}"
|
||||||
|
|
||||||
|
if ! grep -q '^MASTER_ENDPOINT=' "$ENV_OUT"; then
|
||||||
|
echo "MASTER_ENDPOINT=http://master.argus.com:3000" >> "$ENV_OUT"
|
||||||
|
fi
|
||||||
|
|
||||||
|
REQ_VARS=(AGENT_ENV AGENT_USER AGENT_INSTANCE CPU_NODE_HOSTNAME)
|
||||||
|
missing=()
|
||||||
|
for v in "${REQ_VARS[@]}"; do
|
||||||
|
val=$(grep -E "^$v=" "$ENV_OUT" | head -1 | cut -d= -f2-)
|
||||||
|
if [[ -z "$val" ]]; then missing+=("$v"); fi
|
||||||
|
done
|
||||||
|
if [[ ${#missing[@]} -gt 0 ]]; then
|
||||||
|
err "以下变量必须在 compose/.env 中填写：${missing[*]}（已保留你现有的内容，不会被覆盖）"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
info "已生成 compose/.env；可执行 scripts_for_x86/install.sh 启动 ARM Client-CPU"
|
||||||
|
|
||||||
@ -0,0 +1,76 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
# 在 x86_64 主机上安装 ARM Client-CPU：
|
||||||
|
# 1) 确认/安装 binfmt + QEMU（通过 tonistiigi/binfmt）；
|
||||||
|
# 2) 调用通用的 scripts/install.sh 启动 ARM CPU node 容器。
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
ROOT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
|
||||||
|
|
||||||
|
info(){ echo -e "\033[34m[INSTALL-ARM-CLIENT-X86]\033[0m $*"; }
|
||||||
|
err(){ echo -e "\033[31m[ERROR-ARM-CLIENT-X86]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
|
||||||
|
|
||||||
|
ensure_binfmt_arm64() {
|
||||||
|
info "检查当前主机架构: $(uname -m)"
|
||||||
|
if [[ "$(uname -m)" != "x86_64" && "$(uname -m)" != "amd64" ]]; then
|
||||||
|
info "当前并非 x86_64（$(uname -m)），通常应直接在 ARM 服务器上使用 scripts/install.sh。继续执行但不强制安装 binfmt。"
|
||||||
|
return 0
|
||||||
|
fi
|
||||||
|
|
||||||
|
require docker
|
||||||
|
|
||||||
|
# 优先使用随安装包一起提供的 ubuntu-22.04-arm-test 镜像做自检
|
||||||
|
local TEST_IMG="ubuntu:22.04"
|
||||||
|
local TEST_TAR=""
|
||||||
|
if [[ -d "$ROOT_DIR/images" ]]; then
|
||||||
|
TEST_TAR=$(ls "$ROOT_DIR"/images/ubuntu-22.04-arm-test*.tar.gz 2>/dev/null | head -n1 || true)
|
||||||
|
fi
|
||||||
|
|
||||||
|
if [[ -n "$TEST_TAR" && ! $(docker image inspect "$TEST_IMG" >/dev/null 2>&1; echo $?) -eq 0 ]]; then
|
||||||
|
info "从安装包加载 ARM 测试基础镜像: $(basename "$TEST_TAR")"
|
||||||
|
tmp=$(mktemp)
|
||||||
|
gunzip -c "$TEST_TAR" > "$tmp"
|
||||||
|
docker load -i "$tmp" >/dev/null
|
||||||
|
rm -f "$tmp"
|
||||||
|
fi
|
||||||
|
|
||||||
|
info "验证是否已能运行 linux/arm64 容器..."
|
||||||
|
if docker run --rm --platform=linux/arm64 "$TEST_IMG" uname -m 2>/dev/null | grep -q 'aarch64'; then
|
||||||
|
info "检测到本机已支持 ARM64 容器运行 (uname -m = aarch64)"
|
||||||
|
return 0
|
||||||
|
fi
|
||||||
|
|
||||||
|
info "未检测到 ARM64 运行能力，尝试通过 tonistiigi/binfmt 安装 binfmt/QEMU ..."
|
||||||
|
local BINFMT_IMG="tonistiigi/binfmt:latest"
|
||||||
|
local BINFMT_TAR=""
|
||||||
|
if [[ -d "$ROOT_DIR/images" ]]; then
|
||||||
|
BINFMT_TAR=$(ls "$ROOT_DIR"/images/tonistiigi-binfmt*.tar.gz 2>/dev/null | head -n1 || true)
|
||||||
|
fi
|
||||||
|
if [[ -n "$BINFMT_TAR" && ! $(docker image inspect "$BINFMT_IMG" >/dev/null 2>&1; echo $?) -eq 0 ]]; then
|
||||||
|
info "从安装包加载 tonistiigi/binfmt 离线镜像: $(basename "$BINFMT_TAR")"
|
||||||
|
tmp_b=$(mktemp)
|
||||||
|
gunzip -c "$BINFMT_TAR" > "$tmp_b"
|
||||||
|
docker load -i "$tmp_b" >/dev/null
|
||||||
|
rm -f "$tmp_b"
|
||||||
|
fi
|
||||||
|
|
||||||
|
if ! docker run --privileged --rm "$BINFMT_IMG" --install all; then
|
||||||
|
err "tonistiigi/binfmt 安装失败，请检查 Docker 权限或确认离线镜像是否完整。"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
info "再次验证 ARM64 容器可运行状态..."
|
||||||
|
if ! docker run --rm --platform=linux/arm64 "$TEST_IMG" uname -m 2>/dev/null | grep -q 'aarch64'; then
|
||||||
|
err "安装 binfmt/QEMU 后仍无法运行 linux/arm64 容器，请手工排查 binfmt_misc 配置。"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
info "ARM64 容器运行能力检查通过。"
|
||||||
|
}
|
||||||
|
|
||||||
|
ensure_binfmt_arm64
|
||||||
|
|
||||||
|
exec "$SCRIPT_DIR/../scripts/install.sh" "$@"
|
||||||
|
|
||||||
@ -0,0 +1,6 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
exec "$SCRIPT_DIR/../scripts/uninstall.sh" "$@"
|
||||||
|
|
||||||
153
deployment_new/templates/server_arm/compose/docker-compose.yml
Normal file
153
deployment_new/templates/server_arm/compose/docker-compose.yml
Normal file
@ -0,0 +1,153 @@
|
|||||||
|
version: "3.8"
|
||||||
|
|
||||||
|
networks:
|
||||||
|
argus-sys-net:
|
||||||
|
external: true
|
||||||
|
|
||||||
|
services:
|
||||||
|
master:
|
||||||
|
image: ${MASTER_IMAGE_TAG:-argus-master-arm64:${PKG_VERSION}}
|
||||||
|
platform: linux/arm64
|
||||||
|
container_name: argus-master-sys
|
||||||
|
environment:
|
||||||
|
- OFFLINE_THRESHOLD_SECONDS=180
|
||||||
|
- ONLINE_THRESHOLD_SECONDS=120
|
||||||
|
- SCHEDULER_INTERVAL_SECONDS=30
|
||||||
|
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
|
||||||
|
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
|
||||||
|
ports:
|
||||||
|
- "${MASTER_PORT:-32300}:3000"
|
||||||
|
volumes:
|
||||||
|
- ../private/argus/master:/private/argus/master
|
||||||
|
- ../private/argus/metric/prometheus:/private/argus/metric/prometheus
|
||||||
|
- ../private/argus/etc:/private/argus/etc
|
||||||
|
networks:
|
||||||
|
argus-sys-net:
|
||||||
|
aliases:
|
||||||
|
- master.argus.com
|
||||||
|
restart: unless-stopped
|
||||||
|
|
||||||
|
prometheus:
|
||||||
|
image: ${PROM_IMAGE_TAG:-argus-metric-prometheus-arm64:${PKG_VERSION}}
|
||||||
|
platform: linux/arm64
|
||||||
|
container_name: argus-prometheus
|
||||||
|
restart: unless-stopped
|
||||||
|
environment:
|
||||||
|
- TZ=Asia/Shanghai
|
||||||
|
- PROMETHEUS_BASE_PATH=/private/argus/metric/prometheus
|
||||||
|
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
|
||||||
|
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
|
||||||
|
ports:
|
||||||
|
- "${PROMETHEUS_PORT:-9090}:9090"
|
||||||
|
volumes:
|
||||||
|
- ../private/argus/metric/prometheus:/private/argus/metric/prometheus
|
||||||
|
- ../private/argus/etc:/private/argus/etc
|
||||||
|
networks:
|
||||||
|
argus-sys-net:
|
||||||
|
aliases:
|
||||||
|
- prom.metric.argus.com
|
||||||
|
|
||||||
|
prometheus-targets-updater:
|
||||||
|
image: ${PROM_UPDATER_IMAGE_TAG:-argus-metric-prometheus-targets-updater-arm64:${PKG_VERSION}}
|
||||||
|
platform: linux/arm64
|
||||||
|
container_name: argus-prometheus-targets-updater
|
||||||
|
restart: unless-stopped
|
||||||
|
environment:
|
||||||
|
- TZ=Asia/Shanghai
|
||||||
|
volumes:
|
||||||
|
- ../private/argus/metric/prometheus:/private/argus/metric/prometheus
|
||||||
|
networks:
|
||||||
|
argus-sys-net:
|
||||||
|
aliases:
|
||||||
|
- prom-updater.metric.argus.com
|
||||||
|
depends_on:
|
||||||
|
- master
|
||||||
|
- prometheus
|
||||||
|
|
||||||
|
grafana:
