NASP/rpki
84
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

20260721 metrics 服务新增 CCR rpki-client 格式检查指标与 Grafana 面板（#125）

Browse Source
This commit is contained in:
yuyr
2026-07-21 18:07:05 +08:00
parent 4074323302
commit f86fbd4939
9 changed files with 956 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -88,6 +88,12 @@ RPKI_PROGRESS_CONTROL_LOOP_SLOW_MS=2000
METRICS_INSTANCE=__PACKAGE_ARCH__-installer
METRICS_PORT=9556
METRICS_POLL_SECS=10
# CCR rpki-client format check: the artifact-metrics container runs
# `rpki-client -f result.ccr` once for every newly completed run and exports
# ours_rp_ccr_format_check_* metrics. The binary is packaged inside the
# metrics image; adjust only when deliberately testing another binary.
CCR_CHECK_BIN=/opt/ours-rp/bin/rpki-client
CCR_CHECK_TIMEOUT_SECS=120
# 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:

4
deploy/docker-installer/compose/docker-compose.yml
View File

@@ -39,6 +39,10 @@ services:
- ${METRICS_POLL_SECS:-10}
- --instance
- ${METRICS_INSTANCE:-package-installer}
- --ccr-check-bin
- ${CCR_CHECK_BIN:-/opt/ours-rp/bin/rpki-client}
- --ccr-check-timeout-secs
- ${CCR_CHECK_TIMEOUT_SECS:-120}
ports:
- "${METRICS_PORT:-9556}:9556"
volumes:

258
deploy/docker-installer/compose/grafana/dashboards/ours-rp-soak-overview.json
View File

@@ -850,6 +850,264 @@
],
"title": "Fresh PP / Object Counts by Run",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"decimals": 0,
"unit": "none",
"mappings": [
{
"type": "value",
"options": {
"1": {
"text": "PASS",
"color": "green"
},
"0": {
"text": "FAIL",
"color": "red"
}
}
}
]
},
"overrides": []
},
"gridPos": {
"x": 0,
"y": 56,
"w": 6,
"h": 4
},
"id": 19,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.3.1",
"targets": [
{
"expr": "max(ours_rp_ccr_format_check_last_success and on (exported_instance) topk(1, ours_rp_run_sequence))",
"legendFormat": "CCR check",
"refId": "A"
}
],
"title": "Latest CCR Format Check",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"decimals": 0,
"unit": "none"
},
"overrides": []
},
"gridPos": {
"x": 6,
"y": 56,
"w": 6,
"h": 4
},
"id": 20,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.3.1",
"targets": [
{
"expr": "max(ours_rp_ccr_format_check_last_run_sequence and on (exported_instance) topk(1, ours_rp_run_sequence))",
"legendFormat": "run seq",
"refId": "A"
}
],
"title": "CCR Checked Run Sequence",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"decimals": 1,
"unit": "s"
},
"overrides": []
},
"gridPos": {
"x": 12,
"y": 56,
"w": 6,
"h": 4
},
"id": 21,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.3.1",
"targets": [
{
"expr": "max(ours_rp_ccr_format_check_last_duration_seconds and on (exported_instance) topk(1, ours_rp_run_sequence))",
"legendFormat": "duration",
"refId": "A"
}
],
"title": "CCR Check Duration",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"decimals": 0,
"unit": "none",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 1
}
]
}
},
"overrides": []
},
"gridPos": {
"x": 18,
"y": 56,
"w": 6,
"h": 4
},
"id": 22,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.3.1",
"targets": [
{
"expr": "max(ours_rp_ccr_format_check_consecutive_failures and on (exported_instance) topk(1, ours_rp_run_sequence))",
"legendFormat": "failures",
"refId": "A"
}
],
"title": "CCR Check Consecutive Failures",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"unit": "none",
"decimals": 0,
"min": 0
},
"overrides": []
},
"gridPos": {
"x": 0,
"y": 60,
"w": 24,
"h": 8
},
"id": 23,
"options": {
"legend": {
"calcs": [
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"expr": "sum by (result) (ours_rp_ccr_format_check_total)",
"legendFormat": "{{result}} checks",
"refId": "A"
},
{
"expr": "max(ours_rp_ccr_format_check_last_success and on (exported_instance) topk(1, ours_rp_run_sequence))",
"legendFormat": "latest check ok",
"refId": "B"
}
],
"title": "CCR Format Check Results",
"type": "timeseries"
}
],
"refresh": "5s",

