20260626 ARM64 Docker Compose部署与live TA首轮刷新

2026-06-27 11:08:39 +08:00
parent f1a73bd2d1
commit 79a77f6f6e
12 changed files with 832 additions and 5 deletions
--- a/deploy/arm64-compose/.env.example
+++ b/deploy/arm64-compose/.env.example
@@ -0,0 +1,87 @@
+# ours RP ARM64 Docker Compose 示例配置
+# 复制为 .env 后再启动：
+#   cp .env.example .env
+
+# 业务镜像名称；需要先通过 docker load 导入远端 Docker。
+RPKI_IMAGE=ours-rp-runtime-arm64:dev
+
+# 核心 RP 镜像强制以 ARM64 运行；远端233为 x86_64，需要 binfmt/qemu 支持。
+RPKI_PLATFORM=linux/arm64
+
+# 验收默认只跑 APNIC；all5 可改成 afrinic,apnic,arin,lacnic,ripe。
+RIRS=apnic
+
+# 固定跑两轮：首轮 snapshot，第二轮 delta。
+# 负数表示持续运行；ARM64 QEMU 首版验收不建议默认持续运行。
+MAX_RUNS=2
+
+# 两轮之间间隔秒数。
+INTERVAL_SECS=0
+
+# 保留最近多少个 run 目录。
+RETAIN_RUNS=5
+
+# TA/TAL 输入模式：
+# - file-with-ta：完全使用镜像内 fixture；
+# - file-live-ta：snapshot 轮先完成 live TA 获取，delta 轮后台刷新 TA；
+# - url：从 TAL URL 拉取。
+TAL_INPUT_MODE=file-live-ta
+
+# rsync 默认按 module-root 批量拉取，和当前 ours RP soak 默认优化配置一致。
+RSYNC_SCOPE=module-root
+
+# 容器里不需要杀宿主机上的其他 RP 进程；远端宿主机如有竞争进程，请在宿主机侧处理。
+DISABLE_COMPETING_RPS=0
+
+# 运行态数据目录。容器内固定路径，外部由 compose volume 保存。
+RUN_ROOT=/var/lib/ours-rp
+DB_DIR=/var/lib/ours-rp/state/db
+RSYNC_MIRROR_ROOT=/var/lib/ours-rp/state/rsync-mirror
+
+# 每轮结束后清理 daemon 临时目录。
+# Docker Compose 中 tmp 是独立 volume 挂载点，不能删除挂载点本身；默认关闭。
+CLEAN_TMP_AFTER_RUN=0
+
+# 报告使用 compact JSON，降低写盘体积。
+OUTPUT_COMPACT_REPORT=1
+
+# 复用 rsync mirror，避免 delta 每轮从零拉取。
+ALLOW_RSYNC_MIRROR_REUSE=1
+
+# 前一轮失败时，新一轮从 snapshot 恢复。
+FAILURE_SNAPSHOT_RESET=1
+
+# QEMU 验收优先降低额外统计开销；需要精确 DB 统计时改为 3 或其他正整数。
+DB_STATS_EXACT_EVERY=0
+
+# 开启当前主线使用的验证缓存与请求预取能力。
+ENABLE_CHILD_CERTIFICATE_VALIDATION_CACHE=1
+RPKI_ANALYZE=1
+RPKI_EXTRA_ARGS="--enable-transport-request-prefetch --enable-publication-point-validation-cache --enable-roa-validation-cache --parallel-max-repo-sync-workers-global 4 --parallel-phase2-object-workers 4 --memory-trim-after-validation"
+
+# 进度日志阈值。QEMU 下执行较慢，阈值不宜过低。
+RPKI_PROGRESS_LOG=1
+RPKI_PROGRESS_SLOW_SECS=20
+RPKI_PROGRESS_STAGE_FRESH_SLOW_MS=2000
+RPKI_PROGRESS_PP_CONTROL_SLOW_MS=200
+RPKI_PROGRESS_PP_CACHE_SLOW_MS=100
+RPKI_PROGRESS_CONTROL_LOOP_SLOW_MS=2000
+
+# live TA 刷新超时。
+LIVE_TA_REFRESH_CONNECT_TIMEOUT_SECS=15
+LIVE_TA_REFRESH_MAX_TIME_SECS=120
+
+# file-live-ta 在 snapshot 轮先完成 live TA 获取再启动子进程，避免首轮使用旧 fixture TA。
+LIVE_TA_REFRESH_BEFORE_SNAPSHOT=1
+
+# metrics sidecar 配置。
+METRICS_INSTANCE=remote233-arm64-qemu
+METRICS_PORT=9556
+METRICS_POLL_SECS=10
+
+# Prometheus / Grafana 配置。
+PROMETHEUS_PORT=9090
+PROMETHEUS_RETENTION=7d
+GRAFANA_PORT=3000
+GRAFANA_ADMIN_USER=admin
+GRAFANA_ADMIN_PASSWORD=admin
--- a/deploy/arm64-compose/docker-compose.yml
+++ b/deploy/arm64-compose/docker-compose.yml
@@ -0,0 +1,94 @@
+services:
+  ours-rp-soak:
+    image: ${RPKI_IMAGE:-ours-rp-runtime-arm64:dev}
+    platform: ${RPKI_PLATFORM:-linux/arm64}
+    container_name: ours-rp-arm64-soak
+    env_file:
+      - ./.env
+    environment:
+      PACKAGE_ROOT: /opt/ours-rp
+      ENV_FILE: /opt/ours-rp/.env
+      RUN_ROOT: /var/lib/ours-rp
+      BIN_DIR: /opt/ours-rp/bin
+      FIXTURE_DIR: /opt/ours-rp/fixtures
+    volumes:
+      - ./.env:/opt/ours-rp/.env:ro
+      - rpki-state:/var/lib/ours-rp/state
+      - rpki-runs:/var/lib/ours-rp/runs
+      - rpki-logs:/var/lib/ours-rp/logs
+      - rpki-tmp:/var/lib/ours-rp/tmp
+    restart: "no"
+    profiles:
+      - core
+
