NASP/argus
83
0
Fork 0
Code Issues 8 Pull Requests 1 Actions Packages Projects 1 Releases 1 Wiki Activity

Compare commits

base: NASP:dev_1.0.0_xuxt_2
Branches Tags
NASP:main NASP:huhy_20251211 NASP:dev_1.1.0_arm_support NASP:dev_1.0.0 NASP:dev_1.0.0_yuyr_6 NASP:dev_1.0.0_xuxt_3 NASP:dev_1.0.0_yuyr_5 NASP:dev_1.0.0_sundp_3 NASP:dev_1.0.0_xuxt_2 NASP:dev_1.0.0_xuxt NASP:dev_1.0.0_huhy NASP:dev_1.0.0_sundp
NASP:v1.0.0
..
compare: NASP:3d9b229ac06a100a2e72f1e26f23b1a4b822bc10
Branches Tags
NASP:huhy_20251211 NASP:dev_1.1.0_arm_support NASP:main NASP:dev_1.0.0 NASP:dev_1.0.0_yuyr_6 NASP:dev_1.0.0_xuxt_3 NASP:dev_1.0.0_yuyr_5 NASP:dev_1.0.0_sundp_3 NASP:dev_1.0.0_xuxt_2 NASP:dev_1.0.0_xuxt NASP:dev_1.0.0_huhy NASP:dev_1.0.0_sundp
NASP:v1.0.0

3 Commits
dev_1.0.0_ ... 3d9b229ac0

Author SHA1 Message Date
yuyr
3d9b229ac0 [#13] 增加debug模式系统集成测试，使用external network和指定private路径 2025-10-13 15:18:41 +08:00
yuyr
0e96c5bcb0 [#15] 增加镜像构建 --no-cache选项 2025-10-13 15:17:33 +08:00
yuyr
ee13c8d094 [#15] 修复Kibana创建数据视图缺陷 2025-10-13 11:22:19 +08:00
149 changed files with 749 additions and 9648 deletions
Expand all files Collapse all files

12
src/agent/README.md
View File

@@ -34,18 +34,6 @@ Agent 不再依赖配置文件；所有参数均由环境变量与主机名推
| `MASTER_ENDPOINT` | 是 | N/A | Master 基础地址，可写 `http://host:3000` 或 `host:3000`（自动补全 `http://`）。 |
| `REPORT_INTERVAL_SECONDS` | 否 | `60` | 状态上报间隔（秒）。必须为正整数。 |
| `AGENT_HOSTNAME` | 否 | `$(hostname)` | 覆盖容器内主机名，便于测试或特殊命名需求。 |
| `AGENT_ENV` | 否 | 来源于主机名 | 运行环境标识（如 `dev`、`prod`）。与 `AGENT_USER`、`AGENT_INSTANCE` 必须同时设置。 |
| `AGENT_USER` | 否 | 来源于主机名 | 归属用户或团队标识。与 `AGENT_ENV`、`AGENT_INSTANCE` 必须同时设置。 |
| `AGENT_INSTANCE` | 否 | 来源于主机名 | 实例编号或别名。与 `AGENT_ENV`、`AGENT_USER` 必须同时设置。 |
主机名与元数据的解析优先级：
1. 若设置 `AGENT_ENV` / `AGENT_USER` / `AGENT_INSTANCE` 且全部存在，则直接使用这些值。
2. 否则检查历史 `node.json`（注册成功后由 Master 返回的信息），若包含 `env` / `user` / `instance` 则沿用。
3. 若以上均不可用，则按历史约定从主机名解析 `env-user-instance` 前缀。
4. 如果仍无法得到完整结果，Agent 启动会失败并提示需要提供上述环境变量。
> 提示：在首次部署时需确保环境变量或主机名能够提供完整信息。完成注册后，Agent 会把 Master 返回的元数据写入 `node.json`，后续重启无需再次提供环境变量就能保持一致性。
派生路径：

7
src/agent/app/collector.py
View File

@@ -18,12 +18,13 @@ _HOSTNAME_PATTERN = re.compile(r"^([^-]+)-([^-]+)-([^-]+)-.*$")
def collect_metadata(config: AgentConfig) -> Dict[str, Any]:
"""汇总节点注册需要的静态信息。"""
hostname = config.hostname
env, user, instance = _parse_hostname(hostname)
meta = {
"hostname": hostname,
"ip": _detect_ip_address(),
"env": config.environment,
"user": config.user,
"instance": config.instance,
"env": env,
"user": user,
"instance": instance,
"cpu_number": _detect_cpu_count(),
"memory_in_bytes": _detect_memory_bytes(),
"gpu_number": _detect_gpu_count(),

67
src/agent/app/config.py
View File

@@ -6,21 +6,14 @@ from dataclasses import dataclass
from pathlib import Path
from typing import Final
from .state import load_node_state
from .version import VERSION
from .log import get_logger
DEFAULT_REPORT_INTERVAL_SECONDS: Final[int] = 60
LOGGER = get_logger("argus.agent.config")
@dataclass(frozen=True)
class AgentConfig:
hostname: str
environment: str
user: str
instance: str
node_file: str
version: str
master_endpoint: str
@@ -54,68 +47,11 @@ def _resolve_hostname() -> str:
return os.environ.get("AGENT_HOSTNAME") or socket.gethostname()
def _load_metadata_from_state(node_file: str) -> tuple[str, str, str] | None:
state = load_node_state(node_file)
if not state:
return None
meta = state.get("meta_data") or {}
env = meta.get("env") or state.get("env")
user = meta.get("user") or state.get("user")
instance = meta.get("instance") or state.get("instance")
if env and user and instance:
LOGGER.debug("Metadata resolved from node state", extra={"node_file": node_file})
return env, user, instance
LOGGER.warning(
"node.json missing metadata fields; ignoring",
extra={"node_file": node_file, "meta_data": meta},
)
return None
def _resolve_metadata_fields(hostname: str, node_file: str) -> tuple[str, str, str]:
env = os.environ.get("AGENT_ENV")
user = os.environ.get("AGENT_USER")
instance = os.environ.get("AGENT_INSTANCE")
if env and user and instance:
return env, user, instance
if any([env, user, instance]):
LOGGER.warning(
"Incomplete metadata environment variables; falling back to persisted metadata",
extra={
"has_env": bool(env),
"has_user": bool(user),
"has_instance": bool(instance),
},
)
state_metadata = _load_metadata_from_state(node_file)
if state_metadata is not None:
return state_metadata
from .collector import _parse_hostname # Local import to avoid circular dependency
env, user, instance = _parse_hostname(hostname)
if not all([env, user, instance]):
raise ValueError(
"Failed to determine metadata fields; set AGENT_ENV/USER/INSTANCE or use supported hostname pattern"
)
return env, user, instance
def load_config() -> AgentConfig:
"""从环境变量推导配置，移除了外部配置文件依赖。"""
hostname = _resolve_hostname()
node_file = f"/private/argus/agent/{hostname}/node.json"
environment, user, instance = _resolve_metadata_fields(hostname, node_file)
health_dir = f"/private/argus/agent/{hostname}/health/"
master_endpoint_env = os.environ.get("MASTER_ENDPOINT")
@@ -130,9 +66,6 @@ def load_config() -> AgentConfig:
return AgentConfig(
hostname=hostname,
environment=environment,
user=user,
instance=instance,
node_file=node_file,
version=VERSION,
master_endpoint=master_endpoint,

BIN
src/agent/dist/argus-agent vendored
View File

Binary file not shown.

0
src/agent/tests/__init__.py
View File

30
src/agent/tests/docker-compose.yml
View File

@@ -60,36 +60,6 @@ services:
ipv4_address: 172.28.0.20
restart: always
agent_env:
image: ubuntu:22.04
container_name: argus-agent-env-e2e
hostname: host_abc
depends_on:
- master
- bind
environment:
- MASTER_ENDPOINT=http://master.argus.com:3000
- REPORT_INTERVAL_SECONDS=2
- AGENT_ENV=prod
- AGENT_USER=ml
- AGENT_INSTANCE=node-3
- AGENT_HOSTNAME=host_abc
- "ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}"
- "ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}"
volumes:
- ./private/argus/agent/host_abc:/private/argus/agent/host_abc
- ./private/argus/agent/host_abc/health:/private/argus/agent/host_abc/health
- ./private/argus/etc:/private/argus/etc
- ../dist/argus-agent:/usr/local/bin/argus-agent:ro
- ./scripts/agent_entrypoint.sh:/usr/local/bin/agent-entrypoint.sh:ro
- ../scripts/agent_deployment_verify.sh:/usr/local/bin/agent_deployment_verify.sh:ro
entrypoint:
- /usr/local/bin/agent-entrypoint.sh
networks:
default:
ipv4_address: 172.28.0.21
restart: always
networks:
default:
driver: bridge

8
src/agent/tests/scripts/00_e2e_test.sh
View File

@@ -7,10 +7,10 @@ SCRIPTS=(
"02_up.sh"
"03_wait_and_assert_registration.sh"
"04_write_health_files.sh"
"05_verify_agent.sh"
"06_assert_status_on_master.sh"
"07_restart_agent_and_reregister.sh"
"08_down.sh"
"08_verify_agent.sh"
"05_assert_status_on_master.sh"
"06_restart_agent_and_reregister.sh"
"07_down.sh"
)
for script in "${SCRIPTS[@]}"; do

2
src/agent/tests/scripts/02_up.sh
View File

@@ -41,7 +41,7 @@ compose() {
fi
}
docker container rm -f argus-agent-e2e argus-agent-env-e2e argus-master-agent-e2e argus-bind-agent-e2e >/dev/null 2>&1 || true
docker container rm -f argus-agent-e2e argus-master-agent-e2e argus-bind-agent-e2e >/dev/null 2>&1 || true
docker network rm tests_default >/dev/null 2>&1 || true

61
src/agent/tests/scripts/03_wait_and_assert_registration.sh
View File

@@ -6,14 +6,11 @@ TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
TMP_ROOT="$TEST_ROOT/tmp"
API_BASE="http://localhost:32300/api/v1/master"
AGENT_HOSTNAME="dev-e2euser-e2einst-pod-0"
ENV_AGENT_HOSTNAME="host_abc"
NODE_FILE="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME/node.json"
ENV_NODE_FILE="$TEST_ROOT/private/argus/agent/$ENV_AGENT_HOSTNAME/node.json"
mkdir -p "$TMP_ROOT"
primary_node_id=""
env_node_id=""
node_id=""
for _ in {1..30}; do
sleep 2
response=$(curl -sS "$API_BASE/nodes" || true)
@@ -22,49 +19,24 @@ for _ in {1..30}; do
fi
list_file="$TMP_ROOT/nodes_list.json"
echo "$response" > "$list_file"
readarray -t node_ids < <(python3 - "$list_file" "$AGENT_HOSTNAME" "$ENV_AGENT_HOSTNAME" <<'PY'
node_id=$(python3 - "$list_file" <<'PY'
import json, sys
with open(sys.argv[1]) as handle:
nodes = json.load(handle)
target_primary = sys.argv[2]
target_env = sys.argv[3]
primary_id = ""
env_id = ""
for node in nodes:
if node.get("name") == target_primary:
primary_id = node.get("id", "")
if node.get("name") == target_env:
env_id = node.get("id", "")
print(primary_id)
print(env_id)
print(nodes[0]["id"] if nodes else "")
PY
)
primary_node_id="${node_ids[0]}"
env_node_id="${node_ids[1]}"
if [[ -n "$primary_node_id" && -n "$env_node_id" ]]; then
)
if [[ -n "$node_id" ]]; then
break
fi
done
if [[ -z "$primary_node_id" ]]; then
echo "[ERROR] Primary agent did not register within timeout" >&2
if [[ -z "$node_id" ]]; then
echo "[ERROR] Agent did not register within timeout" >&2
exit 1
fi
if [[ -z "$env_node_id" ]]; then
echo "[ERROR] Env-variable agent did not register within timeout" >&2
exit 1
fi
echo "$primary_node_id" > "$TMP_ROOT/node_id"
echo "$env_node_id" > "$TMP_ROOT/node_id_host_abc"
echo "$node_id" > "$TMP_ROOT/node_id"
if [[ ! -f "$NODE_FILE" ]]; then
echo "[ERROR] node.json not created at $NODE_FILE" >&2
@@ -78,20 +50,8 @@ with open(sys.argv[1]) as handle:
assert "id" in node and node["id"], "node.json missing id"
PY
if [[ ! -f "$ENV_NODE_FILE" ]]; then
echo "[ERROR] node.json not created at $ENV_NODE_FILE" >&2
exit 1
fi
python3 - "$ENV_NODE_FILE" <<'PY'
import json, sys
with open(sys.argv[1]) as handle:
node = json.load(handle)
assert "id" in node and node["id"], "env agent node.json missing id"
PY
detail_file="$TMP_ROOT/initial_detail.json"
curl -sS "$API_BASE/nodes/$primary_node_id" -o "$detail_file"
curl -sS "$API_BASE/nodes/$node_id" -o "$detail_file"
python3 - "$detail_file" "$TMP_ROOT/initial_ip" <<'PY'
import json, sys, pathlib
with open(sys.argv[1]) as handle:
@@ -102,5 +62,4 @@ if not ip:
pathlib.Path(sys.argv[2]).write_text(ip)
PY
echo "[INFO] Agent registered with node id $primary_node_id"
echo "[INFO] Env-variable agent registered with node id $env_node_id"
echo "[INFO] Agent registered with node id $node_id"

33
src/agent/tests/scripts/06_assert_status_on_master.sh → src/agent/tests/scripts/05_assert_status_on_master.sh
View File

@@ -6,8 +6,6 @@ TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
TMP_ROOT="$TEST_ROOT/tmp"
API_BASE="http://localhost:32300/api/v1/master"
NODE_ID="$(cat "$TMP_ROOT/node_id")"
ENV_NODE_ID="$(cat "$TMP_ROOT/node_id_host_abc")"
ENV_HOSTNAME="host_abc"
NODES_JSON="$TEST_ROOT/private/argus/metric/prometheus/nodes.json"
success=false
@@ -43,36 +41,13 @@ if [[ ! -f "$NODES_JSON" ]]; then
exit 1
fi
python3 - "$NODES_JSON" "$NODE_ID" "$ENV_NODE_ID" <<'PY'
python3 - "$NODES_JSON" <<'PY'
import json, sys
with open(sys.argv[1]) as handle:
nodes = json.load(handle)
expected_primary = sys.argv[2]
expected_env = sys.argv[3]
ids = {entry.get("node_id") for entry in nodes}
assert expected_primary in ids, nodes
assert expected_env in ids, nodes
assert len(nodes) >= 2, nodes
assert len(nodes) == 1, nodes
entry = nodes[0]
assert entry["node_id"], entry
PY
echo "[INFO] Master reflects agent health and nodes.json entries"
env_detail_file="$TMP_ROOT/env_agent_detail.json"
curl -sS "$API_BASE/nodes/$ENV_NODE_ID" -o "$env_detail_file"
python3 - "$env_detail_file" "$ENV_HOSTNAME" <<'PY'
import json, sys
with open(sys.argv[1]) as handle:
node = json.load(handle)
expected_name = sys.argv[2]
assert node.get("name") == expected_name, node
meta = node.get("meta_data", {})
assert meta.get("env") == "prod", meta
assert meta.get("user") == "ml", meta
assert meta.get("instance") == "node-3", meta
PY
echo "[INFO] Env-variable agent reports expected metadata"

60
src/agent/tests/scripts/05_verify_agent.sh
View File

@@ -1,60 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
REPO_ROOT="$(cd "$TEST_ROOT/.." && pwd)"
VERIFY_SCRIPT="$REPO_ROOT/scripts/agent_deployment_verify.sh"
ENV_NODE_ID_FILE="$TEST_ROOT/tmp/node_id_host_abc"
PRIMARY_CONTAINER="argus-agent-e2e"
ENV_CONTAINER="argus-agent-env-e2e"
PRIMARY_HOSTNAME="dev-e2euser-e2einst-pod-0"
ENV_HOSTNAME="host_abc"
if ! docker ps --format '{{.Names}}' | grep -q "^${PRIMARY_CONTAINER}$"; then
echo "[WARN] agent container not running; skip verification"
exit 0
fi
if docker exec -i "$PRIMARY_CONTAINER" bash -lc 'command -v curl >/dev/null && command -v jq >/dev/null'; then
echo "[INFO] curl/jq already installed in agent container"
else
echo "[INFO] Installing curl/jq in agent container"
docker exec -i "$PRIMARY_CONTAINER" bash -lc 'apt-get update >/dev/null 2>&1 && apt-get install -y curl jq >/dev/null 2>&1' || true
fi
if [[ ! -f "$VERIFY_SCRIPT" ]]; then
echo "[ERROR] Verification script missing at $VERIFY_SCRIPT" >&2
exit 1
fi
run_verifier() {
local container="$1" hostname="$2"
if ! docker ps --format '{{.Names}}' | grep -q "^${container}$"; then
echo "[WARN] container $container not running; skip"
return
fi
if ! docker exec -i "$container" bash -lc 'command -v /usr/local/bin/agent_deployment_verify.sh >/dev/null'; then
echo "[ERROR] /usr/local/bin/agent_deployment_verify.sh missing in $container" >&2
exit 1
fi
echo "[INFO] Running verification for $hostname in $container"
docker exec -i "$container" env VERIFY_HOSTNAME="$hostname" /usr/local/bin/agent_deployment_verify.sh
}
run_verifier "$PRIMARY_CONTAINER" "$PRIMARY_HOSTNAME"
if docker ps --format '{{.Names}}' | grep -q "^${ENV_CONTAINER}$"; then
if docker exec -i "$ENV_CONTAINER" bash -lc 'command -v curl >/dev/null && command -v jq >/dev/null'; then
echo "[INFO] curl/jq already installed in env agent container"
else
echo "[INFO] Installing curl/jq in env agent container"
docker exec -i "$ENV_CONTAINER" bash -lc 'apt-get update >/dev/null 2>&1 && apt-get install -y curl jq >/dev/null 2>&1' || true
fi
run_verifier "$ENV_CONTAINER" "$ENV_HOSTNAME"
else
echo "[WARN] env-driven agent container not running; skip secondary verification"
fi

111
src/agent/tests/scripts/07_restart_agent_and_reregister.sh → src/agent/tests/scripts/06_restart_agent_and_reregister.sh
View File

