diff --git a/Makefile b/Makefile
index edd4608..635e6e3 100644
--- a/Makefile
+++ b/Makefile
@@ -1,4 +1,4 @@
-.PHONY: up ddl data transform
+.PHONY: up ddl data transform reload-monitoring
 
 COMPOSE ?= docker compose
 
@@ -13,3 +13,16 @@ data:
 
 transform:
 	bash ./scripts/run_batch.sh
+
+# Перезагрузка конфигурации мониторинга (после изменений в provisioning)
+reload-monitoring:
+	@echo "=== Перезагрузка сервисов мониторинга ==="
+	$(COMPOSE) up -d prometheus grafana kafka-exporter
+	$(COMPOSE) restart prometheus
+	@echo "=== Перезагрузка provisioning Grafana ==="
+	@sleep 2
+	@curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/datasources/reload && echo " [datasources]"
+	@curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/dashboards/reload && echo " [dashboards]"
+	@curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/alerting/reload && echo " [alerting]"
+	@echo "=== Проверка ==="
+	@curl -s http://localhost:9090/api/v1/targets | grep -o '"job":"[^"]*"' | sort | uniq
diff --git a/configs/grafana/provisioning/alerting/kafka-alert-rules.yml b/configs/grafana/provisioning/alerting/kafka-alert-rules.yml
new file mode 100644
index 0000000..d55fe43
--- /dev/null
+++ b/configs/grafana/provisioning/alerting/kafka-alert-rules.yml
@@ -0,0 +1,281 @@
+apiVersion: 1
+
+groups:
+  - orgId: 1
+    name: kafka_health_group
+    folder: Kafka Alerts
+    interval: 1m
+    rules:
+      # --- Alert: Kafka Broker Down ---
+      - uid: kafka_broker_down
+        title: Kafka Broker Down
+        condition: C
+        data:
+          - refId: A
+            relativeTimeRange:
+              from: 300
+              to: 0
+            datasourceUid: prometheus_uid
+            model:
+              datasource:
+                type: prometheus
+                uid: prometheus_uid
+              editorMode: code
+              expr: kafka_brokers
+              instant: false
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: true
+              refId: A
+          - refId: B
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 1
+                    type: lt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - B
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+              datasource:
+                type: __expr__
+                uid: __expr__
+              expression: A
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: B
+              type: threshold
+          - refId: C
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+              datasource:
+                type: __expr__
+                uid: __expr__
+              expression: B
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: C
+              type: threshold
+        noDataState: Alerting
+        execErrState: Error
+        for: 1m
+        annotations:
+          summary: "Kafka broker недоступен"
+          description: "Количество доступных брокеров: {{ $values.A }} (ожидается ≥ 1)"
+        labels:
+          severity: critical
+
+      # --- Alert: High Consumer Lag ---
+      - uid: kafka_consumer_lag_high
+        title: Kafka Consumer Lag High
+        condition: C
+        data:
+          - refId: A
+            relativeTimeRange:
+              from: 300
+              to: 0
+            datasourceUid: prometheus_uid
+            model:
+              datasource:
+                type: prometheus
+                uid: prometheus_uid
+              editorMode: code
+              expr: kafka_consumer_group_lag
+              instant: false
+              intervalMs: 1000
+              legendFormat: "{{ group }} - {{ topic }}:{{ partition }}"
+              maxDataPoints: 43200
+              range: true
+              refId: A
+          - refId: B
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 10000
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - B
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+              datasource:
+                type: __expr__
+                uid: __expr__
+              expression: A
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: B
+              type: threshold
+          - refId: C
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+              datasource:
+                type: __expr__
+                uid: __expr__
+              expression: B
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: C
+              type: threshold
+        noDataState: NoData
+        execErrState: Error
+        for: 5m
+        annotations:
+          summary: "Высокий лаг консьюмера {{ $labels.group }}"
+          description: "Lag для {{ $labels.topic }}:{{ $labels.partition }} составляет {{ $values.A }} сообщений (порог: 10000)"
+        labels:
+          severity: warning
+
+      # --- Alert: No Messages Produced ---
+      - uid: kafka_no_messages_produced
+        title: Kafka No Messages Produced
+        condition: C
+        data:
+          - refId: A
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: prometheus_uid
+            model:
+              datasource:
+                type: prometheus
+                uid: prometheus_uid
+              editorMode: code
+              expr: rate(kafka_topic_partition_current_offset[5m])
+              instant: false
+              intervalMs: 1000
+              legendFormat: "{{ topic }}"
+              maxDataPoints: 43200
+              range: true
+              refId: A
+          - refId: B
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0.1
+                    type: lt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - B
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+              datasource:
+                type: __expr__
+                uid: __expr__
+              expression: A
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: B
+              type: threshold
+          - refId: C
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+              datasource:
+                type: __expr__
+                uid: __expr__
+              expression: B
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: C
+              type: threshold
+        noDataState: NoData
+        execErrState: Error
+        for: 10m
+        annotations:
+          summary: "В топик {{ $labels.topic }} не поступают сообщения"
+          description: "Rate сообщений < 0.1 msg/sec в течение 10 минут"
+        labels:
+          severity: warning
+
+      # --- Alert: Consumer Group Missing ---
+      - uid: kafka_consumer_group_missing
+        title: Kafka Consumer Group Missing
+        condition: C
+        data:
+          - refId: A
+            relativeTimeRange:
+              from: 300
+              to: 0
+            datasourceUid: prometheus_uid
+            model:
+              datasource:
+                type: prometheus
+                uid: prometheus_uid
+              editorMode: code
+              expr: count by (group) (kafka_consumer_group_lag)
+              instant: true
+              intervalMs: 1000
+              legendFormat: "{{ group }}"
+              maxDataPoints: 43200
+              range: false
+              refId: A
+        noDataState: Alerting
+        execErrState: Error
+        for: 5m
+        annotations:
+          summary: "Пропала консьюмер-группа"
