5 "description": "A monitoring dashboard for OPNFV long duration test",
19 "content": "<img src=\"https://wiki.opnfv.org/download/attachments/13212037/soak_monitoring.png\" alt=\"Monitoring Soak Test logo\" style=\"height: 66px;\">\n\n<p style=\"margin-top: 10px;\">\nYou're using the monitoring suite developed by OPNFV Bottlenecks team for OPNFV long duration test.\nThe monitoring suite consists of a monitoring dashboard - \n<a href=\"http://www.grafana.org/\">Grafana</a> ,\na monitoring data source -\n<a href=\"http://prometheus.io/\">Prometheus</a> and\nseveral monitoring tools -\n<a href=\"https://wiki.opnfv.org/display/fastpath/Barometer+Home/\">Barometer</a>,\n<a href=\"https://github.com/google/cadvisor/\">Cadvisor</a> and\n<a href=\"https://github.com/prometheus/node_exporter/\">Node</a>.\nThe monitoring suite is evolving along with OPNFV releases and enriched features will be included based on practical needs.\n</p>",
33 "content": "### OPNFV Long Duration Test\nThis is a collaborative initiative launched by OPNFV test working group (Testperf) for long duration stability test (soak test) in NFV realm.\nSeveral testing projects in OPNFV has been involved, i.e.,\n[Bottlenecks - system limit testing](https://wiki.opnfv.org/display/bottlenecks),\n[Functest - functional testing](https://wiki.opnfv.org/display/functest),\n[NFVbench -NFVI benchmark testing](https://wiki.opnfv.org/display/bottlenecks),\n[Storperf - storage testing](https://wiki.opnfv.org/display/bottlenecks),\n[VSperf - data path testing](https://wiki.opnfv.org/display/bottlenecks) and\n[Yardstick - performance testing](https://wiki.opnfv.org/display/bottlenecks).\nFor more detail, please refer to the [OPNFV LDT WIKI](https://wiki.opnfv.org/display/testing/Long+Duration+Testing).",
47 "repeatIteration": null,
50 "title": "Dashboard Information",
59 "colorBackground": false,
62 "rgba(245, 54, 54, 0.9)",
63 "rgba(237, 129, 40, 0.89)",
64 "rgba(50, 172, 45, 0.97)"
66 "datasource": "automated-ds",
75 "thresholdLabels": false,
76 "thresholdMarkers": true
85 "name": "value to text",
89 "name": "range to text",
94 "nullPointMode": "connected",
97 "postfixFontSize": "30%",
99 "prefixFontSize": "20%",
109 "fillColor": "rgba(31, 118, 189, 0.18)",
111 "lineColor": "rgb(31, 120, 193)",
117 "expr": "time() - node_boot_time",
118 "format": "time_series",
128 "type": "singlestat",
129 "valueFontSize": "80%",
137 "valueName": "current"
140 "cacheTimeout": null,
141 "colorBackground": false,
144 "rgba(245, 54, 54, 0.9)",
145 "rgba(237, 129, 40, 0.89)",
146 "rgba(50, 172, 45, 0.97)"
148 "datasource": "automated-ds",
156 "thresholdLabels": false,
157 "thresholdMarkers": true
165 "name": "value to text",
169 "name": "range to text",
173 "maxDataPoints": 100,
174 "nullPointMode": "connected",
177 "postfixFontSize": "50%",
179 "prefixFontSize": "50%",
189 "fillColor": "rgba(31, 118, 189, 0.18)",
191 "lineColor": "rgb(31, 120, 193)",
197 "expr": "count(rate(container_last_seen{name=~\".+\"}[$interval]))",
198 "format": "time_series",
205 "title": "Containers",
206 "type": "singlestat",
207 "valueFontSize": "120%",
215 "valueName": "current"
218 "cacheTimeout": null,
219 "colorBackground": false,
222 "rgba(50, 172, 45, 0.97)",
223 "rgba(237, 129, 40, 0.89)",
224 "rgba(245, 54, 54, 0.9)"
226 "datasource": "automated-ds",
230 "format": "percentunit",
235 "thresholdLabels": false,
236 "thresholdMarkers": true
244 "name": "value to text",
248 "name": "range to text",
252 "maxDataPoints": 100,
253 "nullPointMode": "connected",
256 "postfixFontSize": "50%",
258 "prefixFontSize": "50%",
268 "fillColor": "rgba(31, 118, 189, 0.18)",
270 "lineColor": "rgb(31, 120, 193)",
