NASP/rpki
75
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

20260701 installer接入RTR监控目录

Browse Source
This commit is contained in:
yuyr 2026-07-01 12:06:49 +08:00
parent f8988b18cd
commit a501cfb709
12 changed files with 764 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
deploy/arm64-installer/.env.example
View File

@ -80,6 +80,12 @@ RPKI_PROGRESS_CONTROL_LOOP_SLOW_MS=2000
METRICS_INSTANCE=arm64-installer
METRICS_PORT=9556
METRICS_POLL_SECS=10
# Optional external RTR report directory produced by a separately deployed RTR service.
# Default points to an installer-managed empty fallback directory. To enable real RTR
# metrics, set this to the host-side report directory, for example:
# RTR_REPORT_DIR=/root/rpki/report
RTR_REPORT_DIR=/var/lib/ours-rp-arm64-installer/empty-rtr-report
RTR_REPORT_CONTAINER_DIR=/var/lib/ours-rp/rtr-report
# Prometheus / Grafana.
# Monitor images are packaged as docker-save archives and loaded by install.sh.

3
deploy/arm64-installer/compose/docker-compose.yml
View File

@ -27,6 +27,8 @@ services:
container_name: ${COMPOSE_PROJECT_NAME:-ours-rp-package-installer}-artifact-metrics
env_file:
- ../.env
environment:
RPKI_METRICS_RTR_REPORT_DIR: ${RTR_REPORT_CONTAINER_DIR:-/var/lib/ours-rp/rtr-report}
command:
- /opt/ours-rp/bin/rpki_artifact_metrics
- --run-root
@ -43,6 +45,7 @@ services:
- ${HOST_DATA_DIR:-/var/lib/ours-rp-package-installer}/state:/var/lib/ours-rp/state:ro
- ${HOST_DATA_DIR:-/var/lib/ours-rp-package-installer}/runs:/var/lib/ours-rp/runs:ro
- ${HOST_DATA_DIR:-/var/lib/ours-rp-package-installer}/logs:/var/lib/ours-rp/logs:ro
- ${RTR_REPORT_DIR:-/var/lib/ours-rp-package-installer/empty-rtr-report}:${RTR_REPORT_CONTAINER_DIR:-/var/lib/ours-rp/rtr-report}:ro
restart: unless-stopped
profiles:
- sidecar

666
deploy/arm64-installer/compose/grafana/dashboards/ours-rp-rtr-overview.json Normal file
View File