@@ -6,20 +6,10 @@ TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
TMP_ROOT="$TEST_ROOT/tmp"
API_BASE="http://localhost:32300/api/v1/master"
NODE_ID="$(cat "$TMP_ROOT/node_id")"
ENV_NODE_ID_FILE="$TMP_ROOT/node_id_host_abc"
if [[ ! -f "$ENV_NODE_ID_FILE" ]]; then
echo "[ERROR] Env agent node id file missing at $ENV_NODE_ID_FILE" >&2
exit 1
fi
ENV_NODE_ID="$(cat "$ENV_NODE_ID_FILE")"
AGENT_HOSTNAME="dev-e2euser-e2einst-pod-0"
ENV_AGENT_HOSTNAME="host_abc"
NETWORK_NAME="tests_default"
NEW_AGENT_IP="172.28.0.200"
NEW_ENV_AGENT_IP="172.28.0.210"
ENTRYPOINT_SCRIPT="$SCRIPT_DIR/agent_entrypoint.sh"
VERIFY_SCRIPT="$TEST_ROOT/../scripts/agent_deployment_verify.sh"
ENV_FILE="$TEST_ROOT/.env"
# 中文提示：重启场景也需要同样的入口脚本，确保 DNS 注册逻辑一致
@@ -28,11 +18,6 @@ if [[ ! -f "$ENTRYPOINT_SCRIPT" ]]; then
exit 1
fi
if [[ ! -f "$VERIFY_SCRIPT" ]]; then
echo "[ERROR] agent verification script missing at $VERIFY_SCRIPT" >&2
exit 1
fi
if [[ ! -f "$TMP_ROOT/agent_binary_path" ]]; then
echo "[ERROR] Agent binary path missing; rerun bootstrap" >&2
exit 1
@@ -89,37 +74,15 @@ if [[ "$prev_ip" != "$initial_ip" ]]; then
exit 1
fi
env_before_file="$TMP_ROOT/env_before_restart.json"
curl -sS "$API_BASE/nodes/$ENV_NODE_ID" -o "$env_before_file"
env_prev_last_updated=$(python3 - "$env_before_file" <<'PY'
import json, sys
with open(sys.argv[1]) as handle:
node = json.load(handle)
print(node.get("last_updated", ""))
PY
)
env_prev_ip=$(python3 - "$env_before_file" <<'PY'
import json, sys
with open(sys.argv[1]) as handle:
node = json.load(handle)
print(node["meta_data"].get("ip", ""))
PY
)
pushd "$TEST_ROOT" >/dev/null
compose rm -sf agent
compose rm -sf agent_env
popd >/dev/null
docker container rm -f argus-agent-e2e >/dev/null 2>&1 || true
docker container rm -f argus-agent-env-e2e >/dev/null 2>&1 || true
AGENT_DIR="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME"
HEALTH_DIR="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME/health"
ENV_AGENT_DIR="$TEST_ROOT/private/argus/agent/$ENV_AGENT_HOSTNAME"
ENV_HEALTH_DIR="$TEST_ROOT/private/argus/agent/$ENV_AGENT_HOSTNAME/health"
# 先以 sleep 方式启动容器，确保我们掌握注册时的网络状态
if ! docker run -d \
--name argus-agent-e2e \
@@ -131,7 +94,6 @@ if ! docker run -d \
-v "$TEST_ROOT/private/argus/etc:/private/argus/etc" \
-v "$AGENT_BINARY:/usr/local/bin/argus-agent:ro" \
-v "$ENTRYPOINT_SCRIPT:/usr/local/bin/agent-entrypoint.sh:ro" \
-v "$VERIFY_SCRIPT:/usr/local/bin/agent_deployment_verify.sh:ro" \
-e MASTER_ENDPOINT=http://master.argus.com:3000 \
-e REPORT_INTERVAL_SECONDS=2 \
-e ARGUS_BUILD_UID="$AGENT_UID" \
@@ -179,76 +141,3 @@ if [[ "$success" != true ]]; then
fi
echo "[INFO] Agent restart produced successful re-registration with IP change"
# ---- Restart env-driven agent without metadata environment variables ----
if [[ ! -d "$ENV_AGENT_DIR" ]]; then
echo "[ERROR] Env agent data dir missing at $ENV_AGENT_DIR" >&2
exit 1
fi
if [[ ! -d "$ENV_HEALTH_DIR" ]]; then
mkdir -p "$ENV_HEALTH_DIR"
fi
if ! docker run -d \
--name argus-agent-env-e2e \
--hostname "$ENV_AGENT_HOSTNAME" \
--network "$NETWORK_NAME" \
--ip "$NEW_ENV_AGENT_IP" \
-v "$ENV_AGENT_DIR:/private/argus/agent/$ENV_AGENT_HOSTNAME" \
-v "$ENV_HEALTH_DIR:/private/argus/agent/$ENV_AGENT_HOSTNAME/health" \
-v "$TEST_ROOT/private/argus/etc:/private/argus/etc" \
-v "$AGENT_BINARY:/usr/local/bin/argus-agent:ro" \
-v "$ENTRYPOINT_SCRIPT:/usr/local/bin/agent-entrypoint.sh:ro" \
-v "$VERIFY_SCRIPT:/usr/local/bin/agent_deployment_verify.sh:ro" \
-e MASTER_ENDPOINT=http://master.argus.com:3000 \
-e REPORT_INTERVAL_SECONDS=2 \
-e ARGUS_BUILD_UID="$AGENT_UID" \
-e ARGUS_BUILD_GID="$AGENT_GID" \
--entrypoint /usr/local/bin/agent-entrypoint.sh \
ubuntu:22.04 >/dev/null; then
echo "[ERROR] Failed to start env-driven agent container without metadata env" >&2
exit 1
fi
env_success=false
env_detail_file="$TMP_ROOT/env_post_restart.json"
for _ in {1..20}; do
sleep 3
if ! curl -sS "$API_BASE/nodes/$ENV_NODE_ID" -o "$env_detail_file"; then
continue
fi
if python3 - "$env_detail_file" "$env_prev_last_updated" "$ENV_NODE_ID" "$env_prev_ip" "$NEW_ENV_AGENT_IP" <<'PY'
import json, sys
with open(sys.argv[1]) as handle:
node = json.load(handle)
prev_last_updated = sys.argv[2]
expected_id = sys.argv[3]
old_ip = sys.argv[4]
expected_ip = sys.argv[5]
last_updated = node.get("last_updated")
current_ip = node["meta_data"].get("ip")
meta = node.get("meta_data", {})
assert node["id"] == expected_id
if current_ip != expected_ip:
raise SystemExit(1)
if current_ip == old_ip:
raise SystemExit(1)
if not last_updated or last_updated == prev_last_updated:
raise SystemExit(1)
if meta.get("env") != "prod" or meta.get("user") != "ml" or meta.get("instance") != "node-3":
raise SystemExit(1)
PY
then
env_success=true
break
fi
done
if [[ "$env_success" != true ]]; then
echo "[ERROR] Env-driven agent did not reuse persisted metadata after restart" >&2
exit 1
fi
echo "[INFO] Env-driven agent restart succeeded with persisted metadata"

2
src/agent/tests/scripts/08_down.sh → src/agent/tests/scripts/07_down.sh
View File

@@ -13,7 +13,7 @@ compose() {
fi
}
docker container rm -f argus-agent-e2e argus-agent-env-e2e >/dev/null 2>&1 || true
docker container rm -f argus-agent-e2e >/dev/null 2>&1 || true
pushd "$TEST_ROOT" >/dev/null
compose down --remove-orphans

26
src/agent/tests/scripts/08_verify_agent.sh Executable file
View File

@@ -0,0 +1,26 @@
#!/usr/bin/env bash
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
VERIFY_SCRIPT="$(cd "$TEST_ROOT/.." && pwd)/scripts/agent_deployment_verify.sh"
if ! docker ps --format '{{.Names}}' | grep -q '^argus-agent-e2e$'; then
echo "[WARN] agent container not running; skip verification"
exit 0
fi
if docker exec -i argus-agent-e2e bash -lc 'command -v curl >/dev/null && command -v jq >/dev/null'; then
echo "[INFO] curl/jq already installed in agent container"
else
echo "[INFO] Installing curl/jq in agent container"
docker exec -i argus-agent-e2e bash -lc 'apt-get update >/dev/null 2>&1 && apt-get install -y curl jq >/dev/null 2>&1' || true
fi
if docker exec -i argus-agent-e2e bash -lc 'command -v /usr/local/bin/agent_deployment_verify.sh >/dev/null'; then
docker exec -i argus-agent-e2e /usr/local/bin/agent_deployment_verify.sh
elif [[ -x "$VERIFY_SCRIPT" ]]; then
docker exec -i argus-agent-e2e "$VERIFY_SCRIPT"
else
echo "[WARN] agent_deployment_verify.sh not found"
fi

151
src/agent/tests/test_config_metadata.py
View File

@@ -1,151 +0,0 @@
from __future__ import annotations
import os
import unittest
from contextlib import contextmanager
from unittest.mock import patch
from app.config import AgentConfig, load_config
@contextmanager
def temp_env(**overrides: str | None):
originals: dict[str, str | None] = {}
try:
for key, value in overrides.items():
originals[key] = os.environ.get(key)
if value is None:
os.environ.pop(key, None)
else:
os.environ[key] = value
yield
finally:
for key, original in originals.items():
if original is None:
os.environ.pop(key, None)
else:
os.environ[key] = original
class LoadConfigMetadataTests(unittest.TestCase):
@patch("app.config.Path.mkdir")
def test_metadata_from_environment_variables(self, mock_mkdir):
with temp_env(
MASTER_ENDPOINT="http://master.local",
AGENT_HOSTNAME="dev-user-one-pod",
AGENT_ENV="prod",
AGENT_USER="ops",
AGENT_INSTANCE="node-1",
):
config = load_config()
self.assertEqual(config.environment, "prod")
self.assertEqual(config.user, "ops")
self.assertEqual(config.instance, "node-1")
mock_mkdir.assert_called()
@patch("app.config.Path.mkdir")
def test_metadata_falls_back_to_hostname(self, mock_mkdir):
with temp_env(
MASTER_ENDPOINT="http://master.local",
AGENT_HOSTNAME="qa-team-abc-pod-2",
AGENT_ENV=None,
AGENT_USER=None,
AGENT_INSTANCE=None,
):
config = load_config()
self.assertEqual(config.environment, "qa")
self.assertEqual(config.user, "team")
self.assertEqual(config.instance, "abc")
mock_mkdir.assert_called()
@patch("app.config._load_metadata_from_state", return_value=("prod", "ops", "node-1"))
@patch("app.config.Path.mkdir")
def test_metadata_from_node_state(self, mock_mkdir, mock_state):
with temp_env(
MASTER_ENDPOINT="http://master.local",
AGENT_HOSTNAME="host_abc",
AGENT_ENV=None,
AGENT_USER=None,
AGENT_INSTANCE=None,
):
config = load_config()
self.assertEqual(config.environment, "prod")
self.assertEqual(config.user, "ops")
self.assertEqual(config.instance, "node-1")
mock_state.assert_called_once()
mock_mkdir.assert_called()
@patch("app.config.Path.mkdir")
def test_partial_environment_variables_fallback(self, mock_mkdir):
with temp_env(
MASTER_ENDPOINT="http://master.local",
AGENT_HOSTNAME="stage-ml-001-node",
AGENT_ENV="prod",
AGENT_USER=None,
AGENT_INSTANCE=None,
):
config = load_config()
self.assertEqual(config.environment, "stage")
self.assertEqual(config.user, "ml")
self.assertEqual(config.instance, "001")
mock_mkdir.assert_called()
@patch("app.config.Path.mkdir")
def test_invalid_hostname_raises_error(self, mock_mkdir):
with temp_env(
MASTER_ENDPOINT="http://master.local",
AGENT_HOSTNAME="invalidhostname",
AGENT_ENV=None,
AGENT_USER=None,
AGENT_INSTANCE=None,
):
with self.assertRaises(ValueError):
load_config()
mock_mkdir.assert_not_called()
class CollectMetadataTests(unittest.TestCase):
@patch("app.collector._detect_ip_address", return_value="127.0.0.1")
@patch("app.collector._detect_gpu_count", return_value=0)
@patch("app.collector._detect_memory_bytes", return_value=1024)
@patch("app.collector._detect_cpu_count", return_value=8)
def test_collect_metadata_uses_config_fields(
self,
mock_cpu,
mock_memory,
mock_gpu,
mock_ip,
):
config = AgentConfig(
hostname="dev-user-001-pod",
environment="prod",
user="ops",
instance="node-1",
node_file="/tmp/node.json",
version="1.0.0",
master_endpoint="http://master.local",
report_interval_seconds=60,
health_dir="/tmp/health",
)
from app.collector import collect_metadata
metadata = collect_metadata(config)
self.assertEqual(metadata["env"], "prod")
self.assertEqual(metadata["user"], "ops")
self.assertEqual(metadata["instance"], "node-1")
self.assertEqual(metadata["hostname"], "dev-user-001-pod")
self.assertEqual(metadata["ip"], "127.0.0.1")
self.assertEqual(metadata["cpu_number"], 8)
self.assertEqual(metadata["memory_in_bytes"], 1024)
self.assertEqual(metadata["gpu_number"], 0)
if __name__ == "__main__":
unittest.main()

31
src/alert/README.md
View File

@@ -1,31 +0,0 @@
# Alertmanager
## 构建
1. 首先设置构建和部署的环境变量, 在项目根目录下执行：
```bash
cp src/alert/tests/.env.example src/alert/tests/.env
```
然后找到复制出来的.env文件，修改环境变量。
2. 使用脚本构建，在项目根目录下执行：
```bash
bash src/alert/alertmanager/build/build.sh
```
构建成功后，会在项目根目录下生成argus-alertmanager-latest.tar
## 部署
提供docker-compose部署。在src/alert/tests目录下
```bash
docker-compose up -d
```
## 动态配置
配置文件放在`/private/argus/alert/alertmanager/alertmanager.yml`下，修改alertmanager.yml后，调用`http://alertmanager.alert.argus.com:9093/-/reload`接口(POST)可以重新加载配置.
```bash
curl -X POST http://localhost:9093/-/reload
```

89
src/alert/alertmanager/build/Dockerfile
View File

@@ -1,89 +0,0 @@
# 基于 Ubuntu 24.04
FROM ubuntu:24.04
# 切换到 root 用户
USER root
# 安装必要依赖
RUN apt-get update && \
apt-get install -y wget supervisor net-tools inetutils-ping vim ca-certificates passwd && \
apt-get clean && rm -rf /var/lib/apt/lists/*
# 设置 Alertmanager 版本
ARG ALERTMANAGER_VERSION=0.28.1
# 下载并解压 Alertmanager 二进制
RUN wget https://github.com/prometheus/alertmanager/releases/download/v${ALERTMANAGER_VERSION}/alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz && \
tar xvf alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz && \
mv alertmanager-${ALERTMANAGER_VERSION}.linux-amd64 /usr/local/alertmanager && \
rm alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz
ENV ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
ARG ARGUS_UID=2133
ARG ARGUS_GID=2015
ENV ARGUS_UID=${ARGUS_UID}
ENV ARGUS_GID=${ARGUS_GID}
RUN mkdir -p /usr/share/alertmanager && \
mkdir -p ${ALERTMANAGER_BASE_PATH} && \
mkdir -p /private/argus/etc && \
rm -rf /alertmanager && \
ln -s ${ALERTMANAGER_BASE_PATH} /alertmanager
# 创建 alertmanager 用户（可自定义 UID/GID）
# 创建 alertmanager 用户组
RUN groupadd -g ${ARGUS_GID} alertmanager
# 创建 alertmanager 用户并指定组
RUN useradd -M -s /usr/sbin/nologin -u ${ARGUS_UID} -g ${ARGUS_GID} alertmanager
RUN chown -R alertmanager:alertmanager /usr/share/alertmanager && \
chown -R alertmanager:alertmanager /alertmanager && \
chown -R alertmanager:alertmanager ${ALERTMANAGER_BASE_PATH} && \
chown -R alertmanager:alertmanager /private/argus/etc && \
chown -R alertmanager:alertmanager /usr/local/bin
# 配置内网 apt 源 (如果指定了内网选项)
RUN if [ "$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
# 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/alert/alertmanager/build/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
# 复制启动脚本
COPY src/alert/alertmanager/build/start-am-supervised.sh /usr/local/bin/start-am-supervised.sh
RUN chmod +x /usr/local/bin/start-am-supervised.sh
# 复制 Alertmanager 配置文件
COPY src/alert/alertmanager/build/alertmanager.yml /etc/alertmanager/alertmanager.yml
RUN chmod +x /etc/alertmanager/alertmanager.yml
# COPY src/alert/alertmanager/build/alertmanager.yml ${ALERTMANAGER_BASE_PATH}/alertmanager.yml
# 复制 DNS 监控脚本
COPY src/alert/alertmanager/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 控制 user 切换
USER root
# 暴露端口（Alertmanager 默认端口 9093）
EXPOSE 9093
# 使用 supervisor 作为入口点
CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

19
src/alert/alertmanager/build/alertmanager.yml
View File

@@ -1,19 +0,0 @@
global:
resolve_timeout: 5m
route:
group_by: ['alertname', 'instance'] # 分组：相同 alertname + instance 的告警合并
group_wait: 30s # 第一个告警后，等 30s 看是否有同组告警一起发
group_interval: 5m # 同组告警变化后，至少 5 分钟再发一次
repeat_interval: 3h # 相同告警，3 小时重复提醒一次
receiver: 'null'
receivers:
- name: 'null'
inhibit_rules:
- source_match:
severity: 'critical' # critical 告警存在时
target_match:
severity: 'warning' # 抑制相同 instance 的 warning 告警
equal: ['instance']

13
src/alert/alertmanager/build/build.sh
View File

@@ -1,13 +0,0 @@
#!/bin/bash
set -euo pipefail
docker pull ubuntu:24.04
source src/alert/tests/.env
docker build \
--build-arg ARGUS_UID=${ARGUS_UID} \
--build-arg ARGUS_GID=${ARGUS_GID} \
-f src/alert/alertmanager/build/Dockerfile \
-t argus-alertmanager:latest .
docker save -o argus-alertmanager-latest.tar argus-alertmanager:latest

68
src/alert/alertmanager/build/dns-monitor.sh
View File

@@ -1,68 +0,0 @@
#!/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

27
src/alert/alertmanager/build/start-am-supervised.sh
View File

@@ -1,27 +0,0 @@
#!/bin/bash
set -euo pipefail
echo "[INFO] Starting Alertmanager under supervisor..."
ALERTMANAGER_BASE_PATH=${ALERTMANAGER_BASE_PATH:-/private/argus/alert/alertmanager}
echo "[INFO] Alertmanager base path: ${ALERTMANAGER_BASE_PATH}"
# 生成配置文件
echo "[INFO] Generating Alertmanager configuration file..."
sed "s|\${ALERTMANAGER_BASE_PATH}|${ALERTMANAGER_BASE_PATH}|g" \
/etc/alertmanager/alertmanager.yml > ${ALERTMANAGER_BASE_PATH}/alertmanager.yml
# 记录容器 IP 地址
DOMAIN=alertmanager.alert.argus.com
IP=$(ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}')
echo "current IP: ${IP}"
echo "${IP}" > /private/argus/etc/${DOMAIN}
chmod 755 /private/argus/etc/${DOMAIN}
echo "[INFO] Starting Alertmanager process..."
# 启动 Alertmanager 主进程
exec /usr/local/alertmanager/alertmanager --config.file=/etc/alertmanager/alertmanager.yml --storage.path=/alertmanager --cluster.listen-address=""

39
src/alert/alertmanager/build/supervisord.conf
View File

@@ -1,39 +0,0 @@
[supervisord]
nodaemon=true
logfile=/var/log/supervisor/supervisord.log
pidfile=/var/run/supervisord.pid
user=root
[program:alertmanager]
command=/usr/local/bin/start-am-supervised.sh
user=alertmanager
stdout_logfile=/var/log/supervisor/alertmanager.log
stderr_logfile=/var/log/supervisor/alertmanager_error.log
autorestart=true
startretries=3
startsecs=10
stopwaitsecs=20
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

60
src/alert/alertmanager/config/rule_files/README.md
View File

@@ -1,60 +0,0 @@
# 告警配置
> 参考：[自定义Prometheus告警规则](https://yunlzheng.gitbook.io/prometheus-book/parti-prometheus-ji-chu/alert/prometheus-alert-rule)
在Prometheus中配置告警的有两个步骤：
1. 写告警规则文件（rules文件）
2. 在promethues.yml里加载规则，并配置Alertmanager
## 1. 编写告警规则文件
告警规则如下：
```yml
groups:
- name: example-rules
interval: 30s # 每30秒评估一次
rules:
- alert: InstanceDown
expr: up == 0
for: 1m
labels:
severity: critical
annotations:
summary: "实例 {{ $labels.instance }} 已宕机"
description: "{{ $labels.instance }} 在 {{ $labels.job }} 中无响应超过 1 分钟。"
- alert: HighCpuUsage
expr: 100 - (avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
for: 5m
labels:
severity: warning
annotations:
summary: "CPU 使用率过高"
description: "实例 {{ $labels.instance }} CPU 使用率超过 80% 持续 5 分钟。"
```
其中：
- `alert`：告警规则的名称。
- `expr`：基于PromQL表达式告警触发条件，用于计算是否有时间序列满足该条件。
- `for`：评估等待时间，可选参数。用于表示只有当触发条件持续一段时间后才发送告警。在等待期间新产生告警的状态为pending。
- `labels`：自定义标签，允许用户指定要附加到告警上的一组附加标签，可以在Alertmanager中做路由和分组。
- `annotations`：用于指定一组附加信息，比如用于描述告警详细信息的文字等，annotations的内容在告警产生时会一同作为参数发送到Alertmanager。可以提供告警摘要和详细信息。
## 2. promothues.yml里引用
在prometheus.yml中加上`rule_files`和`alerting`:
```yml
global:
[ evaluation_interval: <duration> | default = 1m ]
rule_files:
[ - <filepath_glob> ... ]
alerting:
alertmanagers:
- static_configs:
- targets:
- "alertmanager.alert.argus.com:9093" # Alertmanager 地址
```

37
src/alert/alertmanager/config/rule_files/example_rules.yml
View File

@@ -1,37 +0,0 @@
groups:
- name: example-rules
interval: 30s # 每30秒评估一次
rules:
- alert: InstanceDown
expr: up == 0
for: 1m
labels:
severity: critical
annotations:
summary: "实例 {{ $labels.instance }} 已宕机"
description: "{{ $labels.instance }} 在 {{ $labels.job }} 中无响应超过 1 分钟。"
- alert: HighCpuUsage
expr: 100 - (avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
for: 5m
labels:
severity: warning
annotations:
summary: "CPU 使用率过高"
description: "实例 {{ $labels.instance }} CPU 使用率超过 80% 持续 5 分钟。"
- alert: HighMemoryUsage
expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100 > 80
for: 5m
labels:
severity: warning
annotations:
summary: "内存使用率过高"
description: "实例 {{ $labels.instance }} 内存使用率超过 80% 持续 5 分钟。"
- alert: DiskSpaceLow
expr: (node_filesystem_size_bytes{fstype!~"tmpfs|overlay"} - node_filesystem_free_bytes{fstype!~"tmpfs|overlay"}) / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"} * 100 > 90
for: 10m
labels:
severity: warning
annotations:
summary: "磁盘空间不足"
description: "实例 {{ $labels.instance }} 磁盘空间不足超过 90% 持续 10 分钟。"

5
src/alert/tests/.env
View File

@@ -1,5 +0,0 @@
DATA_ROOT=/home/argus/tmp/private/argus
ARGUS_UID=1048
ARGUS_GID=1048
USE_INTRANET=false

5
src/alert/tests/.env.example
View File

@@ -1,5 +0,0 @@
DATA_ROOT=/home/argus/tmp/private/argus
ARGUS_UID=1048
ARGUS_GID=1048
USE_INTRANET=false

19
src/alert/tests/data/alertmanager/alertmanager.yml
View File

@@ -1,19 +0,0 @@
global:
resolve_timeout: 5m
route:
group_by: ['alertname', 'instance'] # 分组：相同 alertname + instance 的告警合并
group_wait: 30s # 第一个告警后，等 30s 看是否有同组告警一起发
group_interval: 5m # 同组告警变化后，至少 5 分钟再发一次
repeat_interval: 3h # 相同告警，3 小时重复提醒一次
receiver: 'null'
receivers:
- name: 'null'
inhibit_rules:
- source_match:
severity: 'critical' # critical 告警存在时
target_match:
severity: 'warning' # 抑制相同 instance 的 warning 告警
equal: ['instance']

