| { |
| "layouts": [ |
| { |
| "layout_name": "default_hbase_dashboard", |
| "display_name": "Standard HBase Dashboard", |
| "section_name": "HBASE_SUMMARY", |
| "widgetLayoutInfo": [ |
| { |
| "widget_name": "Reads and Writes", |
| "description": "Rate (per second) of read and write requests on all regions in the cluster.", |
| "default_section_name": "HBASE_SUMMARY", |
| "widget_type": "GRAPH", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "regionserver.Server.Get_num_ops._rate", |
| "metric_path": "metrics/hbase/regionserver/Server/Get_num_ops._rate", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "regionserver.Server.Append_num_ops._rate", |
| "metric_path": "metrics/hbase/regionserver/Server/Append_num_ops._rate", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "regionserver.Server.Delete_num_ops._rate", |
| "metric_path": "metrics/hbase/regionserver/Server/Delete_num_ops._rate", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "regionserver.Server.Increment_num_ops._rate", |
| "metric_path": "metrics/hbase/regionserver/Server/Increment_num_ops._rate", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "regionserver.Server.Mutate_num_ops._rate", |
| "metric_path": "metrics/hbase/regionserver/Server/Mutate_num_ops._rate", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "Read Requests", |
| "value": "${regionserver.Server.Get_num_ops._rate}" |
| }, |
| { |
| "name": "Write Requests", |
| "value": "${regionserver.Server.Append_num_ops._rate + regionserver.Server.Delete_num_ops._rate + regionserver.Server.Increment_num_ops._rate + regionserver.Server.Mutate_num_ops._rate}" |
| } |
| ], |
| "properties": { |
| "graph_type": "LINE", |
| "time_range": "1" |
| } |
| }, |
| { |
| "widget_name": "Read Latency", |
| "description": "maximum of 95% read latency.", |
| "default_section_name": "HBASE_SUMMARY", |
| "widget_type": "GRAPH", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "regionserver.Server.Get_95th_percentile._max", |
| "metric_path": "metrics/hbase/regionserver/Server/Get_95th_percentile._max", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "Cluster wide maximum of 95% Get Latency", |
| "value": "${regionserver.Server.Get_95th_percentile._max}" |
| } |
| ], |
| "properties": { |
| "display_unit": "ms", |
| "graph_type": "LINE", |
| "time_range": "1" |
| } |
| }, |
| { |
| "widget_name": "Write Latency", |
| "description": "maximum of 95% write latency.", |
| "default_section_name": "HBASE_SUMMARY", |
| "widget_type": "GRAPH", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "regionserver.Server.Mutate_95th_percentile._max", |
| "metric_path": "metrics/hbase/regionserver/Server/Mutate_95th_percentile._max", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "regionserver.Server.Increment_95th_percentile._max", |
| "metric_path": "metrics/hbase/regionserver/Server/Increment_95th_percentile._max", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "regionserver.Server.Append_95th_percentile._max", |
| "metric_path": "metrics/hbase/regionserver/Server/Append_95th_percentile._max", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "regionserver.Server.Delete_95th_percentile._max", |
| "metric_path": "metrics/hbase/regionserver/Server/Delete_95th_percentile._max", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "Cluster wide maximum of 95% Mutate Latency", |
| "value": "${regionserver.Server.Mutate_95th_percentile._max}" |
| }, |
| { |
| "name": "Cluster wide maximum of 95% Increment Latency", |
| "value": "${regionserver.Server.Increment_95th_percentile._max}" |
| }, |
| { |
| "name": "Cluster wide maximum of 95% Append Latency", |
| "value": "${regionserver.Server.Append_95th_percentile._max}" |
| }, |
| { |
| "name": "Cluster wide maximum of 95% Delete Latency", |
| "value": "${regionserver.Server.Delete_95th_percentile._max}" |
| } |
| ], |
| "properties": { |
| "display_unit": "ms", |
| "graph_type": "LINE", |
| "time_range": "1" |
| } |
| }, |
| { |
| "widget_name": "Open Connections", |
| "description": "Count of open connections across all RegionServer. This is indicative of RegionServer load in the cluster.", |