@ -0,0 +1,666 @@
{
"annotations": {
"list": []
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": null,
"links": [],
"liveNow": false,
"panels": [
{
"id": 1,
"title": "RTR Metrics Enabled",
"type": "stat",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 4,
"w": 4,
"x": 0,
"y": 0
},
"fieldConfig": {
"defaults": {
"unit": "short",
"decimals": 0
},
"overrides": []
},
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"targets": [
{
"expr": "max(ours_rp_rtr_metrics_enabled)",
"legendFormat": "enabled",
"refId": "A",
"instant": true
}
]
},
{
"id": 2,
"title": "Refresh Success",
"type": "stat",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 4,
"w": 5,
"x": 4,
"y": 0
},
"fieldConfig": {
"defaults": {
"unit": "short",
"decimals": 0
},
"overrides": []
},
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"targets": [
{
"expr": "max(ours_rp_rtr_source_refresh_status{status=\"success\"})",
"legendFormat": "success",
"refId": "A",
"instant": true
}
]
},
{
"id": 3,
"title": "Consecutive Failures",
"type": "stat",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 4,
"w": 5,
"x": 9,
"y": 0
},
"fieldConfig": {
"defaults": {
"unit": "short",
"decimals": 0
},
"overrides": []
},
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"targets": [
{
"expr": "max(ours_rp_rtr_source_refresh_consecutive_failures)",
"legendFormat": "failures",
"refId": "A",
"instant": true
}
]
},
{
"id": 4,
"title": "Last Success Age",
"type": "stat",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 4,
"w": 5,
"x": 14,
"y": 0
},
"fieldConfig": {
"defaults": {
"unit": "s",
"decimals": 0,
"min": 0
},
"overrides": []
},
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"targets": [
{
"expr": "max(ours_rp_rtr_source_last_success_age_seconds)",
"legendFormat": "age",
"refId": "A",
"instant": true
}
]
},
{
"id": 5,
"title": "RTR RSS",
"type": "stat",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 4,
"w": 5,
"x": 19,
"y": 0
},
"fieldConfig": {
"defaults": {
"unit": "bytes",
"decimals": 0,
"min": 0
},
"overrides": []
},
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"targets": [
{
"expr": "max(ours_rp_rtr_process_rss_bytes)",
"legendFormat": "rss",
"refId": "A",
"instant": true
}
]
},
{
"id": 6,
"title": "Data Quality Totals",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 4
},
"fieldConfig": {
"defaults": {
"unit": "short",
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "ours_rp_rtr_data_quality_items{stage=~\"ccr_input|before_slurm|after_slurm\",type=\"total\"}",
"legendFormat": "{{stage}} total",
"refId": "A"
},
{
"expr": "ours_rp_rtr_data_quality_items{stage=\"after_slurm\",type=\"vrp\"}",
"legendFormat": "after_slurm vrp",
"refId": "B"
},
{
"expr": "ours_rp_rtr_data_quality_items{stage=\"after_slurm\",type=\"aspa\"}",
"legendFormat": "after_slurm aspa",
"refId": "C"
}
]
},
{
"id": 7,
"title": "SLURM Filters / Assertions",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 4
},
"fieldConfig": {
"defaults": {
"unit": "short",
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "ours_rp_rtr_slurm_filters",
"legendFormat": "filter {{type}}",
"refId": "A"
},
{
"expr": "ours_rp_rtr_slurm_assertions",
"legendFormat": "assert {{type}}",
"refId": "B"
}
]
},
{
"id": 8,
"title": "Cache Ready / Delta Window",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 8,
"w": 8,
"x": 0,
"y": 12
},
"fieldConfig": {
"defaults": {
"unit": "short",
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "ours_rp_rtr_cache_ready",
"legendFormat": "ready",
"refId": "A"
},
{
"expr": "ours_rp_rtr_cache_delta_window_length",
"legendFormat": "v{{version}} length",
"refId": "B"
}
]
},
{
"id": 9,
"title": "Cache Snapshot Items",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 8,
"w": 8,
"x": 8,
"y": 12
},
"fieldConfig": {
"defaults": {
"unit": "short",
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "ours_rp_rtr_cache_snapshot_items",
"legendFormat": "v{{version}} {{type}}",
"refId": "A"
}
]
},
{
"id": 10,
"title": "Latest Delta Items",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 8,
"w": 8,
"x": 16,
"y": 12
},
"fieldConfig": {
"defaults": {
"unit": "short",
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "ours_rp_rtr_cache_delta_items",
"legendFormat": "v{{version}} {{direction}} {{type}}",
"refId": "A"
}
]
},
{
"id": 11,
"title": "Connections",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 8,
"w": 8,
"x": 0,
"y": 20
},
"fieldConfig": {
"defaults": {
"unit": "short",
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "ours_rp_rtr_active_connections",
"legendFormat": "active",
"refId": "A"
},
{
"expr": "ours_rp_rtr_connections",
"legendFormat": "{{transport}}",
"refId": "B"
}
]
},
{
"id": 12,
"title": "Connection Utilization / Max",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 8,
"w": 8,
"x": 8,
"y": 20
},
"fieldConfig": {
"defaults": {
"min": 0
},
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": ".*utilization.*"
},
"properties": [
{
"id": "unit",
"value": "percentunit"
}
]
},
{
"matcher": {
"id": "byRegexp",
"options": ".*max.*"
},
"properties": [
{
"id": "unit",
"value": "short"
}
]
}
]
},
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "ours_rp_rtr_connection_utilization",
"legendFormat": "utilization",
"refId": "A"
},
{
"expr": "ours_rp_rtr_max_connections",
"legendFormat": "max",
"refId": "B"
}
]
},
{
"id": 13,
"title": "Report Age",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 8,
"w": 8,
"x": 16,
"y": 20
},
"fieldConfig": {
"defaults": {
"unit": "s",
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "ours_rp_rtr_source_report_age_seconds",
"legendFormat": "source",
"refId": "A"
},
{
"expr": "ours_rp_rtr_runtime_report_age_seconds",
"legendFormat": "runtime",
"refId": "B"
},
{
"expr": "ours_rp_rtr_clients_report_age_seconds",
"legendFormat": "clients",
"refId": "C"
}
]
}
],
"refresh": "10s",
"schemaVersion": 40,
"tags": [
"rpki",
"inter-rp",
"routinator"
],
"templating": {
"list": []
},
"time": {
"from": "now-6h",
"to": "now"
},
"timezone": "browser",
"title": "RTR Service Overview",
"uid": "ours-rp-rtr-overview",
"version": 1
}