0
src/alert/tests/data/alertmanager/nflog
View File

0
src/alert/tests/data/alertmanager/silences
View File

1
src/alert/tests/data/etc/alertmanager.alert.argus.com
View File

@@ -1 +0,0 @@
172.18.0.2

37
src/alert/tests/docker-compose.yml
View File

@@ -1,37 +0,0 @@
services:
alertmanager:
build:
context: ../../../
dockerfile: src/alert/alertmanager/build/Dockerfile
args:
ARGUS_UID: ${ARGUS_UID:-2133}
ARGUS_GID: ${ARGUS_GID:-2015}
USE_INTRANET: ${USE_INTRANET:-false}
image: argus-alertmanager:latest
container_name: argus-alertmanager
environment:
- ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
- ARGUS_UID=${ARGUS_UID:-2133}
- ARGUS_GID=${ARGUS_GID:-2015}
ports:
- "${ARGUS_PORT:-9093}:9093"
volumes:
- ${DATA_ROOT:-./data}/alert/alertmanager:/private/argus/alert/alertmanager
- ${DATA_ROOT:-./data}/etc:/private/argus/etc
networks:
- argus-debug-net
restart: unless-stopped
logging:
driver: "json-file"
options:
max-size: "10m"
max-file: "3"
networks:
argus-debug-net:
driver: bridge
name: argus-debug-net
volumes:
alertmanager_data:
driver: local

19
src/alert/tests/scripts/01_bootstrap.sh
View File

@@ -1,19 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
root="$(cd "$(dirname "${BASH_SOURCE[0]}")/../" && pwd)"
project_root="$(cd "$root/../../.." && pwd)"
source "$project_root/scripts/common/build_user.sh"
load_build_user
# 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 "$root/private/argus/alert/alertmanager"
mkdir -p "$root/private/argus/etc/"
# 设置数据目录权限
echo "[INFO] Setting permissions for data directories..."
chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/alert/alertmanager" 2>/dev/null || true
chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/etc" 2>/dev/null || true
echo "[INFO] Supervisor-based containers will manage their own scripts and configurations"

10
src/alert/tests/scripts/02_up.sh
View File

@@ -1,10 +0,0 @@
#!/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 alert-mvp up -d --remove-orphans
echo "[OK] 服务已启动：Alertmanager http://localhost:9093"

106
src/alert/tests/scripts/03_alertmanager_add_alert.sh
View File

@@ -1,106 +0,0 @@
#!/bin/bash
set -euo pipefail
# ==========================================================
# Alertmanager 测试脚本
# ==========================================================
ALERTMANAGER_URL="http://localhost:9093"
TEST_ALERT_NAME_CRITICAL="NodeDown"
TEST_ALERT_NAME_WARNING="HighCPU"
TMP_LOG="/tmp/test-alertmanager.log"
# 等待参数
am_wait_attempts=30
am_wait_interval=2
GREEN="\033[1;32m"
RED="\033[1;31m"
YELLOW="\033[1;33m"
RESET="\033[0m"
# ==========================================================
# 函数定义
# ==========================================================
wait_for_alertmanager() {
local attempt=1
echo "[INFO] 等待 Alertmanager 启动中..."
while (( attempt <= am_wait_attempts )); do
if curl -fsS "${ALERTMANAGER_URL}/api/v2/status" >/dev/null 2>&1; then
echo -e "${GREEN}[OK] Alertmanager 已就绪 (attempt=${attempt}/${am_wait_attempts})${RESET}"
return 0
fi
echo "[..] Alertmanager 尚未就绪 (${attempt}/${am_wait_attempts})"
sleep "${am_wait_interval}"
(( attempt++ ))
done
echo -e "${RED}[ERROR] Alertmanager 在 ${am_wait_attempts} 次尝试后仍未就绪${RESET}"
return 1
}
log_step() {
echo -e "${YELLOW}==== $1 ====${RESET}"
}
# ==========================================================
# 主流程
# ==========================================================
log_step "测试 Alertmanager 开始"
echo "[INFO] Alertmanager 地址: $ALERTMANAGER_URL"
# Step 1: 等待 Alertmanager 启动
wait_for_alertmanager
# Step 2: 触发一个critical测试告警
echo "[INFO] 发送critical测试告警..."
curl -fsS -X POST "${ALERTMANAGER_URL}/api/v2/alerts" \
-H "Content-Type: application/json" \
-d '[
{
"labels": {
"alertname": "'"${TEST_ALERT_NAME_CRITICAL}"'",
"instance": "node-1",
"severity": "critical"
},
"annotations": {
"summary": "节点 node-1 宕机"
}
}
]' \
-o "$TMP_LOG"
if [ $? -eq 0 ]; then
echo -e "${GREEN}[OK] 已成功发送critical测试告警${RESET}"
else
echo -e "${RED}[ERROR] critical告警发送失败！${RESET}"
cat "$TMP_LOG"
exit 1
fi
# Step 3: 触发一个warning测试告警
echo "[INFO] 发送warning测试告警..."
curl -fsS -X POST "${ALERTMANAGER_URL}/api/v2/alerts" \
-H "Content-Type: application/json" \
-d '[
{
"labels": {
"alertname": "'"${TEST_ALERT_NAME_WARNING}"'",
"instance": "node-1",
"severity": "warning"
},
"annotations": {
"summary": "节点 node-1 CPU 使用率过高"
}
}
]' \
-o "$TMP_LOG"
if [ $? -eq 0 ]; then
echo -e "${GREEN}[OK] 已成功发送warning测试告警${RESET}"
else
echo -e "${RED}[ERROR] warning告警发送失败！${RESET}"
cat "$TMP_LOG"
exit 1
fi

71
src/alert/tests/scripts/04_query_alerts.sh
View File

@@ -1,71 +0,0 @@
#!/bin/bash
set -euo pipefail
# ==========================================================
# Alertmanager 测试脚本（含启动等待）
# ==========================================================
ALERTMANAGER_URL="http://localhost:9093"
TEST_ALERT_NAME_CRITICAL="NodeDown"
TEST_ALERT_NAME_WARNING="HighCPU"
TMP_LOG="/tmp/test-alertmanager.log"
# 等待参数
am_wait_attempts=30
am_wait_interval=2
GREEN="\033[1;32m"
RED="\033[1;31m"
YELLOW="\033[1;33m"
RESET="\033[0m"
# ==========================================================
# 函数定义
# ==========================================================
wait_for_alertmanager() {
local attempt=1
echo "[INFO] 等待 Alertmanager 启动中..."
while (( attempt <= am_wait_attempts )); do
if curl -fsS "${ALERTMANAGER_URL}/api/v2/status" >/dev/null 2>&1; then
echo -e "${GREEN}[OK] Alertmanager 已就绪 (attempt=${attempt}/${am_wait_attempts})${RESET}"
return 0
fi
echo "[..] Alertmanager 尚未就绪 (${attempt}/${am_wait_attempts})"
sleep "${am_wait_interval}"
(( attempt++ ))
done
echo -e "${RED}[ERROR] Alertmanager 在 ${am_wait_attempts} 次尝试后仍未就绪${RESET}"
return 1
}
log_step() {
echo -e "${YELLOW}==== $1 ====${RESET}"
}
# ==========================================================
# 主流程
# ==========================================================
log_step "查询 Alertmanager 当前告警列表开始"
echo "[INFO] Alertmanager 地址: $ALERTMANAGER_URL"
# Step 1: 等待 Alertmanager 启动
wait_for_alertmanager
# Step 2: 查询当前告警列表
echo "[INFO] 查询当前告警..."
sleep 1
curl -fsS "${ALERTMANAGER_URL}/api/v2/alerts" | jq '.' || {
echo -e "${RED}[WARN] 无法解析返回 JSON，请检查 jq 是否安装${RESET}"
curl -s "${ALERTMANAGER_URL}/api/v2/alerts"
}
# Step 3: 检查告警是否包含 NodeDown
if curl -fsS "${ALERTMANAGER_URL}/api/v2/alerts" | grep -q "${TEST_ALERT_NAME_CRITICAL}"; then
echo -e "${GREEN}✅ 测试通过：Alertmanager 已成功接收告警 ${TEST_ALERT_NAME_CRITICAL}${RESET}"
else
echo -e "${RED}❌ 测试失败：未检测到告警 ${TEST_ALERT_NAME_CRITICAL}${RESET}"
fi
log_step "测试结束"

21
src/alert/tests/scripts/05_down.sh
View File

@@ -1,21 +0,0 @@
#!/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
$compose_cmd -p alert-mvp down
echo "[OK] 已停止所有容器"
# 清理private目录内容
echo "[INFO] 清理private目录内容..."
cd "$(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

105
src/alert/tests/scripts/e2e_test.sh
View File

@@ -1,105 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
echo "======================================="
echo "ARGUS Alert System End-to-End Test"
echo "======================================="
echo ""
# 记录测试开始时间
test_start_time=$(date +%s)
# 函数：等待服务就绪
wait_for_services() {
echo "[INFO] Waiting for all services to be ready..."
local max_attempts=${SERVICE_WAIT_ATTEMPTS:-120}
local attempt=1
while [ $attempt -le $max_attempts ]; do
if curl -fs http://localhost:9093/api/v2/status >/dev/null 2>&1; then
echo "[OK] All services are ready!"
return 0
fi
echo " Waiting for services... ($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
# 发送告警数据
show_step "3" "Add alerts - Send test alerts to Alertmanager"
./scripts/03_alertmanager_add_alert.sh
verify_step "Send test alerts"
# 查询告警数据
show_step "4" "Verify data - Query Alertmanager"
./scripts/04_query_alerts.sh
verify_step "Data verification"
# 检查服务健康状态
show_step "Health" "Check service health"
echo "[INFO] Checking service health..."
# 检查 Alertmanager 状态
if curl -fs "http://localhost:9093/api/v2/status" >/dev/null 2>&1; then
am_status="available"
echo "✅ Alertmanager status: $am_status"
else
am_status="unavailable"
echo "⚠️ Alertmanager status: $am_status"
fi
verify_step "Service health check"
# 清理环境
show_step "5" "Cleanup - Stop all services"
./scripts/05_down.sh
verify_step "Service cleanup"
# 计算总测试时间
test_end_time=$(date +%s)
total_time=$((test_end_time - test_start_time))
echo ""
echo "======================================="
echo "🎉 END-TO-END TEST COMPLETED SUCCESSFULLY!"
echo "======================================="
echo "📊 Test Summary:"
echo " • Total time: ${total_time}s"
echo " • Alertmanager status: $am_status"
echo " • All services started and stopped successfully"
echo ""
echo "✅ The ARGUS Alert system is working correctly!"
echo ""

3
src/bind/build/dns-monitor.sh
View File

@@ -17,9 +17,6 @@ log_message() {
log_message "DNS监控脚本启动"
log_message "删除DNS备份文件（如果存在）"
rm -f $DNS_BACKUP
while true; do
if [ -f "$DNS_CONF" ]; then
if [ -f "$DNS_BACKUP" ]; then

9
src/metric/client-plugins/all-in-one-demo/scripts/check_health.sh
View File

@@ -4,15 +4,6 @@
set -e
# PID 文件检测，防止重复执行
PIDFILE="/var/run/check_health.pid"
if [ -f "$PIDFILE" ] && kill -0 $(cat "$PIDFILE") 2>/dev/null; then
echo "健康检查脚本已在运行中，跳过本次执行" >&2
exit 0
fi
echo $$ > "$PIDFILE"
trap "rm -f $PIDFILE" EXIT
# 获取脚本所在目录
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
HEALTH_LOG_FILE="$SCRIPT_DIR/.health_log"

164
src/metric/client-plugins/all-in-one-demo/scripts/install_artifact.sh
View File

@@ -200,22 +200,22 @@ parse_version_info() {
VERSION=$(grep '"version"' "$VERSION_FILE_PATH" | sed 's/.*"version": *"\([^"]*\)".*/\1/')
BUILD_TIME=$(grep '"build_time"' "$VERSION_FILE_PATH" | sed 's/.*"build_time": *"\([^"]*\)".*/\1/')
# 解析 artifact_list（跳过字段名本身）
grep -A 100 '"artifact_list"' "$VERSION_FILE_PATH" | grep -v '"artifact_list"' | grep -E '^\s*"[^"]+":\s*"[^"]+"' | while read line; do
# 解析 artifact_list
grep -A 100 '"artifact_list"' "$VERSION_FILE_PATH" | grep -E '^\s*"[^"]+":\s*"[^"]+"' | while read line; do
component=$(echo "$line" | sed 's/.*"\([^"]*\)":\s*"[^"]*".*/\1/')
version=$(echo "$line" | sed 's/.*"[^"]*":\s*"\([^"]*\)".*/\1/')
echo "$component:$version" >> "$TEMP_DIR/components.txt"
done
# 解析 checksums（跳过字段名本身）
grep -A 100 '"checksums"' "$VERSION_FILE_PATH" | grep -v '"checksums"' | grep -E '^\s*"[^"]+":\s*"[^"]+"' | while read line; do
# 解析 checksums
grep -A 100 '"checksums"' "$VERSION_FILE_PATH" | grep -E '^\s*"[^"]+":\s*"[^"]+"' | while read line; do
component=$(echo "$line" | sed 's/.*"\([^"]*\)":\s*"[^"]*".*/\1/')
checksum=$(echo "$line" | sed 's/.*"[^"]*":\s*"\([^"]*\)".*/\1/')
echo "$component:$checksum" >> "$TEMP_DIR/checksums.txt"
done
# 解析 install_order（跳过字段名本身，只取数组元素）
grep -A 100 '"install_order"' "$VERSION_FILE_PATH" | grep -v '"install_order"' | grep -E '^\s*"[^"]+"' | while read line; do
# 解析 install_order
grep -A 100 '"install_order"' "$VERSION_FILE_PATH" | grep -E '^\s*"[^"]+"' | while read line; do
component=$(echo "$line" | sed 's/.*"\([^"]*\)".*/\1/')
echo "$component" >> "$TEMP_DIR/install_order.txt"
done
@@ -317,30 +317,6 @@ create_install_dirs() {
log_success "安装目录创建完成: $INSTALL_DIR"
}
# 获取系统版本
get_system_version() {
if [[ ! -f /etc/os-release ]]; then
log_error "无法检测操作系统版本"
return 1
fi
source /etc/os-release
# 提取主版本号
case "$VERSION_ID" in
"20.04")
echo "ubuntu20"
;;
"22.04")
echo "ubuntu22"
;;
*)
log_warning "未识别的Ubuntu版本: $VERSION_ID，尝试使用ubuntu22"
echo "ubuntu22"
;;
esac
}
# 安装系统依赖包
install_system_deps() {
log_info "检查系统依赖包..."
@@ -354,43 +330,21 @@ install_system_deps() {
return 0
fi
# 获取系统版本对应的依赖目录
local system_version=$(get_system_version)
local version_deps_dir="$deps_dir/$system_version"
log_info "检测到系统版本: $system_version"
# 检查版本特定的依赖目录是否存在
if [[ ! -d "$version_deps_dir" ]]; then
log_warning "未找到 $system_version 版本的依赖目录: $version_deps_dir"
# 回退到旧的逻辑，检查根deps目录
# 检查是否有tar.gz文件
local deps_count=$(find "$deps_dir" -name "*.tar.gz" | wc -l)
if [[ $deps_count -eq 0 ]]; then
log_info "deps 目录中没有 tar.gz 文件，跳过系统依赖包安装"
return 0
fi
version_deps_dir="$deps_dir"
else
# 检查版本目录中是否有tar.gz文件
local deps_count=$(find "$version_deps_dir" -name "*.tar.gz" | wc -l)
if [[ $deps_count -eq 0 ]]; then
log_info "$system_version 版本目录中没有 tar.gz 文件，跳过系统依赖包安装"
return 0
fi
fi
log_info "找到 $system_version 版本的依赖包，开始安装..."
log_info "找到 $deps_count 个系统依赖包，开始安装..."
# 创建临时目录用于解压依赖包
local deps_temp_dir="${TEMP_DIR:-/tmp}/deps"
local deps_temp_dir="$TEMP_DIR/deps"
mkdir -p "$deps_temp_dir"
# 定义要检查的核心依赖
local CORE_DEPS=(jq cron curl)
local FAILED_DEPS=()
# 处理每个tar.gz文件
find "$version_deps_dir" -name "*.tar.gz" | while read tar_file; do
find "$deps_dir" -name "*.tar.gz" | while read tar_file; do
local tar_basename=$(basename "$tar_file")
local extract_name="${tar_basename%.tar.gz}"
@@ -408,61 +362,40 @@ install_system_deps() {
fi
# 进入解压目录，查找deb包
cd "$extract_dir" || continue
local deb_files=(*.deb)
if [[ ${#deb_files[@]} -gt 0 ]]; then
log_info " 找到 ${#deb_files[@]} 个 deb 包，开始安装..."
cd "$extract_dir"
local deb_count=$(find . -name "*.deb" | wc -l)
for deb in "${deb_files[@]}"; do
local pkg_name
pkg_name=$(dpkg-deb -f "$deb" Package 2>/dev/null)
if [[ $deb_count -gt 0 ]]; then
log_info " 找到 $deb_count 个 deb 包，开始安装..."
# 如果已安装，则跳过
if dpkg -s "$pkg_name" &>/dev/null; then
log_success " $pkg_name 已安装，跳过"
continue
fi
# 1. 先尝试安装所有deb包
log_info " 第1步：批量安装deb包..."
if dpkg -i *.deb 2>/dev/null; then
log_success " 所有deb包安装成功"
else
log_warning " 部分deb包安装失败，可能存在依赖问题"
# 尝试安装
log_info " 安装 $pkg_name..."
if DEBIAN_FRONTEND=noninteractive dpkg -i "$deb" &>/dev/null; then
log_success " $pkg_name 安装成功"
# 2. 使用apt-get修复依赖
log_info " 第2步：修复依赖关系..."
if apt-get install -f -y; then
log_success " 依赖关系修复完成"
else
log_warning " $pkg_name 安装失败，尝试修复依赖..."
if DEBIAN_FRONTEND=noninteractive apt-get install -f -y &>/dev/null; then
if dpkg -s "$pkg_name" &>/dev/null; then
log_success " $pkg_name 修复安装成功"
else
log_error " $pkg_name 仍未安装成功"
FAILED_DEPS+=("$pkg_name")
fi
else
log_error " $pkg_name 自动修复失败"
FAILED_DEPS+=("$pkg_name")
log_error " 依赖关系修复失败"
# 继续处理其他包，不退出
fi
fi
done
else
log_info " $tar_basename 中没有找到deb包，跳过"
fi
# 返回到依赖临时目录
cd "$deps_temp_dir" || continue
cd "$deps_temp_dir"
done
# 检查并启动 cron 服务
start_cron_service
# 总结安装结果
if [[ ${#FAILED_DEPS[@]} -gt 0 ]]; then
log_error "以下系统依赖未能成功安装，安装终止，请手动安装后重试："
for f in "${FAILED_DEPS[@]}"; do
echo " - $f"
done
exit 1
else
log_success "系统依赖包安装完成，全部就绪"
fi
log_success "系统依赖包安装完成"
}
# 启动 cron 服务
@@ -704,18 +637,6 @@ EOF
log_success "安装记录已创建: $install_record_file"
}
# 检查cron任务是否已存在
check_cron_task_exists() {
local task_pattern="$1"
local temp_cron="$2"
if grep -q "$task_pattern" "$temp_cron"; then
return 0 # 任务已存在
else
return 1 # 任务不存在
fi
}
# 设置健康检查定时任务
setup_health_check_cron() {
log_info "设置健康检查定时任务..."
@@ -740,7 +661,7 @@ setup_health_check_cron() {
crontab -l 2>/dev/null > "$temp_cron" || touch "$temp_cron"
# 检查并删除旧的健康检查任务
if check_cron_task_exists "check_health.sh" "$temp_cron"; then
if grep -q "check_health.sh" "$temp_cron"; then
log_info "发现旧的健康检查定时任务，正在更新..."
# 删除所有包含check_health.sh的行
grep -v "check_health.sh" "$temp_cron" > "$temp_cron.new"
@@ -795,7 +716,7 @@ setup_dns_sync_cron() {
crontab -l 2>/dev/null > "$temp_cron" || touch "$temp_cron"
# 检查并删除旧的 DNS 同步任务
if check_cron_task_exists "sync_dns.sh" "$temp_cron"; then
if grep -q "sync_dns.sh" "$temp_cron"; then
log_info "发现旧的 DNS 同步定时任务，正在更新..."
# 删除所有包含sync_dns.sh的行
grep -v "sync_dns.sh" "$temp_cron" > "$temp_cron.new"
@@ -803,15 +724,16 @@ setup_dns_sync_cron() {
log_info "旧的 DNS 同步定时任务已删除"
fi
# 添加新的定时任务（每1分钟执行一次）
# 添加新的定时任务（每30秒执行一次）
# 直接使用版本目录中的 DNS 同步脚本
echo "# Argus-Metrics DNS 同步定时任务" >> "$temp_cron"
echo "* * * * * $sync_dns_script >> $INSTALL_DIR/.dns_sync.log 2>&1" >> "$temp_cron"
echo "* * * * * sleep 30; $sync_dns_script >> $INSTALL_DIR/.dns_sync.log 2>&1" >> "$temp_cron"
# 安装新的crontab
if crontab "$temp_cron"; then
log_success "DNS 同步定时任务设置成功"
log_info " 执行频率: 每1分钟"
log_info " 执行频率: 每30秒"
log_info " 日志文件: $INSTALL_DIR/.dns_sync.log"
log_info " 查看定时任务: crontab -l"
log_info " 删除定时任务: crontab -e"
@@ -849,7 +771,7 @@ setup_version_check_cron() {
crontab -l > "$temp_cron" 2>/dev/null || touch "$temp_cron"
# 检查是否已存在版本校验定时任务
if check_cron_task_exists "check_version.sh" "$temp_cron"; then
if grep -q "check_version.sh" "$temp_cron"; then
log_info "发现旧的版本校验定时任务，正在更新..."
# 删除所有包含check_version.sh的行
grep -v "check_version.sh" "$temp_cron" > "$temp_cron.new"
@@ -902,7 +824,7 @@ setup_restart_cron() {
crontab -l > "$temp_cron" 2>/dev/null || touch "$temp_cron"
# 检查是否已存在自动重启定时任务
if check_cron_task_exists "restart_unhealthy.sh" "$temp_cron"; then
if grep -q "restart_unhealthy.sh" "$temp_cron"; then
log_info "发现旧的自动重启定时任务，正在更新..."
# 删除所有包含restart_unhealthy.sh的行
grep -v "restart_unhealthy.sh" "$temp_cron" > "$temp_cron.new"
@@ -963,9 +885,9 @@ main() {
check_system
find_version_file
create_install_dirs
install_system_deps
parse_version_info
verify_checksums
install_system_deps
install_components
copy_config_files
create_install_record
@@ -973,20 +895,6 @@ main() {
setup_dns_sync_cron
setup_version_check_cron
setup_restart_cron
# 注释掉立即执行健康检查，避免与cron任务重复执行
# log_info "立即执行一次健康检查..."
# local check_health_script="$INSTALL_DIR/check_health.sh"
# if [[ -f "$check_health_script" ]]; then
# if "$check_health_script" >> "$INSTALL_DIR/.health_check.log" 2>&1; then
# log_success "健康检查执行完成"
# else
# log_warning "健康检查执行失败，请检查日志: $INSTALL_DIR/.health_check.log"
# fi
# else
# log_warning "健康检查脚本不存在: $check_health_script"
# fi
show_install_info
}

