[#31] grafana 面板uid冲突问题解决

build/build_images.sh

@@ -12,7 +12,7 @@ Options:
   --master-offline  Build master offline image (requires src/master/offline_wheels.tar.gz)
   --metric          Build metric module images (ftp, prometheus, grafana, test nodes)
   --no-cache        Build all images without using Docker layer cache
-  --only LIST       Comma-separated targets to build: core,master,metric,web,alert,all
+  --only LIST       Comma-separated targets to build: core,master,metric,web,alert,sys,all
   -h, --help        Show this help message
 
 Examples:
@@ -31,6 +31,7 @@ build_master_offline=false
 build_metric=true
 build_web=true
 build_alert=true
+build_sys=true
 no_cache=false
 
 while [[ $# -gt 0 ]]; do
@@ -62,7 +63,7 @@ while [[ $# -gt 0 ]]; do
       fi
       sel="$2"; shift 2
       # reset all, then enable selected
-      build_core=false; build_master=false; build_metric=false; build_web=false; build_alert=false
+      build_core=false; build_master=false; build_metric=false; build_web=false; build_alert=false; build_sys=false
       IFS=',' read -ra parts <<< "$sel"
       for p in "${parts[@]}"; do
         case "$p" in
@@ -71,7 +72,8 @@ while [[ $# -gt 0 ]]; do
           metric) build_metric=true ;;
           web) build_web=true ;;
           alert) build_alert=true ;;
-          all) build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true ;;
+          sys) build_sys=true ;;
+          all) build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true; build_sys=true ;;
           *) echo "Unknown --only target: $p" >&2; exit 1 ;;
         esac
       done
@@ -286,6 +288,42 @@ if [[ "$build_metric" == true ]]; then
   done
 fi
 
+# =======================================
+# Sys (system tests) node images
+# =======================================
+
+if [[ "$build_sys" == true ]]; then
+  echo ""
+  echo "Building Sys node images..."
+
+  sys_base_images=(
+    "ubuntu:22.04"
+    "nvidia/cuda:12.2.2-runtime-ubuntu22.04"
+  )
+
+  for base_image in "${sys_base_images[@]}"; do
+    if ! pull_base_image "$base_image"; then
+      build_failed=true
+    fi
+  done
+
+  sys_builds=(
+    "Sys Node|src/sys/build/node/Dockerfile|argus-sys-node:latest|."
+    "Sys Metric Test Node|src/sys/build/test-node/Dockerfile|argus-sys-metric-test-node:latest|."
+    "Sys Metric Test GPU Node|src/sys/build/test-gpu-node/Dockerfile|argus-sys-metric-test-gpu-node:latest|."
+  )
+
+  for build_spec in "${sys_builds[@]}"; do
+    IFS='|' read -r image_label dockerfile_path image_tag build_context <<< "$build_spec"
+    if build_image "$image_label" "$dockerfile_path" "$image_tag" "$build_context"; then
+      images_built+=("$image_tag")
+    else
+      build_failed=true
+    fi
+    echo ""
+  done
+fi
+
 # =======================================
 # Web & Alert module images
 # =======================================

src/metric/client-plugins/all-in-one-full/config/VERSION

@@ -1 +1 @@
-1.33.0
+1.35.0

src/metric/grafana/build/dashboards/default_dashboard_by_hostname.json

@@ -581,6 +581,372 @@
       ],
       "title": "Node Process Count",
       "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "GPU Utilization (%)",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 80
+              },
+              {
+                "color": "red",
+                "value": 95
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "id": 301,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "DCGM_FI_DEV_GPU_UTIL{hostname=~\"$hostname\"}",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 利用率 (单卡)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": true,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Memory Used (%)",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            }
+          },
+          "mappings": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "orange",
+                "value": 80
+              },
+              {
+                "color": "red",
+                "value": 95
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "id": 403,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "round(DCGM_FI_DEV_FB_USED{hostname=~\"$hostname\"} / (DCGM_FI_DEV_FB_USED{hostname=~\"$hostname\"} + DCGM_FI_DEV_FB_FREE{hostname=~\"$hostname\"}) * 100)",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 显存使用率 (单卡)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": true,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Temperature (℃)",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 75
+              },
+              {
+                "color": "red",
+                "value": 85
+              }
+            ]
+          },
+          "unit": "celsius"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 32
+      },
+      "id": 501,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "DCGM_FI_DEV_GPU_TEMP{hostname=~\"$hostname\"}",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 温度（单卡）",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": true,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Power (W)",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "max": 300,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 200
+              },
+              {
+                "color": "red",
+                "value": 300
+              }
+            ]
+          },
+          "unit": "watt"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 32
+      },
+      "id": 502,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "DCGM_FI_DEV_POWER_USAGE{hostname=~\"$hostname\"}",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 功率 (单卡)",
+      "type": "timeseries"
     }
   ],
   "refresh": "15s",
@@ -589,11 +955,6 @@
   "templating": {
     "list": [
       {
-        "current": {
-          "selected": true,
-          "text": "node-exporter-A1",
-          "value": "node-exporter-A1"
-        },
         "datasource": {
           "type": "prometheus"
         },
@@ -623,7 +984,7 @@
   },
   "timepicker": {},
   "timezone": "",
-  "title": "Node and GPU Metrics",
-  "uid": "node_gpu_metrics",
+  "title": "Node and GPU Metrics (by hostname)",
+  "uid": "node_gpu_metrics_by_hostname",
   "weekStart": ""
-}
+}