| "default_section_name": "HBASE_SUMMARY", |
| "widget_type": "GRAPH", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "regionserver.RegionServer.numOpenConnections._sum", |
| "metric_path": "metrics/hbase/ipc/IPC/numOpenConnections._sum", |
| "category": "", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "Open Connections", |
| "value": "${regionserver.RegionServer.numOpenConnections._sum}" |
| } |
| ], |
| "properties": { |
| "graph_type": "LINE", |
| "time_range": "1" |
| } |
| }, |
| { |
| "widget_name": "Request Handlers", |
| "description": "Count of Active handlers vs count of calls waiting in the general queue.", |
| "widget_type": "GRAPH", |
| "default_section_name": "HBASE_SUMMARY", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "regionserver.RegionServer.numActiveHandler._sum", |
| "metric_path": "metrics/hbase/ipc/IPC/numActiveHandler._sum", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "regionserver.RegionServer.numCallsInGeneralQueue._sum", |
| "metric_path": "metrics/hbase/ipc/IPC/numCallsInGeneralQueue._sum", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "Active Handlers", |
| "value": "${regionserver.RegionServer.numActiveHandler._sum}" |
| }, |
| { |
| "name": "Calls in General Queue", |
| "value": "${regionserver.RegionServer.numCallsInGeneralQueue._sum}" |
| } |
| ], |
| "properties": { |
| "graph_type": "LINE", |
| "time_range": "1" |
| } |
| }, |
| { |
| "widget_name": "Files Local", |
| "description": "Average percentage of local files to RegionServer in the cluster.", |
| "default_section_name": "HBASE_SUMMARY", |
| "widget_type": "NUMBER", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "regionserver.Server.percentFilesLocal", |
| "metric_path": "metrics/hbase/regionserver/Server/percentFilesLocal", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "Files Local", |
| "value": "${regionserver.Server.percentFilesLocal}" |
| } |
| ], |
| "properties": { |
| "display_unit": "%", |
| "error_threshold":"25", |
| "warning_threshold": "75" |
| } |
| }, |
| { |
| "widget_name": "Blocked Updates", |
| "description": "Number of milliseconds updates have been blocked so the memstore can be flushed.", |
| "default_section_name": "HBASE_SUMMARY", |
| "widget_type": "GRAPH", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "regionserver.Server.updatesBlockedTime._rate", |
| "metric_path": "metrics/hbase/regionserver/Server/updatesBlockedTime._rate", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "Updates Blocked Time", |
| "value": "${regionserver.Server.updatesBlockedTime._rate}" |
| } |
| ], |
| "properties": { |
| "display_unit": "ms", |
| "graph_type": "LINE", |
| "time_range": "1" |
| } |
| }, |
| { |
| "widget_name": "Cluster CPU", |
| "description": "Percentage of CPU utilized across all RegionServer hosts.", |
| "default_section_name": "HBASE_SUMMARY", |
| "widget_type": "GRAPH", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "cpu_system._sum", |
| "metric_path": "metrics/cpu/cpu_system._sum", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "cpu_user._sum", |
| "metric_path": "metrics/cpu/cpu_user._sum", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "cpu_nice._sum", |
| "metric_path": "metrics/cpu/cpu_nice._sum", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "cpu_idle._sum", |
| "metric_path": "metrics/cpu/cpu_idle._sum", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "cpu_wio._sum", |
| "metric_path": "metrics/cpu/cpu_wio._sum", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "CPU utilization", |
| "value": "${((cpu_system._sum + cpu_user._sum + cpu_nice._sum)/(cpu_system._sum + cpu_user._sum + cpu_nice._sum + cpu_idle._sum + cpu_wio._sum)) * 100}" |
| } |
| ], |
| "properties": { |
| "graph_type": "LINE", |
| "time_range": "1", |
| "display_unit": "%" |
| } |
| }, |
| { |
| "widget_name": "Cluster Network", |
| "description": "Average of Network IO utilized across all RegionServer hosts.", |
| "default_section_name": "HBASE_SUMMARY", |
| "widget_type": "GRAPH", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "pkts_in._avg", |