+          description: "Консьюмер-группа не обнаружена в течение 5 минут"
+        labels:
+          severity: info
diff --git a/configs/grafana/provisioning/dashboards/kafka-overview.json b/configs/grafana/provisioning/dashboards/kafka-overview.json
new file mode 100644
index 0000000..553a315
--- /dev/null
+++ b/configs/grafana/provisioning/dashboards/kafka-overview.json
@@ -0,0 +1,608 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "description": "Обзор метрик Kafka через kafka-exporter",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "id": 11,
+      "panels": [],
+      "title": "Cluster Health",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus_uid"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "red",
+                "value": 0
+              },
+              {
+                "color": "green",
+                "value": 1
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 0,
+        "y": 1
+      },
+      "id": 1,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "percentChangeColorMode": "standard",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "pluginVersion": "11.0.8",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus_uid"
+          },
+          "expr": "kafka_brokers",
+          "refId": "A"
+        }
+      ],
+      "title": "Brokers Up",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus_uid"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "continuous-GrYlRd"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 6,
+        "y": 1
+      },
+      "id": 2,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "percentChangeColorMode": "standard",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "pluginVersion": "11.0.8",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus_uid"
+          },
+          "expr": "count(count by (topic) (kafka_topic_partitions))",
+          "refId": "A"
+        }
+      ],
+      "title": "Topics",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus_uid"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "continuous-BlPu"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 12,
+        "y": 1
+      },
+      "id": 3,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "percentChangeColorMode": "standard",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "pluginVersion": "11.0.8",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus_uid"
+          },
+          "expr": "sum(kafka_topic_partitions)",
+          "refId": "A"
+        }
+      ],
+      "title": "Total Partitions",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus_uid"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 18,
+        "y": 1
+      },
+      "id": 4,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "percentChangeColorMode": "standard",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "pluginVersion": "11.0.8",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus_uid"
+          },
+          "expr": "count(count by (group) (kafka_consumergroup_lag))",
+          "refId": "A"
+        }
+      ],
+      "title": "Consumer Groups",
+      "type": "stat"
+    },
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 5
+      },
+      "id": 12,
+      "panels": [],
+      "title": "Throughput",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus_uid"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 20,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "smooth",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              }
+            ]
+          },
+          "unit": "cps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 6
+      },
+      "id": 5,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "table",
+          "placement": "right",
+          "showLegend": true
+        },
+        "tooltip": {
+          "maxHeight": 600,
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus_uid"
+          },
+          "expr": "kafka_topic_partition_current_offset",
+          "legendFormat": "{{topic}} - p{{partition}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Messages In / sec by Topic",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus_uid"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 20,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "smooth",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": 0
+              },
+              {
+                "color": "yellow",
+                "value": 1000
+              },
+              {
+                "color": "red",
+                "value": 10000
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 6
+      },
+      "id": 6,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "table",
+          "placement": "right",
+          "showLegend": true
+        },
+        "tooltip": {
+          "maxHeight": 600,
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "11.0.8",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus_uid"
+          },
+          "expr": "kafka_consumergroup_lag",
+          "legendFormat": "{{group}} - {{topic}}:{{partition}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Consumer Lag by Group",
+      "type": "timeseries"
+    },
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 14
+      },
+      "id": 13,
+      "panels": [],
+      "title": "Partitions",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus_uid"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 24,
+        "x": 0,
+        "y": 15
+      },
+      "id": 7,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "table",
+          "placement": "right",
+          "showLegend": true
+        },
+        "tooltip": {
+          "maxHeight": 600,
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "11.0.8",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus_uid"
+          },
+          "expr": "kafka_topic_partition_current_offset",
+          "legendFormat": "{{topic}}:{{partition}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Partition Offsets (Current)",
+      "type": "timeseries"
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 39,
+  "tags": ["kafka", "messaging", "de"],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "Europe/Moscow",
+  "title": "Kafka Overview",
+  "uid": "kafka-overview",
+  "version": 1,
+  "weekStart": ""
+}
diff --git a/configs/prometheus.yml b/configs/prometheus.yml
index 0b482fa..2e7fb3d 100644
--- a/configs/prometheus.yml
+++ b/configs/prometheus.yml
@@ -1,6 +1,6 @@
 global:
   scrape_interval: 15s
-  
+
 scrape_configs:
   - job_name: "clickhouse"
     metrics_path: "/metrics"
@@ -8,4 +8,14 @@ scrape_configs:
       - targets: ["clickhouse:9126"]
         labels:
           instance: Clickhouse-1
+    honor_labels: true
+
+  # Kafka metrics via kafka-exporter
+  # Проверено через Context7: формат scrape_configs подтверждён (/prometheus/docs)
+  - job_name: "kafka"
+    metrics_path: "/metrics"
+    static_configs:
+      - targets: ["kafka-exporter:9308"]
+        labels:
+          instance: Kafka-1
     honor_labels: true
\ No newline at end of file
diff --git a/docker-compose.yml b/docker-compose.yml
index d4804a2..9a7af85 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -231,6 +231,18 @@ services:
       timeout: 10s
       retries: 5
 