276 "expr": "min((node_filesystem_size{fstype=~\"xfs|ext4\"} - node_filesystem_free{fstype=~\"xfs|ext4\"} )/ node_filesystem_size{fstype=~\"xfs|ext4\"})",
277 "format": "time_series",
284 "thresholds": "0.75, 0.90",
285 "title": "Disk space",
286 "type": "singlestat",
287 "valueFontSize": "80%",
295 "valueName": "current"
298 "cacheTimeout": null,
299 "colorBackground": false,
302 "rgba(50, 172, 45, 0.97)",
303 "rgba(237, 129, 40, 0.89)",
304 "rgba(245, 54, 54, 0.9)"
306 "datasource": "automated-ds",
315 "thresholdLabels": false,
316 "thresholdMarkers": true
324 "name": "value to text",
328 "name": "range to text",
332 "maxDataPoints": 100,
333 "nullPointMode": "connected",
336 "postfixFontSize": "50%",
338 "prefixFontSize": "50%",
348 "fillColor": "rgba(31, 118, 189, 0.18)",
350 "lineColor": "rgb(31, 120, 193)",
356 "expr": "((node_memory_MemTotal - node_memory_MemAvailable) / node_memory_MemTotal) * 100",
357 "format": "time_series",
363 "thresholds": "70, 90",
365 "type": "singlestat",
366 "valueFontSize": "80%",
374 "valueName": "current"
378 "{id=\"/\",instance=\"cadvisor:8080\",job=\"prometheus\"}": "#BA43A9"
383 "datasource": "automated-ds",
401 "nullPointMode": "null as zero",
406 "seriesOverrides": [],
410 "steppedLine": false,
413 "expr": "sum(rate(container_cpu_system_seconds_total[1m]))",
414 "format": "time_series",
422 "expr": "sum(rate(container_cpu_system_seconds_total{name=~\".+\"}[1m]))",
423 "format": "time_series",
427 "legendFormat": "nur container",
432 "expr": "sum(rate(container_cpu_system_seconds_total{id=\"/\"}[1m]))",
433 "format": "time_series",
437 "legendFormat": "nur docker host",
443 "expr": "sum(rate(process_cpu_seconds_total[$interval])) * 100",
444 "format": "time_series",
454 "expr": "sum(rate(container_cpu_system_seconds_total{name=~\".+\"}[1m])) + sum(rate(container_cpu_system_seconds_total{id=\"/\"}[1m])) + sum(rate(process_cpu_seconds_total[1m]))",
455 "format": "time_series",
466 "title": "CPU Usage",
468 "msResolution": true,
471 "value_type": "cumulative"
502 "Available Memory": "#7EB26D",
503 "Unavailable Memory": "#7EB26D"
508 "datasource": "automated-ds",
526 "nullPointMode": "null as zero",
531 "seriesOverrides": [],
535 "steppedLine": false,
538 "expr": "container_memory_rss{name=~\".+\"}",
539 "format": "time_series",
542 "legendFormat": "{{__name__}}",
547 "expr": "sum(container_memory_rss{name=~\".+\"})",
548 "format": "time_series",
551 "legendFormat": "{{__name__}}",
556 "expr": "container_memory_usage_bytes{name=~\".+\"}",
557 "format": "time_series",
560 "legendFormat": "{{name}}",
565 "expr": "container_memory_rss{id=\"/\"}",
566 "format": "time_series",
569 "legendFormat": "{{__name__}}",
574 "expr": "sum(container_memory_rss)",
575 "format": "time_series",
578 "legendFormat": "{{__name__}}",
583 "expr": "node_memory_Buffers",
584 "format": "time_series",
587 "legendFormat": "node_memory_Dirty",
592 "expr": "node_memory_MemFree",
593 "format": "time_series",
596 "legendFormat": "Free Memory",
601 "expr": "node_memory_MemAvailable",
602 "format": "time_series",
605 "legendFormat": "Available Memory",
610 "expr": "node_memory_MemTotal - node_memory_MemAvailable",
611 "format": "time_series",
614 "legendFormat": "Unavailable Memory",
619 "expr": "node_memory_Inactive",
620 "format": "time_series",
623 "legendFormat": "{{__name__}}",
628 "expr": "node_memory_KernelStack",
629 "format": "time_series",
632 "legendFormat": "{{__name__}}",
637 "expr": "node_memory_Active",
638 "format": "time_series",
641 "legendFormat": "{{__name__}}",
646 "expr": "node_memory_MemTotal - (node_memory_Active + node_memory_MemFree + node_memory_Inactive)",
647 "format": "time_series",
650 "legendFormat": "Unknown",
655 "expr": "node_memory_MemFree + node_memory_Inactive ",