|
||||||
|
image: ${GRAFANA_IMAGE_TAG:-argus-metric-grafana-arm64:${PKG_VERSION}}
|
||||||
|
platform: linux/arm64
|
||||||
|
container_name: argus-grafana
|
||||||
|
restart: unless-stopped
|
||||||
|
environment:
|
||||||
|
- TZ=Asia/Shanghai
|
||||||
|
- GRAFANA_BASE_PATH=/private/argus/metric/grafana
|
||||||
|
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
|
||||||
|
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
|
||||||
|
- GF_SERVER_HTTP_PORT=3000
|
||||||
|
- GF_LOG_LEVEL=warn
|
||||||
|
- GF_LOG_MODE=console
|
||||||
|
- GF_PATHS_PROVISIONING=/private/argus/metric/grafana/provisioning
|
||||||
|
- GF_AUTH_ANONYMOUS_ENABLED=true
|
||||||
|
- GF_AUTH_ANONYMOUS_ORG_ROLE=Viewer
|
||||||
|
ports:
|
||||||
|
- "${GRAFANA_PORT:-3000}:3000"
|
||||||
|
volumes:
|
||||||
|
- ../private/argus/metric/grafana:/private/argus/metric/grafana
|
||||||
|
- ../private/argus/etc:/private/argus/etc
|
||||||
|
depends_on: [prometheus]
|
||||||
|
networks:
|
||||||
|
argus-sys-net:
|
||||||
|
aliases:
|
||||||
|
- grafana.metric.argus.com
|
||||||
|
|
||||||
|
alertmanager:
|
||||||
|
image: ${ALERT_IMAGE_TAG:-argus-alertmanager-arm64:${PKG_VERSION}}
|
||||||
|
platform: linux/arm64
|
||||||
|
container_name: argus-alertmanager
|
||||||
|
environment:
|
||||||
|
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
|
||||||
|
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
|
||||||
|
volumes:
|
||||||
|
- ../private/argus/etc:/private/argus/etc
|
||||||
|
- ../private/argus/alert/alertmanager:/private/argus/alert/alertmanager
|
||||||
|
networks:
|
||||||
|
argus-sys-net:
|
||||||
|
aliases:
|
||||||
|
- alertmanager.alert.argus.com
|
||||||
|
ports:
|
||||||
|
- "${ALERTMANAGER_PORT:-9093}:9093"
|
||||||
|
restart: unless-stopped
|
||||||
|
|
||||||
|
web-frontend:
|
||||||
|
image: ${FRONT_IMAGE_TAG:-argus-web-frontend-arm64:${PKG_VERSION}}
|
||||||
|
platform: linux/arm64
|
||||||
|
container_name: argus-web-frontend
|
||||||
|
environment:
|
||||||
|
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
|
||||||
|
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
|
||||||
|
- EXTERNAL_MASTER_PORT=${WEB_PROXY_PORT_8085:-8085}
|
||||||
|
- EXTERNAL_ALERTMANAGER_PORT=${WEB_PROXY_PORT_8084:-8084}
|
||||||
|
- EXTERNAL_GRAFANA_PORT=${WEB_PROXY_PORT_8081:-8081}
|
||||||
|
- EXTERNAL_PROMETHEUS_PORT=${WEB_PROXY_PORT_8082:-8082}
|
||||||
|
volumes:
|
||||||
|
- ../private/argus/etc:/private/argus/etc
|
||||||
|
networks:
|
||||||
|
argus-sys-net:
|
||||||
|
aliases:
|
||||||
|
- web.argus.com
|
||||||
|
restart: unless-stopped
|
||||||
|
|
||||||
|
web-proxy:
|
||||||
|
image: ${WEB_PROXY_IMAGE_TAG:-argus-web-proxy-arm64:${PKG_VERSION}}
|
||||||
|
platform: linux/arm64
|
||||||
|
container_name: argus-web-proxy
|
||||||
|
depends_on: [master, grafana, prometheus, alertmanager]
|
||||||
|
environment:
|
||||||
|
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
|
||||||
|
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
|
||||||
|
volumes:
|
||||||
|
- ../private/argus/etc:/private/argus/etc
|
||||||
|
networks:
|
||||||
|
argus-sys-net:
|
||||||
|
aliases:
|
||||||
|
- proxy.argus.com
|
||||||
|
ports:
|
||||||
|
- "${WEB_PROXY_PORT_8080:-8080}:8080"
|
||||||
|
- "${WEB_PROXY_PORT_8081:-8081}:8081"
|
||||||
|
- "${WEB_PROXY_PORT_8082:-8082}:8082"
|
||||||
|
- "${WEB_PROXY_PORT_8083:-8083}:8083"
|
||||||
|
- "${WEB_PROXY_PORT_8084:-8084}:8084"
|
||||||
|
- "${WEB_PROXY_PORT_8085:-8085}:8085"
|
||||||
|
restart: unless-stopped
|
||||||
|
|
||||||
@ -0,0 +1,158 @@
|
|||||||
|
# ARM Server 安装指南（server_arm）
|
||||||
|
|
||||||
|
本包用于在 ARM64 服务器上部署 Argus 的最小 server 端组件集：
|
||||||
|
|
||||||
|
- master
|
||||||
|
- Prometheus
|
||||||
|
- Prometheus targets-updater sidecar
|
||||||
|
- Grafana
|
||||||
|
- Alertmanager
|
||||||
|
- Web 前端 + Web Proxy
|
||||||
|
|
||||||
|
> 注意：本 ARM 版本 **不包含 Elasticsearch / Kibana / FTP / BIND9**，仅提供指标与告警能力。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 1. 前置条件
|
||||||
|
|
||||||
|
- 目标机器为 ARM64（例如：aarch64 服务器）；
|
||||||
|
- 已安装 Docker 和 docker compose（v2，支持 `docker compose` 命令）；
|
||||||
|
- 已准备好 overlay 网络 `argus-sys-net`（如不需要也可将 compose 改为 `bridge` 网络）。
|
||||||
|
|
||||||
|
创建 overlay 网络示例：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker network create --driver overlay argus-sys-net || true
|
||||||
|
```
|
||||||
|
|
||||||
|
如未使用 Swarm，也可以在 compose 中将 `networks: argus-sys-net` 改成本地 `bridge` 网络。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 2. 解压和加载镜像
|
||||||
|
|
||||||
|
假设你已经将 `server_arm_YYYYMMDD.tar.gz` 拷贝到目标 ARM 服务器：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
tar -xzf server_arm_YYYYMMDD.tar.gz
|
||||||
|
cd server_arm/YYYYMMDD
|
||||||
|
```
|
||||||
|
|
||||||
|
加载镜像：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
for f in images/*.tar.gz; do
|
||||||
|
gunzip -c "$f" | docker load
|
||||||
|
done
|
||||||
|
```
|
||||||
|
|
||||||
|
加载后可以用：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker images | grep 'argus-.*arm64'
|
||||||
|
```
|
||||||
|
|
||||||
|
确认 master / prometheus / grafana / alertmanager / web 镜像已就绪。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 3. 配置 .env
|
||||||
|
|
||||||
|
在 `compose/` 目录下有自动生成的 `.env.example`：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd compose
|
||||||
|
cp .env.example .env
|
||||||
|
```
|
||||||
|
|
||||||
|
`.env` 中主要字段：
|
||||||
|
|
||||||
|
- `PKG_VERSION`：包版本（不建议修改）。
|
||||||
|
- 镜像 tag（默认使用构建时的 `*-arm64:${PKG_VERSION}`）：
|
||||||
|
- `MASTER_IMAGE_TAG`
|
||||||
|
- `PROM_IMAGE_TAG`
|
||||||
|
- `PROM_UPDATER_IMAGE_TAG`
|
||||||
|
- `GRAFANA_IMAGE_TAG`
|
||||||
|
- `ALERT_IMAGE_TAG`
|
||||||
|
- `FRONT_IMAGE_TAG`
|
||||||
|
- `WEB_PROXY_IMAGE_TAG`
|
||||||
|
- 端口：
|
||||||
|
- `MASTER_PORT`（默认 32300）
|
||||||
|
- `PROMETHEUS_PORT`（默认 9090）
|
||||||
|
- `GRAFANA_PORT`（默认 3000）
|
||||||
|
- `ALERTMANAGER_PORT`（默认 9093）
|
||||||
|
- `WEB_PROXY_PORT_8080` ~ `WEB_PROXY_PORT_8085`
|
||||||
|
- 其他：
|
||||||
|
- `ARGUS_BUILD_UID` / `ARGUS_BUILD_GID`（用于挂载目录的权限对齐）。
|
||||||
|
|
||||||
|
根据实际环境按需调整端口和 UID/GID。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 4. 准备挂载目录
|
||||||
|
|
||||||
|
在 package 根目录（与 `compose/` 同级）下，已预创建所需的 `private/argus` 目录骨架：
|
||||||
|
|
||||||
|
- `private/argus/etc`
|
||||||
|
- `private/argus/master`
|
||||||
|
- `private/argus/metric/prometheus`（含 `data` / `rules` / `targets`）
|
||||||
|
- `private/argus/metric/grafana`（含 `data` / `logs` / `plugins` / `provisioning` 等）
|
||||||
|
|
||||||
|
可根据需要调整访问权限，例如：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd ..
