AirflowDAGMonitor/zabbix/zbx_template_airflow_monitor_5x.xml

<?xml version="1.0" encoding="UTF-8"?>
<zabbix_export>
    <version>5.0</version>
    <groups>
        <group>
            <name>Templates/Applications</name>
        </group>
    </groups>
    <templates>
        <template>
            <template>Airflow DAG Monitor</template>
            <name>Airflow DAG Monitor</name>
            <description>Мониторинг Apache Airflow DAG-ов через сервис airflow-monitor.&#13;
Сервис пишет данные в файлы, Zabbix Agent читает через UserParameter.&#13;
&#13;
Требования:&#13;
- Установлен airflow-monitor (/opt/airflow-monitor)&#13;
- Установлен конфиг /etc/zabbix/zabbix_agentd.conf.d/airflow-monitor.conf&#13;
&#13;
Версия шаблона: 1.0.1 (Zabbix 5.0)</description>
            <groups>
                <group>
                    <name>Templates/Applications</name>
                </group>
            </groups>
            <items>
                <!-- Problematic DAGs JSON -->
                <item>
                    <name>Airflow: Problematic DAGs (JSON)</name>
                    <key>airflow.dag.problems</key>
                    <delay>1m</delay>
                    <history>7d</history>
                    <value_type>TEXT</value_type>
                    <description>JSON-массив проблемных DAG-запусков. [] = нет проблем.</description>
                </item>

                <!-- Problematic DAGs count -->
                <item>
                    <name>Airflow: Problematic DAGs count</name>
                    <key>airflow.dag.problems.count</key>
                    <delay>1m</delay>
                    <history>7d</history>
                    <trends>365d</trends>
                    <value_type>UNSIGNED</value_type>
                    <description>Количество DAG-запусков с проблемами.</description>
                </item>

                <!-- Heartbeat -->
                <item>
                    <name>Airflow Monitor: Heartbeat</name>
                    <key>airflow.monitor.heartbeat</key>
                    <delay>1m</delay>
                    <history>7d</history>
                    <trends>365d</trends>
                    <value_type>UNSIGNED</value_type>
                    <description>Epoch timestamp последнего успешного цикла мониторинга.</description>
                </item>

                <!-- Status JSON -->
                <item>
                    <name>Airflow Monitor: Status (JSON)</name>
                    <key>airflow.monitor.status</key>
                    <delay>5m</delay>
                    <history>7d</history>
                    <value_type>TEXT</value_type>
                    <description>JSON со статусом монитора.</description>
                </item>

                <!-- Service alive -->
                <item>
                    <name>Airflow Monitor: Service alive</name>
                    <key>airflow.monitor.alive</key>
                    <delay>1m</delay>
                    <history>7d</history>
                    <trends>365d</trends>
                    <value_type>UNSIGNED</value_type>
                    <description>1 = сервис запущен, 0 = остановлен.</description>
                    <valuemap>
                        <name>Service state</name>
                    </valuemap>
                </item>

                <!-- DAG count (dependent from status) -->
                <item>
                    <name>Airflow Monitor: DAG count</name>
                    <type>DEPENDENT</type>
                    <key>airflow.monitor.dag_count</key>
                    <history>7d</history>
                    <trends>365d</trends>
                    <value_type>UNSIGNED</value_type>
                    <description>Количество отслеживаемых DAG-ов.</description>
                    <master_item>
                        <key>airflow.monitor.status</key>
                    </master_item>
                    <preprocessing>
                        <step>
                            <type>JSONPATH</type>
                            <params>$.dag_count</params>
                        </step>
                        <step>
                            <type>DISCARD_UNCHANGED_HEARTBEAT</type>
                            <params>1h</params>
                        </step>
                    </preprocessing>
                </item>

                <!-- Cycle time (dependent from status) -->
                <item>
                    <name>Airflow Monitor: Cycle time (seconds)</name>
                    <type>DEPENDENT</type>
                    <key>airflow.monitor.cycle_time</key>
                    <history>7d</history>
                    <trends>365d</trends>
                    <value_type>FLOAT</value_type>
                    <units>s</units>
                    <description>Время выполнения последнего цикла мониторинга.</description>
                    <master_item>
                        <key>airflow.monitor.status</key>
                    </master_item>
                    <preprocessing>
                        <step>
                            <type>JSONPATH</type>
                            <params>$.cycle_time_seconds</params>
                        </step>
                    </preprocessing>
                </item>