12
deploy/arm64-installer/docs/README.en.md
View File

@ -43,6 +43,7 @@ Defaults:
- `METRICS_PLATFORM=__PACKAGE_PLATFORM__`
- `MONITOR_PLATFORM=__PACKAGE_PLATFORM__`
- `ALLOW_CROSS_ARCH=0`
- `RTR_REPORT_DIR=__HOST_DATA_DIR__/empty-rtr-report`, which mounts an empty fallback directory by default; set it to a real host directory such as `/root/rpki/report` to ingest reports from a separately deployed RTR service
## First Start Semantics
@ -89,6 +90,17 @@ GRAFANA_ADMIN_PASSWORD=admin
Change the password and restrict public access for production deployments.
## Optional RTR report metrics input
If a separately deployed RTR service on the same host continuously writes `rtr-source-*`, `rtr-runtime-*`, and `rtr-clients-*` JSON reports, configure:
```bash
RTR_REPORT_DIR=/root/rpki/report
RTR_REPORT_CONTAINER_DIR=/var/lib/ours-rp/rtr-report
```
The `artifact-metrics` container mounts the host directory read-only and reads it through `RPKI_METRICS_RTR_REPORT_DIR`, producing `ours_rp_rtr_*` metrics. By default, `RTR_REPORT_DIR` points at an empty fallback directory under the installer data root, so the metrics container also starts cleanly without an RTR service.
## Data Directory
Default host directory:

12
deploy/arm64-installer/docs/README.zh-CN.md
View File

@ -43,6 +43,7 @@ vim .env
- `METRICS_PLATFORM=__PACKAGE_PLATFORM__`
- `MONITOR_PLATFORM=__PACKAGE_PLATFORM__`
- `ALLOW_CROSS_ARCH=0`
- `RTR_REPORT_DIR=__HOST_DATA_DIR__/empty-rtr-report`，默认挂载空目录；如需接入独立 RTR 服务 report，可设置为宿主机真实目录，例如 `/root/rpki/report`
## 首次启动语义
@ -89,6 +90,17 @@ GRAFANA_ADMIN_PASSWORD=admin
生产部署时应修改密码并限制外部访问。
## 可选 RTR report 监控接入
如果同一台机器上已经有独立部署的 RTR 服务，并且它持续输出 `rtr-source-*`、`rtr-runtime-*`、`rtr-clients-*` JSON report，可在 `.env` 中配置：
```bash
RTR_REPORT_DIR=/root/rpki/report
RTR_REPORT_CONTAINER_DIR=/var/lib/ours-rp/rtr-report
```
`artifact-metrics` 容器会以只读方式挂载该目录，并通过 `RPKI_METRICS_RTR_REPORT_DIR` 读取 report，输出 `ours_rp_rtr_*` 指标。默认 `RTR_REPORT_DIR` 指向安装包数据目录下的空 fallback 目录，因此未接入 RTR 服务时 metrics 容器也能稳定启动。
## 数据目录
默认宿主机目录：