|
||||||
|
sudo chown -R $UID:$GID private/argus
|
||||||
|
```
|
||||||
|
|
||||||
|
确保与 `.env` 中的 `ARGUS_BUILD_UID/GID` 一致。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 5. 启动服务
|
||||||
|
|
||||||
|
在 `compose/` 目录执行：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker compose --env-file .env up -d
|
||||||
|
```
|
||||||
|
|
||||||
|
检查服务状态：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker compose ps
|
||||||
|
```
|
||||||
|
|
||||||
|
预期看到：
|
||||||
|
|
||||||
|
- `argus-master-sys`
|
||||||
|
- `argus-prometheus`
|
||||||
|
- `argus-prometheus-targets-updater`
|
||||||
|
- `argus-grafana`
|
||||||
|
- `argus-alertmanager`
|
||||||
|
- `argus-web-frontend`
|
||||||
|
- `argus-web-proxy`
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 6. 验证
|
||||||
|
|
||||||
|
1. Master：
|
||||||
|
- `curl http://localhost:${MASTER_PORT}/readyz`
|
||||||
|
2. Prometheus：
|
||||||
|
- 浏览器访问：`http://<host>:${PROMETHEUS_PORT}`
|
||||||
|
3. Grafana：
|
||||||
|
- 浏览器访问：`http://<host>:${GRAFANA_PORT}`
|
||||||
|
4. Web 门户：
|
||||||
|
- 浏览器访问：`http://<host>:${WEB_PROXY_PORT_8080}`
|
||||||
|
|
||||||
|
确认这些页面能够正常打开，并且在没有任何节点注册时，Prometheus 中 `job="node"` 可为空，但基础 UI 应可访问。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 7. 注意事项
|
||||||
|
|
||||||
|
- 本 ARM server 包仅包含 metrics + alert 相关组件，不提供日志链路（ES/Kibana），也不包含 DNS/FTP 相关服务；
|
||||||
|
- 若后续需要扩展 ES/Kibana，可在新的 spec 中单独设计 ARM 日志栈；
|
||||||
|
- 对于多节点/Swarm 部署，请结合 `src/sys/arm_swarm_tests` 中的 compose 与脚本进行扩展。
|
||||||
|
|
||||||
111
deployment_new/templates/server_arm/scripts/config.sh
Normal file
111
deployment_new/templates/server_arm/scripts/config.sh
Normal file
@ -0,0 +1,111 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
PKG_ROOT="$ROOT_DIR"
|
||||||
|
ENV_EX="$PKG_ROOT/compose/.env.example"
|
||||||
|
ENV_OUT="$PKG_ROOT/compose/.env"
|
||||||
|
|
||||||
|
info(){ echo -e "\033[34m[CONFIG]\033[0m $*"; }
|
||||||
|
err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
|
||||||
|
|
||||||
|
# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
|
||||||
|
require_compose(){
|
||||||
|
if docker compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
|
||||||
|
}
|
||||||
|
|
||||||
|
require docker awk sed
|
||||||
|
require_compose
|
||||||
|
|
||||||
|
[[ -f "$ENV_EX" ]] || { err "缺少模板文件: $ENV_EX"; exit 1; }
|
||||||
|
|
||||||
|
# 磁盘空间检查（简化版，默认 >= 5GB）
|
||||||
|
check_disk(){ local p="$1"; local need="${2:-5120}"; local free;
|
||||||
|
free=$(df -Pm "$p" 2>/dev/null | awk 'NR==2{print $4+0}')
|
||||||
|
if [[ -z "$free" || "$free" -lt "$need" ]]; then
|
||||||
|
err "磁盘空间不足: $p 剩余 ${free:-0}MB (<${need}MB)，请清理后再继续"
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
check_disk "$PKG_ROOT" 5120 || true
|
||||||
|
check_disk "/var/lib/docker" 5120 || true
|
||||||
|
|
||||||
|
cp "$ENV_EX" "$ENV_OUT"
|
||||||
|
|
||||||
|
# 读取/生成 SWARM_MANAGER_ADDR（ARM 下同样引导 Swarm + cluster-info）
|
||||||
|
SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}
|
||||||
|
if [[ -z "${SWARM_MANAGER_ADDR}" ]]; then
|
||||||
|
read -rp "请输入本机管理地址 SWARM_MANAGER_ADDR: " SWARM_MANAGER_ADDR
|
||||||
|
fi
|
||||||
|
info "SWARM_MANAGER_ADDR=$SWARM_MANAGER_ADDR"
|
||||||
|
|
||||||
|
# 校验 IP 属于本机网卡
|
||||||
|
if ! ip -o addr | awk '{print $4}' | cut -d'/' -f1 | grep -qx "$SWARM_MANAGER_ADDR"; then
|
||||||
|
err "SWARM_MANAGER_ADDR 非本机地址: $SWARM_MANAGER_ADDR"; exit 1; fi
|
||||||
|
|
||||||
|
info "开始分配服务端口（起始=20000，避免系统占用与相互冲突）"
|
||||||
|
is_port_used(){ local p="$1"; ss -tulnH 2>/dev/null | awk '{print $5}' | sed 's/.*://g' | grep -qx "$p"; }
|
||||||
|
declare -A PRESENT=() CHOSEN=() USED=()
|
||||||
|
START_PORT="${START_PORT:-20000}"; cur=$START_PORT
|
||||||
|
ORDER=(MASTER_PORT PROMETHEUS_PORT GRAFANA_PORT ALERTMANAGER_PORT \
|
||||||
|
WEB_PROXY_PORT_8080 WEB_PROXY_PORT_8081 WEB_PROXY_PORT_8082 \
|
||||||
|
WEB_PROXY_PORT_8083 WEB_PROXY_PORT_8084 WEB_PROXY_PORT_8085)
|
||||||
|
|
||||||
|
# 标记 .env.example 中实际存在的键
|
||||||
|
for key in "${ORDER[@]}"; do
|
||||||
|
if grep -q "^${key}=" "$ENV_EX"; then PRESENT[$key]=1; fi
|
||||||
|
done
|
||||||
|
|
||||||
|
next_free(){ local p="$1"; while :; do if [[ -n "${USED[$p]:-}" ]] || is_port_used "$p"; then p=$((p+1)); else echo "$p"; return; fi; done; }
|
||||||
|
|
||||||
|
for key in "${ORDER[@]}"; do
|
||||||
|
[[ -z "${PRESENT[$key]:-}" ]] && continue
|
||||||
|
p=$(next_free "$cur"); CHOSEN[$key]="$p"; USED[$p]=1; cur=$((p+1))
|
||||||
|
done
|
||||||
|
|
||||||
|
info "端口分配结果：MASTER=${CHOSEN[MASTER_PORT]:-} PROM=${CHOSEN[PROMETHEUS_PORT]:-} GRAFANA=${CHOSEN[GRAFANA_PORT]:-} ALERT=${CHOSEN[ALERTMANAGER_PORT]:-} WEB_PROXY(8080..8085)=${CHOSEN[WEB_PROXY_PORT_8080]:-}/${CHOSEN[WEB_PROXY_PORT_8081]:-}/${CHOSEN[WEB_PROXY_PORT_8082]:-}/${CHOSEN[WEB_PROXY_PORT_8083]:-}/${CHOSEN[WEB_PROXY_PORT_8084]:-}/${CHOSEN[WEB_PROXY_PORT_8085]:-}"
|
||||||
|
|
||||||
|
# 覆盖端口（按唯一化结果写回）
|
||||||
|
for key in "${ORDER[@]}"; do
|
||||||
|
val="${CHOSEN[$key]:-}"
|
||||||
|
[[ -z "$val" ]] && continue
|
||||||
|
sed -i -E "s#^$key=.*#$key=${val}#" "$ENV_OUT"
|
||||||
|
done
|
||||||
|
|
||||||
|
# 覆盖/补充 Overlay 名称
|
||||||
|
grep -q '^ARGUS_OVERLAY_NET=' "$ENV_OUT" || echo 'ARGUS_OVERLAY_NET=argus-sys-net' >> "$ENV_OUT"
|
||||||
|
|
||||||
|
# 覆盖/补充构建账户 UID/GID，避免权限问题
|
||||||
|
RUID=$(id -u)
|
||||||
|
RGID=$(id -g)
|
||||||
|
|
||||||
|
if grep -q '^ARGUS_BUILD_UID=' "$ENV_OUT"; then
|
||||||
|
sed -i -E "s#^ARGUS_BUILD_UID=.*#ARGUS_BUILD_UID=${RUID}#" "$ENV_OUT"
|
||||||
|
else
|
||||||
|
echo "ARGUS_BUILD_UID=${RUID}" >> "$ENV_OUT"
|
||||||
|
fi
|
||||||
|
|
||||||
|