| "metric_path": "metrics/network/pkts_in._avg", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "pkts_out._avg", |
| "metric_path": "metrics/network/pkts_out._avg", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "Packets In", |
| "value": "${pkts_in._avg}" |
| }, |
| { |
| "name": "Packets Out", |
| "value": "${pkts_out._avg}" |
| } |
| ], |
| "properties": { |
| "graph_type": "LINE", |
| "time_range": "1" |
| } |
| }, |
| { |
| "widget_name": "Cluster Disk", |
| "description": "Sum of disk throughput for all RegionServer hosts.", |
| "default_section_name": "HBASE_SUMMARY", |
| "widget_type": "GRAPH", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "read_bps._sum", |
| "metric_path": "metrics/disk/read_bps._sum", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| }, |
| { |
| "name": "write_bps._sum", |
| "metric_path": "metrics/disk/write_bps._sum", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "Read throughput", |
| "value": "${read_bps._sum/1048576}" |
| }, |
| { |
| "name": "Write throughput", |
| "value": "${write_bps._sum/1048576}" |
| } |
| ], |
| "properties": { |
| "display_unit": "Mbps", |
| "graph_type": "LINE", |
| "time_range": "1" |
| } |
| } |
| ] |
| }, |
| { |
| "layout_name": "default_hbase_heatmap", |
| "display_name": "HBase Heatmaps", |
| "section_name": "HBASE_HEATMAPS", |
| "widgetLayoutInfo": [ |
| { |
| "widget_name": "HBase Compaction Queue Size", |
| "description": "", |
| "widget_type": "HEATMAP", |
| "is_visible": true, |
| "metrics": [ |
| { |
| "name": "Hadoop:service=HBase,name=RegionServer,sub=Server.compactionQueueLength", |
| "metric_path": "metrics/hbase/regionserver/compactionQueueSize", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "HBase Compaction Queue Size", |
| "value": "${Hadoop:service=HBase,name=RegionServer,sub=Server.compactionQueueLength} " |
| } |
| ], |
| "properties": { |
| "display_unit": "", |
| "max_limit": "10" |
| } |
| }, |
| { |
| "widget_name": "HBase Memstore Sizes", |
| "description": "", |
| "widget_type": "HEATMAP", |
| "is_visible": false, |
| "metrics": [ |
| { |
| "name": "Hadoop:service=HBase,name=RegionServer,sub=Server.memStoreSize", |
| "metric_path": "metrics/hbase/regionserver/memstoreSize", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "HBase Memstore Sizes", |
| "value": "${Hadoop:service=HBase,name=RegionServer,sub=Server.memStoreSize}" |
| } |
| ], |
| "properties": { |
| "display_unit": "B", |
| "max_limit": "104857600" |
| } |
| }, |
| { |
| "widget_name": "HBase Read Request Count", |
| "description": "", |
| "widget_type": "HEATMAP", |
| "is_visible": false, |
| "metrics": [ |
| { |
| "name": "Hadoop:service=HBase,name=RegionServer,sub=Server.readRequestCount", |
| "metric_path": "metrics/hbase/regionserver/readRequestsCount", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "HBase Read Request Count", |
| "value": "${Hadoop:service=HBase,name=RegionServer,sub=Server.readRequestCount}" |
| } |
| ], |
| "properties": { |
| "max_limit": "200" |
| } |
| }, |
| { |
| "widget_name": "HBase Write Request Count", |
| "description": "", |
| "widget_type": "HEATMAP", |
| "is_visible": false, |
| "metrics": [ |
| { |
| "name": "Hadoop:service=HBase,name=RegionServer,sub=Server.writeRequestCount", |
| "metric_path": "metrics/hbase/regionserver/writeRequestsCount", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "HBase Write Request Count", |
| "value": "${Hadoop:service=HBase,name=RegionServer,sub=Server.writeRequestCount}" |
| } |
| ], |
| "properties": { |
| "max_limit": "200" |
| } |
| }, |
| { |
| "widget_name": "HBase Regions", |
| "description": "", |
| "widget_type": "HEATMAP", |
| "is_visible": false, |
| "metrics": [ |
| { |
| "name": "Hadoop:service=HBase,name=RegionServer,sub=Server.regionCount", |
| "metric_path": "metrics/hbase/regionserver/regions", |
| "service_name": "HBASE", |
| "component_name": "HBASE_REGIONSERVER" |
| } |
| ], |
| "values": [ |
| { |
| "name": "HBase Regions", |
| "value": "${Hadoop:service=HBase,name=RegionServer,sub=Server.regionCount}" |
| } |
| ], |
| "properties": { |
| "max_limit": "10" |
| } |
| } |
| ] |
| } |
| ] |
| } |