src/metric/grafana/build/dashboards/default_dashboard_by_instance.json

@@ -622,7 +622,7 @@
     },
     "timepicker": {},
     "timezone": "",
-    "title": "Node and GPU Metrics",
-    "uid": "node_gpu_metrics",
+    "title": "Node and GPU Metrics (by instance)",
+    "uid": "node_gpu_metrics_by_instance",
     "weekStart": ""
-  }
+  }

src/sys/build/node/Dockerfile

@@ -0,0 +1,36 @@
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    TZ=Asia/Shanghai
+
+ARG USE_INTRANET=false
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# Optional: switch to intranet apt mirrors during build
+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
+
+# Install base tools and all libs that Fluent Bit may require at runtime
+# so that start-fluent-bit.sh will NOT fallback to apt during container start.
+RUN set -eux; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+      ca-certificates tzdata \
+      procps iproute2 net-tools lsof \
+      libpq5 libyaml-0-2 libsasl2-2 libldap-2.5-0; \
+    rm -rf /var/lib/apt/lists/*
+
+# Keep root; compose provides entrypoint via bind mount
+USER root
+
+CMD ["bash", "-lc", "sleep infinity"]
+

src/sys/build/test-gpu-node/Dockerfile

@@ -0,0 +1,34 @@
+FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    TZ=Asia/Shanghai \
+    NVIDIA_VISIBLE_DEVICES=all \
+    NVIDIA_DRIVER_CAPABILITIES=compute,utility
+
+ARG USE_INTRANET=false
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# Optional intranet mirror for build-time apt
+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
+
+# Pre-install curl and diagnostics to avoid runtime apt installs in GPU test node
+RUN set -eux; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+      curl ca-certificates tzdata \
+      procps iproute2 net-tools lsof; \
+    rm -rf /var/lib/apt/lists/*
+
+USER root
+CMD ["bash", "-lc", "sleep infinity"]
+

src/sys/build/test-node/Dockerfile

@@ -0,0 +1,32 @@
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    TZ=Asia/Shanghai
+
+ARG USE_INTRANET=false
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# Optional intranet mirror for build-time apt
+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
+
+# Pre-install curl and common diagnostics to avoid runtime apt installs
+RUN set -eux; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+      curl ca-certificates tzdata \
+      procps iproute2 net-tools lsof; \
+    rm -rf /var/lib/apt/lists/*
+
+USER root
+CMD ["bash", "-lc", "sleep infinity"]
+

src/sys/tests/docker-compose.yml

@@ -78,7 +78,7 @@ services:
         ipv4_address: 172.31.0.4
 
   node-a:
-    image: ubuntu:22.04
+    image: argus-sys-node:latest
     container_name: argus-node-a
     hostname: dev-yyrshare-nbnyx10-cp2f-pod-0
     depends_on:
@@ -113,7 +113,7 @@ services:
       - sysnet
 
   node-b:
-    image: ubuntu:22.04
+    image: argus-sys-node:latest
     container_name: argus-node-b
     hostname: dev-yyrshare-uuuu10-ep2f-pod-0
     depends_on:
@@ -260,7 +260,7 @@ services:
         max-file: "3"
 
   test-node:
-    image: ubuntu:22.04
+    image: argus-sys-metric-test-node:latest
     container_name: argus-metric-test-node
     hostname: test-metric-node-001
     restart: unless-stopped
@@ -303,7 +303,7 @@ services:
 
   test-gpu-node:
     profiles: ["gpu"]
-    image: nvidia/cuda:12.2.2-runtime-ubuntu22.04
+    image: argus-sys-metric-test-gpu-node:latest
     container_name: argus-metric-test-gpu-node
     hostname: test-metric-gpu-node-001
     restart: unless-stopped