656 "format": "time_series",
659 "legendFormat": "{{__name__}}",
664 "expr": "container_memory_rss{name=~\".+\"}",
665 "format": "time_series",
668 "legendFormat": "{{__name__}}",
673 "expr": "node_memory_Inactive + node_memory_MemFree + node_memory_MemAvailable",
674 "format": "time_series",
684 "colorMode": "critical",
693 "title": "Available Memory",
695 "msResolution": true,
698 "value_type": "individual"
738 "title": "Status Quick Access",
743 "repeatIteration": null,
746 "title": "Nodes Overview - CPU, Network, Storage, Container Count",
777 "executionErrorState": "alerting",
780 "name": "Panel Title alert",
781 "noDataState": "keep_state",
792 "datasource": "automated-ds",
799 "alignAsTable": false,
812 "nullPointMode": "connected",
817 "seriesOverrides": [],
821 "steppedLine": false,
824 "expr": "node_load1 / count by(job, instance)(count by(job, instance, cpu)(node_cpu))",
825 "format": "time_series",
833 "expr": "count by(exported_instance, job)(collectd_load_0{exported_instance=~\"host.\"}) / (count by(job, exported_instance)(count by(exported_instance, job, cpu)(collectd_cpu{exported_instance=~\"host.\"})))",
834 "format": "time_series",
843 "colorMode": "critical",
852 "title": "CPU Loads on Nodes",
854 "msResolution": false,
857 "value_type": "individual"
869 "format": "percentunit",
893 "datasource": "automated-ds",
911 "nullPointMode": "null as zero",
916 "seriesOverrides": [],
920 "steppedLine": false,
923 "expr": "sum(rate(container_network_transmit_bytes_total[$interval])) by (instance) - sum(rate(container_network_receive_bytes_total[$interval])) by (instance)",
924 "format": "time_series",
926 "legendFormat": "(SENT - RECEIVED) {{instance}}",
931 "expr": "- sum(rate(container_network_transmit_bytes_total[$interval])) by (instance)",
932 "format": "time_series",
935 "legendFormat": "SENT - {{instance}}",
940 "expr": "sum(rate(container_network_receive_bytes_total[$interval])) by (instance)",
941 "format": "time_series",
943 "legendFormat": "RECEIVED - {{instance}}",
951 "title": "Network Loads on Nodes",
953 "msResolution": true,
956 "value_type": "cumulative"
958 "transparent": false,
988 "IN on /sda": "#7EB26D",
989 "OUT on /sda": "#890F02"
994 "datasource": "automated-ds",
1012 "nullPointMode": "null as zero",
1013 "percentage": false,
1017 "seriesOverrides": [],
1021 "steppedLine": false,
1024 "expr": "-sum(rate(node_disk_bytes_read[$interval])) by (device)",
1025 "format": "time_series",
1027 "intervalFactor": 2,
1028 "legendFormat": "OUT on /{{device}}",
1029 "metric": "node_disk_bytes_read",
1034 "expr": "sum(rate(node_disk_bytes_written[$interval])) by (device)",
1035 "format": "time_series",
1036 "intervalFactor": 2,
1037 "legendFormat": "IN on /{{device}}",
1046 "title": "Disk I/O",
1048 "msResolution": true,
1051 "value_type": "cumulative"
1082 "repeatIteration": null,
1083 "repeatRowId": null,
1085 "title": "Loads on Nodes - CPU, Network, Disk Loads Records",
1097 "datasource": "automated-ds",
1104 "alignAsTable": true,
1117 "nullPointMode": "null as zero",
1118 "percentage": false,
1122 "seriesOverrides": [],
1126 "steppedLine": false,
1129 "expr": "sum(rate(container_network_receive_bytes_total{name=~\".+\"}[$interval])) by (name)",
1130 "intervalFactor": 2,
1131 "legendFormat": "{{name}}",
1136 "expr": "- rate(container_network_transmit_bytes_total{name=~\".+\"}[$interval])",
1138 "intervalFactor": 2,
1139 "legendFormat": "{{name}}",
1147 "title": "Received Network Traffic per Container",
1149 "msResolution": true,
1152 "value_type": "cumulative"
1154 "transparent": false,
1187 "datasource": "automated-ds",
1194 "alignAsTable": true,
1209 "nullPointMode": "null as zero",
1210 "percentage": false,