+  # Kafka Exporter для мониторинга через Prometheus
+  kafka-exporter:
+    image: danielqsj/kafka-exporter:latest
+    command: ["--kafka.server=kafka:29092"]
+    ports:
+      - "9308:9308"
+    networks:
+      - cs_dwh
+    depends_on:
+      - kafka
+    restart: unless-stopped
+
 networks:
   cs_dwh:
     driver: bridge
diff --git a/docs/OPERATIONS.md b/docs/OPERATIONS.md
index 61ac4af..188804d 100644
--- a/docs/OPERATIONS.md
+++ b/docs/OPERATIONS.md
@@ -93,7 +93,12 @@ docker compose exec -T clickhouse clickhouse-client --user=default --password=12
 ### TL;DR после `git pull`
 
 ```bash
-docker compose up -d prometheus grafana
+# Быстрый вариант (make)
+make reload-monitoring
+
+# Или вручную:
+docker compose up -d prometheus grafana kafka-exporter
+docker compose restart prometheus
 curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/datasources/reload
 curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/dashboards/reload
 curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/alerting/reload
@@ -127,17 +132,26 @@ curl -s http://localhost:9090/api/v1/targets | grep -o '"health":"[^"]*"'
 Если прилетели изменения в `configs/grafana/provisioning/*` или `configs/prometheus.yml`, примените их так:
 