8
deploy/arm64-installer/docs/operations.en.md
View File

@ -67,6 +67,14 @@ Important checks:
- `allow_cross_arch`
- `periodic_snapshot_reset`
- `periodic_snapshot_max_deltas`
- `rtr_report_dir`
- `rtr_report_container_dir`
To verify RTR report ingestion:
```bash
curl -s "http://127.0.0.1:${METRICS_PORT:-9556}/metrics" | grep '^ours_rp_rtr_' | head
```
## Upgrade

8
deploy/arm64-installer/docs/operations.zh-CN.md
View File

@ -67,6 +67,14 @@ ALLOW_CROSS_ARCH=1
- `allow_cross_arch`
- `periodic_snapshot_reset`
- `periodic_snapshot_max_deltas`
- `rtr_report_dir`
- `rtr_report_container_dir`
如需确认 RTR report 已接入：
```bash
curl -s "http://127.0.0.1:${METRICS_PORT:-9556}/metrics" | grep '^ours_rp_rtr_' | head
```
## 升级

16
deploy/arm64-installer/docs/troubleshooting.en.md
View File

@ -53,6 +53,22 @@ docker run --rm --platform __PACKAGE_PLATFORM__ \
/opt/ours-rp/bin/rpki_artifact_metrics --help
```
## RTR report metrics are empty
Check `.env`:
```bash
grep '^RTR_REPORT_DIR=' .env
test -d "$(grep '^RTR_REPORT_DIR=' .env | cut -d= -f2-)" && echo ok
```
Check the metrics container mount:
```bash
docker inspect "$(grep '^COMPOSE_PROJECT_NAME=' .env | cut -d= -f2-)-artifact-metrics" \
| jq '.[0].Mounts[] | select(.Destination=="/var/lib/ours-rp/rtr-report")'
```
## First Snapshot Times Out
All-five snapshot can be slow, especially under QEMU. Increase timeout:

16
deploy/arm64-installer/docs/troubleshooting.zh-CN.md
View File

@ -53,6 +53,22 @@ docker run --rm --platform __PACKAGE_PLATFORM__ \
/opt/ours-rp/bin/rpki_artifact_metrics --help
```
## RTR report 指标为空
检查 `.env`：
```bash
grep '^RTR_REPORT_DIR=' .env
test -d "$(grep '^RTR_REPORT_DIR=' .env | cut -d= -f2-)" && echo ok
```
检查 metrics 容器是否挂载该目录：
```bash
docker inspect "$(grep '^COMPOSE_PROJECT_NAME=' .env | cut -d= -f2-)-artifact-metrics" \
| jq '.[0].Mounts[] | select(.Destination=="/var/lib/ours-rp/rtr-report")'
```
## 首轮 snapshot 超时
all5 snapshot 可能很慢，尤其在 QEMU 环境。可以提高超时：