6
deploy/docker-installer/docs/README.en.md
View File

@@ -125,6 +125,12 @@ If a separately deployed RTR service on the same host continuously writes `rtr-s
The command accepts only an absolute path on the same host, validates the candidate Compose mount, and atomically updates `.env`. It recreates only `artifact-metrics`, Prometheus, and Grafana; it does not restart or recreate `ours-rp-soak`. The `artifact-metrics` container mounts the 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.
## CCR artifact format check metrics
The metrics image ships the official `rpki-client 9.8`. For every newly completed run, `artifact-metrics` runs `rpki-client -f result.ccr` once and exports `ours_rp_ccr_format_check_*` metrics (cumulative pass/ccr_parse_error/tool_error counters, latest check result, check duration, consecutive failures). The Grafana `Ours RP Soak Overview` dashboard shows them in a dedicated panel row. On service start only the latest existing run is checked; older history is not backfilled.
Related environment variables (normally no need to change): `CCR_CHECK_BIN` (defaults to the in-image `/opt/ours-rp/bin/rpki-client`) and `CCR_CHECK_TIMEOUT_SECS` (default 120 seconds).
## Data Directory
Default host directory:

6
deploy/docker-installer/docs/README.zh-CN.md
View File

@@ -125,6 +125,12 @@ GRAFANA_ADMIN_PASSWORD=admin
该命令只接受本机绝对路径，会先校验候选 Compose 挂载，再原子更新 `.env`。随后只重建 `artifact-metrics`、Prometheus 和 Grafana，不重启或重建 `ours-rp-soak`。`artifact-metrics` 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。
## CCR 产物格式检查监控
metrics 镜像内置官方 `rpki-client 9.8`。`artifact-metrics` 会对每个新完成 run 的 `result.ccr` 执行一次 `rpki-client -f` 格式检查，并输出 `ours_rp_ccr_format_check_*` 指标（累计 pass/ccr_parse_error/tool_error、最近检查结果、检查耗时、连续失败数）。Grafana `Ours RP Soak Overview` 底部有对应面板。服务启动时只补查最新的一个历史 run，不回扫全部历史。
相关环境变量（通常无需修改）：`CCR_CHECK_BIN`（默认为镜像内 `/opt/ours-rp/bin/rpki-client`）、`CCR_CHECK_TIMEOUT_SECS`（默认 120 秒）。
## 数据目录
默认宿主机目录：

12
deploy/docker-installer/scripts/common.sh
View File

@@ -756,6 +756,18 @@ verify_metrics_image() {
log "verifying metrics image $METRICS_IMAGE on $METRICS_PLATFORM"
verify_image_platform "$METRICS_IMAGE" "$METRICS_PLATFORM" "metrics"
verify_image_usage_output "$METRICS_IMAGE" "$METRICS_PLATFORM" "metrics" /opt/ours-rp/bin/rpki_artifact_metrics --help
verify_metrics_image_rpki_client
}
verify_metrics_image_rpki_client() {
local output
local status
set +e
output="$(docker run --rm --platform "$METRICS_PLATFORM" "$METRICS_IMAGE" /opt/ours-rp/bin/rpki-client -V 2>&1)"
status=$?
set -e
[[ "$status" == "0" ]] || die "metrics image rpki-client -V failed: image=$METRICS_IMAGE exit=$status output=$output"
grep -q "rpki-client" <<<"$output" || die "metrics image rpki-client -V unexpected output: $output"
}
verify_image_platform() {