{ "title": "Cluster Overview", "description": "Generated from AutoMQ opsbox Grafana dashboard cluster-overview.json. Complex PromQL expressions are tracked in dashboard-mapping.json.\n\nRendered as Datadog ordered/fixed sections. The matching free-layout backup is kept as cluster-overview-free-bak.json.", "notify_list": null, "layout_type": "ordered", "template_variables": [ { "name": "automq_env_id", "prefix": "env_id", "default": "*" }, { "name": "automq_instance_id", "prefix": "instance_id", "default": "*" }, { "name": "cluster_id", "prefix": "service", "default": "*" } ], "reflow_type": "fixed", "widgets": [ { "definition": { "type": "group", "title": "Cluster Metadata", "layout_type": "ordered", "show_title": true, "widgets": [ { "definition": { "type": "note", "content": "**InstanceId**\n\n​$automq_instance_id.value", "background_color": "white", "font_size": "16", "has_padding": true, "show_tick": false, "text_align": "left", "vertical_align": "center" }, "layout": { "x": 0, "y": 0, "width": 2, "height": 3 } }, { "definition": { "type": "note", "content": "**EnvId**\n\n​$automq_env_id.value", "background_color": "white", "font_size": "16", "has_padding": true, "show_tick": false, "text_align": "left", "vertical_align": "center" }, "layout": { "x": 2, "y": 0, "width": 2, "height": 3 } }, { "definition": { "type": "note", "content": "**AutoMQ Version**\n\n​N/A", "background_color": "white", "font_size": "16", "has_padding": true, "show_tick": false, "text_align": "left", "vertical_align": "center" }, "layout": { "x": 4, "y": 0, "width": 2, "height": 3 } }, { "definition": { "type": "query_value", "title": "Cluster Total CPU Usage", "requests": [ { "response_format": "scalar", "queries": [ { "data_source": "metrics", "name": "query1", "query": "sum:jvm_cpu_count{$automq_env_id,$automq_instance_id,$cluster_id}", "aggregator": "last" } ], "formulas": [ { "formula": "query1", "alias": "Cluster Total CPU Usage" } ] } ], "autoscale": true, "precision": 0 }, "layout": { "x": 6, "y": 0, "width": 3, "height": 3 } }, { "definition": { "type": "note", "content": "**ClusterId**\n\n​$cluster_id.value", "background_color": "white", "font_size": "16", "has_padding": true, "show_tick": false, "text_align": "left", "vertical_align": "center" }, "layout": { "x": 9, "y": 0, "width": 3, "height": 3 } } ] } }, { "definition": { "type": "group", "title": "Cluster Summary", "layout_type": "ordered", "show_title": true, "widgets": [ { "definition": { "type": "query_value", "title": "Topics", "requests": [ { "response_format": "scalar", "queries": [ { "data_source": "metrics", "name": "query1", "query": "avg:kafka_topic_count{$automq_env_id,$automq_instance_id,$cluster_id}", "aggregator": "last" } ], "formulas": [ { "formula": "query1", "alias": "Topics" } ] } ], "autoscale": true, "precision": 0 }, "layout": { "x": 0, "y": 0, "width": 2, "height": 3 } }, { "definition": { "type": "query_value", "title": "Partitions", "requests": [ { "response_format": "scalar", "queries": [ { "data_source": "metrics", "name": "query1", "query": "avg:kafka_partition_total_count{$automq_env_id,$automq_instance_id,$cluster_id}", "aggregator": "last" } ], "formulas": [ { "formula": "query1", "alias": "Partitions" } ] } ], "autoscale": true, "precision": 0 }, "layout": { "x": 2, "y": 0, "width": 2, "height": 3 } }, { "definition": { "type": "query_value", "title": "Error Ratio", "requests": [ { "response_format": "scalar", "queries": [ { "data_source": "metrics", "name": "query1", "query": "sum:automq_request_error_count_total{$automq_env_id,$automq_instance_id,$cluster_id,!error:none}.as_rate()", "aggregator": "last" }, { "data_source": "metrics", "name": "query2", "query": "sum:automq_request_error_count_total{$automq_env_id,$automq_instance_id,$cluster_id}.as_rate()", "aggregator": "last" } ], "formulas": [ { "formula": "query1 / query2 * 100", "alias": "Error Ratio", "number_format": { "unit": { "type": "canonical_unit", "unit_name": "percent" } } } ] } ], "autoscale": true, "precision": 