73
src/metric/client-plugins/all-in-one-demo/scripts/publish_artifact.sh
View File

@@ -29,68 +29,26 @@ log_error() {
show_help() {
echo "Argus-Metric Artifact 发布脚本"
echo
echo "用法: $0 <版本号> [选项]"
echo "用法: $0 <版本号>"
echo
echo "参数:"
echo " <版本号> 要发布的版本号，对应 artifact 目录中的版本"
echo
echo "选项:"
echo " --output-dir <路径> 指定输出目录 (默认: /private/argus/ftp/share/)"
echo " --owner <uid:gid> 指定文件所有者 (默认: 2133:2015)"
echo " -h, --help 显示此帮助信息"
echo
echo "示例:"
echo " $0 1.20.0 # 使用默认配置发布"
echo " $0 1.20.0 --output-dir /tmp/publish # 指定输出目录"
echo " $0 1.20.0 --owner 1000:1000 # 指定文件所有者"
echo " $0 1.20.0 --output-dir /srv/ftp --owner root:root # 同时指定两者"
echo " $0 1.20.0 # 发布 1.20.0 版本"
echo
}
# 默认配置
DEFAULT_PUBLISH_DIR="/private/argus/ftp/share/"
DEFAULT_OWNER="2133:2015"
# 解析参数
VERSION=""
PUBLISH_DIR="$DEFAULT_PUBLISH_DIR"
OWNER="$DEFAULT_OWNER"
while [[ $# -gt 0 ]]; do
case $1 in
-h|--help)
show_help
exit 0
;;
--output-dir)
PUBLISH_DIR="$2"
shift 2
;;
--owner)
OWNER="$2"
shift 2
;;
*)
if [[ -z "$VERSION" ]]; then
VERSION="$1"
shift
else
log_error "未知参数: $1"
show_help
exit 1
fi
;;
esac
done
# 检查版本号是否提供
if [[ -z "$VERSION" ]]; then
# 检查参数
if [[ $# -ne 1 ]]; then
log_error "请提供版本号参数"
show_help
exit 1
fi
VERSION="$1"
ARTIFACT_DIR="artifact/$VERSION"
PUBLISH_DIR="/Users/sundapeng/Project/nlp/aiops/client-plugins/all-in-one/publish/"
# 检查版本目录是否存在
if [[ ! -d "$ARTIFACT_DIR" ]]; then
@@ -99,12 +57,10 @@ if [[ ! -d "$ARTIFACT_DIR" ]]; then
fi
log_info "开始发布版本: $VERSION"
log_info "输出目录: $PUBLISH_DIR"
log_info "文件所有者: $OWNER"
# 确保发布目录存在
log_info "确保发布目录存在: $PUBLISH_DIR"
sudo mkdir -p "$PUBLISH_DIR"
mkdir -p "$PUBLISH_DIR"
# 创建临时目录用于打包
TEMP_PACKAGE_DIR="/tmp/argus-metric-package-$$"
@@ -208,26 +164,20 @@ fi
TAR_NAME="argus-metric_$(echo $VERSION | tr '.' '_').tar.gz"
log_info "创建发布包: $TAR_NAME"
cd "$TEMP_PACKAGE_DIR"
sudo tar -czf "$PUBLISH_DIR/$TAR_NAME" *
tar -czf "$PUBLISH_DIR/$TAR_NAME" *
cd - > /dev/null
# 设置文件所有者
log_info "设置文件所有者为: $OWNER"
sudo chown "$OWNER" "$PUBLISH_DIR/$TAR_NAME"
# 清理临时目录
rm -rf "$TEMP_PACKAGE_DIR"
# 更新 LATEST_VERSION 文件
log_info "更新 LATEST_VERSION 文件..."
echo "$VERSION" | sudo tee "$PUBLISH_DIR/LATEST_VERSION" > /dev/null
sudo chown "$OWNER" "$PUBLISH_DIR/LATEST_VERSION"
echo "$VERSION" > "$PUBLISH_DIR/LATEST_VERSION"
# 复制 DNS 配置文件到发布目录根目录（直接从 config 目录复制）
if [[ -f "config/dns.conf" ]]; then
log_info "复制 DNS 配置文件到发布目录根目录..."
sudo cp "config/dns.conf" "$PUBLISH_DIR/"
sudo chown "$OWNER" "$PUBLISH_DIR/dns.conf"
cp "config/dns.conf" "$PUBLISH_DIR/"
log_success "DNS 配置文件复制完成: $PUBLISH_DIR/dns.conf"
else
log_warning "未找到 config/dns.conf 文件，跳过 DNS 配置文件复制"
@@ -236,8 +186,7 @@ fi
# 复制 setup.sh 到发布目录
if [[ -f "scripts/setup.sh" ]]; then
log_info "复制 setup.sh 到发布目录..."
sudo cp "scripts/setup.sh" "$PUBLISH_DIR/"
sudo chown "$OWNER" "$PUBLISH_DIR/setup.sh"
cp "scripts/setup.sh" "$PUBLISH_DIR/"
fi
# 显示发布结果

9
src/metric/client-plugins/all-in-one-demo/scripts/restart_unhealthy.sh
View File

@@ -2,15 +2,6 @@
# 此脚本会检查各组件的健康状态，并重启不健康的组件
# PID 文件检测，防止重复执行
PIDFILE="/var/run/restart_unhealthy.pid"
if [ -f "$PIDFILE" ] && kill -0 $(cat "$PIDFILE") 2>/dev/null; then
echo "自动重启脚本已在运行中，跳过本次执行" >&2
exit 0
fi
echo $$ > "$PIDFILE"
trap "rm -f $PIDFILE" EXIT
# 获取脚本所在目录
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
INSTALL_RECORD_FILE="$SCRIPT_DIR/.install_record"

287
src/metric/client-plugins/all-in-one-demo/scripts/sync_dns.sh
View File

@@ -1,143 +1,244 @@
#!/bin/bash
# DNS 同步脚本
# 比较 FTP 根目录的 dns.conf 和本地的 dns.conf，如果有变化则同步到 /etc/resolv.conf
set -e
# 颜色
RED='\033[0;31m'; GREEN='\033[0;32m'; YELLOW='\033[1;33m'; BLUE='\033[0;34m'; NC='\033[0m'
# 颜色定义
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color
# 日志函数
log_info() { echo -e "${BLUE}[INFO]${NC} $1" >&2; }
log_success() { echo -e "${GREEN}[SUCCESS]${NC} $1" >&2; }
log_warning() { echo -e "${YELLOW}[WARNING]${NC} $1" >&2; }
log_error() { echo -e "${RED}[ERROR]${NC} $1" >&2; }
# 日志函数 - 输出到 stderr 避免影响函数返回值
log_info() {
echo -e "${BLUE}[INFO]${NC} $1" >&2
}
log_success() {
echo -e "${GREEN}[SUCCESS]${NC} $1" >&2
}
log_warning() {
echo -e "${YELLOW}[WARNING]${NC} $1" >&2
}
log_error() {
echo -e "${RED}[ERROR]${NC} $1" >&2
}
# 获取脚本所在目录
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
LOCAL_DNS_CONF="/opt/argus-metric/dns.conf"
RESOLV_CONF="/etc/resolv.conf"
ALT_RESOLV_CONF="/run/resolv.conf"
LOG_FILE="/opt/argus-metric/.dns_sync.log"
REMOTE_DNS_CONF_URL=""
RESOLV_CONF="/etc/resolv.conf"
LOG_FILE="/opt/argus-metric/.dns_sync.log"
# 获取 FTP 配置
# 从环境变量或配置文件获取 FTP 服务器信息
get_ftp_config() {
# 优先从环境变量获取配置
log_info "获取 FTP 配置信息..."
# 如果环境变量中没有设置，则尝试从配置文件读取
if [[ -z "$FTP_SERVER" || -z "$FTP_USER" || -z "$FTP_PASSWORD" ]]; then
[[ -f "$SCRIPT_DIR/config.env" ]] && source "$SCRIPT_DIR/config.env"
local config_file="$SCRIPT_DIR/config.env"
if [[ -f "$config_file" ]]; then
log_info "从配置文件读取 FTP 配置: $config_file"
source "$config_file"
fi
else
log_info "使用环境变量中的 FTP 配置"
fi
# 设置默认值（如果环境变量和配置文件都没有设置）
FTP_SERVER="${FTP_SERVER:-localhost}"
FTP_USER="${FTP_USER:-ftpuser}"
FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
# 构建远程 DNS 配置文件 URL
REMOTE_DNS_CONF_URL="ftp://${FTP_USER}:${FTP_PASSWORD}@${FTP_SERVER}/dns.conf"
log_info "FTP 配置来源: ${FTP_CONFIG_SOURCE:-环境变量/配置文件}"
}
# 下载远程 dns.conf
# 下载远程 DNS 配置文件
download_remote_dns_conf() {
local tmp="/tmp/dns.remote.$$"
local temp_file="/tmp/dns.conf.remote.$$"
log_info "从 FTP 服务器下载 DNS 配置文件..."
log_info "远程地址: $REMOTE_DNS_CONF_URL"
log_info "FTP 服务器: $FTP_SERVER"
log_info "FTP 用户: $FTP_USER"
# 先测试 FTP 连接
log_info "测试 FTP 连接..."
if ! curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/" >/dev/null; then
log_error "无法连接到 FTP 服务器: $FTP_SERVER"; return 1
fi
if ! curl -u "${FTP_USER}:${FTP_PASSWORD}" -sf "ftp://${FTP_SERVER}/dns.conf" -o "$tmp" 2>/dev/null; then
log_error "下载 dns.conf 失败"; rm -f "$tmp"; return 1
fi
echo "$tmp"
}
# 文件比较
compare_files() { diff -q "$1" "$2" >/dev/null 2>&1; }
# 从 dns.conf 提取有效 IP
get_dns_ips() {
grep -Eo '^[0-9]{1,3}(\.[0-9]{1,3}){3}$' "$1" | sort -u
}
# 安全更新 resolv.conf（保留符号链接）
update_resolv_conf() {
local dns_conf="$1"
local dns_ips
mapfile -t dns_ips < <(get_dns_ips "$dns_conf")
[[ ${#dns_ips[@]} -eq 0 ]] && { log_warning "未检测到有效 DNS"; return; }
local target_file="$RESOLV_CONF"
if [[ ! -w "$RESOLV_CONF" ]]; then
log_warning "/etc/resolv.conf 不可写，使用兜底路径 $ALT_RESOLV_CONF"
target_file="$ALT_RESOLV_CONF"
fi
local temp="/tmp/resolv.new.$$"
cp "$target_file" "${target_file}.backup.$(date +%Y%m%d_%H%M%S)" 2>/dev/null || true
log_info "更新 DNS 配置文件: $target_file"
# 写入新的 nameserver 行
for ip in "${dns_ips[@]}"; do
echo "nameserver $ip"
done >"$temp"
# 追加原内容（去掉重复 nameserver）
grep -v '^nameserver' "$target_file" >>"$temp" 2>/dev/null || true
awk '!a[$0]++' "$temp" >"${temp}.uniq"
# ⚙️ 使用 cat 原地覆盖，避免 mv 引发 “设备忙”
if cat "${temp}.uniq" >"$target_file" 2>/dev/null; then
chmod 644 "$target_file"
log_success "DNS 更新完成: ${dns_ips[*]}"
if curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/" >/dev/null 2>&1; then
log_success "FTP 服务器连接成功"
else
log_error "无法写入 $target_file，可能被系统锁定"
log_error "无法连接到 FTP 服务器: $FTP_SERVER"
log_error "请检查:"
log_error " 1. FTP 服务器是否运行"
log_error " 2. 网络连接是否正常"
log_error " 3. 服务器地址是否正确"
return 1
fi
rm -f "$temp" "${temp}.uniq"
}
# 检查 resolv.conf 是否包含 dns.conf 内容
ensure_dns_in_resolv() {
local dns_conf="$1"
local dns_ips
mapfile -t dns_ips < <(get_dns_ips "$dns_conf")
[[ ${#dns_ips[@]} -eq 0 ]] && return
for ip in "${dns_ips[@]}"; do
if ! grep -q "nameserver $ip" "$RESOLV_CONF" 2>/dev/null; then
log_warning "检测到 /etc/resolv.conf 缺少 $ip，执行兜底修复"
update_resolv_conf "$dns_conf"
return
# 测试 dns.conf 文件是否存在
log_info "检查远程 dns.conf 文件是否存在..."
if curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/dns.conf" >/dev/null 2>&1; then
log_success "远程 dns.conf 文件存在"
else
log_error "远程 dns.conf 文件不存在或无法访问"
log_error "请检查 FTP 服务器根目录下是否有 dns.conf 文件"
return 1
fi
# 尝试下载文件
log_info "开始下载 dns.conf 文件..."
if curl -u "${FTP_USER}:${FTP_PASSWORD}" -sf "ftp://${FTP_SERVER}/dns.conf" -o "$temp_file" 2>/dev/null; then
log_success "远程 DNS 配置文件下载成功"
echo "$temp_file"
else
log_error "下载 dns.conf 文件失败"
log_error "尝试手动测试命令:"
log_error " curl -u ${FTP_USER}:${FTP_PASSWORD} ftp://${FTP_SERVER}/dns.conf"
rm -f "$temp_file"
return 1
fi
done
log_info "/etc/resolv.conf 已包含所有 DNS"
}
log_sync() { echo "[$(date '+%F %T')] $1" >>"$LOG_FILE"; }
# 比较两个文件是否相同
compare_files() {
local file1="$1"
local file2="$2"
if [[ ! -f "$file1" || ! -f "$file2" ]]; then
return 1
fi
# 使用 diff 比较文件内容
if diff -q "$file1" "$file2" >/dev/null 2>&1; then
return 0 # 文件相同
else
return 1 # 文件不同
fi
}
# 将 DNS 配置追加到 /etc/resolv.conf
update_resolv_conf() {
local dns_conf_file="$1"
log_info "更新 /etc/resolv.conf 文件..."
# 备份原始文件
if [[ -f "$RESOLV_CONF" ]]; then
cp "$RESOLV_CONF" "${RESOLV_CONF}.backup.$(date +%Y%m%d_%H%M%S)"
log_info "已备份原始 resolv.conf 文件"
fi
# 读取 DNS 配置文件并追加到 resolv.conf
while IFS= read -r line; do
# 跳过空行和注释行
[[ -z "$line" || "$line" =~ ^[[:space:]]*# ]] && continue
# 验证是否为有效的 IP 地址
if [[ "$line" =~ ^[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}$ ]]; then
# 检查是否已存在相同的 nameserver 行
if ! grep -q "nameserver $line" "$RESOLV_CONF" 2>/dev/null; then
echo "nameserver $line" >> "$RESOLV_CONF"
log_info "添加 DNS 服务器: $line"
else
log_info "DNS 服务器已存在，跳过: $line"
fi
else
log_warning "跳过无效的 DNS 地址: $line"
fi
done < "$dns_conf_file"
# 设置文件权限
chmod 644 "$RESOLV_CONF"
log_success "/etc/resolv.conf 文件更新完成"
}
# 记录同步日志
log_sync() {
local message="$1"
local timestamp=$(date '+%Y-%m-%d %H:%M:%S')
echo "[$timestamp] $message" >> "$LOG_FILE"
}
# 主函数
main() {
log_info "开始 DNS 同步检查..."
mkdir -p /opt/argus-metric
log_sync "DNS 同步检查开始"
# 确保系统目录存在
mkdir -p "/opt/argus-metric"
# 获取 FTP 配置
get_ftp_config
local remote_file
if ! remote_file=$(download_remote_dns_conf); then
log_error "下载失败"; log_sync "同步失败"; exit 1
fi
# 检查本地 DNS 配置文件是否存在
if [[ ! -f "$LOCAL_DNS_CONF" ]]; then
log_info "本地 dns.conf 不存在，初始化..."
log_warning "本地 DNS 配置文件不存在: $LOCAL_DNS_CONF"
log_warning "将下载远程配置文件并更新系统 DNS 设置"
# 下载远程配置文件
if remote_file=$(download_remote_dns_conf); then
# 复制到本地
cp "$remote_file" "$LOCAL_DNS_CONF"
log_success "远程 DNS 配置文件已保存到本地"
# 更新 resolv.conf
update_resolv_conf "$LOCAL_DNS_CONF"
log_sync "首次同步完成"
log_sync "首次同步完成，DNS 配置已更新"
# 清理临时文件
rm -f "$remote_file"
else
log_error "无法下载远程 DNS 配置文件，同步失败"
log_sync "同步失败：无法下载远程配置文件"
exit 1
fi
else
log_info "本地 DNS 配置文件存在: $LOCAL_DNS_CONF"
# 下载远程配置文件进行比较
if remote_file=$(download_remote_dns_conf); then
# 比较文件
if compare_files "$LOCAL_DNS_CONF" "$remote_file"; then
log_info "dns.conf 无变化"
ensure_dns_in_resolv "$LOCAL_DNS_CONF"
log_sync "dns.conf 无变化，执行兜底检查"
log_info "DNS 配置文件无变化，无需更新"
log_sync "DNS 配置文件无变化"
else
log_info "检测到 DNS 配置更新"
log_info "检测到 DNS 配置文件有变化，开始同步..."
log_sync "检测到 DNS 配置文件变化，开始同步"
# 更新本地配置文件
cp "$remote_file" "$LOCAL_DNS_CONF"
log_success "本地 DNS 配置文件已更新"
# 更新 resolv.conf
update_resolv_conf "$LOCAL_DNS_CONF"
log_sync "DNS 配置同步完成"
fi
# 清理临时文件
rm -f "$remote_file"
else
log_error "无法下载远程 DNS 配置文件，跳过本次同步"
log_sync "同步失败：无法下载远程配置文件"
exit 1
fi
fi
rm -f "$remote_file"
log_success "DNS 同步流程完成"
log_success "DNS 同步检查完成"
log_sync "DNS 同步检查完成"
}
# 脚本入口
if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
main "$@"
fi

19
src/metric/ftp/build/Dockerfile
View File

@@ -31,26 +31,25 @@ RUN mkdir -p /var/log/supervisor
ENV FTP_BASE_PATH=/private/argus/ftp
# 设置域名环境变量
ENV DOMAIN=ftp.metric.argus.com
ENV DOMAIN=prom.ftp.argus.com
# 设置FTP用户密码环境变量
ENV FTP_PASSWORD=ZGClab1234!
# 设置用户和组ID环境变量
ARG ARGUS_BUILD_UID=2133
ARG ARGUS_BUILD_GID=2015
ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
ARG FTP_UID=2133
ARG FTP_GID=2015
ENV FTP_UID=${FTP_UID}
ENV FTP_GID=${FTP_GID}
# 创建FTP用户和目录结构
RUN groupadd -g ${ARGUS_BUILD_GID} ftpuser && \
useradd -u ${ARGUS_BUILD_UID} -g ${ARGUS_BUILD_GID} -d ${FTP_BASE_PATH}/share -s /bin/bash ftpuser && \
RUN groupadd -g ${FTP_GID} ftpuser && \
useradd -u ${FTP_UID} -g ${FTP_GID} -d ${FTP_BASE_PATH}/share -s /bin/bash ftpuser && \
mkdir -p ${FTP_BASE_PATH}/share \
&& mkdir -p /private/argus/etc \
&& mkdir -p /var/log/vsftpd \
&& chown -R ftpuser:ftpuser ${FTP_BASE_PATH} \
&& mkdir -p /var/run/vsftpd/empty
&& mkdir -p /var/run/vsftpd/empty \
&& chown -R ftpuser:ftpuser ${FTP_BASE_PATH}
# 创建vsftpd配置目录和用户列表文件
RUN mkdir -p /etc/vsftpd && \