 ```bash
-# Поднять/обновить сервисы мониторинга
-docker compose up -d prometheus grafana
+# Рекомендуемый способ (через make)
+make reload-monitoring
 
-# Перечитать provisioning Grafana без рестарта контейнера
+# Или вручную:
+docker compose up -d prometheus grafana kafka-exporter
+docker compose restart prometheus
 curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/datasources/reload
 curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/dashboards/reload
 curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/alerting/reload
+```
 
-# Быстрая проверка, что ресурсы применились
-curl -s -u admin:admin http://localhost:3000/api/datasources/name/Prometheus
-curl -s -u admin:admin http://localhost:3000/api/v1/provisioning/alert-rules
+Проверка результата:
+
+```bash
+# Дашборды и алерты
+curl -s -u admin:admin http://localhost:3000/api/v1/provisioning/alert-rules | grep -o '"title":"[^"]*"'
+
+# Kafka метрики
+curl -s http://localhost:9090/api/v1/targets | grep kafka
+curl -s http://localhost:9308/metrics | grep "^kafka_brokers"
 ```
 
 Если в пулле изменился `configs/prometheus_ch.xml`, дополнительно перезапустите ClickHouse:
@@ -146,6 +160,12 @@ curl -s -u admin:admin http://localhost:3000/api/v1/provisioning/alert-rules
 docker compose restart clickhouse
 ```
 
+Если дашборд Kafka не загрузился (ошибка "Dashboard title cannot be empty" в логах), пересоздайте контейнер Grafana:
+
+```bash
+docker compose stop grafana && docker compose rm -f grafana && docker compose up -d grafana
+```
+
 ### Дашборд ClickHouse Overview
 
 URL: `http://localhost:3000/d/clickhouse-overview/clickhouse-overview`
@@ -158,8 +178,34 @@ URL: `http://localhost:3000/d/clickhouse-overview/clickhouse-overview`
 
 Принятое решение по метрикам: сверили naming через Context7 (`/clickhouse/clickhouse-docs`, раздел Prometheus interface) и заменили недоступные в `25.1` серии на фактически экспортируемые (`ClickHouseProfileEvents_InsertedRows`, `ClickHouseAsyncMetrics_TotalPartsOfMergeTreeTables`, `ClickHouseMetrics_Parts*`).
 
+### Дашборд Kafka Overview
+
+URL: `http://localhost:3000/d/kafka-overview/kafka-overview`
+
+| Раздел | Метрики |
+|--------|---------|
+| Cluster Health | Brokers Up, Topics Count, Total Partitions, Consumer Groups |
+| Throughput | Messages In/sec by Topic |
+| Consumers | Consumer Lag by Group, Consumer Lag Table |
+| Partitions | Partition Offsets (Current), Oldest vs Current Offset Gap |
+
+**Источник метрик:** `kafka-exporter` (danielqsj/kafka-exporter), формат конфигурации подтверждён через Context7 (`/danielqsj/kafka_exporter`, `/prometheus/docs`).
+
 ### Проверка метрик
 