1214 "seriesOverrides": [],
1218 "steppedLine": false,
1221 "expr": "sum(rate(container_network_transmit_bytes_total{name=~\".+\"}[$interval])) by (name)",
1222 "format": "time_series",
1223 "intervalFactor": 2,
1224 "legendFormat": "{{name}}",
1229 "expr": "rate(container_network_transmit_bytes_total{id=\"/\"}[$interval])",
1230 "format": "time_series",
1232 "intervalFactor": 2,
1241 "title": "Sent Network Traffic per Container",
1243 "msResolution": true,
1246 "value_type": "cumulative"
1248 "transparent": false,
1300 "executionErrorState": "alerting",
1303 "name": "Free/Used Disk Space alert",
1304 "noDataState": "keep_state",
1312 "Belegete Festplatte": "#BF1B00",
1313 "Free Disk Space": "#7EB26D",
1314 "Used Disk Space": "#7EB26D",
1320 "datasource": "automated-ds",
1338 "nullPointMode": "null as zero",
1339 "percentage": false,
1343 "seriesOverrides": [
1345 "alias": "Used Disk Space",
1352 "steppedLine": false,
1355 "expr": "node_filesystem_size{fstype=\"aufs\"} - node_filesystem_free{fstype=\"aufs\"}",
1356 "format": "time_series",
1358 "intervalFactor": 2,
1366 "colorMode": "critical",
1370 "value": 850000000000
1375 "title": "Used Disk Space",
1377 "msResolution": true,
1380 "value_type": "individual"
1395 "max": 1000000000000,
1414 "datasource": "automated-ds",
1421 "alignAsTable": true,
1434 "nullPointMode": "null as zero",
1435 "percentage": false,
1439 "seriesOverrides": [],
1443 "steppedLine": false,
1446 "expr": "sum(rate(container_cpu_usage_seconds_total{name=~\".+\"}[$interval])) by (name) * 100",
1447 "format": "time_series",
1450 "intervalFactor": 2,
1451 "legendFormat": "{{name}}",
1460 "title": "CPU Usage per Container",
1462 "msResolution": true,
1465 "value_type": "individual"
1477 "format": "percent",
1498 "datasource": "automated-ds",
1505 "alignAsTable": true,
1518 "nullPointMode": "null as zero",
1519 "percentage": false,
1523 "seriesOverrides": [],
1527 "steppedLine": false,
1530 "expr": "sum(container_memory_rss{name=~\".+\"}) by (name)",
1532 "intervalFactor": 2,
1533 "legendFormat": "{{name}}",
1538 "expr": "container_memory_usage_bytes{name=~\".+\"}",
1540 "intervalFactor": 2,
1541 "legendFormat": "{{name}}",
1549 "title": "Memory Usage per Container",
1551 "msResolution": true,
1554 "value_type": "individual"
1588 "datasource": "automated-ds",
1595 "alignAsTable": true,
1608 "nullPointMode": "null as zero",
1609 "percentage": false,
1613 "seriesOverrides": [],
1617 "steppedLine": false,
1620 "expr": "sum(container_memory_swap{name=~\".+\"}) by (name)",
1621 "format": "time_series",
1623 "intervalFactor": 2,
1624 "legendFormat": "{{name}}",
1629 "expr": "container_memory_usage_bytes{name=~\".+\"}",
1630 "format": "time_series",
1632 "intervalFactor": 2,
1633 "legendFormat": "{{name}}",
1641 "title": "Memory Swap per Container",
1643 "msResolution": true,
1646 "value_type": "individual"
1680 "datasource": "automated-ds",
1684 "alignAsTable": true,
1697 "nullPointMode": "null",
1698 "percentage": false,
1702 "seriesOverrides": [],
1706 "steppedLine": false,
1709 "expr": "count by(device)(container_fs_io_current)",
1710 "format": "time_series",
1712 "intervalFactor": 2,
1717 "expr": "container_fs_read_seconds_total{name=~\".+\"}",
1718 "format": "time_series",
1720 "intervalFactor": 2,
1721 "legendFormat": "Read - {{name}}",
1726 "expr": "-container_fs_write_seconds_total{name=~\".+\"}",
1727 "format": "time_series",
1728 "intervalFactor": 2,
1729 "legendFormat": "Write - {{name}}",
1737 "title": "Container IO Seconds Total",
1741 "value_type": "individual"
1775 "datasource": "automated-ds",
1779 "alignAsTable": true,
1792 "nullPointMode": "null",
1793 "percentage": false,
1797 "seriesOverrides": [],
1801 "steppedLine": false,