3
src/metric/ftp/build/start-ftp-supervised.sh
View File

@@ -32,9 +32,6 @@ IP=$(ifconfig eth0 | awk '/inet /{print $2}' || hostname -i)
echo "current IP: ${IP}"
echo "${IP}" > /private/argus/etc/${DOMAIN}
chown ${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID} /private/argus/etc/${DOMAIN}
chmod +x /private/argus/etc/${DOMAIN}
# 启动vsftpd
echo "[INFO] Starting vsftpd..."
exec /usr/sbin/vsftpd /tmp/vsftpd.conf

31
src/metric/grafana/build/Dockerfile
View File

@@ -17,31 +17,30 @@ RUN mkdir -p /var/log/supervisor
ENV GRAFANA_BASE_PATH=/private/argus/metric/grafana
# 设置用户和组ID环境变量
ARG ARGUS_BUILD_UID=2133
ARG ARGUS_BUILD_GID=2015
ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
ARG GRAFANA_UID=2133
ARG GRAFANA_GID=2015
ENV GRAFANA_UID=${GRAFANA_UID}
ENV GRAFANA_GID=${GRAFANA_GID}
# 创建基本目录结构
RUN mkdir -p /private/argus/etc \
&& mkdir -p ${GRAFANA_BASE_PATH}/data \
&& mkdir -p ${GRAFANA_BASE_PATH}/logs \
&& mkdir -p ${GRAFANA_BASE_PATH}/plugins \
&& mkdir -p ${GRAFANA_BASE_PATH}/provisioning/datasources \
&& mkdir -p ${GRAFANA_BASE_PATH}/provisioning/dashboards \
&& mkdir -p ${GRAFANA_BASE_PATH}/data/sessions \
&& mkdir -p ${GRAFANA_BASE_PATH}/data/dashboards \
&& mkdir -p ${GRAFANA_BASE_PATH}/config \
&& mkdir -p /private/argus/metric/grafana/data \
&& mkdir -p /private/argus/metric/grafana/logs \
&& mkdir -p /private/argus/metric/grafana/plugins \
&& mkdir -p /private/argus/metric/grafana/provisioning/datasources \
&& mkdir -p /private/argus/metric/grafana/provisioning/dashboards \
&& mkdir -p /private/argus/metric/grafana/data/sessions \
&& mkdir -p /private/argus/metric/grafana/data/dashboards \
&& mkdir -p /private/argus/metric/grafana/config \
&& mkdir -p /etc/grafana \
&& mkdir -p /var/lib/grafana \
&& mkdir -p /var/log/grafana
# 修改 Grafana 用户 UID/GID 并授权
RUN deluser grafana && \
addgroup -g ${ARGUS_BUILD_GID} grafana && \
adduser -u ${ARGUS_BUILD_UID} -G grafana -s /bin/sh -D grafana && \
chown -R grafana:grafana /var/lib/grafana /etc/grafana /var/log/grafana ${GRAFANA_BASE_PATH}
addgroup -g ${GRAFANA_GID} grafana && \
adduser -u ${GRAFANA_UID} -G grafana -s /bin/sh -D grafana && \
chown -R grafana:grafana /var/lib/grafana /etc/grafana /var/log/grafana /private/argus
# 复制配置文件到容器内临时位置
COPY grafana.ini /tmp/grafana.ini

570
src/metric/grafana/build/dashboards/default_cluster_dashboard.json
View File

@@ -1,570 +0,0 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 3,
"links": [],
"panels": [
{
"datasource": "prometheus",
"fieldConfig": {
"defaults": {
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 8,
"x": 0,
"y": 0
},
"id": 1,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"mean"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.1.0",
"targets": [
{
"expr": "100 * (1 - avg(rate(node_cpu_seconds_total{mode='idle'}[5m])))",
"refId": "A"
}
],
"title": "CPU 平均利用率（%）",
"type": "stat"
},
{
"datasource": "prometheus",
"fieldConfig": {
"defaults": {
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 8,
"x": 8,
"y": 0
},
"id": 2,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"mean"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.1.0",
"targets": [
{
"expr": "avg(1 - ((node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) / node_memory_MemTotal_bytes)) * 100",
"refId": "A"
}
],
"title": "内存平均利用率（%）",
"type": "stat"
},
{
"datasource": "prometheus",
"fieldConfig": {
"defaults": {
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 8,
"x": 16,
"y": 0
},
"id": 4,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"last"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.1.0",
"targets": [
{
"expr": "count(count by(hostname) (up{job='node'} == 1))",
"refId": "A"
}
],
"title": "节点在线数",
"type": "stat"
},
{
"datasource": "prometheus",
"fieldConfig": {
"defaults": {
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 6,
"x": 0,
"y": 5
},
"id": 6,
"options": {
"minVizHeight": 75,
"minVizWidth": 75,
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"sizing": "auto"
},
"pluginVersion": "11.1.0",
"targets": [
{
"expr": "avg by (hostname) (DCGM_FI_DEV_GPU_UTIL)",
"refId": "A"
}
],
"title": "GPU 平均利用率 (%)",
"type": "gauge"
},
{
"datasource": "prometheus",
"fieldConfig": {
"defaults": {
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 6,
"x": 6,
"y": 5
},
"id": 12,
"options": {
"minVizHeight": 75,
"minVizWidth": 75,
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"sizing": "auto"
},
"pluginVersion": "11.1.0",
"targets": [
{
"expr": "round(avg(DCGM_FI_DEV_FB_USED{job='dcgm'}/(DCGM_FI_DEV_FB_USED{job='dcgm'} + DCGM_FI_DEV_FB_FREE{job='dcgm'})) * 100)",
"refId": "A"
}
],
"title": "显存平均利用率 (%)",
"type": "gauge"
},
{
"datasource": "prometheus",
"fieldConfig": {
"defaults": {
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 6,
"x": 12,
"y": 5
},
"id": 7,
"options": {
"minVizHeight": 75,
"minVizWidth": 75,
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"sizing": "auto"
},
"pluginVersion": "11.1.0",
"targets": [
{
"expr": "avg by (hostname) (DCGM_FI_DEV_GPU_TEMP)",
"refId": "A"
}
],
"title": "GPU 温度 (℃)",
"type": "gauge"
},
{
"datasource": "prometheus",
"fieldConfig": {
"defaults": {
"mappings": [],
"max": 300,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "orange",
"value": 200
},
{
"color": "red",
"value": 300
}
]
},
"unit": "watt"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 6,
"x": 18,
"y": 5
},
"id": 8,
"options": {
"minVizHeight": 75,
"minVizWidth": 75,
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": true,
"showThresholdMarkers": true,
"sizing": "auto"
},
"pluginVersion": "11.1.0",
"targets": [
{
"expr": "avg by (hostname) (DCGM_FI_DEV_POWER_USAGE)",
"refId": "A"
}
],
"title": "GPU 平均实时功耗 (W)",
"type": "gauge"
},
{
"datasource": "prometheus",
"fieldConfig": {
"defaults": {
"custom": {
"align": "center",
"cellOptions": {
"type": "auto"
},
"inspect": false
},
"decimals": 1,
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 12,
"w": 24,
"x": 0,
"y": 11
},
"id": 11,
"options": {
"cellHeight": "sm",
"cellLinks": [
{
"title": "跳转至节点详情",
"url": "http://127.0.0.1:3000/d/node_gpu_metrics/node-and-gpu-metrics?orgId=1&refresh=15s&var-hostname=${__data.fields.hostname}"
}
],
"footer": {
"countRows": false,
"fields": "",
"reducer": [
"sum"
],
"show": false
},
"showHeader": true,
"sortBy": [
{
"desc": true,
"displayName": "GPU 使用率"
}
]
},
"pluginVersion": "11.1.0",
"targets": [
{
"expr": "up{job=\"dcgm\"} + on(hostname) group_left(ip, node_id) up{job=\"dcgm\"}*0",
"format": "table",
"instant": true,
"refId": "node_info"
},
{
"expr": "round(100 - avg by(hostname)(rate(node_cpu_seconds_total{job=\"node\",mode=\"idle\"}[5m])) * 100, 0.1)",
"format": "table",
"instant": true,
"refId": "CPU"
},
{
"expr": "round((1 - avg by(hostname)(node_memory_MemAvailable_bytes{job=\"node\"} / node_memory_MemTotal_bytes{job=\"node\"})) * 100, 0.1)",
"format": "table",
"instant": true,
"refId": "MEM"
},
{
"expr": "round(avg by(hostname)(DCGM_FI_DEV_GPU_UTIL{job=\"dcgm\"}), 0.1)",
"format": "table",
"instant": true,
"refId": "GPU_UTIL"
},
{
"expr": "round(avg by(hostname)(DCGM_FI_DEV_FB_USED{job=\"dcgm\"} / (DCGM_FI_DEV_FB_USED{job=\"dcgm\"} + DCGM_FI_DEV_FB_FREE{job=\"dcgm\"}) * 100), 0.1)",
"format": "table",
"instant": true,
"refId": "GPU_MEM"
}
],
"title": "节点列表（CPU / 内存 / GPU）",
"transformations": [
{
"id": "seriesToColumns",
"options": {
"byField": "hostname"
}
},
{
"id": "organize",
"options": {
"excludeByName": {
"Time": true,
"Value #node_info": true,
"hostname_1": true,
"hostname_2": true,
"hostname_3": true,
"instance": true,
"ip_1": true,
"job": true,
"node_id_1": true
},
"indexByName": {
"CPU 使用率": 3,
"GPU 使用率": 5,
"GPU 显存占用": 6,
"IP 地址": 1,
"主机名": 0,
"内存使用率": 4,
"节点 ID": 2
},
"renameByName": {
"Value #CPU": "CPU 使用率",
"Value #GPU_MEM": "GPU 显存占用",
"Value #GPU_UTIL": "GPU 使用率",
"Value #MEM": "内存使用率",
"hostname": "主机名",
"ip": "IP 地址",
"node_id": "节点 ID",
"user_id": "用户ID"
}
}
}
],
"type": "table"
}
],
"refresh": "5s",
"schemaVersion": 39,
"tags": [
"cluster",
"gpu",
"system"
],
"templating": {
"list": []
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {},
"timezone": "browser",
"title": "Cluster Dashboard",
"uid": "cluster-dashboard",
"version": 34,
"weekStart": ""
}

10
src/metric/grafana/build/start-grafana-supervised.sh
View File

@@ -9,7 +9,6 @@ DOMAIN=grafana.metric.argus.com
IP=$(ifconfig | awk '/inet / && $2 != "127.0.0.1" {print $2; exit}')
echo "current IP: ${IP}"
echo "${IP}" > /private/argus/etc/${DOMAIN}
chmod +x /private/argus/etc/${DOMAIN}
# 确保必要目录存在（权限已在 Dockerfile 中设置）
mkdir -p /private/argus/metric/grafana/data
@@ -28,6 +27,7 @@ mkdir -p /var/lib/grafana
if [ -f "/tmp/grafana.ini" ]; then
echo "[INFO] Copying grafana.ini to /private/argus/metric/grafana/config/"
cp /tmp/grafana.ini /private/argus/metric/grafana/config/grafana.ini
chown grafana:grafana /private/argus/metric/grafana/config/grafana.ini
echo "[INFO] Grafana configuration copied successfully"
fi
@@ -47,9 +47,12 @@ fi
if [ -f "/tmp/datasources.yml" ]; then
echo "[INFO] Copying datasource configuration to /private/argus/metric/grafana/provisioning/datasources/"
cp /tmp/datasources.yml /private/argus/metric/grafana/provisioning/datasources/datasources.yml
chown grafana:grafana /private/argus/metric/grafana/provisioning/datasources/datasources.yml
echo "[INFO] Datasource configuration copied successfully"
elif [ -d "/private/argus/metric/grafana/provisioning/datasources" ] && [ "$(ls -A /private/argus/metric/grafana/provisioning/datasources)" ]; then
echo "[INFO] Found existing datasource provisioning files in /private/argus/metric/grafana/provisioning/datasources"
# 确保数据源配置目录权限正确
chown -R grafana:grafana /private/argus/metric/grafana/provisioning/datasources
elif [ -d "/etc/grafana/provisioning/datasources" ] && [ "$(ls -A /etc/grafana/provisioning/datasources)" ]; then
echo "[INFO] Found datasource provisioning files in /etc/grafana/provisioning/datasources"
# 确保数据源配置目录权限正确
@@ -62,6 +65,7 @@ fi
if [ -f "/tmp/dashboards.yml" ]; then
echo "[INFO] Copying dashboard configuration to /private/argus/metric/grafana/provisioning/dashboards/"
cp /tmp/dashboards.yml /private/argus/metric/grafana/provisioning/dashboards/dashboards.yml
chown grafana:grafana /private/argus/metric/grafana/provisioning/dashboards/dashboards.yml
echo "[INFO] Dashboard configuration copied successfully"
fi
@@ -69,9 +73,13 @@ fi
if [ -f "/tmp/default_dashboard.json" ]; then
echo "[INFO] Copying default dashboard to /private/argus/metric/grafana/provisioning/dashboards/"
cp /tmp/default_dashboard.json /private/argus/metric/grafana/provisioning/dashboards/default_dashboard.json
chown grafana:grafana /private/argus/metric/grafana/provisioning/dashboards/default_dashboard.json
echo "[INFO] Default dashboard copied successfully"
fi
# 确保所有配置目录权限正确
chown -R grafana:grafana /private/argus/metric/grafana/provisioning/
# 启动 Grafana
if [ -n "$CONFIG_FILE" ]; then
echo "[INFO] Starting Grafana with custom configuration..."

16
src/metric/prometheus/build/Dockerfile
View File

@@ -48,11 +48,11 @@ RUN mkdir -p /var/log/supervisor
ENV PROMETHEUS_BASE_PATH=/private/argus/metric/prometheus
# 设置用户和组ID环境变量
ARG ARGUS_BUILD_UID=2133
ARG ARGUS_BUILD_GID=2015
ARG PROMETHEUS_UID=2133
ARG PROMETHEUS_GID=2015
ENV PROMETHEUS_UID=${PROMETHEUS_UID}
ENV PROMETHEUS_GID=${PROMETHEUS_GID}
ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
# 创建目录结构
RUN mkdir -p ${PROMETHEUS_BASE_PATH}/rules \
&& mkdir -p ${PROMETHEUS_BASE_PATH}/targets \
@@ -61,11 +61,11 @@ RUN mkdir -p ${PROMETHEUS_BASE_PATH}/rules \
&& ln -s ${PROMETHEUS_BASE_PATH} /prometheus
# 修改 Prometheus 用户 UID/GID 并授权
RUN usermod -u ${ARGUS_BUILD_UID} nobody && \
groupmod -g ${ARGUS_BUILD_GID} nogroup && \
RUN usermod -u ${PROMETHEUS_UID} nobody && \
groupmod -g ${PROMETHEUS_GID} nogroup && \
chown -h nobody:nogroup /prometheus && \
chown -R nobody:nogroup ${PROMETHEUS_BASE_PATH} && \
chown -R nobody:nogroup /etc/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

2
src/metric/prometheus/build/prometheus.yml
View File

@@ -7,7 +7,7 @@ global:
alerting:
alertmanagers:
- static_configs:
- targets: ["alertmanager.alert.argus.com:9093"]
- targets: []
# 规则目录
rule_files:

1
src/metric/prometheus/build/start-prometheus-supervised.sh
View File

@@ -17,7 +17,6 @@ sed "s|\${PROMETHEUS_BASE_PATH}|${PROMETHEUS_BASE_PATH}|g" \
IP=$(ifconfig eth0 | awk '/inet /{print $2}')
echo "current IP: ${IP}"
echo "${IP}" > /private/argus/etc/${DOMAIN}
chmod +x /private/argus/etc/${DOMAIN}
exec /bin/prometheus \
--config.file=${PROMETHEUS_BASE_PATH}/prometheus.yml \

2
src/metric/tests/.gitignore vendored
View File

@@ -1,7 +1,7 @@
.env
data/
images-cache/
private-test-node/
*.tar
*.log
.DS_Store

214
src/metric/tests/README.md
View File

@@ -1,97 +1,171 @@
# E2E Test - Argus Metric 部署测试
## 1. 概述
## 概述
本项目用于对 Argus Metric 模块进行端到端（E2E）部署测试。
通过一键脚本可快速搭建 Prometheus、FTP、Grafana 等服务，验证 Metric 模块的完整部署与运行流程。
功能包括：
## 拉取完整项目，进入 metric.tests 目录
- 自动启动所需服务和测试节点
- 发布安装包到 FTP
- CPU/GPU 节点客户端安装测试
- 验证安装结果与服务可用性
- 支持环境清理和分步调试
``` bash
git clone https://git.nasp.fit/NASP/argus.git
## 2. 前置条件
在开始部署和测试之前，请确保完成以下准备工作：
### 2.1 检查 all-in-one-full 客户端安装包
确认客户端安装包目录是否存在：
```bash
{$PROJECT_ROOT}/argus/src/metric/client-plugins/all-in-one-full
```
本项目依赖完整的 all-in-one-full 安装包，其中包含大量二进制文件、依赖包和测试制品，由于体积较大，无法直接上传到 Git 仓库。**请联系项目管理员获取最新版本的完整框架。**
### 2.2 配置环境变量
查看配置文件是否存在，如不存在，则复制示例配置文件并根据实际环境修改：
```bash
cd {$PROJECT_ROOT}/argus/src/metric/tests
```
## 一键构建与部署 Prometheus / FTP / Grafana
### 1. 修改环境变量文件
将示例配置文件复制为 .env 并根据实际情况修改：
``` bash
cp env.example .env
```
.env 文件用于指定构建UID:GID、FTP 配置、版本号等信息，确保各脚本运行时可以正确访问资源。
### 2.3 离线镜像准备
- 步骤1：在**在线服务器**执行以下脚本，会拉取和构建所需的 Docker 镜像：
``` bash
cd {$PROJECT_ROOT}/argus/src/metric/tests
bash scripts/01_start_services.sh
bash scripts/save-images.sh
```
- 步骤2：镜像将被保存到 metric.tests.images-cache 目录中，用于离线迁移和后续导入。
- 步骤3：若目标服务器无法联网，可将该目录拷贝到离线服务器，并执行：
``` bash
cd {$PROJECT_ROOT}/argus/src/metric/tests
bash scripts/load-images.sh
```
- 即可导入镜像并执行下面的QuickStart或分步操作。
### 2. 一键启动服务
## 3. QuickStart
执行以下命令完成环境初始化、镜像构建与服务启动：
执行完整的端到端测试流程：
```bash
bash scripts/00_e2e_test.sh
``` bash
sudo bash start-all.sh
```
该脚本将自动执行以下步骤：
1. 启动所有服务（Prometheus、FTP、Grafana、测试节点）
2. 发布安装包到 FTP 服务
3. 在 CPU 测试节点上安装客户端
4. 在 GPU 测试节点上安装客户端
5. 验证安装结果
6. 清理测试环境
该脚本将自动完成：
- 初始化目录结构（如 /private/argus/metric）
- 构建各服务 Docker 镜像
- 启动 Prometheus、FTP、Grafana 容器
## 4. 分步执行
### 3. 检查容器日志
| 步骤 | 脚本 | 功能描述 |
|--------------|-------------------------------------------|--------------------------------------------------------|
| 启动基础服务 | bash scripts/01_start_services.sh | 构建 Docker 镜像、创建持久化目录、启动容器服务 |
| 发布安装包 | bash scripts/02_publish_artifact.sh | 自动递增版本号、打包安装制品、发布到 FTP |
| CPU 节点安装 | bash scripts/03_test_node_install.sh | 在 CPU 节点下载安装程序并执行安装 |
| GPU 节点安装 | bash scripts/04_test_gpu_node_install.sh | 在 GPU 节点下载安装程序并执行安装 |
| 验证安装 | bash scripts/05_verify_install.sh | 检查监控端口、端口连通性及服务可用性 |
| 清理环境 | bash scripts/06_cleanup.sh | 停止并清理所有测试容器及环境 |
可手动验证容器运行状态：
## 5. 查看监控采集数据及展示面板
``` bash
docker logs argus-metric-ftp
docker logs argus-metric-grafana
docker logs argus-metric-prometheus
```
如日志输出中无 ERROR 或 supervisor 报错信息，则表示服务启动正常。
## 客户端安装包打包与分发
> **前置说明**：完整的 `all-in-one` 安装包打包分发框架因包含大量二进制文件和依赖包，无法上传至 Git 仓库。请先联系项目管理员获取最新的 `all-in-one` 完整框架，再执行后续操作。
打包后服务端会将安装包发布至 FTP 共享目录，默认路径为：
``` bash
$DATA_ROOT/ftp/share
```
发布后的文件权限与 FTP 目录账户保持一致。
### 1. 递增版本号
``` bash
bash scripts/version-manager.sh bump minor
```
该脚本会自动更新版本号（如 1.101.0 → 1.102.0）。
### 2. 打包安装制品
``` bash
bash scripts/package_artifact.sh
```
执行后会在输出目录中生成压缩包或安装脚本。
### 3. 发布制品至 FTP
``` bash
sudo bash scripts/publish_artifact.sh $VERSION --output-dir $OUTPUT_DIR --owner $UID:$GID
```
参数说明：
参数 说明
$VERSION 发布版本号（如 1.102.0）
$OUTPUT_DIR 输出目录（默认 /private/argus/ftp/share）
$UID:$GID 文件属主（用户ID:组ID）
示例：
``` bash
sudo bash scripts/publish_artifact.sh 1.102.0 --output-dir /private/argus/ftp/share --owner 2133:2015
```
更多详情可参考 client-plugins/all-in-one/README.md。
## 客户端安装（通过 FTP）
客户端下载与安装步骤如下：
``` bash
curl -u ${USER}:${PASSWD} ftp://${FTP_SERVER}/setup.sh -o setup.sh
chmod +x setup.sh
sudo bash setup.sh --server ${FTP_SERVER} --user ${USER} --password ${PASSWD} --port ${PORT}
```
参数说明：
参数 说明
$FTP_SERVER 服务器 IP 地址
$USER 默认 ftpuser
$PASSWD 默认 ZGClab1234!
$PORT FTP 服务端口（需与 .env 保持一致）
示例：
``` bash
curl -u ftpuser:ZGClab1234! ftp://10.211.55.4/setup.sh -o setup.sh
chmod +x setup.sh
sudo bash setup.sh --server 10.211.55.4 --user ftpuser --password 'ZGClab1234!' --port 2122
```
更多细节可参考 client-plugins/all-in-one/README.md。
## 模拟 Argus-Master 配置下发
可通过手动写入 nodes.json 文件模拟 Argus-Master 对 Argus-Metric 的配置下发：
``` json
[
{
"node_id": "A1",
"user_id": "sundapeng",
"ip": "10.211.55.4",
"hostname": "dev-sundapeng-nsche-wohen-pod-0",
"labels": ["label-a", "label-b"]
}
]
```
路径：
``` bash
${DATA_ROOT}/prometheus/nodes.json
```
Argus-Metric 中的 prometheus 模块会自动解析该文件，并将其拆分生成目标配置：
``` bash
${DATA_ROOT}/prometheus/targets/
```
## Grafana 手动配置（如未自动接入 Prometheus）
如 Grafana 未自动导入 Prometheus 数据源，可手动执行以下操作：
1. 添加数据源
- 进入 Grafana → Data sources
- 选择 Add data source → Prometheus
- URL 填写：http://prometheus:9090(Docker 内部 DNS 地址)
2. 导入测试 Dashboard
- 打开 Grafana → Dashboards → Import
- 上传或粘贴 test_grafana_dashboard.json
## 查看监控数据
Prometheus 访问以下地址查看节点活性：
``` bash
http://127.0.0.1:9090/targets
http://127.0.0.1:9091/targets
```
Grafana 访问以下地址查看监控大屏：
``` bash
http://127.0.0.1:3000/d/node_gpu_metrics/node-and-gpu-metrics
```
PS: 如果 Grafana 未自动导入 Prometheus 数据源，可手动执行以下操作：
1. 添加数据源
- 进入 Grafana → Data sources
- 选择 Add data source → Prometheus
- URL 填写：http://prom.metric.argus.com:9090
2. 导入测试 Dashboard
- 打开 Grafana → Dashboards → Import
- 上传或粘贴 test_grafana_dashboard.json