if grep -q '^ARGUS_BUILD_GID=' "$ENV_OUT"; then
|
||||||
|
sed -i -E "s#^ARGUS_BUILD_GID=.*#ARGUS_BUILD_GID=${RGID}#" "$ENV_OUT"
|
||||||
|
else
|
||||||
|
echo "ARGUS_BUILD_GID=${RGID}" >> "$ENV_OUT"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# 更新 cluster-info.env 的 SWARM_MANAGER_ADDR（ARM 版本也保留该机制）
|
||||||
|
CI="$PKG_ROOT/cluster-info.env"
|
||||||
|
if [[ -f "$CI" ]]; then
|
||||||
|
if grep -q '^SWARM_MANAGER_ADDR=' "$CI"; then
|
||||||
|
sed -i -E "s#^SWARM_MANAGER_ADDR=.*#SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}#" "$CI"
|
||||||
|
else
|
||||||
|
echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}" >> "$CI"
|
||||||
|
fi
|
||||||
|
else
|
||||||
|
echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}" > "$CI"
|
||||||
|
fi
|
||||||
|
|
||||||
|
info "已生成 compose/.env 并更新 cluster-info.env 的 SWARM_MANAGER_ADDR。"
|
||||||
|
info "下一步可执行: scripts/install.sh"
|
||||||
91
deployment_new/templates/server_arm/scripts/diagnose.sh
Normal file
91
deployment_new/templates/server_arm/scripts/diagnose.sh
Normal file
@ -0,0 +1,91 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
|
||||||
|
|
||||||
|
ENV_FILE="$ROOT/compose/.env"; [[ -f "$ENV_FILE" ]] && set -a && source "$ENV_FILE" && set +a
|
||||||
|
|
||||||
|
ts="$(date -u +%Y%m%d-%H%M%SZ)"
|
||||||
|
LOG_DIR="$ROOT/logs"; mkdir -p "$LOG_DIR" || true
|
||||||
|
if ! ( : > "$LOG_DIR/.w" 2>/dev/null ); then LOG_DIR="/tmp/argus-logs"; mkdir -p "$LOG_DIR" || true; fi
|
||||||
|
|
||||||
|
PROJECT="${COMPOSE_PROJECT_NAME:-argus-server-arm}"
|
||||||
|
DETAILS="$LOG_DIR/diagnose_arm_server_details_${ts}.log"
|
||||||
|
ERRORS="$LOG_DIR/diagnose_arm_server_error_${ts}.log"
|
||||||
|
: > "$DETAILS"; : > "$ERRORS"
|
||||||
|
|
||||||
|
logd() { echo "$(date '+%F %T') $*" >> "$DETAILS"; }
|
||||||
|
append_err() { echo "$*" >> "$ERRORS"; }
|
||||||
|
http_code() { curl -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
|
||||||
|
http_body_head() { curl -s --max-time 3 "$1" 2>/dev/null | sed -n '1,5p' || true; }
|
||||||
|
header_val() { curl -s -D - -o /dev/null "$@" | awk -F': ' 'BEGIN{IGNORECASE=1}$1=="Access-Control-Allow-Origin"{gsub("\r","",$2);print $2}'; }
|
||||||
|
|
||||||
|
section() { local name="$1"; logd "===== [$name] ====="; }
|
||||||
|
|
||||||
|
svc() {
|
||||||
|
local svc_name="$1"; local cname="$2"
|
||||||
|
section "$svc_name ($cname)"
|
||||||
|
logd "docker ps:"; docker ps -a --format '{{.Names}}\t{{.Status}}\t{{.Image}}' | awk -v n="$cname" '$1==n' >> "$DETAILS" || true
|
||||||
|
logd "docker inspect:"; docker inspect -f '{{.State.Status}} rc={{.RestartCount}} started={{.State.StartedAt}}' "$cname" >> "$DETAILS" 2>&1 || true
|
||||||
|
logd "last 200 container logs:"; docker logs --tail 200 "$cname" >> "$DETAILS" 2>&1 || true
|
||||||
|
docker logs --tail 200 "$cname" 2>&1 | \
|
||||||
|
grep -Ei '\b(error|failed|fail|exception|panic|fatal|critical|unhealthy|permission denied|forbidden|refused|traceback|错误|失败)\b' | \
|
||||||
|
sed "s/^/[${svc_name}][container] /" >> "$ERRORS" || true
|
||||||
|
if docker exec "$cname" sh -lc 'command -v supervisorctl >/dev/null 2>&1' >/dev/null 2>&1; then
|
||||||
|
logd "supervisorctl status:"; docker exec "$cname" sh -lc 'supervisorctl status' >> "$DETAILS" 2>&1 || true
|
||||||
|
local files; files=$(docker exec "$cname" sh -lc 'ls /var/log/supervisor/*.log 2>/dev/null' || true)
|
||||||
|
for f in $files; do
|
||||||
|
logd "tail -n 80 $f:"; docker exec "$cname" sh -lc "tail -n 80 $f 2>/dev/null || true" >> "$DETAILS" 2>&1 || true
|
||||||
|
docker exec "$cname" sh -lc "tail -n 200 $f 2>/dev/null" 2>/dev/null | \
|
||||||
|
grep -Ei '\b(error|failed|fail|exception|panic|fatal|critical|unhealthy|permission denied|forbidden|refused|traceback|错误|失败)\b' | \
|
||||||
|
sed "s/^/[${svc_name}][supervisor:$(basename "$f")] /" >> "$ERRORS" || true
|
||||||
|
done
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
# 关键服务
|
||||||
|
svc master argus-master-sys
|
||||||
|
svc prometheus argus-prometheus
|
||||||
|
svc prom-updater argus-prometheus-targets-updater
|
||||||
|
svc grafana argus-grafana
|
||||||
|
svc alertmanager argus-alertmanager
|
||||||
|
svc web-frontend argus-web-frontend
|
||||||
|
svc web-proxy argus-web-proxy
|
||||||
|
|
||||||
|
section HTTP
|
||||||
|
logd "Master: $(http_code \"http://localhost:${MASTER_PORT:-32300}/readyz\")"
|
||||||
|
logd "Prometheus: $(http_code \"http://localhost:${PROMETHEUS_PORT:-9090}/-/ready\")"
|
||||||
|
logd "Grafana: $(http_code \"http://localhost:${GRAFANA_PORT:-3000}/api/health\")"; http_body_head "http://localhost:${GRAFANA_PORT:-3000}/api/health" >> "$DETAILS" 2>&1 || true
|
||||||
|
logd "Alertmanager: $(http_code \"http://localhost:${ALERTMANAGER_PORT:-9093}/api/v2/status\")"
|
||||||
|
cors8084=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8084:-8084}/api/v2/status" || true)
|
||||||
|
cors8085=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8085:-8085}/api/v1/master/nodes" || true)
|
||||||
|
logd "Web-Proxy 8080: $(http_code \"http://localhost:${WEB_PROXY_PORT_8080:-8080}/\")"
|
||||||
|
logd "Web-Proxy 8083: $(http_code \"http://localhost:${WEB_PROXY_PORT_8083:-8083}/\")"
|
||||||
|
logd "Web-Proxy 8084 CORS: ${cors8084}"
|
||||||
|
logd "Web-Proxy 8085 CORS: ${cors8085}"
|
||||||
|
|
||||||
|
section SYSTEM
|
||||||
|
logd "uname -a:"; uname -a >> "$DETAILS"
|
||||||
|
logd "docker version:"; docker version --format '{{.Server.Version}}' >> "$DETAILS" 2>&1 || true
|
||||||
|
logd "compose ps (project=$PROJECT):"; (cd "$ROOT/compose" && docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f docker-compose.yml ps) >> "$DETAILS" 2>&1 || true