1804 "expr": "container_fs_io_current{name=~\".+\"}",
1805 "format": "time_series",
1808 "intervalFactor": 2,
1809 "legendFormat": "{{name}}",
1814 "expr": "container_fs_read_seconds_total{name=~\".+\"}",
1815 "format": "time_series",
1817 "intervalFactor": 2,
1818 "legendFormat": "Read - {{name}}",
1823 "expr": "container_fs_write_seconds_total{name=~\".+\"}",
1824 "format": "time_series",
1826 "intervalFactor": 2,
1827 "legendFormat": "Write - {{name}}",
1835 "title": "Container IO Current",
1839 "value_type": "individual"
1870 "repeatIteration": null,
1871 "repeatRowId": null,
1873 "title": "Containers on Nodes - CPU, Traffic, Memory Usage",
1882 "datasource": "automated-ds",
1885 "filterNull": false,
1888 "hideTimeOverride": false,
1904 "rgba(245, 54, 54, 0.9)",
1905 "rgba(237, 129, 40, 0.89)",
1906 "rgba(50, 172, 45, 0.97)"
1917 "expr": "cadvisor_version_info",
1918 "format": "time_series",
1919 "intervalFactor": 2,
1920 "legendFormat": "{{instance}} - cAdvisor Version: {{cadvisorVersion}} - Docker Version: {{dockerVersion}} - OS Version: {{osVersion}} - Host Kernel Version: {{kernelVersion}}",
1925 "expr": "prometheus_build_info",
1926 "format": "time_series",
1927 "intervalFactor": 2,
1928 "legendFormat": "{{instance}} - Prometheus Version: {{version}} - Go Version: {{goversion}} - Prometheus Branch: {{branch}}",
1933 "expr": "node_exporter_build_info",
1934 "format": "time_series",
1935 "intervalFactor": 2,
1936 "legendFormat": "{{instance}} - Node-Exporter Version: {{version}} - Go Version: {{goversion}} - Node Exporter Branch: {{branch}}",
1941 "expr": "collectd_exporter_build_info",
1942 "format": "time_series",
1944 "intervalFactor": 2,
1945 "legendFormat": "{{instance}} - Collectd Exporter Version: {{version}} - Go Version: {{goversion}} - Collectd Exporter Branch: {{branch}} ",
1952 "title": "Versions",
1953 "transform": "timeseries_aggregations",
1963 "datasource": "automated-ds",
1982 "rgba(245, 54, 54, 0.9)",
1983 "rgba(237, 129, 40, 0.89)",
1984 "rgba(50, 172, 45, 0.97)"
1998 "expr": "sum(container_spec_memory_limit_bytes{name=~\".+\"} - container_memory_usage_bytes{name=~\".+\"}) by (name) ",
1999 "format": "time_series",
2001 "intervalFactor": 2,
2002 "legendFormat": "{{name}}",
2008 "expr": "sum(container_spec_memory_limit_bytes{name=~\".+\"}) by (name) ",
2009 "format": "time_series",
2011 "intervalFactor": 2,
2012 "legendFormat": "{{name}}",
2017 "expr": "container_memory_usage_bytes{name=~\".+\"}",
2018 "format": "time_series",
2020 "intervalFactor": 2,
2021 "legendFormat": "{{name}}",
2026 "title": "Limit memory",
2027 "transform": "timeseries_aggregations",
2032 "repeatIteration": null,
2033 "repeatRowId": null,
2035 "title": "Versions - Host OS, Docker, APP, Build Information",
2043 "repeatIteration": null,
2044 "repeatRowId": null,
2046 "title": "OVS Bridges on Nodes - TODO",
2054 "repeatIteration": null,
2055 "repeatRowId": null,
2057 "title": "VMs on Nodes - TODO",
2065 "repeatIteration": null,
2066 "repeatRowId": null,
2068 "title": "Traffic Generators Status - TODO",
2072 "schemaVersion": 14,
2083 "datasource": "automated-ds",
2086 "label": "Container Group",
2088 "name": "containergroup",
2090 "query": "label_values(container_group)",
2094 "tagValuesQuery": null,
2106 "value": "$__auto_interval"
2110 "includeAll": false,
2111 "label": "Interval",
2118 "value": "$__auto_interval"
2196 "query": "30s,1m,2m,3m,5m,7m,10m,30m,1h,6h,12h,1d,7d,14d,30d",
2206 "datasource": "automated-ds",
2208 "includeAll": false,
2213 "query": "label_values(node_boot_time, instance)",
2215 "regex": "/([^:]+):.*/",
2217 "tagValuesQuery": null,
2230 "refresh_intervals": [
2254 "timezone": "browser",
2255 "title": "Stats Overview",