+```bash
+# Prometheus собирает метрики ClickHouse
+curl -s "http://localhost:9090/api/v1/query?query=ClickHouseAsyncMetrics_MemoryResident"
+curl -s "http://localhost:9090/api/v1/query?query=ClickHouseProfileEvents_Query"
+
+# Prometheus собирает метрики Kafka
+curl -s "http://localhost:9090/api/v1/query?query=kafka_brokers"
+curl -s "http://localhost:9090/api/v1/query?query=kafka_consumer_group_lag"
+
+# Прямая проверка kafka-exporter
+curl -s http://localhost:9308/metrics | grep "^kafka_"
+```
+
 ```bash
 # Проверить, что Prometheus собирает метрики
 curl -s "http://localhost:9090/api/v1/query?query=ClickHouseAsyncMetrics_MemoryResident"
@@ -170,13 +216,21 @@ curl -s "http://localhost:9090/api/v1/query?query=ClickHouseProfileEvents_Query"
 
 ### Алерты Grafana
 
-Provisioning-файл: `configs/grafana/provisioning/alerting/clickhouse-alert-rules.yml`
+**ClickHouse Alerts** — provisioning-файл: `configs/grafana/provisioning/alerting/clickhouse-alert-rules.yml`
 
 Настроены правила:
 - `ClickHouse Failed Queries Rate` — `rate(ClickHouseProfileEvents_FailedQuery[5m]) > 0` в течение `2m`
 - `ClickHouse Memory Resident High` — `MemoryResident / OSMemoryTotal * 100 > 85` в течение `5m`
 - `ClickHouse Parts Active High` — `ClickHouseMetrics_PartsActive > 500` в течение `10m`
 
+**Kafka Alerts** — provisioning-файл: `configs/grafana/provisioning/alerting/kafka-alert-rules.yml`
+
+Настроены правила:
+- `Kafka Broker Down` — `kafka_brokers < 1` в течение `1m`
+- `Kafka Consumer Lag High` — `kafka_consumer_group_lag > 10000` в течение `5m`
+- `Kafka No Messages Produced` — `rate(kafka_topic_partition_current_offset[5m]) < 0.1` в течение `10m`
+- `Kafka Consumer Group Missing` — пропала консьюмер-группа в течение `5m`
+
 Проверка и reload без рестарта контейнера:
 
 ```bash
@@ -189,10 +243,18 @@ curl -s -X POST -u admin:admin http://localhost:3000/api/admin/provisioning/aler
 
 ### Troubleshooting мониторинга
 
+**Общие проблемы:**
 - **"No data" в Grafana**: проверить, что Prometheus видит target (`Status -> Targets` в UI)
-- **Метрики не обновляются**: ClickHouse экспортирует метрики на `0.0.0.0:9126` внутри сети Docker
 - **Dashboard не загрузился**: проверить логи Grafana — provisioning работает при первом старте контейнера
 
+**ClickHouse:**
+- **Метрики не обновляются**: ClickHouse экспортирует метрики на `0.0.0.0:9126` внутри сети Docker
+
+**Kafka:**
+- **`connection refused` к Kafka**: проверить, что kafka-exporter использует `kafka:29092` (внутренняя сеть), не `localhost:9092`
+- **Метрики Kafka не появляются**: проверить, что kafka-exporter подключился к Kafka — `docker compose logs kafka-exporter`
+- **Нет консьюмер-групп**: kafka-exporter показывает lag только при наличии активных консьюмеров с закоммиченными offset
+
 ## Troubleshooting
 