|
||||||
|
|
||||||
|
section SUMMARY
|
||||||
|
[[ $(http_code "http://localhost:${MASTER_PORT:-32300}/readyz") != 200 ]] && echo "[master][http] /readyz not 200" >> "$ERRORS"
|
||||||
|
[[ $(http_code "http://localhost:${PROMETHEUS_PORT:-9090}/-/ready") != 200 ]] && echo "[prometheus][http] /-/ready not 200" >> "$ERRORS"
|
||||||
|
gfcode=$(http_code "http://localhost:${GRAFANA_PORT:-3000}/api/health"); [[ "$gfcode" != 200 ]] && echo "[grafana][http] /api/health=$gfcode" >> "$ERRORS"
|
||||||
|
[[ $(http_code "http://localhost:${ALERTMANAGER_PORT:-9093}/api/v2/status") != 200 ]] && echo "[alertmanager][http] /api/v2/status not 200" >> "$ERRORS"
|
||||||
|
[[ -z "$cors8084" ]] && echo "[web-proxy][cors] 8084 missing Access-Control-Allow-Origin" >> "$ERRORS"
|
||||||
|
[[ -z "$cors8085" ]] && echo "[web-proxy][cors] 8085 missing Access-Control-Allow-Origin" >> "$ERRORS"
|
||||||
|
sort -u -o "$ERRORS" "$ERRORS"
|
||||||
|
|
||||||
|
echo "Diagnostic details -> $DETAILS"
|
||||||
|
echo "Detected errors -> $ERRORS"
|
||||||
|
|
||||||
|
if [[ "$LOG_DIR" == "$ROOT/logs" ]]; then
|
||||||
|
ln -sfn "$(basename "$DETAILS")" "$ROOT/logs/diagnose_arm_server_details.log" 2>/dev/null || cp "$DETAILS" "$ROOT/logs/diagnose_arm_server_details.log" 2>/dev/null || true
|
||||||
|
ln -sfn "$(basename "$ERRORS")" "$ROOT/logs/diagnose_arm_server_error.log" 2>/dev/null || cp "$ERRORS" "$ROOT/logs/diagnose_arm_server_error.log" 2>/dev/null || true
|
||||||
|
fi
|
||||||
|
|
||||||
|
exit 0
|
||||||
|
|
||||||
130
deployment_new/templates/server_arm/scripts/install.sh
Normal file
130
deployment_new/templates/server_arm/scripts/install.sh
Normal file
@ -0,0 +1,130 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
PKG_ROOT="$ROOT_DIR"
|
||||||
|
ENV_FILE="$PKG_ROOT/compose/.env"
|
||||||
|
COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
|
||||||
|
|
||||||
|
info(){ echo -e "\033[34m[INSTALL]\033[0m $*"; }
|
||||||
|
err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
|
||||||
|
|
||||||
|
require_compose(){
|
||||||
|
if docker compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
|
||||||
|
}
|
||||||
|
|
||||||
|
require docker curl jq awk sed tar gzip
|
||||||
|
require_compose
|
||||||
|
|
||||||
|
[[ -f "$ENV_FILE" ]] || { err "缺少 compose/.env，请先运行 scripts/config.sh"; exit 1; }
|
||||||
|
info "使用环境文件: $ENV_FILE"
|
||||||
|
set -a; source "$ENV_FILE"; set +a
|
||||||
|
|
||||||
|
# 兼容：若 .env 未包含 SWARM_MANAGER_ADDR，则从已存在的 cluster-info.env 读取以避免写空
|
||||||
|
SMADDR="${SWARM_MANAGER_ADDR:-}"
|
||||||
|
CI_FILE="$PKG_ROOT/cluster-info.env"
|
||||||
|
if [[ -z "$SMADDR" && -f "$CI_FILE" ]]; then
|
||||||
|
SMADDR=$(sed -n 's/^SWARM_MANAGER_ADDR=\(.*\)$/\1/p' "$CI_FILE" | head -n1)
|
||||||
|
fi
|
||||||
|
SWARM_MANAGER_ADDR="$SMADDR"
|
||||||
|
|
||||||
|
# Swarm init & overlay（ARM 版也按生产环境方式启用 Swarm）
|
||||||
|
NET_NAME="${ARGUS_OVERLAY_NET:-argus-sys-net}"
|
||||||
|
if ! docker info 2>/dev/null | grep -q "Swarm: active"; then
|
||||||
|
[[ -n "${SWARM_MANAGER_ADDR:-}" ]] || { err "SWARM_MANAGER_ADDR 未设置，请在 scripts/config.sh 中配置"; exit 1; }
|
||||||
|
info "初始化 Swarm (--advertise-addr $SWARM_MANAGER_ADDR)"
|
||||||
|
docker swarm init --advertise-addr "$SWARM_MANAGER_ADDR" >/dev/null 2>&1 || true
|
||||||
|
else
|
||||||
|
info "Swarm 已激活"
|
||||||
|
fi
|
||||||
|
|
||||||
|
if ! docker network inspect "$NET_NAME" >/dev/null 2>&1; then
|
||||||
|
info "创建 overlay 网络: $NET_NAME"
|
||||||
|
docker network create -d overlay --attachable "$NET_NAME" >/dev/null
|
||||||
|
else
|
||||||
|
info "overlay 网络已存在: $NET_NAME"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# 将 Swarm join token 写入 cluster-info.env，供 ARM client 使用
|
||||||
|
TOKEN_WORKER=$(docker swarm join-token -q worker 2>/dev/null || echo "")
|
||||||
|
TOKEN_MANAGER=$(docker swarm join-token -q manager 2>/dev/null || echo "")
|
||||||
|
CI_OUT="$PKG_ROOT/cluster-info.env"
|
||||||
|
info "写入 cluster-info.env (manager/token)"
|
||||||
|
{
|
||||||
|
echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}"
|
||||||
|
echo "SWARM_JOIN_TOKEN_WORKER=${TOKEN_WORKER:-}"
|
||||||
|
echo "SWARM_JOIN_TOKEN_MANAGER=${TOKEN_MANAGER:-}"
|
||||||
|
} > "$CI_OUT"
|
||||||
|
|
||||||
|
# 导入镜像
|
||||||
|
IMAGES_DIR="$PKG_ROOT/images"
|
||||||
|
shopt -s nullglob
|
||||||
|
tars=("$IMAGES_DIR"/*.tar.gz)
|
||||||
|
if [[ ${#tars[@]} -eq 0 ]]; then err "images 目录为空，缺少镜像 tar.gz"; exit 1; fi
|
||||||
|
total=${#tars[@]}; idx=0
|
||||||
|
for tgz in "${tars[@]}"; do
|
||||||
|
idx=$((idx+1))
|
||||||
|
info "导入镜像 ($idx/$total): $(basename "$tgz")"
|
||||||
|
tmp=$(mktemp); gunzip -c "$tgz" > "$tmp"; docker load -i "$tmp" >/dev/null; rm -f "$tmp"
|
||||||
|
done
|
||||||
|
shopt -u nullglob
|
||||||
|
|
||||||
|
# 启动服务
|
||||||
|
PROJECT="${COMPOSE_PROJECT_NAME:-argus-server-arm}"
|
||||||
|
info "启动服务栈 (docker compose -p $PROJECT up -d)"
|
||||||
|
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" up -d
|
||||||
|
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps
|
||||||
|
|
||||||
|
# 简单就绪检查（best-effort，不阻塞安装）
|
||||||
|
code(){ curl -4 -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
|
||||||
|
gf_ok(){ local body; body=$(curl -s "http://127.0.0.1:${GRAFANA_PORT:-3000}/api/health" || true); echo "$body" | grep -q '"database"\s*:\s*"ok"'; }
|
||||||
|
|
||||||
|
RETRIES=${RETRIES:-60}; SLEEP=${SLEEP:-5}; ok=0
|
||||||
|
info "等待基础服务就绪 (<= $((RETRIES*SLEEP))s)"
|
||||||
|
for i in $(seq 1 "$RETRIES"); do
|
||||||
|
e1=$(code "http://127.0.0.1:${MASTER_PORT:-32300}/readyz")