9
src/metric/tests/scripts/common/check-paths.sh → src/metric/tests/check-paths.sh
View File

@@ -6,8 +6,7 @@
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
cd "$TEST_DIR"
cd "$SCRIPT_DIR"
echo "=========================================="
echo " 路径检查脚本"
@@ -19,15 +18,15 @@ echo ""
# 检查配置文件
echo "检查配置文件..."
if [ -f "$TEST_DIR/docker-compose.yml" ]; then
if [ -f "$SCRIPT_DIR/docker-compose.yml" ]; then
echo " ✓ docker-compose.yml 存在"
else
echo " ✗ docker-compose.yml 不存在"
fi
if [ -f "$TEST_DIR/.env" ]; then
if [ -f "$SCRIPT_DIR/.env" ]; then
echo " ✓ .env 存在"
elif [ -f "$TEST_DIR/env.example" ]; then
elif [ -f "$SCRIPT_DIR/env.example" ]; then
echo " ⚠ .env 不存在，但 env.example 存在"
else
echo " ✗ .env 和 env.example 都不存在"

39
src/metric/tests/client-test-gpu-node/build/Dockerfile
View File

@@ -1,39 +0,0 @@
# 使用NVIDIA官方CUDA基础镜像
FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04
ENV DEBIAN_FRONTEND=noninteractive
# 设置时区
ENV TZ=Asia/Shanghai
RUN apt-get update -qq && \
apt-get install -y -qq \
tzdata \
curl \
wget \
gnupg2 \
software-properties-common \
ca-certificates \
&& rm -rf /var/lib/apt/lists/*
# 配置时区
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
WORKDIR /app
# 创建启动脚本，在运行时验证GPU
COPY <<EOF /app/start.sh
#!/bin/bash
echo "检查GPU环境..."
if command -v nvidia-smi &> /dev/null; then
nvidia-smi
echo "GPU环境正常"
else
echo "警告: nvidia-smi 命令不可用，请确保容器运行时启用了GPU支持"
fi
exec "\$@"
EOF
RUN chmod +x /app/start.sh
CMD ["/app/start.sh", "/bin/bash"]

6
src/metric/tests/client-test-node/build/Dockerfile
View File

@@ -1,6 +0,0 @@
FROM ubuntu:22.04
RUN apt-get update -qq && \
DEBIAN_FRONTEND=noninteractive apt-get install -y -qq tzdata && \
rm -rf /var/lib/apt/lists/*
ENV TZ=Asia/Shanghai

146
src/metric/tests/docker-compose.yml
View File

@@ -1,39 +1,29 @@
networks:
default:
name: argus-debug-net
external: true
services:
ftp:
build:
context: ../ftp/build
dockerfile: Dockerfile
args:
ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
USE_INTRANET: ${USE_INTRANET:-false}
FTP_UID: ${FTP_UID:-2133}
FTP_GID: ${FTP_GID:-2015}
image: argus-metric-ftp:latest
container_name: argus-ftp
restart: unless-stopped
environment:
- TZ=Asia/Shanghai
- FTP_BASE_PATH=/private/argus/ftp
- FTP_PASSWORD=${FTP_PASSWORD:-ZGClab1234!}
- DOMAIN=${FTP_DOMAIN:-ftp.metric.argus.com}
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
- DOMAIN=${FTP_DOMAIN:-prom.ftp.argus.com}
- FTP_UID=${FTP_UID:-2133}
- FTP_GID=${FTP_GID:-2015}
ports:
- "${FTP_PORT:-21}:21"
- "${FTP_DATA_PORT:-20}:20"
- "21100-21110:21100-21110"
volumes:
- ${DATA_ROOT:-/private}/argus/metric/ftp:/private/argus/ftp
- ${DATA_ROOT:-/private}/argus/etc:/private/argus/etc
- /etc/localtime:/etc/localtime:ro
- /etc/timezone:/etc/timezone:ro
- ${DATA_ROOT:-./data}/ftp:/private/argus/ftp
- ${DATA_ROOT:-./data}/etc:/private/argus/etc
networks:
default:
ipv4_address: 172.30.0.40
- argus-network
logging:
driver: "json-file"
options:
@@ -45,27 +35,23 @@ services:
context: ../prometheus/build
dockerfile: Dockerfile
args:
ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
PROMETHEUS_UID: ${PROMETHEUS_UID:-2133}
PROMETHEUS_GID: ${PROMETHEUS_GID:-2015}
USE_INTRANET: ${USE_INTRANET:-false}
image: argus-metric-prometheus:latest
container_name: argus-prometheus
restart: unless-stopped
environment:
- TZ=Asia/Shanghai
- PROMETHEUS_BASE_PATH=/private/argus/metric/prometheus
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
- PROMETHEUS_UID=${PROMETHEUS_UID:-2133}
- PROMETHEUS_GID=${PROMETHEUS_GID:-2015}
ports:
- "${PROMETHEUS_PORT:-9090}:9090"
volumes:
- ${DATA_ROOT:-/private}/argus/metric/prometheus:/private/argus/metric/prometheus
- ${DATA_ROOT:-/private}/argus/etc:/private/argus/etc
- /etc/localtime:/etc/localtime:ro
- /etc/timezone:/etc/timezone:ro
- ${DATA_ROOT:-./data}/prometheus:/private/argus/metric/prometheus
- ${DATA_ROOT:-./data}/etc:/private/argus/etc
networks:
default:
ipv4_address: 172.30.0.41
- argus-network
logging:
driver: "json-file"
options:
@@ -77,29 +63,25 @@ services:
context: ../grafana/build
dockerfile: Dockerfile
args:
ARGUS_BUILD_UID: ${ARGUS_BUILD_UID:-2133}
ARGUS_BUILD_GID: ${ARGUS_BUILD_GID:-2015}
GRAFANA_UID: ${GRAFANA_UID:-2133}
GRAFANA_GID: ${GRAFANA_GID:-2015}
image: argus-metric-grafana:latest
container_name: argus-grafana
restart: unless-stopped
environment:
- TZ=Asia/Shanghai
- GRAFANA_BASE_PATH=/private/argus/metric/grafana
- ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
- ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
- GRAFANA_UID=${GRAFANA_UID:-2133}
- GRAFANA_GID=${GRAFANA_GID:-2015}
- GF_SERVER_HTTP_PORT=3000
- GF_LOG_LEVEL=warn
- GF_LOG_MODE=console
ports:
- "${GRAFANA_PORT:-3000}:3000"
volumes:
- ${DATA_ROOT:-/private}/argus/metric/grafana:/private/argus/metric/grafana
- ${DATA_ROOT:-/private}/argus/etc:/private/argus/etc
- /etc/localtime:/etc/localtime:ro
- /etc/timezone:/etc/timezone:ro
- ${DATA_ROOT:-./data}/grafana:/private/argus/metric/grafana
- ${DATA_ROOT:-./data}/etc:/private/argus/etc
networks:
default:
ipv4_address: 172.30.0.42
- argus-network
depends_on:
- prometheus
logging:
@@ -108,78 +90,16 @@ services:
max-size: "10m"
max-file: "3"
test-node:
build:
context: ./client-test-node/build
dockerfile: Dockerfile
image: argus-metric-test-node:latest
container_name: argus-metric-test-node
hostname: test-metric-node-001
restart: unless-stopped
privileged: true
depends_on:
- ftp
- prometheus
environment:
- TZ=Asia/Shanghai
- DEBIAN_FRONTEND=noninteractive
- FTP_DOMAIN=${FTP_DOMAIN:-ftp.metric.argus.com}
- FTP_SERVER=${FTP_SERVER:-172.30.0.40}
- FTP_USER=${FTP_USER:-ftpuser}
- FTP_PASSWORD=${FTP_PASSWORD:-ZGClab1234!}
- FTP_PORT=${FTP_PORT:-21}
volumes:
- ${DATA_ROOT:-/private}/argus/agent:/private/argus/agent
- /etc/localtime:/etc/localtime:ro
- /etc/timezone:/etc/timezone:ro
command: sleep infinity
networks:
default:
ipv4_address: 172.30.0.50
logging:
driver: "json-file"
options:
max-size: "10m"
max-file: "3"
networks:
argus-network:
driver: bridge
name: argus-network
test-gpu-node:
build:
context: ./client-test-gpu-node/build
dockerfile: Dockerfile
image: argus-metric-test-gpu-node:latest
container_name: argus-metric-test-gpu-node
hostname: test-metric-gpu-node-001
restart: unless-stopped
privileged: true
runtime: nvidia
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities:
- gpu
depends_on:
- ftp
- prometheus
environment:
- TZ=Asia/Shanghai
- DEBIAN_FRONTEND=noninteractive
- NVIDIA_VISIBLE_DEVICES=all
- NVIDIA_DRIVER_CAPABILITIES=compute,utility
- GPU_MODE=gpu
volumes:
- ${DATA_ROOT:-/private}/argus/agent:/private/argus/agent
- /etc/localtime:/etc/localtime:ro
- /etc/timezone:/etc/timezone:ro
command: sleep infinity
networks:
default:
ipv4_address: 172.30.0.51
logging:
driver: "json-file"
options:
max-size: "10m"
max-file: "3"
volumes:
ftp_data:
driver: local
prometheus_data:
driver: local
grafana_data:
driver: local

18
src/metric/tests/env.example
View File

@@ -1,15 +1,19 @@
# 统一用户和组配置
ARGUS_BUILD_UID=1048
ARGUS_BUILD_GID=1048
# 用户和组配置
FTP_UID=2133
FTP_GID=2015
PROMETHEUS_UID=2133
PROMETHEUS_GID=2015
GRAFANA_UID=2133
GRAFANA_GID=2015
# 数据根目录
DATA_ROOT=/private
DATA_ROOT=/private/argus
# FTP 配置
FTP_PORT=21
FTP_DATA_PORT=20
FTP_PORT=2122
FTP_DATA_PORT=2022
FTP_PASSWORD=ZGClab1234!
FTP_DOMAIN=ftp.metric.argus.com
FTP_DOMAIN=prom.ftp.argus.com
# Prometheus 配置
PROMETHEUS_PORT=9090

90
src/metric/tests/init-directories.sh Executable file
View File

@@ -0,0 +1,90 @@
#!/bin/bash
# 初始化目录脚本
# 用于创建所有必要的数据目录并设置正确的权限
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
cd "$SCRIPT_DIR"
# 加载 .env 文件（如果存在）
if [ -f .env ]; then
echo "加载 .env 配置文件..."
source .env
fi
# 默认配置
FTP_UID=${FTP_UID:-2133}
FTP_GID=${FTP_GID:-2015}
PROMETHEUS_UID=${PROMETHEUS_UID:-2133}
PROMETHEUS_GID=${PROMETHEUS_GID:-2015}
GRAFANA_UID=${GRAFANA_UID:-2133}
GRAFANA_GID=${GRAFANA_GID:-2015}
DATA_ROOT=${DATA_ROOT:-./data}
echo "开始初始化目录结构..."
echo "数据目录: ${DATA_ROOT}"
echo ""
# 创建 FTP 目录
echo "创建 FTP 目录..."
sudo mkdir -p ${DATA_ROOT}/ftp/share
sudo chown -R ${FTP_UID}:${FTP_GID} ${DATA_ROOT}/ftp
sudo chmod -R 755 ${DATA_ROOT}/ftp
# 创建 Prometheus 目录
echo "创建 Prometheus 目录..."
sudo mkdir -p ${DATA_ROOT}/prometheus/{data,rules,targets}
# 创建默认的 targets 文件（先创建文件再改权限）
if [ ! -f "${DATA_ROOT}/prometheus/targets/node_exporter.json" ]; then
echo "创建默认 node_exporter targets..."
echo '[
{
"targets": [],
"labels": {
"job": "node"
}
}
]' | sudo tee ${DATA_ROOT}/prometheus/targets/node_exporter.json > /dev/null
fi
if [ ! -f "${DATA_ROOT}/prometheus/targets/dcgm_exporter.json" ]; then
echo "创建默认 dcgm_exporter targets..."
echo '[
{
"targets": [],
"labels": {
"job": "dcgm"
}
}
]' | sudo tee ${DATA_ROOT}/prometheus/targets/dcgm_exporter.json > /dev/null
fi
# 统一设置 Prometheus 目录权限
sudo chown -R ${PROMETHEUS_UID}:${PROMETHEUS_GID} ${DATA_ROOT}/prometheus
sudo chmod -R 755 ${DATA_ROOT}/prometheus
# 创建 Grafana 目录
echo "创建 Grafana 目录..."
sudo mkdir -p ${DATA_ROOT}/grafana/{data,logs,plugins,provisioning/datasources,provisioning/dashboards,data/sessions,data/dashboards,config}
sudo chown -R ${GRAFANA_UID}:${GRAFANA_GID} ${DATA_ROOT}/grafana
sudo chmod -R 755 ${DATA_ROOT}/grafana
# 创建公共配置目录
sudo mkdir -p ${DATA_ROOT}/etc
sudo chown -R ${FTP_UID}:${FTP_GID} ${DATA_ROOT}/etc
sudo chmod -R 755 ${DATA_ROOT}/etc
echo "目录初始化完成！"
echo ""
echo "目录结构："
echo " ${DATA_ROOT}/"
echo " ├── ftp/ (UID:${FTP_UID}, GID:${FTP_GID})"
echo " ├── prometheus/ (UID:${PROMETHEUS_UID}, GID:${PROMETHEUS_GID})"
echo " ├── grafana/ (UID:${GRAFANA_UID}, GID:${GRAFANA_GID})"
echo " └── etc/ (UID:${FTP_UID}, GID:${FTP_GID})"
echo ""
echo "您现在可以运行 'docker-compose up -d' 来启动所有服务"

0
src/metric/tests/scripts/common/init-environment.sh → src/metric/tests/init-environment.sh
View File

5
src/metric/tests/scripts/common/manage-images.sh → src/metric/tests/manage-images.sh
View File

@@ -6,8 +6,7 @@
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
cd "$TEST_DIR"
cd "$SCRIPT_DIR"
# 检测 docker-compose 命令
if command -v docker-compose &> /dev/null; then
@@ -20,7 +19,7 @@ else
fi
# 镜像缓存目录
IMAGE_CACHE_DIR="$TEST_DIR/images-cache"
IMAGE_CACHE_DIR="./images-cache"
mkdir -p "$IMAGE_CACHE_DIR"
# 定义镜像列表

20
src/metric/tests/scripts/00_e2e_test.sh
View File

@@ -1,20 +0,0 @@
#!/bin/bash
set -e
SCRIPT_DIR="$(dirname "$0")"
echo "=========================================="
echo "Argus Metric E2E Test"
echo "=========================================="
bash "$SCRIPT_DIR/01_start_services.sh"
bash "$SCRIPT_DIR/02_publish_artifact.sh"
bash "$SCRIPT_DIR/03_test_node_install.sh"
bash "$SCRIPT_DIR/04_test_gpu_node_install.sh"
bash "$SCRIPT_DIR/05_verify_install.sh"
bash "$SCRIPT_DIR/06_cleanup.sh"
echo "=========================================="
echo "E2E 测试完成"
echo "=========================================="

27
src/metric/tests/scripts/01_start_services.sh
View File

@@ -1,27 +0,0 @@
#!/bin/bash
set -e
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
# 解析参数
REBUILD_FLAG=""
if [[ "$1" == "--rebuild" || "$1" == "-r" ]]; then
REBUILD_FLAG="--rebuild"
echo "[01] 启用强制重新构建模式"
fi
echo "[01] 启动所有服务..."
bash "$SCRIPT_DIR/common/start-all.sh" $REBUILD_FLAG
echo "[01] 等待服务就绪..."
sleep 5
echo "[01] 检查服务状态..."
docker ps | grep argus-ftp
docker ps | grep argus-prometheus
docker ps | grep argus-grafana
docker ps | grep argus-metric-test-node
docker ps | grep argus-metric-test-gpu-node
echo "[01] 基础服务已启动"

60
src/metric/tests/scripts/02_publish_artifact.sh
View File

@@ -1,60 +0,0 @@
#!/bin/bash
set -e
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
TEST_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
PLUGIN_DIR="$(cd "$SCRIPT_DIR/../../client-plugins/all-in-one-full" && pwd)"
# 加载 .env
if [ -f "$TEST_DIR/.env" ]; then
source "$TEST_DIR/.env"
fi
# 检测容器挂载目录
if docker ps --format '{{.Names}}' | grep -q '^argus-ftp$'; then
FTP_MOUNT=$(docker inspect argus-ftp --format '{{range .Mounts}}{{if eq .Destination "/private/argus/ftp"}}{{.Source}}{{end}}{{end}}')
OUTPUT_DIR="${FTP_MOUNT}/share"
echo "[02] 容器挂载: $OUTPUT_DIR"
else
OUTPUT_DIR="${DATA_ROOT:-$TEST_DIR/data}/ftp/share"
echo "[02] 默认路径: $OUTPUT_DIR"
fi
OWNER="${ARGUS_BUILD_UID:-2133}:${ARGUS_BUILD_GID:-2015}"
cd "$PLUGIN_DIR"
echo "[02] 递增版本号..."
bash scripts/version-manager.sh bump minor
VERSION_FILE="config/VERSION"
if [ ! -f "$VERSION_FILE" ]; then
echo "[02] 错误: 未找到 $VERSION_FILE"
exit 1
fi
VERSION=$(cat "$VERSION_FILE" | tr -d '[:space:]')
echo "[02] 新版本: $VERSION"
echo "[02] 构建安装包..."
bash scripts/package_artifact.sh --force
echo "[02] 发布到 FTP: $OUTPUT_DIR"
sudo bash scripts/publish_artifact.sh "$VERSION" --output-dir "$OUTPUT_DIR" --owner "$OWNER"
echo "[02] 设置文件权限..."
# 设置所有者
sudo chown -R "$OWNER" "$OUTPUT_DIR"
# 设置目录权限为 755 (rwxr-xr-x)
sudo find "$OUTPUT_DIR" -type d -exec chmod 755 {} \;
# 设置文件权限为 644 (rw-r--r--)
sudo find "$OUTPUT_DIR" -type f -exec chmod 644 {} \;
# 特别处理 .sh 文件，给予执行权限 755
sudo find "$OUTPUT_DIR" -type f -name "*.sh" -exec chmod 755 {} \;
echo "[02] 权限设置完成 (UID:GID=$OWNER, dirs=755, files=644, scripts=755)"
echo "[02] 发布完成，验证文件..."
ls -lh "$OUTPUT_DIR"
echo "[02] 完成"