2 }, "layout": { "x": 4, "y": 0, "width": 2, "height": 3 } }, { "definition": { "type": "query_value", "title": "Groups", "requests": [ { "response_format": "scalar", "queries": [ { "data_source": "metrics", "name": "query1", "query": "sum:automq_group_count{$automq_env_id,$automq_instance_id,$cluster_id}", "aggregator": "last" } ], "formulas": [ { "formula": "query1", "alias": "Groups" } ] } ], "autoscale": true, "precision": 0 }, "layout": { "x": 6, "y": 0, "width": 2, "height": 3 } }, { "definition": { "type": "timeseries", "title": "Broker Count", "requests": [ { "response_format": "timeseries", "queries": [ { "data_source": "metrics", "name": "query1", "query": "max:kafka_broker_active_count{$automq_env_id,$automq_instance_id,$cluster_id} by {service}" }, { "data_source": "metrics", "name": "query2", "query": "avg:kafka_broker_fenced_count{$automq_env_id,$automq_instance_id,$cluster_id}" } ], "formulas": [ { "formula": "query1", "alias": "Active" }, { "formula": "query2", "alias": "Fenced" } ] } ], "show_legend": true, "legend_layout": "horizontal", "legend_size": "auto", "legend_columns": [ "min", "max", "avg" ] }, "layout": { "x": 8, "y": 0, "width": 4, "height": 4 } } ] } }, { "definition": { "type": "group", "title": "Traffic and Resource Trends", "layout_type": "ordered", "show_title": true, "widgets": [ { "definition": { "type": "timeseries", "title": "Bytes In (+) / Out (-)", "requests": [ { "response_format": "timeseries", "queries": [ { "data_source": "metrics", "name": "query1", "query": "sum:automq_cluster_broker_network_io_bytes_total{$automq_env_id,$automq_instance_id,$cluster_id,direction:in}.as_rate()" }, { "data_source": "metrics", "name": "query2", "query": "sum:automq_cluster_broker_network_io_bytes_total{$automq_env_id,$automq_instance_id,$cluster_id,direction:out}.as_rate()" } ], "formulas": [ { "formula": "query1", "alias": "In", "number_format": { "unit": { "type": "canonical_unit", "unit_name": "byte", "per_unit_name": "second" } } }, { "formula": "query2 * -1", "alias": "Out", "number_format": { "unit": { "type": "canonical_unit", "unit_name": "byte", "per_unit_name": "second" } } } ] } ], "show_legend": true, "legend_layout": "horizontal", "legend_size": "auto", "legend_columns": [ "min", "max", "avg" ] }, "layout": { "x": 0, "y": 0, "width": 6, "height": 4 } }, { "definition": { "type": "timeseries", "title": "QPS In (+) / Out (-)", "requests": [ { "response_format": "timeseries", "queries": [ { "data_source": "metrics", "name": "query1", "query": "sum:automq_topic_request_count_total{$automq_env_id,$automq_instance_id,$cluster_id,type:produce}.as_rate()" }, { "data_source": "metrics", "name": "query2", "query": "sum:automq_topic_request_count_total{$automq_env_id,$automq_instance_id,$cluster_id,type:fetch}.as_rate()" } ], "formulas": [ { "formula": "query1", "alias": "In", "number_format": { "unit": { "type": "custom_unit_label", "label": "req/s" } } }, { "formula": "query2 * -1", "alias": "Out", "number_format": { "unit": { "type": "custom_unit_label", "label": "req/s" } } } ] } ], "show_legend": true, "legend_layout": "horizontal", "legend_size": "auto", "legend_columns": [ "min", "max", "avg" ] }, "layout": { "x": 6, "y": 0, "width": 6, "height": 4 } }, { "definition": { "type": "timeseries", "title": "Size", "requests": [ { "response_format": "timeseries", "queries": [ { "data_source": "metrics", "name": "query1", "query": "sum:automq_topic_log_size{$automq_env_id,$automq_instance_id,$cluster_id}" } ], "formulas": [ { "formula": "query1", "alias": "Size", "number_format": { "unit": { "type": "canonical_unit", "unit_name": "byte" } } } ] } ], "show_legend": true, "legend_layout": "horizontal", "legend_size": "auto", "legend_columns": [ "min", "max", "avg", "value" ] }, "layout": { "x": 0, "y": 4, "width": 6, "height": 4 } }, { "definition": { "type": "timeseries", "title": "Cluster Max CPU Utilization", "requests": [ { "response_format": "timeseries", "queries": [ { "data_source": "metrics", "name": "query1", "query": "max:jvm_cpu_time_seconds_total{$automq_env_id,$automq_instance_id,$cluster_id} by {service}.as_rate()" }, { "data_source": "metrics", "name": "query2", "query": "max:jvm_cpu_count{$automq_env_id,$automq_instance_id,$cluster_id} by {service}" } ], "formulas": [ { "formula": "(query1 / query2) * 100", "alias": "Cluster Max CPU Utilization", "number_format": { "unit": { "type": "canonical_unit", "unit_name": "percent" } } } ] } ], "show_legend": true, "legend_layout": "horizontal", "legend_size": "auto", "legend_columns": [ "min", "max", "avg" ] }, "layout": { "x": 6, "y": 4, "width": 6, "height": 4 } } ] } }, { "definition": { "type": "group", "title": "Topic Statistics", "layout_type": "ordered", "show_title": true, "widgets": [ { "definition": { "type": "query_table", "title": "Topic Statistics", "requests": [ { "response_format": "scalar", "queries": [ { "data_source": "metrics", "name": "query1", "query": "sum:automq_topic_network_io_bytes_total{$automq_env_id,$automq_instance_id,$cluster_id,direction:in} by {topic}.as_rate()" }, { "data_source": "metrics", "name": "query2", "query": "sum:automq_topic_network_io_bytes_total{$automq_env_id,$automq_instance_id,$cluster_id,direction:out} by {topic}.as_rate()" }, { "data_source": "metrics", "name": "query3", "query": "sum:automq_topic_request_count_total{$automq_env_id,$automq_instance_id,$cluster_id,type:produce} by {topic}.as_rate()" }, { "data_source": "metrics", "name": "query4", "query": "sum:automq_topic_request_count_total{$automq_env_id,$automq_instance_id,$cluster_id,type:fetch} by {topic}.as_rate()" }, { "data_source": "metrics", "name": "query5", "query": "sum:automq_topic_message_count_total{$automq_env_id,$automq_instance_id,$cluster_id,direction:in} by {topic}.as_rate()" }, { "data_source": "metrics", "name": "query6", "query": "sum:automq_topic_log_size{$automq_env_id,$automq_instance_id,$cluster_id} by {topic}" } ], "formulas": [ { "formula": "query1", "alias": "Bytes In", "number_format": { "unit": { "type": "canonical_unit", "unit_name": "byte", "per_unit_name": "second" } } }, { "formula": "query2", "alias": "Bytes Out", "number_format": { "unit": { "type": "canonical_unit", "unit_name": "byte", "per_unit_name": "second" } } }, { "formula": "query3", "alias": "Produce QPS", "number_format": { "unit": { "type": "custom_unit_label", "label": "req/s" } } }, { "formula": "query5", "alias": "Messages In", "number_format": { "unit": { "type": "custom_unit_label", "label": "msg/s" } } }, { "formula": "query5 / query3", "alias": "Msg / Batch" }, { "formula": "query4", "alias": "Fetch QPS", "number_format": { "unit": { "type": "custom_unit_label", "label": "req/s" } } }, { "formula": "query6", "alias": "Size", "number_format": { "unit": { "type": "canonical_unit", "unit_name": "byte" } } } ] } ] }, "layout": { "x": 0, "y": 0, "width": 12, "height": 8 } } ] } }, { "definition": { "type": "group", "title": "Group Statistics", "layout_type": "ordered", "show_title": true, "widgets": [ { "definition": { "type": "query_table", "title": "Group Statistics", "requests": [ { "response_format": "scalar", "queries": [ { "data_source": "metrics", "name": "query1", "query": "sum:automq_consumer_group_topic_commit_offset{$automq_env_id,$automq_instance_id,$cluster_id,consumer_group:*} by {consumer_group,topic}" }, { "data_source": "metrics", "name": "query2", "query": "sum:automq_group_topic_offset_lag{$automq_env_id,$automq_instance_id,$cluster_id,consumer_group:*} by {consumer_group,topic}" }, { "data_source": "metrics", "name": "query3", "query": "sum:automq_consumer_group_topic_commit_offset{$automq_env_id,$automq_instance_id,$cluster_id,consumer_group:*} by {consumer_group,topic}" } ], "formulas": [ { "formula": "per_second(query3)", "alias": "Consume Throughput", "number_format": { "unit": { "type": "custom_unit_label", "label": "msg/s" } } }, { "formula": "query2", "alias": "Consumer Lag" } ] } ] }, "layout": { "x": 0, "y": 0, "width": 12, "height": 8 } } ] } } ] }