|
||||||
|
e2=$(code "http://127.0.0.1:${PROMETHEUS_PORT:-9090}/-/ready")
|
||||||
|
e3=$(code "http://127.0.0.1:${ALERTMANAGER_PORT:-9093}/api/v2/status")
|
||||||
|
e4=000; gf_ok && e4=200
|
||||||
|
info "[ready] t=$((i*SLEEP))s master=$e1 prom=$e2 graf=$e4 alert=$e3"
|
||||||
|
[[ "$e1" == 200 ]] && ok=$((ok+1))
|
||||||
|
[[ "$e2" == 200 ]] && ok=$((ok+1))
|
||||||
|
[[ "$e3" == 200 ]] && ok=$((ok+1))
|
||||||
|
[[ "$e4" == 200 ]] && ok=$((ok+1))
|
||||||
|
if [[ $ok -ge 4 ]]; then break; fi; ok=0; sleep "$SLEEP"
|
||||||
|
done
|
||||||
|
[[ $ok -ge 4 ]] || err "部分服务未就绪（可稍后执行 scripts/selfcheck.sh 进行复查）"
|
||||||
|
|
||||||
|
# 安装报告（ARM 精简版）
|
||||||
|
ts=$(date +%Y%m%d-%H%M%S)
|
||||||
|
RPT="$PKG_ROOT/安装报告_ARM_${ts}.md"
|
||||||
|
{
|
||||||
|
echo "# Argus ARM Server 安装报告 (${ts})"
|
||||||
|
echo
|
||||||
|
echo "## 端口映射"
|
||||||
|
echo "- MASTER_PORT=${MASTER_PORT}"
|
||||||
|
echo "- PROMETHEUS_PORT=${PROMETHEUS_PORT}"
|
||||||
|
echo "- GRAFANA_PORT=${GRAFANA_PORT}"
|
||||||
|
echo "- ALERTMANAGER_PORT=${ALERTMANAGER_PORT}"
|
||||||
|
echo "- WEB_PROXY_PORT_8080=${WEB_PROXY_PORT_8080} ... 8085=${WEB_PROXY_PORT_8085}"
|
||||||
|
echo
|
||||||
|
echo "## 网络"
|
||||||
|
echo "- NET=${NET_NAME}"
|
||||||
|
echo "- ARGUS_OVERLAY_NET=${ARGUS_OVERLAY_NET:-argus-sys-net}"
|
||||||
|
echo
|
||||||
|
echo "## 健康检查（简要）"
|
||||||
|
echo "- master/readyz=$(code http://127.0.0.1:${MASTER_PORT:-32300}/readyz)"
|
||||||
|
echo "- prometheus/ready=$(code http://127.0.0.1:${PROMETHEUS_PORT:-9090}/-/ready)"
|
||||||
|
echo "- grafana/api/health=$(code http://127.0.0.1:${GRAFANA_PORT:-3000}/api/health)"
|
||||||
|
echo "- alertmanager/api/v2/status=$(code http://127.0.0.1:${ALERTMANAGER_PORT:-9093}/api/v2/status)"
|
||||||
|
} > "$RPT"
|
||||||
|
info "已生成报告: $RPT"
|
||||||
|
|
||||||
|
# 刷新 web-proxy 上的 nginx 配置（best-effort）
|
||||||
|
docker exec argus-web-proxy nginx -t >/dev/null 2>&1 && docker exec argus-web-proxy nginx -s reload >/dev/null 2>&1 || true
|
||||||
|
|
||||||
|
info "安装完成。可通过 scripts/status.sh 查看当前服务状态。"
|
||||||
74
deployment_new/templates/server_arm/scripts/selfcheck.sh
Normal file
74
deployment_new/templates/server_arm/scripts/selfcheck.sh
Normal file
@ -0,0 +1,74 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
|
||||||
|
|
||||||
|
log() { echo -e "\033[0;34m[CHECK]\033[0m $*"; }
|
||||||
|
err() { echo -e "\033[0;31m[ERROR]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
ENV_FILE="$ROOT/compose/.env"; [[ -f "$ENV_FILE" ]] && set -a && source "$ENV_FILE" && set +a
|
||||||
|
|
||||||
|
wait_http() { local url="$1"; local attempts=${2:-120}; local i=1; while ((i<=attempts)); do curl -fsS "$url" >/dev/null 2>&1 && return 0; echo "[..] waiting $url ($i/$attempts)"; sleep 5; ((i++)); done; return 1; }
|
||||||
|
code_for() { curl -s -o /dev/null -w "%{http_code}" "$1" || echo 000; }
|
||||||
|
header_val() { curl -s -D - -o /dev/null "$@" | awk -F': ' 'BEGIN{IGNORECASE=1}$1=="Access-Control-Allow-Origin"{gsub("\r","",$2);print $2}'; }
|
||||||
|
|
||||||
|
LOG_DIR="$ROOT/logs"; mkdir -p "$LOG_DIR" || true
|
||||||
|
OUT_JSON="$LOG_DIR/selfcheck_arm_server.json"; tmp=$(mktemp)
|
||||||
|
|
||||||
|
ok=1
|
||||||
|
|
||||||
|
log "checking network (${ARGUS_OVERLAY_NET:-argus-sys-net})"
|
||||||
|
net_ok=false
|
||||||
|
if docker network inspect "${ARGUS_OVERLAY_NET:-argus-sys-net}" >/dev/null 2>&1; then
|
||||||
|
net_ok=true
|
||||||
|
fi
|
||||||
|
[[ "$net_ok" == true ]] || ok=0
|
||||||
|
|
||||||
|
log "checking Master"
|
||||||
|
[[ $(code_for "http://localhost:${MASTER_PORT:-32300}/readyz") == 200 ]] || ok=0
|
||||||
|
|
||||||
|
log "checking Prometheus"
|
||||||
|
wait_http "http://localhost:${PROMETHEUS_PORT:-9090}/-/ready" 60 || ok=0
|
||||||
|
|
||||||
|
log "checking Grafana"
|
||||||
|
gf_code=$(code_for "http://localhost:${GRAFANA_PORT:-3000}/api/health")
|
||||||
|
gf_ok=false
|
||||||
|
if [[ "$gf_code" == 200 ]]; then
|
||||||
|
body=$(curl -sS "http://localhost:${GRAFANA_PORT:-3000}/api/health" || true)
|
||||||
|
echo "$body" | grep -q '"database"\s*:\s*"ok"' && gf_ok=true
|
||||||
|
fi
|
||||||
|
[[ "$gf_ok" == true ]] || ok=0
|
||||||
|
|
||||||
|
log "checking Alertmanager"
|
||||||
|
wait_http "http://localhost:${ALERTMANAGER_PORT:-9093}/api/v2/status" 60 || ok=0
|
||||||
|
|
||||||
|
log "checking Web-Proxy (CORS)"
|
||||||
|
cors8084=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8084:-8084}/api/v2/status" || true)
|
||||||
|
cors8085=$(header_val -H "Origin: http://localhost:${WEB_PROXY_PORT_8080:-8080}" "http://localhost:${WEB_PROXY_PORT_8085:-8085}/api/v1/master/nodes" || true)
|
||||||
|
wp_ok=true
|
||||||
|
[[ -n "$cors8084" && -n "$cors8085" ]] || wp_ok=false
|
||||||
|
[[ "$wp_ok" == true ]] || ok=0
|
||||||
|
|
||||||
|
cat > "$tmp" <<JSON
|
||||||
|
{
|
||||||
|
"overlay_net": $net_ok,
|
||||||
|
"master_readyz": true,
|
||||||
|
"prometheus": true,
|
||||||
|
"grafana": $gf_ok,
|
||||||
|
"alertmanager": true,
|
||||||
|
"web_proxy_cors": $wp_ok,
|
||||||
|
"timestamp": "$(date -u +%Y-%m-%dT%H:%M:%SZ)"
|
||||||
|
}
|
||||||
|
JSON
|
||||||
|
|
||||||
|
mv "$tmp" "$OUT_JSON" 2>/dev/null || cp "$tmp" "$OUT_JSON"
|
||||||
|
|
||||||
|
if [[ "$ok" == 1 ]]; then
|
||||||
|
log "selfcheck OK -> $OUT_JSON"
|
||||||
|
exit 0
|
||||||
|
else
|
||||||
|
err "selfcheck FAILED -> $OUT_JSON"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
15
deployment_new/templates/server_arm/scripts/status.sh
Normal file
15
deployment_new/templates/server_arm/scripts/status.sh
Normal file
@ -0,0 +1,15 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