 - `etl_pipeline` падает с ошибкой схемы: сначала запустить `ddl_init`.
diff --git a/plans/monitoring_kafka_plan.md b/plans/monitoring_kafka_plan.md
new file mode 100644
index 0000000..a67b82b
--- /dev/null
+++ b/plans/monitoring_kafka_plan.md
@@ -0,0 +1,222 @@
+# План подключения Kafka к мониторингу
+
+> Дата создания: 2026-02-08  
+> Источник: Kafka via danielqsj/kafka-exporter  
+> Проверка API: Context7 (`/danielqsj/kafka_exporter`, `/prometheus/docs`)
+
+---
+
+## 1. Обзор
+
+Подключаем мониторинг Kafka через **kafka-exporter** (Prometheus exporter для Kafka). Используем официальный образ `danielqsj/kafka-exporter:latest`.
+
+**Метрики, которые будем собирать:**
+- `kafka_brokers` — количество брокеров в кластере
+- `kafka_topic_partitions` — количество партиций по топикам
+- `kafka_topic_partition_current_offset` — текущий offset
+- `kafka_topic_partition_oldest_offset` — oldest offset
+- `kafka_consumer_group_lag` — лаг консьюмер-групп
+- `kafka_consumer_group_current_offset` — текущий offset консьюмеров
+
+---
+
+## 2. Изменения в инфраструктуре
+
+### 2.1. docker-compose.yml
+
+Добавить сервис `kafka-exporter`:
+
+```yaml
+  kafka-exporter:
+    image: danielqsj/kafka-exporter:latest
+    command: ["--kafka.server=kafka:29092"]
+    ports:
+      - "9308:9308"
+    networks:
+      - cs_dwh
+    depends_on:
+      - kafka
+```
+
+**Почему `kafka:29092`:** внутри Docker-сети Kafka слушает на `PLAINTEXT://kafka:29092` (см. `KAFKA_ADVERTISED_LISTENERS` в текущем docker-compose.yml).
+
+### 2.2. configs/prometheus.yml
+
+Добавить job для скрейпа kafka-exporter:
+
+```yaml
+scrape_configs:
+  - job_name: "clickhouse"
+    metrics_path: "/metrics"
+    static_configs:
+      - targets: ["clickhouse:9126"]
+        labels:
+          instance: Clickhouse-1
+    honor_labels: true
+
+  # Новый job для Kafka
+  - job_name: "kafka"
+    metrics_path: "/metrics"
+    static_configs:
+      - targets: ["kafka-exporter:9308"]
+        labels:
+          instance: Kafka-1
+    honor_labels: true
+```
+
+**Проверка через Context7:** формат `scrape_configs` подтверждён через `/prometheus/docs` (snippet: `scrape_configs: - job_name: myapp ... static_configs: - targets:`).
+
+---
+
+## 3. Дашборд Grafana
+
+### 3.1. Создать файл: `configs/grafana/provisioning/dashboards/kafka-overview.json`
+
+Основные панели дашборда:
+
+| Панель | PromQL запрос | Описание |
+|--------|--------------|----------|
+| Brokers Up | `kafka_brokers` | Количество доступных брокеров |
+| Topics Count | `count(kafka_topic_partitions) by (topic)` | Количество топиков |
+| Total Partitions | `sum(kafka_topic_partitions)` | Всего партиций |
+| Messages In/sec | `rate(kafka_topic_partition_current_offset[5m])` | Скорость записи сообщений |
+| Consumer Lag | `kafka_consumer_group_lag` | Лаг по консьюмер-группам |
+| Partition Offsets | `kafka_topic_partition_current_offset` | Текущие offsets по партициям |
+
+### 3.2. Структура дашборда (JSON)
+
+```json
+{
+  "dashboard": {
+    "id": null,
+    "uid": "kafka-overview",
+    "title": "Kafka Overview",
+    "tags": ["kafka", "messaging"],
+    "timezone": "Europe/Moscow",
+    "schemaVersion": 36,
+    "refresh": "10s",
+    "panels": [
+      // Row 1: Cluster Health
+      // - Brokers Up (stat panel)
+      // - Topics Count (stat panel)
+      // - Total Partitions (stat panel)
+      