+  artifact-metrics:
+    image: ${RPKI_IMAGE:-ours-rp-runtime-arm64:dev}
+    platform: ${RPKI_PLATFORM:-linux/arm64}
+    container_name: ours-rp-arm64-artifact-metrics
+    env_file:
+      - ./.env
+    command:
+      - /opt/ours-rp/bin/rpki_artifact_metrics
+      - --run-root
+      - /var/lib/ours-rp
+      - --listen
+      - 0.0.0.0:9556
+      - --poll-secs
+      - ${METRICS_POLL_SECS:-10}
+      - --instance
+      - ${METRICS_INSTANCE:-remote233-arm64-qemu}
+    ports:
+      - "${METRICS_PORT:-9556}:9556"
+    volumes:
+      - rpki-state:/var/lib/ours-rp/state:ro
+      - rpki-runs:/var/lib/ours-rp/runs:ro
+      - rpki-logs:/var/lib/ours-rp/logs:ro
+    restart: unless-stopped
+    profiles:
+      - sidecar
+
+  prometheus:
+    image: ${PROMETHEUS_IMAGE:-prom/prometheus:v2.55.1}
+    container_name: ours-rp-arm64-prometheus
+    command:
+      - --config.file=/etc/prometheus/prometheus.yml
+      - --storage.tsdb.path=/prometheus
+      - --storage.tsdb.retention.time=${PROMETHEUS_RETENTION:-7d}
+      - --web.enable-lifecycle
+    depends_on:
+      - artifact-metrics
+    ports:
+      - "${PROMETHEUS_PORT:-9090}:9090"
+    volumes:
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - prometheus-data:/prometheus
+    restart: unless-stopped
+    profiles:
+      - monitor
+
+  grafana:
+    image: ${GRAFANA_IMAGE:-grafana/grafana:11.3.1}
+    container_name: ours-rp-arm64-grafana
+    depends_on:
+      - prometheus
+    ports:
+      - "${GRAFANA_PORT:-3000}:3000"
+    environment:
+      GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
+      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-admin}
+      GF_USERS_ALLOW_SIGN_UP: "false"
+    volumes:
+      - grafana-data:/var/lib/grafana
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
+    restart: unless-stopped
+    profiles:
+      - monitor
+
+volumes:
+  rpki-state:
+  rpki-runs:
+  rpki-logs:
+  rpki-tmp:
+  prometheus-data:
+  grafana-data:
--- a/deploy/arm64-compose/grafana/dashboards/ours-rp-arm64-overview.json
+++ b/deploy/arm64-compose/grafana/dashboards/ours-rp-arm64-overview.json
@@ -0,0 +1,80 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {"type": "prometheus", "uid": "Prometheus"},
+      "fieldConfig": {"defaults": {"color": {"mode": "thresholds"}, "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}}, "overrides": []},
+      "gridPos": {"h": 5, "w": 6, "x": 0, "y": 0},
+      "id": 1,
+      "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": "ours_rp_latest_run_sequence", "legendFormat": "latest run", "refId": "A"}],
+      "title": "Latest Run Sequence",
+      "type": "stat"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "Prometheus"},
+      "fieldConfig": {"defaults": {"color": {"mode": "thresholds"}, "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}}, "overrides": []},
+      "gridPos": {"h": 5, "w": 6, "x": 6, "y": 0},
+      "id": 2,
+      "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": "ours_rp_latest_run_wall_ms / 1000", "legendFormat": "wall seconds", "refId": "A"}],
+      "title": "Latest Wall Seconds",
+      "type": "stat"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "Prometheus"},
+      "fieldConfig": {"defaults": {"color": {"mode": "palette-classic"}, "custom": {"drawStyle": "line", "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 4, "showPoints": "never"}}, "overrides": []},