PKG_ROOT="$ROOT_DIR"
|
||||||
|
ENV_FILE="$PKG_ROOT/compose/.env"
|
||||||
|
COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
|
||||||
|
|
||||||
|
if [[ -f "$ENV_FILE" ]]; then
|
||||||
|
set -a; source "$ENV_FILE"; set +a
|
||||||
|
fi
|
||||||
|
|
||||||
|
PROJECT="${COMPOSE_PROJECT_NAME:-argus-server-arm}"
|
||||||
|
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" ps
|
||||||
|
|
||||||
28
deployment_new/templates/server_arm/scripts/uninstall.sh
Normal file
28
deployment_new/templates/server_arm/scripts/uninstall.sh
Normal file
@ -0,0 +1,28 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
PKG_ROOT="$ROOT_DIR"
|
||||||
|
ENV_FILE="$PKG_ROOT/compose/.env"
|
||||||
|
COMPOSE_FILE="$PKG_ROOT/compose/docker-compose.yml"
|
||||||
|
|
||||||
|
if [[ -f "$ENV_FILE" ]]; then
|
||||||
|
set -a; source "$ENV_FILE"; set +a
|
||||||
|
fi
|
||||||
|
|
||||||
|
PROJECT="${COMPOSE_PROJECT_NAME:-argus-server-arm}"
|
||||||
|
|
||||||
|
err(){ echo -e "\033[31m[ERROR]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
require_compose(){
|
||||||
|
if docker compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
|
||||||
|
}
|
||||||
|
|
||||||
|
require_compose
|
||||||
|
|
||||||
|
echo "[UNINSTALL] stopping compose (project=$PROJECT)"
|
||||||
|
docker compose -p "$PROJECT" --env-file "$ENV_FILE" -f "$COMPOSE_FILE" down --remove-orphans || true
|
||||||
|
echo "[UNINSTALL] done"
|
||||||
|
|
||||||
116
deployment_new/templates/server_arm/scripts_for_x86/config.sh
Normal file
116
deployment_new/templates/server_arm/scripts_for_x86/config.sh
Normal file
@ -0,0 +1,116 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
# x86 专用：为 ARM Server 包生成 compose/.env
|
||||||
|
# - 带磁盘空间检查
|
||||||
|
# - 自动分配端口，避免与本机已有服务冲突
|
||||||
|
# - 写入 ARGUS_OVERLAY_NET 和 ARGUS_BUILD_UID/GID
|
||||||
|
|
||||||
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
PKG_ROOT="$ROOT_DIR"
|
||||||
|
ENV_EX="$PKG_ROOT/compose/.env.example"
|
||||||
|
ENV_OUT="$PKG_ROOT/compose/.env"
|
||||||
|
|
||||||
|
info(){ echo -e "\033[34m[CONFIG_X86]\033[0m $*"; }
|
||||||
|
err(){ echo -e "\033[31m[ERROR_X86]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
|
||||||
|
|
||||||
|
# Compose 检测：优先 docker compose（v2），回退 docker-compose（v1）
|
||||||
|
require_compose(){
|
||||||
|
if docker compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
if command -v docker-compose >/dev/null 2>&1 && docker-compose version >/dev/null 2>&1; then return 0; fi
|
||||||
|
err "未检测到 Docker Compose，请安装 docker compose v2 或 docker-compose v1"; exit 1
|
||||||
|
}
|
||||||
|
|
||||||
|
require docker awk sed
|
||||||
|
require_compose
|
||||||
|
|
||||||
|
[[ -f "$ENV_EX" ]] || { err "缺少模板文件: $ENV_EX"; exit 1; }
|
||||||
|
|
||||||
|
# 磁盘空间检查（简化版，默认 >= 5GB）
|
||||||
|
check_disk(){ local p="$1"; local need="${2:-5120}"; local free;
|
||||||
|
free=$(df -Pm "$p" 2>/dev/null | awk 'NR==2{print $4+0}')
|
||||||
|
if [[ -z "$free" || "$free" -lt "$need" ]]; then
|
||||||
|
err "磁盘空间不足: $p 剩余 ${free:-0}MB (<${need}MB)，请清理后再继续"
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
check_disk "$PKG_ROOT" 5120 || true
|
||||||
|
check_disk "/var/lib/docker" 5120 || true
|
||||||
|
|
||||||
|
cp "$ENV_EX" "$ENV_OUT"
|
||||||
|
|
||||||
|
# 读取/生成 SWARM_MANAGER_ADDR（与 ARM server 配置保持一致）
|
||||||
|
SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR:-}
|
||||||
|
if [[ -z "${SWARM_MANAGER_ADDR}" ]]; then
|
||||||
|
read -rp "请输入本机管理地址 SWARM_MANAGER_ADDR: " SWARM_MANAGER_ADDR
|
||||||
|
fi
|
||||||
|
info "SWARM_MANAGER_ADDR=$SWARM_MANAGER_ADDR"
|
||||||
|
|
||||||
|
# 校验 IP 属于本机网卡
|
||||||
|
if ! ip -o addr | awk '{print $4}' | cut -d'/' -f1 | grep -qx "$SWARM_MANAGER_ADDR"; then
|
||||||
|
err "SWARM_MANAGER_ADDR 非本机地址: $SWARM_MANAGER_ADDR"; exit 1; fi
|
||||||
|
|
||||||
|
info "开始分配服务端口（起始=20000，避免系统占用与相互冲突）"
|
||||||
|
is_port_used(){ local p="$1"; ss -tulnH 2>/dev/null | awk '{print $5}' | sed 's/.*://g' | grep -qx "$p"; }
|
||||||
|
declare -A PRESENT=() CHOSEN=() USED=()
|
||||||
|
START_PORT="${START_PORT:-20000}"; cur=$START_PORT
|
||||||
|
ORDER=(MASTER_PORT PROMETHEUS_PORT GRAFANA_PORT ALERTMANAGER_PORT \
|
||||||
|
WEB_PROXY_PORT_8080 WEB_PROXY_PORT_8081 WEB_PROXY_PORT_8082 \
|
||||||
|
WEB_PROXY_PORT_8083 WEB_PROXY_PORT_8084 WEB_PROXY_PORT_8085)
|
||||||
|
|
||||||
|
# 标记 .env.example 中实际存在的键
|
||||||
|
for key in "${ORDER[@]}"; do
|
||||||
|
if grep -q "^${key}=" "$ENV_EX"; then PRESENT[$key]=1; fi
|
||||||
|
done
|
||||||
|
|
||||||
|
next_free(){ local p="$1"; while :; do if [[ -n "${USED[$p]:-}" ]] || is_port_used "$p"; then p=$((p+1)); else echo "$p"; return; fi; done; }
|
||||||
|
|
||||||
|
for key in "${ORDER[@]}"; do
|
||||||
|
[[ -z "${PRESENT[$key]:-}" ]] && continue
|
||||||
|
p=$(next_free "$cur"); CHOSEN[$key]="$p"; USED[$p]=1; cur=$((p+1))
|
||||||
|
done
|
||||||
|
|
||||||
|
info "端口分配结果：MASTER=${CHOSEN[MASTER_PORT]:-} PROM=${CHOSEN[PROMETHEUS_PORT]:-} GRAFANA=${CHOSEN[GRAFANA_PORT]:-} ALERT=${CHOSEN[ALERTMANAGER_PORT]:-} WEB_PROXY(8080..8085)=${CHOSEN[WEB_PROXY_PORT_8080]:-}/${CHOSEN[WEB_PROXY_PORT_8081]:-}/${CHOSEN[WEB_PROXY_PORT_8082]:-}/${CHOSEN[WEB_PROXY_PORT_8083]:-}/${CHOSEN[WEB_PROXY_PORT_8084]:-}/${CHOSEN[WEB_PROXY_PORT_8085]:-}"
|
||||||
|
|
||||||
|
# 覆盖端口（按唯一化结果写回）
|
||||||
|
for key in "${ORDER[@]}"; do
|
||||||
|
val="${CHOSEN[$key]:-}"
|
||||||
|
[[ -z "$val" ]] && continue
|
||||||
|
sed -i -E "s#^$key=.*#$key=${val}#" "$ENV_OUT"
|
||||||
|
done
|
||||||
|
|
||||||
|
# 覆盖/补充 Overlay 名称
|
||||||
|
grep -q '^ARGUS_OVERLAY_NET=' "$ENV_OUT" || echo 'ARGUS_OVERLAY_NET=argus-sys-net' >> "$ENV_OUT"