13
deploy/arm64-installer/scripts/common.sh
View File

@ -196,6 +196,8 @@ load_env() {
RPKI_PLATFORM="${RPKI_PLATFORM:-$PACKAGE_PLATFORM}"
METRICS_IMAGE="${METRICS_IMAGE:-ours-rp-metrics-${PACKAGE_ARCH}:dev}"
METRICS_PLATFORM="${METRICS_PLATFORM:-$PACKAGE_PLATFORM}"
RTR_REPORT_DIR="${RTR_REPORT_DIR:-$HOST_DATA_DIR/empty-rtr-report}"
RTR_REPORT_CONTAINER_DIR="${RTR_REPORT_CONTAINER_DIR:-/var/lib/ours-rp/rtr-report}"
MONITOR_PLATFORM="${MONITOR_PLATFORM:-$PACKAGE_PLATFORM}"
PROMETHEUS_IMAGE="${PROMETHEUS_IMAGE:-prom/prometheus:v2.55.1}"
GRAFANA_IMAGE="${GRAFANA_IMAGE:-grafana/grafana:11.3.1}"
@ -205,12 +207,21 @@ load_env() {
persist_env_default "$ENV_FILE" "METRICS_IMAGE" "$METRICS_IMAGE"
persist_env_default "$ENV_FILE" "METRICS_PLATFORM" "$METRICS_PLATFORM"
persist_env_default "$ENV_FILE" "RTR_REPORT_DIR" "$RTR_REPORT_DIR"
persist_env_default "$ENV_FILE" "RTR_REPORT_CONTAINER_DIR" "$RTR_REPORT_CONTAINER_DIR"
}
compose_cmd() {
docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" -p "$COMPOSE_PROJECT_NAME" "$@"
}
validate_rtr_report_dir() {
load_env
[[ -n "${RTR_REPORT_DIR:-}" ]] || return 0
[[ "$RTR_REPORT_DIR" = /* ]] || die "RTR_REPORT_DIR must be an absolute host path: $RTR_REPORT_DIR"
[[ -d "$RTR_REPORT_DIR" ]] || die "RTR_REPORT_DIR does not exist or is not a directory: $RTR_REPORT_DIR"
}
create_data_dirs() {
load_env
mkdir -p \
@ -218,8 +229,10 @@ create_data_dirs() {
"$HOST_DATA_DIR/runs" \
"$HOST_DATA_DIR/logs" \
"$HOST_DATA_DIR/tmp" \
"$HOST_DATA_DIR/empty-rtr-report" \
"$HOST_DATA_DIR/prometheus" \
"$HOST_DATA_DIR/grafana"
validate_rtr_report_dir
chmod 755 "$HOST_DATA_DIR" "$HOST_DATA_DIR/state" "$HOST_DATA_DIR/runs" "$HOST_DATA_DIR/logs" "$HOST_DATA_DIR/tmp" || true
chmod 777 "$HOST_DATA_DIR/prometheus" "$HOST_DATA_DIR/grafana" || true
}

2
deploy/arm64-installer/status.sh
View File

@ -36,6 +36,8 @@ echo "runtime_image=$RPKI_IMAGE"
echo "runtime_platform=$RPKI_PLATFORM"
echo "metrics_image=$METRICS_IMAGE"
echo "metrics_platform=$METRICS_PLATFORM"
echo "rtr_report_dir=$RTR_REPORT_DIR"
echo "rtr_report_container_dir=$RTR_REPORT_CONTAINER_DIR"
echo "monitor_platform=$MONITOR_PLATFORM"
echo "rirs=${RIRS:-}"
echo "max_runs=${MAX_RUNS:-}"

2
scripts/docker/build_docker_installer_package.sh
View File

@ -329,6 +329,8 @@ if [[ -f "$stage/.env.example" ]]; then
replace_or_append_env "$stage/.env.example" "METRICS_IMAGE" "$METRICS_IMAGE"
replace_or_append_env "$stage/.env.example" "METRICS_PLATFORM" "$TARGET_PLATFORM"
replace_or_append_env "$stage/.env.example" "HOST_DATA_DIR" "$HOST_DATA_DIR_DEFAULT"
replace_or_append_env "$stage/.env.example" "RTR_REPORT_DIR" "$HOST_DATA_DIR_DEFAULT/empty-rtr-report"
replace_or_append_env "$stage/.env.example" "RTR_REPORT_CONTAINER_DIR" "/var/lib/ours-rp/rtr-report"
replace_or_append_env "$stage/.env.example" "ALLOW_CROSS_ARCH" "0"
replace_or_append_env "$stage/.env.example" "METRICS_INSTANCE" "$METRICS_INSTANCE_DEFAULT"
replace_or_append_env "$stage/.env.example" "MONITOR_PLATFORM" "$TARGET_PLATFORM"