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 0},
+      "id": 3,
+      "options": {"legend": {"displayMode": "list", "placement": "bottom", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "none"}},
+      "targets": [{"expr": "ours_rp_latest_run_wall_ms / 1000", "legendFormat": "wall seconds", "refId": "A"}],
+      "title": "Wall Time Trend",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "Prometheus"},
+      "fieldConfig": {"defaults": {"color": {"mode": "palette-classic"}, "custom": {"drawStyle": "line", "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 4, "showPoints": "never"}}, "overrides": []},
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 5},
+      "id": 4,
+      "options": {"legend": {"displayMode": "list", "placement": "bottom", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "none"}},
+      "targets": [
+        {"expr": "ours_rp_latest_run_vrps", "legendFormat": "VRPs", "refId": "A"},
+        {"expr": "ours_rp_latest_run_aspas", "legendFormat": "VAPs", "refId": "B"},
+        {"expr": "ours_rp_latest_run_publication_points", "legendFormat": "PP", "refId": "C"}
+      ],
+      "title": "Output Counts",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "Prometheus"},
+      "fieldConfig": {"defaults": {"color": {"mode": "palette-classic"}, "custom": {"drawStyle": "line", "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 4, "showPoints": "never"}}, "overrides": []},
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 8},
+      "id": 5,
+      "options": {"legend": {"displayMode": "list", "placement": "bottom", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "none"}},
+      "targets": [{"expr": "ours_rp_latest_run_max_rss_kb / 1024", "legendFormat": "Max RSS MiB", "refId": "A"}],
+      "title": "Max RSS Trend",
+      "type": "timeseries"
+    }
+  ],
+  "preload": false,
+  "refresh": "10s",
+  "schemaVersion": 40,
+  "tags": ["ours-rp", "arm64", "qemu"],
+  "templating": {"list": []},
+  "time": {"from": "now-1h", "to": "now"},
+  "timepicker": {},
+  "timezone": "browser",
+  "title": "Ours RP ARM64 Compose Overview",
+  "uid": "ours-rp-arm64-overview",
+  "version": 1,
+  "weekStart": ""
+}
--- a/deploy/arm64-compose/grafana/provisioning/dashboards/dashboard.yml
+++ b/deploy/arm64-compose/grafana/provisioning/dashboards/dashboard.yml
@@ -0,0 +1,12 @@
+apiVersion: 1
+
+providers:
+  - name: ours-rp-arm64
+    orgId: 1
+    folder: Ours RP ARM64
+    type: file
+    disableDeletion: false
+    updateIntervalSeconds: 10
+    allowUiUpdates: true
+    options:
+      path: /var/lib/grafana/dashboards
--- a/deploy/arm64-compose/grafana/provisioning/datasources/prometheus.yml
+++ b/deploy/arm64-compose/grafana/provisioning/datasources/prometheus.yml
@@ -0,0 +1,10 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    uid: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: true
--- a/deploy/arm64-compose/prometheus.yml
+++ b/deploy/arm64-compose/prometheus.yml
@@ -0,0 +1,13 @@
+global:
+  scrape_interval: 5s
+  evaluation_interval: 5s
+
+scrape_configs:
+  - job_name: ours-rp-artifact-metrics
+    metrics_path: /metrics
+    static_configs:
+      - targets:
+          - artifact-metrics:9556
+        labels:
+          rp: ours-rp
+          source: arm64-compose-artifact-sidecar