33
src/metric/tests/scripts/03_test_node_install.sh
View File

@@ -1,33 +0,0 @@
#!/bin/bash
set -e
FTP_SERVER="${FTP_SERVER:-172.30.0.40}"
FTP_USER="${FTP_USER:-ftpuser}"
FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
FTP_PORT="${FTP_PORT:-21}"
FTP_HOST="${FTP_SERVER}"
echo "[03] 进入测试节点执行安装..."
echo "[03] 使用 FTP 地址: ${FTP_HOST}:${FTP_PORT}"
docker exec argus-metric-test-node bash -c "
set -e
if ! command -v curl &>/dev/null; then
echo '[03] curl 未安装，正在安装...'
apt-get update && apt-get install -y curl
fi
cd /tmp
echo '[03] 下载 setup.sh...'
curl -u ${FTP_USER}:${FTP_PASSWORD} ftp://${FTP_HOST}:${FTP_PORT}/setup.sh -o setup.sh
echo '[03] 执行安装...'
chmod +x setup.sh
bash setup.sh --server ${FTP_HOST} --user ${FTP_USER} --password '${FTP_PASSWORD}' --port ${FTP_PORT}
echo '[03] 安装完成'
"
echo "[03] 完成"

33
src/metric/tests/scripts/04_test_gpu_node_install.sh
View File

@@ -1,33 +0,0 @@
#!/bin/bash
set -e
FTP_SERVER="${FTP_SERVER:-172.30.0.40}"
FTP_USER="${FTP_USER:-ftpuser}"
FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
FTP_PORT="${FTP_PORT:-21}"
FTP_HOST="${FTP_SERVER}"
echo "[03] 进入测试节点执行安装..."
echo "[03] 使用 FTP 地址: ${FTP_HOST}:${FTP_PORT}"
docker exec argus-metric-test-gpu-node bash -c "
set -e
if ! command -v curl &>/dev/null; then
echo '[03] curl 未安装，正在安装...'
apt-get update && apt-get install -y curl
fi
cd /tmp
echo '[03] 下载 setup.sh...'
curl -u ${FTP_USER}:${FTP_PASSWORD} ftp://${FTP_HOST}:${FTP_PORT}/setup.sh -o setup.sh
echo '[03] 执行安装...'
chmod +x setup.sh
bash setup.sh --server ${FTP_HOST} --user ${FTP_USER} --password '${FTP_PASSWORD}' --port ${FTP_PORT}
echo '[03] 安装完成'
"
echo "[03] 完成"

96
src/metric/tests/scripts/05_verify_install.sh
View File

@@ -1,96 +0,0 @@
#!/bin/bash
set -e
echo "[04] 验证安装结果 - 检查监控端口..."
echo "=========================================="
# 检查容器是否运行
if ! docker ps --format '{{.Names}}' | grep -q '^argus-metric-test-node$'; then
echo "错误: 容器 argus-metric-test-node 未运行"
exit 1
fi
ERRORS=0
# ==================== 检查监听端口 ====================
echo ""
echo "[1] 检查监听端口..."
echo "----------------------------------------"
CHECK_RESULT=$(docker exec argus-metric-test-node bash -c '
if command -v netstat >/dev/null 2>&1; then
echo "使用 netstat 检查端口:"
if netstat -tlnp 2>/dev/null | grep -E ":(9100|9400|2020)"; then
echo "✓ 找到监控端口"
exit 0
else
echo "✗ 未找到监控端口 (9100/9400/2020)"
exit 1
fi
elif command -v ss >/dev/null 2>&1; then
echo "使用 ss 检查端口:"
if ss -tlnp 2>/dev/null | grep -E ":(9100|9400|2020)"; then
echo "✓ 找到监控端口"
exit 0
else
echo "✗ 未找到监控端口 (9100/9400/2020)"
exit 1
fi
elif command -v lsof >/dev/null 2>&1; then
echo "使用 lsof 检查端口:"
if lsof -i :9100 -i :9400 -i :2020 2>/dev/null | grep LISTEN; then
echo "✓ 找到监控端口"
exit 0
else
echo "✗ 未找到监控端口 (9100/9400/2020)"
exit 1
fi
else
echo "? 没有可用的端口检查工具 (netstat/ss/lsof)，跳过此检查"
exit 0
fi
')
echo "$CHECK_RESULT"
# 只有在明确失败时才计入错误（exit 1），没有工具（exit 0）不算错误
if echo "$CHECK_RESULT" | grep -q "✗ 未找到监控端口"; then
ERRORS=$((ERRORS + 1))
fi
# ==================== 测试端口连通性 ====================
echo ""
echo "[2] 测试端口连通性..."
echo "----------------------------------------"
docker exec argus-metric-test-node bash -c '
if command -v curl >/dev/null 2>&1; then
FAILED=0
for port in 9100 9400 2020; do
echo -n "端口 $port: "
if curl -s --connect-timeout 2 "http://localhost:$port/metrics" > /dev/null 2>&1; then
echo "✓ 可访问 (/metrics)"
elif curl -s --connect-timeout 2 "http://localhost:$port/" > /dev/null 2>&1; then
echo "✓ 可访问 (根路径)"
else
echo "✗ 不可访问"
FAILED=$((FAILED + 1))
fi
done
exit $FAILED
else
echo "? curl 不可用，跳过连通性测试"
exit 0
fi
' || ERRORS=$((ERRORS + 1))
echo ""
echo "=========================================="
if [ $ERRORS -eq 0 ]; then
echo "✓ [04] 验证完成 - 所有端口检查通过"
else
echo "✗ [04] 验证失败 - 发现 $ERRORS 个问题"
echo ""
echo "调试建议："
echo " 1. 进入容器检查: docker exec -it argus-metric-test-node bash"
echo " 2. 查看进程: docker exec argus-metric-test-node ps aux"
echo " 3. 查看日志: docker exec argus-metric-test-node cat /tmp/argus_install.log"
exit 1
fi
echo "=========================================="

11
src/metric/tests/scripts/06_cleanup.sh
View File

@@ -1,11 +0,0 @@
#!/bin/bash
set -e
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
echo "[05] 清理环境..."
bash "$SCRIPT_DIR/common/stop-all.sh" || true
echo "[05] 清理完成"

61
src/metric/tests/scripts/common/init-directories.sh
View File

@@ -1,61 +0,0 @@
#!/bin/bash
# 初始化目录脚本
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
cd "$TEST_DIR"
# 加载 .env 文件（如果存在）
if [ -f .env ]; then
echo "加载 .env 配置文件..."
source .env
fi
# 默认配置
ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
DATA_ROOT=${DATA_ROOT:-/private}
echo "开始初始化目录结构..."
echo "数据根目录: ${DATA_ROOT}"
echo "统一 UID: ${ARGUS_BUILD_UID}"
echo "统一 GID: ${ARGUS_BUILD_GID}"
# 创建基础目录结构
echo "创建基础目录结构..."
sudo mkdir -p ${DATA_ROOT}/argus/metric
sudo mkdir -p ${DATA_ROOT}/argus/etc
sudo mkdir -p ${DATA_ROOT}/argus/agent
# 创建 FTP 目录
echo "创建 FTP 目录..."
sudo mkdir -p ${DATA_ROOT}/argus/metric/ftp/share
# 创建 Prometheus 目录
echo "创建 Prometheus 目录..."
sudo mkdir -p ${DATA_ROOT}/argus/metric/prometheus/{data,rules,targets}
# 创建 Grafana 目录
echo "创建 Grafana 目录..."
sudo mkdir -p ${DATA_ROOT}/argus/metric/grafana/{data,logs,plugins,provisioning/datasources,provisioning/dashboards,data/sessions,data/dashboards,config}
# 统一设置所有目录权限
echo "设置目录权限..."
sudo chown -R ${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID} ${DATA_ROOT}/argus/metric
sudo chmod -R 755 ${DATA_ROOT}/argus/metric
echo "目录初始化完成！"
echo ""
echo "目录结构："
echo " ${DATA_ROOT}/"
echo " ├── argus/ (UID:${ARGUS_BUILD_UID}, GID:${ARGUS_BUILD_GID})"
echo " │ ├── metric/"
echo " │ │ ├── ftp/"
echo " │ │ ├── prometheus/"
echo " │ │ └── grafana/"
echo ""
echo "您现在可以运行 'docker-compose up -d' 来启动所有服务"

50
src/metric/tests/scripts/common/stop-all.sh
View File

@@ -1,50 +0,0 @@
#!/bin/bash
# 停止所有服务脚本
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
cd "$TEST_DIR"
# 检查 docker compose 命令
if ! docker compose version &> /dev/null 2>&1; then
echo "错误: 未找到 docker compose 命令，请确保 Docker Compose V2 已安装"
exit 1
fi
echo "=========================================="
echo " 停止 Argus Metrics 服务"
echo "=========================================="
echo ""
echo "使用: docker compose"
echo "Compose 文件: $TEST_DIR/docker-compose.yml"
echo ""
# 检查是否有运行的容器
if [ "$(docker compose ps -q)" ]; then
echo "停止所有服务..."
docker compose stop
echo ""
read -p "是否要删除容器? (y/N): " -n 1 -r
echo
if [[ $REPLY =~ ^[Yy]$ ]]; then
docker compose down
echo "容器已删除"
read -p "是否要删除数据卷? (y/N): " -n 1 -r
echo
if [[ $REPLY =~ ^[Yy]$ ]]; then
docker compose down -v
echo "数据卷已删除"
fi
fi
else
echo "没有运行的服务"
fi
echo ""
echo "完成！"

85
src/metric/tests/scripts/load-images.sh
View File

@@ -1,85 +0,0 @@
#!/bin/bash
# 镜像加载脚本
# 用于从 tar 文件加载 Docker 镜像
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
INPUT_DIR="${1:-$TEST_DIR/images-cache}"
echo "=========================================="
echo " Docker 镜像加载脚本"
echo "=========================================="
echo ""
echo "输入目录: $INPUT_DIR"
echo ""
# 检查输入目录是否存在
if [ ! -d "$INPUT_DIR" ]; then
echo "错误: 目录不存在: $INPUT_DIR"
exit 1
fi
# 查找所有tar文件并加载
total=0
success=0
failed=0
# 查找目录下所有.tar文件
tar_files=($(find "$INPUT_DIR" -name "*.tar" -type f 2>/dev/null | sort))
if [ ${#tar_files[@]} -eq 0 ]; then
echo "错误: 在目录 $INPUT_DIR 中未找到任何 .tar 文件"
exit 1
fi
echo "找到 ${#tar_files[@]} 个镜像文件："
for tar_file in "${tar_files[@]}"; do
echo " - $(basename "$tar_file")"
done
echo ""
for tar_file in "${tar_files[@]}"; do
total=$((total + 1))
tar_filename=$(basename "$tar_file")
echo "[$total] 处理: $tar_filename"
# 强制加载，不检查镜像是否已存在
echo " 加载镜像..."
if docker load -i "$tar_file"; then
echo " 加载成功: $tar_filename"
success=$((success + 1))
else
echo " 加载失败: $tar_filename"
failed=$((failed + 1))
fi
echo ""
done
echo "=========================================="
echo " 加载完成"
echo "=========================================="
echo ""
echo "统计："
echo " 总计: $total"
echo " 成功: $success"
echo " 失败: $failed"
echo ""
# 显示当前所有镜像
echo "当前所有镜像："
docker images
echo ""
if [ $failed -gt 0 ]; then
echo "部分镜像加载失败，请检查！"
exit 1
fi
if [ $success -gt 0 ]; then
echo "镜像加载成功！"
fi

94
src/metric/tests/scripts/save-images.sh
View File

@@ -1,94 +0,0 @@
#!/bin/bash
# 镜像保存脚本
# 用于保存 Docker 镜像到 tar 文件，便于离线部署
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
OUTPUT_DIR="${1:-$TEST_DIR/images-cache}"
echo "=========================================="
echo " Docker 镜像保存脚本"
echo "=========================================="
echo ""
echo "输出目录: $OUTPUT_DIR"
echo ""
# 创建输出目录
mkdir -p "$OUTPUT_DIR"
# 定义镜像名称（与 docker-compose.yml 保持一致）
declare -A IMAGES=(
["argus-metric-ftp:latest"]="argus-ftp.tar"
["argus-metric-prometheus:latest"]="argus-prometheus.tar"
["argus-metric-grafana:latest"]="argus-grafana.tar"
["argus-metric-test-node:latest"]="argus-test-node.tar"
["argus-metric-test-gpu-node:latest"]="argus-test-gpu-node.tar"
)
# 检查镜像是否存在并保存
total=0
success=0
failed=0
for image in "${!IMAGES[@]}"; do
total=$((total + 1))
output_file="${OUTPUT_DIR}/${IMAGES[$image]}"
echo "[$total] 检查镜像: $image"
if docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^${image}$"; then
echo " ✓ 镜像存在，开始保存..."
if docker save -o "$output_file" "$image"; then
file_size=$(ls -lh "$output_file" | awk '{print $5}')
echo " ✓ 保存成功: ${IMAGES[$image]} ($file_size)"
success=$((success + 1))
else
echo " ✗ 保存失败: $image"
failed=$((failed + 1))
fi
else
echo " ✗ 镜像不存在，请先构建镜像"
failed=$((failed + 1))
fi
echo ""
done
echo "=========================================="
echo " 保存完成"
echo "=========================================="
echo ""
echo "统计："
echo " 总计: $total"
echo " 成功: $success"
echo " 失败: $failed"
echo ""
echo "输出目录: $OUTPUT_DIR"
echo ""
if [ $success -gt 0 ]; then
echo "已保存的文件："
ls -lh "$OUTPUT_DIR"/*.tar 2>/dev/null || true
echo ""
echo "文件列表："
for image in "${!IMAGES[@]}"; do
output_file="${OUTPUT_DIR}/${IMAGES[$image]}"
if [ -f "$output_file" ]; then
file_size=$(ls -lh "$output_file" | awk '{print $5}')
echo " - ${IMAGES[$image]} ($file_size)"
fi
done
fi
echo ""
echo "使用说明："
echo "1. 将 images-cache 目录复制到目标服务器的 ~/argus/src/metric/tests/ 下"
echo "2. 在目标服务器运行: bash scripts/common/start-all.sh"
echo ""
if [ $failed -gt 0 ]; then
exit 1
fi

104
src/metric/tests/scripts/common/start-all.sh → src/metric/tests/start-all.sh
View File

@@ -6,20 +6,13 @@
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TEST_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
cd "$TEST_DIR"
# 解析参数
FORCE_REBUILD=false
if [[ "$1" == "--rebuild" ]]; then
FORCE_REBUILD=true
fi
cd "$SCRIPT_DIR"
echo "=========================================="
echo " Argus Metrics 一键启动脚本"
echo "=========================================="
echo ""
echo "当前工作目录: $TEST_DIR"
echo "当前工作目录: $SCRIPT_DIR"
echo ""
# 检查 Docker 和 Docker Compose
@@ -28,13 +21,19 @@ if ! command -v docker &> /dev/null; then
exit 1
fi
# 检查 docker compose 命令
if ! docker compose version &> /dev/null 2>&1; then
echo "错误: 未找到 docker compose 命令，请确保 Docker Compose V2 已安装"
# 检测 docker-compose 命令（兼容新旧版本）
COMPOSE_FILE="$SCRIPT_DIR/docker-compose.yml"
if command -v docker-compose &> /dev/null; then
DOCKER_COMPOSE="docker-compose -f $COMPOSE_FILE"
echo "使用: docker-compose"
elif docker compose version &> /dev/null 2>&1; then
DOCKER_COMPOSE="docker compose -f $COMPOSE_FILE"
echo "使用: docker compose"
else
echo "错误: 未找到 docker-compose 或 docker compose 命令"
exit 1
fi
echo "使用: docker compose"
echo "Compose 文件: $TEST_DIR/docker-compose.yml"
echo "Compose 文件: $COMPOSE_FILE"
echo ""
# 检查必要的构建目录
@@ -43,8 +42,6 @@ BUILD_DIRS=(
"../ftp/build"
"../prometheus/build"
"../grafana/build"
"client-test-node/build"
"client-test-gpu-node/build"
)
for dir in "${BUILD_DIRS[@]}"; do
@@ -68,18 +65,6 @@ fi
# 加载环境变量
source .env
# 检查并创建 Docker 网络
echo "检查 Docker 网络..."
NETWORK_NAME="argus-debug-net"
if docker network inspect "$NETWORK_NAME" >/dev/null 2>&1; then
echo "网络 $NETWORK_NAME 已存在"
else
echo "创建网络 $NETWORK_NAME..."
docker network create --driver bridge --subnet 172.30.0.0/16 "$NETWORK_NAME"
echo "网络创建成功"
fi
echo ""
echo "1. 初始化目录结构..."
bash "$SCRIPT_DIR/init-directories.sh"
@@ -87,8 +72,8 @@ echo ""
echo "2. 准备 Docker 镜像..."
# 检查镜像是否存在
IMAGE_CACHE_DIR="$TEST_DIR/images-cache"
IMAGES=("argus-metric-ftp:latest" "argus-metric-prometheus:latest" "argus-metric-grafana:latest" "argus-metric-test-node:latest" "argus-metric-test-gpu-node:latest")
IMAGE_CACHE_DIR="./images-cache"
IMAGES=("argus-metric-ftp:latest" "argus-metric-prometheus:latest" "argus-metric-grafana:latest")
all_images_exist=true
for image in "${IMAGES[@]}"; do
@@ -98,12 +83,7 @@ for image in "${IMAGES[@]}"; do
fi
done
if $FORCE_REBUILD; then
echo "强制重新构建镜像（--rebuild 模式）..."
cd "$TEST_DIR"
docker compose build --no-cache
echo "镜像重新构建完成"
elif $all_images_exist; then
if $all_images_exist; then
echo "所有镜像已存在，跳过构建"
else
echo "检测到缺失镜像，尝试从缓存加载..."
@@ -124,12 +104,6 @@ else
"argus-metric-grafana:latest")
cache_file="${IMAGE_CACHE_DIR}/argus-grafana.tar"
;;
"argus-metric-test-node:latest")
cache_file="${IMAGE_CACHE_DIR}/argus-test-node.tar"
;;
"argus-metric-test-gpu-node:latest")
cache_file="${IMAGE_CACHE_DIR}/argus-test-gpu-node.tar"
;;
esac
if [ -f "$cache_file" ]; then
@@ -154,8 +128,8 @@ else
echo ""
echo "部分镜像缺失，开始构建..."
echo "工作目录: $(pwd)"
cd "$TEST_DIR"
docker compose build --no-cache
cd "$SCRIPT_DIR"
$DOCKER_COMPOSE build
# 询问是否保存镜像
echo ""
@@ -175,12 +149,6 @@ else
"argus-metric-grafana:latest")
docker save -o "${IMAGE_CACHE_DIR}/argus-grafana.tar" "$image" && echo " 已保存: argus-grafana.tar"
;;
"argus-metric-test-node:latest")
docker save -o "${IMAGE_CACHE_DIR}/argus-test-node.tar" "$image" && echo " 已保存: argus-test-node.tar"
;;
"argus-metric-test-gpu-node:latest")
docker save -o "${IMAGE_CACHE_DIR}/argus-test-gpu-node.tar" "$image" && echo " 已保存: argus-test-gpu-node.tar"
;;
esac
done
echo "镜像已保存到: $IMAGE_CACHE_DIR/"
@@ -192,12 +160,40 @@ else
fi
echo ""
echo "3. 启动基础服务..."
cd "$TEST_DIR"
# 启动除GPU节点外的所有服务
docker compose up -d ftp prometheus grafana test-node test-gpu-node
echo "3. 启动服务..."
cd "$SCRIPT_DIR"
$DOCKER_COMPOSE up -d
echo ""
echo "4. 等待服务启动..."
sleep 5
echo ""
echo "5. 检查服务状态..."
cd "$SCRIPT_DIR"
$DOCKER_COMPOSE ps
echo ""
echo "=========================================="
echo " 服务启动完成！"
echo "=========================================="
echo ""
echo "服务访问地址："
echo " - FTP: ftp://localhost:${FTP_PORT:-21}"
echo " 用户名: ftpuser"
echo " 密码: ${FTP_PASSWORD:-ZGClab1234!}"
echo ""
echo " - Prometheus: http://localhost:${PROMETHEUS_PORT:-9090}"
echo ""
echo " - Grafana: http://localhost:${GRAFANA_PORT:-3000}"
echo " 用户名: admin"
echo " 密码: admin"
echo ""
echo "常用命令："
echo " 查看日志: $DOCKER_COMPOSE logs -f [service]"
echo " 停止服务: $DOCKER_COMPOSE stop"
echo " 重启服务: $DOCKER_COMPOSE restart"
echo " 停止并删除: $DOCKER_COMPOSE down"
echo " 停止并删除卷: $DOCKER_COMPOSE down -v"
echo ""

51
src/metric/tests/stop-all.sh Executable file
View File

@@ -0,0 +1,51 @@
#!/bin/bash
# 停止所有服务脚本
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
cd "$SCRIPT_DIR"
# 检测 docker-compose 命令（兼容新旧版本）
COMPOSE_FILE="$SCRIPT_DIR/docker-compose.yml"
if command -v docker-compose &> /dev/null; then
DOCKER_COMPOSE="docker-compose -f $COMPOSE_FILE"
elif docker compose version &> /dev/null 2>&1; then
DOCKER_COMPOSE="docker compose -f $COMPOSE_FILE"
else
echo "错误: 未找到 docker-compose 或 docker compose 命令"
exit 1
fi
echo "=========================================="
echo " 停止 Argus Metrics 服务"
echo "=========================================="
echo ""
# 检查是否有运行的容器
if [ "$($DOCKER_COMPOSE ps -q)" ]; then
echo "停止所有服务..."
$DOCKER_COMPOSE stop
echo ""
read -p "是否要删除容器? (y/N): " -n 1 -r
echo
if [[ $REPLY =~ ^[Yy]$ ]]; then
$DOCKER_COMPOSE down
echo "容器已删除"
read -p "是否要删除数据卷? (y/N): " -n 1 -r
echo
if [[ $REPLY =~ ^[Yy]$ ]]; then
$DOCKER_COMPOSE down -v
echo "数据卷已删除"
fi
fi
else
echo "没有运行的服务"
fi
echo ""
echo "完成！"