                <!-- Cycle count (dependent from status) -->
                <item>
                    <name>Airflow Monitor: Cycle count</name>
                    <type>DEPENDENT</type>
                    <key>airflow.monitor.cycle_count</key>
                    <history>7d</history>
                    <trends>365d</trends>
                    <value_type>UNSIGNED</value_type>
                    <description>Номер текущего цикла мониторинга.</description>
                    <master_item>
                        <key>airflow.monitor.status</key>
                    </master_item>
                    <preprocessing>
                        <step>
                            <type>JSONPATH</type>
                            <params>$.cycle_count</params>
                        </step>
                        <step>
                            <type>DISCARD_UNCHANGED_HEARTBEAT</type>
                            <params>1h</params>
                        </step>
                    </preprocessing>
                </item>
            </items>

            <macros>
                <macro>
                    <macro>{$AIRFLOW.STALE_THRESHOLD}</macro>
                    <value>600</value>
                    <description>Порог устаревания данных (секунды).</description>
                </macro>
                <macro>
                    <macro>{$AIRFLOW.CYCLE_TIME_WARN}</macro>
                    <value>60</value>
                    <description>Порог предупреждения о долгом цикле (секунды).</description>
                </macro>
            </macros>
        </template>
    </templates>

    <triggers>
        <!-- Problematic DAGs detected -->
        <trigger>
            <expression>{Airflow DAG Monitor:airflow.dag.problems.count.last()}&gt;0</expression>
            <recovery_expression></recovery_expression>
            <name>Airflow: {ITEM.LASTVALUE1} problematic DAG run(s) detected</name>
            <priority>HIGH</priority>
            <description>Обнаружены проблемные DAG-запуски (failed или long_running).&#13;
Подробности в item "Airflow: Problematic DAGs (JSON)".&#13;
Триггер снимается автоматически при разрешении всех проблем.</description>
        </trigger>

        <!-- Heartbeat stale -->
        <trigger>
            <expression>{Airflow DAG Monitor:airflow.monitor.heartbeat.nodata(600)}=1 or (({Airflow DAG Monitor:airflow.monitor.heartbeat.last()}&gt;0) and ({Airflow DAG Monitor:airflow.monitor.heartbeat.fuzzytime(600)}=0))</expression>
            <name>Airflow Monitor: Data is stale (no update for 10+ minutes)</name>
            <priority>DISASTER</priority>
            <description>Данные мониторинга не обновлялись более 10 минут.&#13;
Возможные причины: сервис остановлен, Airflow API недоступен.</description>
            <dependencies>
                <dependency>
                    <name>Airflow Monitor: Service is not running</name>
                    <expression>{Airflow DAG Monitor:airflow.monitor.alive.last()}=0</expression>
                </dependency>
            </dependencies>
        </trigger>

        <!-- Service down -->
        <trigger>
            <expression>{Airflow DAG Monitor:airflow.monitor.alive.last()}=0</expression>
            <name>Airflow Monitor: Service is not running</name>
            <priority>HIGH</priority>
            <description>Сервис airflow-monitor не запущен.&#13;
Запустить: sudo systemctl start airflow-monitor</description>
        </trigger>

        <!-- Slow cycle -->
        <trigger>
            <expression>{Airflow DAG Monitor:airflow.monitor.cycle_time.last()}&gt;60</expression>
            <name>Airflow Monitor: Cycle time is high ({ITEM.LASTVALUE1}s)</name>
            <priority>WARNING</priority>
            <description>Цикл мониторинга выполняется дольше 60 секунд.</description>
        </trigger>
    </triggers>

    <graphs>
        <!-- Problem count graph -->
        <graph>
            <name>Airflow: Problem DAG count</name>
            <graph_items>
                <graph_item>
                    <color>FF0000</color>
                    <item>
                        <host>Airflow DAG Monitor</host>
                        <key>airflow.dag.problems.count</key>
                    </item>
                </graph_item>
                <graph_item>
                    <color>00AA00</color>
                    <yaxisside>RIGHT</yaxisside>
                    <item>
                        <host>Airflow DAG Monitor</host>
                        <key>airflow.monitor.dag_count</key>
                    </item>
                </graph_item>
            </graph_items>
        </graph>

        <!-- Cycle time graph -->
        <graph>
            <name>Airflow Monitor: Cycle time</name>
            <graph_items>
                <graph_item>
                    <color>0000FF</color>
                    <item>
                        <host>Airflow DAG Monitor</host>
                        <key>airflow.monitor.cycle_time</key>
                    </item>
                </graph_item>
            </graph_items>
        </graph>
    </graphs>

    <value_maps>
        <value_map>
            <name>Service state</name>
            <mappings>
                <mapping>
                    <value>0</value>
                    <newvalue>Stopped</newvalue>
                </mapping>
                <mapping>
                    <value>1</value>
                    <newvalue>Running</newvalue>
                </mapping>
            </mappings>
        </value_map>
    </value_maps>
</zabbix_export>