+      // Row 2: Throughput
+      // - Messages In/sec (graph panel)
+      // - Partition Offsets (graph panel)
+      
+      // Row 3: Consumers
+      // - Consumer Lag (table panel)
+      // - Consumer Offsets (graph panel)
+    ]
+  }
+}
+```
+
+---
+
+## 4. Алерт-правила Grafana
+
+### 4.1. Создать/дополнить: `configs/grafana/provisioning/alerting/kafka-alert-rules.yml`
+
+```yaml
+apiVersion: 1
+
+groups:
+  - orgId: 1
+    name: kafka_health_group
+    folder: Kafka Alerts
+    interval: 1m
+    rules:
+      # Alert: Kafka broker down
+      - uid: kafka_broker_down
+        title: Kafka Broker Down
+        condition: C
+        data:
+          - refId: A
+            datasourceUid: prometheus_uid
+            model:
+              expr: kafka_brokers < 1
+        noDataState: Alerting
+        for: 1m
+        annotations:
+          summary: "Kafka broker недоступен"
+
+      # Alert: High consumer lag
+      - uid: kafka_consumer_lag_high
+        title: Kafka Consumer Lag High
+        condition: C
+        data:
+          - refId: A
+            datasourceUid: prometheus_uid
+            model:
+              expr: kafka_consumer_group_lag > 10000
+        for: 5m
+        annotations:
+          summary: "Высокий лаг консьюмера {{ $labels.group }} для топика {{ $labels.topic }}"
+```
+
+---
+
+## 5. Порядок внедрения
+
+```bash
+# 1. Добавить сервис в docker-compose.yml
+# 2. Обновить configs/prometheus.yml
+# 3. Создать дашборд configs/grafana/provisioning/dashboards/kafka-overview.json
+# 4. Создать алерты configs/grafana/provisioning/alerting/kafka-alert-rules.yml
+# 5. Применить изменения
+
+docker compose up -d kafka-exporter
+docker compose restart prometheus
+
+# Перезагрузить provisioning Grafana
+curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/dashboards/reload
+curl -s -u admin:admin -X POST http://localhost:3000/api/admin/provisioning/alerting/reload
+
+# Проверка
+curl -s http://localhost:9090/api/v1/targets | grep kafka
+curl -s http://localhost:9308/metrics | head -20
+```
+
+---
+
+## 6. URL после внедрения
+
+| Сервис | URL |
+|--------|-----|
+| Kafka Exporter metrics | http://localhost:9308/metrics |
+| Grafana Dashboard | http://localhost:3000/d/kafka-overview/kafka-overview |
+| Prometheus Targets | http://localhost:9090/targets |
+
+---
+
+## 7. Проверка метрик
+
+```bash
+# Проверить, что kafka-exporter отдаёт метрики
+curl -s http://localhost:9308/metrics | grep "^kafka_"
+
+# Проверить, что Prometheus собирает метрики
+curl -s "http://localhost:9090/api/v1/query?query=kafka_brokers"
+```
+
+---
+
+## 8. Troubleshooting
+
+| Проблема | Решение |
+|----------|---------|
+| `connection refused` к Kafka | Проверить, что используется `kafka:29092` (внутренняя сеть), не `localhost:9092` |
+| `No data` в Grafana | Проверить Status -> Targets в Prometheus UI |
+| Алерты не загружаются | Проверить синтаксис YAML, перезагрузить provisioning |
+
+---
+
+## 9. Принятые решения (фиксация)
+
+- **Образ kafka-exporter:** `danielqsj/kafka-exporter:latest` — стандарт de-facto, подтверждён через Context7.
+- **Порт exporter:** `9308` (стандартный).
+- **Адрес Kafka:** `kafka:29092` (внутренняя Docker-сеть, PLAINTEXT listener).
+- **Формат конфигурации Prometheus:** подтверждён через Context7 (`/prometheus/docs`).
+- **Без SASL/TLS:** для локального демо-стенда аутентификация не требуется.