|
||||||
|
|
||||||
|
# 覆盖/补充构建账户 UID/GID，避免权限问题
|
||||||
|
RUID=$(id -u)
|
||||||
|
RGID=$(id -g)
|
||||||
|
|
||||||
|
if grep -q '^ARGUS_BUILD_UID=' "$ENV_OUT"; then
|
||||||
|
sed -i -E "s#^ARGUS_BUILD_UID=.*#ARGUS_BUILD_UID=${RUID}#" "$ENV_OUT"
|
||||||
|
else
|
||||||
|
echo "ARGUS_BUILD_UID=${RUID}" >> "$ENV_OUT"
|
||||||
|
fi
|
||||||
|
|
||||||
|
if grep -q '^ARGUS_BUILD_GID=' "$ENV_OUT"; then
|
||||||
|
sed -i -E "s#^ARGUS_BUILD_GID=.*#ARGUS_BUILD_GID=${RGID}#" "$ENV_OUT"
|
||||||
|
else
|
||||||
|
echo "ARGUS_BUILD_GID=${RGID}" >> "$ENV_OUT"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# 更新 cluster-info.env 的 SWARM_MANAGER_ADDR（ARM + x86 一致）
|
||||||
|
CI="$PKG_ROOT/cluster-info.env"
|
||||||
|
if [[ -f "$CI" ]]; then
|
||||||
|
if grep -q '^SWARM_MANAGER_ADDR=' "$CI"; then
|
||||||
|
sed -i -E "s#^SWARM_MANAGER_ADDR=.*#SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}#" "$CI"
|
||||||
|
else
|
||||||
|
echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}" >> "$CI"
|
||||||
|
fi
|
||||||
|
else
|
||||||
|
echo "SWARM_MANAGER_ADDR=${SWARM_MANAGER_ADDR}" > "$CI"
|
||||||
|
fi
|
||||||
|
|
||||||
|
info "已生成 compose/.env 并更新 cluster-info.env 的 SWARM_MANAGER_ADDR。"
|
||||||
|
info "下一步可执行: scripts_for_x86/install.sh"
|
||||||
@ -0,0 +1,6 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
exec "$SCRIPT_DIR/../scripts/diagnose.sh" "$@"
|
||||||
|
|
||||||
@ -0,0 +1,77 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
# 在 x86_64 主机上安装 ARM server 包：
|
||||||
|
# 1) 确认/安装 binfmt + QEMU（通过 tonistiigi/binfmt）；
|
||||||
|
# 2) 调用通用的 scripts/install.sh 启动服务。
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
ROOT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
|
||||||
|
|
||||||
|
info(){ echo -e "\033[34m[INSTALL_X86]\033[0m $*"; }
|
||||||
|
err(){ echo -e "\033[31m[ERROR_X86]\033[0m $*" >&2; }
|
||||||
|
|
||||||
|
require(){ local ok=1; for c in "$@"; do command -v "$c" >/dev/null 2>&1 || { err "缺少依赖: $c"; ok=0; }; done; [[ $ok -eq 1 ]]; }
|
||||||
|
|
||||||
|
ensure_binfmt_arm64() {
|
||||||
|
info "检查当前主机架构: $(uname -m)"
|
||||||
|
if [[ "$(uname -m)" != "x86_64" && "$(uname -m)" != "amd64" ]]; then
|
||||||
|
info "当前并非 x86_64（$(uname -m)），通常应直接在 ARM 服务器上使用 scripts/install.sh。继续执行但不强制安装 binfmt。"
|
||||||
|
return 0
|
||||||
|
fi
|
||||||
|
|
||||||
|
require docker
|
||||||
|
|
||||||
|
# 优先使用随安装包一起提供的 ubuntu-22.04-arm-test 镜像做自检
|
||||||
|
local TEST_IMG="ubuntu:22.04"
|
||||||
|
local TEST_TAR=""
|
||||||
|
if [[ -d "$ROOT_DIR/images" ]]; then
|
||||||
|
TEST_TAR=$(ls "$ROOT_DIR"/images/ubuntu-22.04-arm-test*.tar.gz 2>/dev/null | head -n1 || true)
|
||||||
|
fi
|
||||||
|
|
||||||
|
if [[ -n "$TEST_TAR" && ! $(docker image inspect "$TEST_IMG" >/dev/null 2>&1; echo $?) -eq 0 ]]; then
|
||||||
|
info "从安装包加载 ARM 测试基础镜像: $(basename "$TEST_TAR")"
|
||||||
|
tmp=$(mktemp)
|
||||||
|
gunzip -c "$TEST_TAR" > "$tmp"
|
||||||
|
docker load -i "$tmp" >/dev/null
|
||||||
|
rm -f "$tmp"
|
||||||
|
fi
|
||||||
|
|
||||||
|
info "验证是否已能运行 linux/arm64 容器..."
|
||||||
|
if docker run --rm --platform=linux/arm64 "$TEST_IMG" uname -m 2>/dev/null | grep -q 'aarch64'; then
|
||||||
|
info "检测到本机已支持 ARM64 容器运行 (uname -m = aarch64)"
|
||||||
|
return 0
|
||||||
|
fi
|
||||||
|
|
||||||
|
info "未检测到 ARM64 运行能力，尝试通过 tonistiigi/binfmt 安装 binfmt/QEMU ..."
|
||||||
|
# 优先从离线包加载 tonistiigi/binfmt 镜像
|
||||||
|
local BINFMT_IMG="tonistiigi/binfmt:latest"
|
||||||
|
local BINFMT_TAR=""
|
||||||
|
if [[ -d "$ROOT_DIR/images" ]]; then
|
||||||
|
BINFMT_TAR=$(ls "$ROOT_DIR"/images/tonistiigi-binfmt*.tar.gz 2>/dev/null | head -n1 || true)
|
||||||
|
fi
|
||||||
|
if [[ -n "$BINFMT_TAR" && ! $(docker image inspect "$BINFMT_IMG" >/dev/null 2>&1; echo $?) -eq 0 ]]; then
|
||||||
|
info "从安装包加载 tonistiigi/binfmt 离线镜像: $(basename "$BINFMT_TAR")"
|
||||||
|
tmp_b=$(mktemp)
|
||||||
|
gunzip -c "$BINFMT_TAR" > "$tmp_b"
|
||||||
|
docker load -i "$tmp_b" >/dev/null
|
||||||
|
rm -f "$tmp_b"
|
||||||
|
fi
|
||||||
|
|
||||||
|
if ! docker run --privileged --rm "$BINFMT_IMG" --install all; then
|
||||||
|
err "tonistiigi/binfmt 安装失败，请检查 Docker 权限或确认离线镜像是否完整。"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
info "再次验证 ARM64 容器可运行状态..."
|
||||||
|
if ! docker run --rm --platform=linux/arm64 "$TEST_IMG" uname -m 2>/dev/null | grep -q 'aarch64'; then
|
||||||
|
err "安装 binfmt/QEMU 后仍无法运行 linux/arm64 容器，请手工排查 binfmt_misc 配置。"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
info "ARM64 容器运行能力检查通过。"
|
||||||
|
}
|
||||||
|
|
||||||
|
ensure_binfmt_arm64
|
||||||
|
|
||||||
|
# 准备完 x86 -> ARM 运行环境后，交由通用 install.sh 负责后续部署
|
||||||
|
exec "$SCRIPT_DIR/../scripts/install.sh" "$@"
|
||||||
@ -0,0 +1,6 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
exec "$SCRIPT_DIR/../scripts/selfcheck.sh" "$@"
|
||||||
|
|
||||||
@ -0,0 +1,6 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
exec "$SCRIPT_DIR/../scripts/status.sh" "$@"
|
||||||
|
|
||||||
@ -0,0 +1,6 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
exec "$SCRIPT_DIR/../scripts/uninstall.sh" "$@"
|
||||||
|
|
||||||
@ -42,6 +42,11 @@ auto_assign_org = true
|
|||||||
auto_assign_org_role = Viewer
|
auto_assign_org_role = Viewer
|
||||||
verify_email_enabled = false
|
verify_email_enabled = false
|
||||||
|
|
||||||
|
[auth.anonymous]
|
||||||
|
enabled = true
|
||||||
|
org_name = Main Org.
|
||||||
|
org_role = Viewer
|
||||||
|
|
||||||
[log]
|
[log]
|
||||||
mode = console
|
mode = console
|
||||||
level = info
|
level = info
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user