1
src/sys/debug/README.md
View File

@@ -57,7 +57,6 @@ cd src/sys/debug
- `scripts/network-create.sh` / `network-destroy.sh`：管理 external 网络。
- `scripts/00_debug_all.sh`：顺序执行 01～08（默认不执行 09）。
- `scripts/clean-data.sh`：选择性清理宿主机私有数据。
- `scripts/03_wait_ready.sh`：除了等待各服务就绪，还会在 Elasticsearch 就绪后自动将磁盘水位阈值放宽（97%/98%/99%），避免在磁盘紧张的调试环境中分片分配失败。
- `scripts/08_restart_agent_reregister.sh`：将 node-b 切换到 `SYS_DEBUG_NODEB_FIXED_IP`（默认 `172.30.0.200`），如果目标地址与当前 IP 相同脚本会报错提醒重新选择地址。
- 其它 `01～09` 与测试目录对应，但针对参数化路径及网络做了调整。

11
src/sys/debug/scripts/03_wait_ready.sh
View File

@@ -41,17 +41,6 @@ if (( attempt > max )); then
exit 1
fi
log "Applying relaxed ES disk watermarks for debug"
curl -fsS -XPUT "http://localhost:9200/_cluster/settings" \
-H 'Content-Type: application/json' \
-d '{
"transient": {
"cluster.routing.allocation.disk.watermark.low": "99%",
"cluster.routing.allocation.disk.watermark.high": "99%",
"cluster.routing.allocation.disk.watermark.flood_stage": "99%"
}
}' >/dev/null || echo "[WARN] Failed to adjust ES watermarks"
log "Waiting for Kibana to be available (HTTP 200)"
kb_attempt=1; kb_max=180
while (( kb_attempt <= kb_max )); do

10
src/sys/tests/scripts/08_restart_agent_reregister.sh
View File

@@ -8,16 +8,6 @@ REPO_ROOT="$(cd "$TEST_ROOT/../../.." && pwd)"
API_BASE="http://localhost:32300/api/v1/master"
if [[ -f "$TEST_ROOT/.env" ]]; then
set -a
# shellcheck disable=SC1090
source "$TEST_ROOT/.env"
set +a
else
source "$REPO_ROOT/scripts/common/build_user.sh"
load_build_user
fi
ID_B="$(cat "$TMP_DIR/node_id_b")"
IP0_B="$(cat "$TMP_DIR/initial_ip_b")"

45
src/web/.gitignore vendored
View File

@@ -1,45 +0,0 @@
# Node modules
node_modules/
# Build output
/dist
/build
# Dependency directories
jspm_packages/
# Logs
npm-debug.log*
yarn-debug.log*
yarn-error.log*
# Editor directories and files
.idea/
.vscode/
*.suo
*.ntvs*
*.njsproj
*.sln
*.sw?
# OS generated files
.DS_Store
Thumbs.db
# Environment variables
.env
.env.local
.env.development.local
.env.test.local
.env.production.local
# Testing
/coverage/
# Optional: service worker cache
/.pwa-cache/
# Misc
*.log
.vite/

34
src/web/README.md
View File

@@ -1,34 +0,0 @@
# Argus-web
前端页面架构：React + Vite + Mantine
该模块分为两个部分，argus-web-frontend和argus-web-proxy。其中argus-web-frontend负责前端页面展示，argus-web-proxy负责反向代理，实现对其他网站的反向代理功能
## 构建
在构建前需要设置构建和部署的环境变量。根目录下运行：
```bash
cp src/web/tests/.env.example src/web/tests/.env
```
修改.env的内容。
### argus-web-frontend
根目录下运行
```bash
bash src/web/buld_tools/frontend/build.sh
```
构建成功后，会在根目录下有一个打包好的tar包argus-web-frontend-latest.tar。
### argus-web-proxy
根目录下运行
```bash
bash src/web/build_tools/proxy/build.sh
```
构建成功后，会在根目录下有一个打包好的tar包argus-web-proxy-latest.tar。
## 部署
提供docker-compose部署。在src/web/tests目录下
```bash
docker-compose up -d
```
会同时启动argus-web-frontend和argus-web-proxy两个容器服务。

93
src/web/build_tools/frontend/Dockerfile
View File

@@ -1,93 +0,0 @@
# ========== 构建阶段 ==========
FROM node:20 AS builder
# 设置工作目录
WORKDIR /app/src/web
# 复制依赖文件并安装
COPY src/web/package*.json ./
RUN npm install
# 复制源码并打包
COPY src/web ./
RUN npm run build
# ========== 运行阶段 ==========
FROM ubuntu:24.04
USER root
# 安装 nginx 和 supervisor
RUN apt-get update && \
apt-get install -y nginx supervisor curl vim net-tools inetutils-ping ca-certificates passwd && \
apt-get clean && rm -rf /var/lib/apt/lists/*
ENV FRONTEND_BASE_PATH=/private/argus/web/frontend
ARG ARGUS_UID=2133
ARG ARGUS_GID=2015
ENV ARGUS_UID=${ARGUS_UID}
ENV ARGUS_GID=${ARGUS_GID}
RUN mkdir -p ${FRONTEND_BASE_PATH} && \
mkdir -p /private/argus/etc
# 创建 web 用户（可自定义 UID/GID）
# 创建 web 用户组
RUN groupadd -g ${ARGUS_GID} web
# 创建 web 用户并指定组
RUN useradd -M -s /usr/sbin/nologin -u ${ARGUS_UID} -g ${ARGUS_GID} web
RUN chown -R web:web ${FRONTEND_BASE_PATH} && \
chown -R web:web /private/argus/etc && \
chown -R web:web /usr/local/bin
# 配置内网 apt 源 (如果指定了内网选项)
RUN if [ "$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
# 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
# 前端编译产物放到 nginx 目录
COPY --from=builder /app/src/web/dist /usr/share/nginx/html
# 复制 nginx 配置（保证 React 前端路由兼容）
COPY src/web/build_tools/frontend/nginx.conf /etc/nginx/nginx.conf
# COPY src/web/build_tools/frontend/conf.d/ /etc/nginx/conf.d/
# 复制 supervisor 配置
COPY src/web/build_tools/frontend/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
# 创建 supervisor 日志目录
RUN mkdir -p /var/log/supervisor
# 复制启动脚本
COPY src/web/build_tools/frontend/start-web-supervised.sh /usr/local/bin/start-web-supervised.sh
RUN chmod +x /usr/local/bin/start-web-supervised.sh
# 复制 DNS 监控脚本
COPY src/web/build_tools/frontend/dns-monitor.sh /usr/local/bin/dns-monitor.sh
RUN chmod +x /usr/local/bin/dns-monitor.sh
# 复制健康检查脚本
COPY src/web/build_tools/frontend/health-check.sh /usr/local/bin/health-check.sh
RUN chmod +x /usr/local/bin/health-check.sh
# 暴露端口
EXPOSE 8080
# 保持 root 用户，由 supervisor 控制 user 切换
USER root
# 以 supervisor 为入口
CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

10
src/web/build_tools/frontend/build.sh
View File

@@ -1,10 +0,0 @@
docker pull node:20
docker pull ubuntu:24.04
source src/web/tests/.env
docker build \
--build-arg ARGUS_UID=${ARGUS_UID} \
--build-arg ARGUS_GID=${ARGUS_GID} \
-f src/web/build_tools/frontend/Dockerfile -t argus-web-frontend:latest .
docker save -o argus-web-frontend-latest.tar argus-web-frontend:latest

68
src/web/build_tools/frontend/dns-monitor.sh
View File

@@ -1,68 +0,0 @@
#!/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

16
src/web/build_tools/frontend/health-check.sh
View File

@@ -1,16 +0,0 @@
#!/bin/bash
set -euo pipefail
URL="http://127.0.0.1:8080"
echo "[INFO] Starting Argus web health check loop for $URL..."
while true; do
if curl -s --max-time 5 "$URL" > /dev/null; then
echo "[OK] $(date '+%Y-%m-%d %H:%M:%S') Argus web is healthy"
else
echo "[ERROR] $(date '+%Y-%m-%d %H:%M:%S') Argus web health check failed"
exit 1
fi
sleep 10
done

28
src/web/build_tools/frontend/nginx.conf
View File

@@ -1,28 +0,0 @@
user web;
worker_processes auto;
events {
worker_connections 1024;
}
http {
include mime.types;
default_type application/octet-stream;
sendfile on;
# React 前端服务
server {
listen 8080;
server_name web.argus.com;
root /usr/share/nginx/html;
index index.html;
# React 前端路由兼容
location / {
try_files $uri /index.html;
}
}
}

32
src/web/build_tools/frontend/start-web-supervised.sh
View File

@@ -1,32 +0,0 @@
#!/bin/bash
set -euo pipefail
echo "[INFO] Starting React frontend under supervisor..."
DNS_DIR="/private/argus/etc"
DNS_SCRIPT="${DNS_DIR}/update-dns.sh"
DOMAIN=web.argus.com
WEB_DOMAIN_FILE="${DNS_DIR}/${DOMAIN}"
RUNTIME_USER="${ARGUS_RUNTIME_USER:-argus}"
RUNTIME_UID="${ARGUS_UID:-2133}"
RUNTIME_GID="${ARGUS_GID:-2015}"
mkdir -p "$DNS_DIR"
chown -R "$RUNTIME_UID:$RUNTIME_GID" "$DNS_DIR" 2>/dev/null || true
# 记录容器 IP
IP=$(ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}' || true)
if [[ -n "${IP}" ]]; then
echo "current IP: ${IP}"
echo "${IP}" > "$WEB_DOMAIN_FILE"
chown "$RUNTIME_UID:$RUNTIME_GID" "$WEB_DOMAIN_FILE" 2>/dev/null || true
else
echo "[WARN] Failed to detect web IP via ifconfig"
fi
chmod 755 "$WEB_DOMAIN_FILE"
echo "[INFO] Launching nginx..."
# 启动 nginx 前台模式
exec /usr/sbin/nginx -g "daemon off;"

51
src/web/build_tools/frontend/supervisord.conf
View File

@@ -1,51 +0,0 @@
[supervisord]
nodaemon=true
logfile=/var/log/supervisor/supervisord.log
pidfile=/var/run/supervisord.pid
user=root
[program:web]
command=/usr/local/bin/start-web-supervised.sh
user=root
stdout_logfile=/var/log/supervisor/web-frontend.log
stderr_logfile=/var/log/supervisor/web-frontend_error.log
autorestart=true
startretries=3
startsecs=5
stopwaitsecs=10
killasgroup=true
stopasgroup=true
[program:web-health]
command=/usr/local/bin/health-check.sh
user=web
stdout_logfile=/var/log/supervisor/web-health.log
stderr_logfile=/var/log/supervisor/web-health_error.log
autorestart=true
startretries=3
startsecs=5
stopwaitsecs=10
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

71
src/web/build_tools/proxy/Dockerfile
View File

@@ -1,71 +0,0 @@
FROM ubuntu:24.04
USER root
# 安装 nginx 和 supervisor
RUN apt-get update && \
apt-get install -y nginx supervisor curl vim net-tools inetutils-ping ca-certificates passwd && \
apt-get clean && rm -rf /var/lib/apt/lists/*
ENV FRONTEND_BASE_PATH=/private/argus/web/proxy
ARG ARGUS_UID=2133
ARG ARGUS_GID=2015
ENV ARGUS_UID=${ARGUS_UID}
ENV ARGUS_GID=${ARGUS_GID}
RUN mkdir -p ${FRONTEND_BASE_PATH} && \
mkdir -p /private/argus/etc
# 创建 proxy 用户（可自定义 UID/GID）
# 创建 proxy 用户组
RUN groupadd -g ${ARGUS_GID} web_proxy
# 创建 proxy 用户并指定组
RUN useradd -M -s /usr/sbin/nologin -u ${ARGUS_UID} -g ${ARGUS_GID} web_proxy
RUN chown -R web_proxy:web_proxy ${FRONTEND_BASE_PATH} && \
chown -R web_proxy:web_proxy /private/argus/etc && \
chown -R web_proxy:web_proxy /usr/local/bin
# 配置内网 apt 源 (如果指定了内网选项)
RUN if [ "$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
# 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
# 复制 nginx 配置（保证 React 前端路由兼容）
COPY src/web/build_tools/proxy/nginx.conf.template /etc/nginx/nginx.conf.template
COPY src/web/build_tools/proxy/conf.d/ /etc/nginx/conf.d/
# 复制 supervisor 配置
COPY src/web/build_tools/proxy/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
# 创建 supervisor 日志目录
RUN mkdir -p /var/log/supervisor
# 复制启动脚本
COPY src/web/build_tools/proxy/start-proxy-supervised.sh /usr/local/bin/start-proxy-supervised.sh
RUN chmod +x /usr/local/bin/start-proxy-supervised.sh
# 复制 DNS 监控脚本
COPY src/web/build_tools/proxy/dns-monitor.sh /usr/local/bin/dns-monitor.sh
RUN chmod +x /usr/local/bin/dns-monitor.sh
# 暴露端口
EXPOSE 80
# 保持 root 用户，由 supervisor 控制 user 切换
USER root
# 以 supervisor 为入口
CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

9
src/web/build_tools/proxy/build.sh
View File

@@ -1,9 +0,0 @@
docker pull ubuntu:24.04
source src/web/tests/.env
docker build \
--build-arg ARGUS_UID=${ARGUS_UID} \
--build-arg ARGUS_GID=${ARGUS_GID} \
-f src/web/build_tools/proxy/Dockerfile -t argus-web-proxy:latest .
docker save -o argus-web-proxy-latest.tar argus-web-proxy:latest

9
src/web/build_tools/proxy/conf.d/alert.conf
View File

@@ -1,9 +0,0 @@
server {
listen 80;
server_name alertmanager.alert.argus.com;
location / {
set $alert_backend http://alertmanager.alert.argus.com:9093;
proxy_pass $alert_backend;
}
}

21
src/web/build_tools/proxy/conf.d/log.conf
View File

@@ -1,21 +0,0 @@
# Elasticsearch
server {
listen 80;
server_name es.log.argus.com;
location / {
set $es_backend http://es.log.argus.com:9200;
proxy_pass $es_backend;
}
}
# Kibana
server {
listen 80;
server_name kibana.log.argus.com;
location / {
set $kibana_backend http://kibana.log.argus.com:5601;
proxy_pass $kibana_backend;
}
}

27
src/web/build_tools/proxy/conf.d/master.conf
View File

@@ -1,27 +0,0 @@
server {
listen 80;
server_name master.argus.com;
location / {
set $master_backend http://master.argus.com:3000;
proxy_pass $master_backend;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
# CORS 支持
add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
if ($request_method = OPTIONS) {
add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
add_header 'Content-Length' 0;
add_header 'Content-Type' 'text/plain';
return 204;
}
}
}

21
src/web/build_tools/proxy/conf.d/metric.conf
View File

@@ -1,21 +0,0 @@
# Prometheus
server {
listen 80;
server_name prometheus.metric.argus.com;
location / {
set $prom_backend http://prom.metric.argus.com:9090;
proxy_pass $prom_backend;
}
}
# Grafana
server {
listen 80;
server_name grafana.metric.argus.com;
location / {
set $grafana_backend http://grafana.metric.argus.com:3000;
proxy_pass $grafana_backend;
}
}

9
src/web/build_tools/proxy/conf.d/web.conf
View File

@@ -1,9 +0,0 @@
server {
listen 80;
server_name web.argus.com;
location / {
set $web_backend http://web.argus.com:8080;
proxy_pass $web_backend;
}
}

68
src/web/build_tools/proxy/dns-monitor.sh
View File

@@ -1,68 +0,0 @@
#!/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

39
src/web/build_tools/proxy/nginx.conf.template
View File

@@ -1,39 +0,0 @@
user web_proxy;
worker_processes auto;
events {
worker_connections 1024;
}
http {
include mime.types;
default_type application/octet-stream;
sendfile on;
# 使用系统 resolv.conf（由 update-dns.sh 动态更新）
resolver __RESOLVERS__ valid=30s ipv6=off;
# 启用访问日志
access_log /var/log/nginx/access.log;
error_log /var/log/nginx/error.log;
# 反向代理默认头部
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
server {
listen 80 default_server;
server_name _;
location / {
set $web_backend http://web.argus.com:8080;
proxy_pass $web_backend;
}
}
include /etc/nginx/conf.d/*.conf;
}

61
src/web/build_tools/proxy/start-proxy-supervised.sh
View File

@@ -1,61 +0,0 @@
#!/bin/bash
set -euo pipefail
echo "[INFO] Starting proxy under supervisor..."
TEMPLATE="/etc/nginx/nginx.conf.template"
TARGET="/etc/nginx/nginx.conf"
DNS_CONF_PRIVATE="/private/argus/etc/dns.conf"
DNS_CONF_SYSTEM="/etc/resolv.conf"
DNS_DIR="/private/argus/etc"
DNS_SCRIPT="${DNS_DIR}/update-dns.sh"
RUNTIME_UID="${ARGUS_UID:-2133}"
RUNTIME_GID="${ARGUS_GID:-2015}"
mkdir -p "$DNS_DIR"
chown -R "$RUNTIME_UID:$RUNTIME_GID" "$DNS_DIR" 2>/dev/null || true
if [[ -x "$DNS_SCRIPT" ]]; then
echo "[INFO] Running update-dns.sh before master starts"
# 若脚本存在则执行，保证容器使用 bind 作为 DNS
"$DNS_SCRIPT" || echo "[WARN] update-dns.sh execution failed"
else
echo "[WARN] DNS update script not found or not executable: $DNS_SCRIPT"
fi
# ========== 读取 DNS ==========
if [ -f "$DNS_CONF_PRIVATE" ]; then
echo "从 $DNS_CONF_PRIVATE 读取 DNS 服务器..."
RESOLVERS=$(awk '/^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$/ {print $1}' "$DNS_CONF_PRIVATE" | tr '\n' ' ')
fi
# 如果 /private 文件不存在则 fallback
if [ -z "${RESOLVERS:-}" ]; then
echo "未在 $DNS_CONF_PRIVATE 中找到有效 DNS，使用系统 /etc/resolv.conf"
RESOLVERS=$(awk '/^nameserver/ {print $2}' "$DNS_CONF_SYSTEM" | tr '\n' ' ')
fi
# 最后兜底：若仍为空，使用公共 DNS
if [ -z "$RESOLVERS" ]; then
echo "警告: 未找到任何 DNS，使用默认 8.8.8.8"
RESOLVERS="8.8.8.8"
fi
echo "检测到 DNS 服务器列表: $RESOLVERS"
# ========== 生成 nginx.conf ==========
if [ -f "$TEMPLATE" ]; then
echo "从模板生成 nginx.conf ..."
sed "s|__RESOLVERS__|$RESOLVERS|" "$TEMPLATE" > "$TARGET"
else
echo "错误: 找不到 nginx.conf.template ($TEMPLATE)"
exit 1
fi
# 打印生成结果供排查
grep resolver "$TARGET" || true
echo "[INFO] Launching nginx..."
# 启动 nginx 前台模式
exec /usr/sbin/nginx -g "daemon off;"

39
src/web/build_tools/proxy/supervisord.conf
View File

@@ -1,39 +0,0 @@
[supervisord]
nodaemon=true
logfile=/var/log/supervisor/supervisord.log
pidfile=/var/run/supervisord.pid
user=root
[program:proxy]
command=/usr/local/bin/start-proxy-supervised.sh
user=root
stdout_logfile=/var/log/supervisor/web-proxy.log
stderr_logfile=/var/log/supervisor/web-proxy_error.log
autorestart=true
startretries=3
startsecs=5
stopwaitsecs=10
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

29
src/web/eslint.config.js
View File

@@ -1,29 +0,0 @@
import js from '@eslint/js'
import globals from 'globals'
import reactHooks from 'eslint-plugin-react-hooks'
import reactRefresh from 'eslint-plugin-react-refresh'
import { defineConfig, globalIgnores } from 'eslint/config'
export default defineConfig([
globalIgnores(['dist']),
{
files: ['**/*.{js,jsx}'],
extends: [
js.configs.recommended,
reactHooks.configs['recommended-latest'],
reactRefresh.configs.vite,
],
languageOptions: {
ecmaVersion: 2020,
globals: globals.browser,
parserOptions: {
ecmaVersion: 'latest',
ecmaFeatures: { jsx: true },
sourceType: 'module',
},
},
rules: {
'no-unused-vars': ['error', { varsIgnorePattern: '^[A-Z_]' }],
},
},
])

13
src/web/index.html
View File

@@ -1,13 +0,0 @@
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>GPU集群运维系统</title>
<link rel="icon" type="image/png" href="/src/assets/argus.png" />
</head>
<body>
<div id="root"></div>
<script type="module" src="/src/main.jsx"></script>
</body>
</html>

3617
src/web/package-lock.json generated
View File

File diff suppressed because it is too large Load Diff

Some files were not shown because too many files have changed in this diff Show More