{ "annotations": { "list": [ { "builtIn": 1, "datasource": { "type": "grafana", "uid": "-- Grafana --" }, "enable": true, "hide": true, "iconColor": "rgba(0, 211, 255, 1)", "name": "Annotations & Alerts", "type": "dashboard" } ] }, "editable": true, "fiscalYearStartMonth": 0, "graphTooltip": 1, "links": [], "liveNow": true, "panels": [ { "collapsed": false, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 }, "id": 10, "panels": [], "title": "Salud del Data Lake (Namenodes & DataNodes)", "type": "row" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Número de DataNodes que están enviando Heartbeats correctamente al NameNode. En nuestro clúster deben ser 3.", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "red", "value": 0 }, { "color": "orange", "value": 2 }, { "color": "green", "value": 3 } ] } }, "overrides": [] }, "gridPos": { "h": 6, "w": 5, "x": 0, "y": 1 }, "id": 2, "options": { "colorMode": "value", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "percentChangeColorMode": "standard", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "12.4.1", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "hadoop_namenode_numlivedatanodes{job=\"hadoop-namenode\"}", "legendFormat": "Nodos Vivos", "range": false, "refId": "A" } ], "title": "Live DataNodes", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Número de bloques de datos perdidos porque todos los DataNodes que tenían una réplica han caído. Significa pérdida de datos irrecuperable.", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": 0 }, { "color": "red", "value": 1 } ] } }, "overrides": [] }, "gridPos": { "h": 6, "w": 5, "x": 5, "y": 1 }, "id": 4, "options": { "colorMode": "value", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "percentChangeColorMode": "standard", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "12.4.1", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "hadoop_namenode_missingblocks{job=\"hadoop-namenode\"}", "legendFormat": "Bloques Perdidos", "range": false, "refId": "A" } ], "title": "Missing Blocks", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Estado del Secondary NameNode. Debe estar activo para fusionar periódicamente el FSImage y los Edits Logs, evitando que el NameNode principal colapse de memoria.", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [ { "options": { "0": { "color": "red", "index": 0, "text": "DOWN" }, "1": { "color": "green", "index": 1, "text": "UP" } }, "type": "value" } ], "thresholds": { "mode": "absolute", "steps": [ { "color": "red", "value": 0 }, { "color": "green", "value": 1 } ] } }, "overrides": [] }, "gridPos": { "h": 6, "w": 4, "x": 10, "y": 1 }, "id": 20, "options": { "colorMode": "value", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "percentChangeColorMode": "standard", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "12.4.1", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "up{job=\"hadoop-secondarynamenode\"}", "legendFormat": "Estado", "range": false, "refId": "A" } ], "title": "Secondary NameNode", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Porcentaje de disco utilizado en los DataNodes.", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "max": 100, "min": 0, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": 0 }, { "color": "orange", "value": 75 }, { "color": "red", "value": 90 } ] }, "unit": "percent" }, "overrides": [] }, "gridPos": { "h": 6, "w": 10, "x": 14, "y": 1 }, "id": 6, "options": { "minVizHeight": 10, "minVizWidth": 0, "orientation": "horizontal", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showThresholdLabels": false, "showThresholdMarkers": true, "sizing": "auto" }, "pluginVersion": "12.4.1", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "(hadoop_namenode_capacityused / hadoop_namenode_capacitytotal) * 100", "legendFormat": "Uso de HDFS", "range": false, "refId": "A" } ], "title": "HDFS Capacity Used", "type": "gauge" }, { "collapsed": false, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 7 }, "id": 12, "panels": [], "title": "Estadísticas del Sistema de Ficheros", "type": "row" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Total de ficheros, directorios y bloques indexados en la RAM del NameNode.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "showValues": false, "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": 0 } ] } }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 }, "id": 8, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "hideZeros": false, "mode": "single", "sort": "none" } }, "pluginVersion": "12.4.1", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "hadoop_namenode_filestotal{job=\"hadoop-namenode\"}", "legendFormat": "Total Ficheros y Carpetas", "range": true, "refId": "A" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "hadoop_namenode_blocks_total{job=\"hadoop-namenode\"}", "legendFormat": "Total Bloques", "range": true, "refId": "B" } ], "title": "Evolución de Metadatos (Namespace)", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "El volumen de datos que se está leyendo o escribiendo a través de HDFS.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "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", "showValues": false, "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": 0 } ] }, "unit": "Bps" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 }, "id": 14, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "hideZeros": false, "mode": "single", "sort": "none" } }, "pluginVersion": "12.4.1", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "rate(hadoop_datanode_bytesread{job=\"hadoop-datanodes\"}[1m])", "legendFormat": "{{instance}} (Lectura)", "range": true, "refId": "A" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "rate(hadoop_datanode_byteswritten{job=\"hadoop-datanodes\"}[1m])", "legendFormat": "{{instance}} (Escritura)", "range": true, "refId": "B" } ], "title": "Throughput en DataNodes (Lectura / Escritura)", "type": "timeseries" }, { "collapsed": false, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 16 }, "id": 23, "panels": [], "title": "Recursos (Memoria JVM)", "type": "row" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Consumo de memoria Heap. El Secondary NameNode necesita bastante RAM durante el proceso de Checkpoint (fusionar FSImage y Edits). Verás picos y caídas periódicas cuando se lanza el Garbage Collector.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 15, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "showValues": false, "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": 0 }, { "color": "red", "value": 80 } ] }, "unit": "bytes" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 17 }, "id": 21, "options": { "legend": { "calcs": [], "displayMode": "table", "placement": "bottom", "showLegend": true }, "tooltip": { "hideZeros": false, "mode": "single", "sort": "none" } }, "pluginVersion": "12.4.1", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "builder", "expr": "jvm_memory_pool_used_bytes{job=\"hadoop-namenode\"}", "legendFormat": "NameNode - {{pool}}", "range": true, "refId": "A" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "builder", "expr": "jvm_memory_pool_used_bytes{job=\"hadoop-secondarynamenode\"}", "legendFormat": "Secondary - {{pool}}", "range": true, "refId": "B" } ], "title": "Uso de RAM (Capa de Control)", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Consumo de memoria Heap en los DataNodes. Sube cuando hay operaciones intensivas de lectura/escritura desde Spark o Kafka Connect.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 15, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "showValues": false, "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": 0 }, { "color": "red", "value": 80 } ] }, "unit": "bytes" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 17 }, "id": 22, "options": { "legend": { "calcs": [], "displayMode": "table", "placement": "bottom", "showLegend": true }, "tooltip": { "hideZeros": false, "mode": "single", "sort": "none" } }, "pluginVersion": "12.4.1", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "jvm_memory_pool_used_bytes{job=\"hadoop-datanodes\"}", "legendFormat": "{{instance}} - {{pool}}", "range": true, "refId": "A" } ], "title": "Uso de RAM (Capa de Datos)", "type": "timeseries" } ], "preload": false, "refresh": "", "schemaVersion": 42, "tags": [ "hadoop", "hdfs", "bda", "educacion" ], "templating": { "list": [ { "current": { "text": "prometheus", "value": "cfil757c75xj4f" }, "includeAll": false, "name": "DS_PROMETHEUS", "options": [], "query": "prometheus", "refresh": 1, "regex": "", "type": "datasource" } ] }, "time": { "from": "now-30m", "to": "now" }, "timepicker": {}, "timezone": "browser", "title": "BDA - Hadoop HDFS Monitor (Docker Cluster) - Jaime Rabasco", "uid": "bda-hdfs-custom", "version": 5, "weekStart": "" }