4 "name": "DS_PROMETHEUS",
8 "pluginId": "prometheus",
9 "pluginName": "Prometheus"
23 "name": "Graph (old)",
45 "uid": "${DS_PROMETHEUS}"
49 "iconColor": "rgba(0, 211, 255, 1)",
50 "name": "Annotations & Alerts",
62 "fiscalYearStartMonth": 0,
71 "uid": "${DS_PROMETHEUS}"
102 "options": "Earliest SSL cert expiration"
116 "value": __TLS_EXPIRATION_YELLOW__
119 "color": "transparent",
120 "value": __TLS_EXPIRATION_GREEN__
126 "id": "custom.cellOptions",
128 "type": "color-background"
155 "pluginVersion": "10.2.0",
159 "type": "prometheus",
160 "uid": "${DS_PROMETHEUS}"
162 "editorMode": "code",
164 "expr": "min(probe_ssl_earliest_cert_expiry)-time()",
165 "format": "time_series",
167 "legendFormat": "__auto",
172 "title": "Earliest SSL certificate expiration",
183 "min(probe_ssl_earliest_cert_expiry)-time()": "Earliest SSL cert expiration"
196 "type": "prometheus",
197 "uid": "${DS_PROMETHEUS}"
207 "hiddenSeries": false,
220 "nullPointMode": "null as zero",
222 "alertThreshold": true
225 "pluginVersion": "10.2.0",
231 "$$hashKey": "object:424",
234 "transform": "negative-Y"
239 "steppedLine": false,
243 "type": "prometheus",
244 "uid": "${DS_PROMETHEUS}"
246 "expr": "sum(rate(arvados_keepstore_volume_io_bytes{}[1m])) without (operation,device_id)",
248 "legendFormat": "{{ instance }} {{ direction }}",
254 "title": "Keepstore bandwidth [1m]",
258 "value_type": "individual"
268 "$$hashKey": "object:159",
274 "$$hashKey": "object:160",
290 "type": "prometheus",
291 "uid": "${DS_PROMETHEUS}"
307 "hiddenSeries": false,
320 "nullPointMode": "null as zero",
322 "alertThreshold": true
325 "pluginVersion": "10.2.0",
329 "seriesOverrides": [],
332 "steppedLine": false,
336 "type": "prometheus",
337 "uid": "${DS_PROMETHEUS}"
339 "expr": "arvados_dispatchcloud_containers_running{}",
341 "legendFormat": "# containers",
347 "title": "Containers running",
351 "value_type": "individual"
361 "$$hashKey": "object:973",
369 "$$hashKey": "object:974",
385 "type": "prometheus",
386 "uid": "${DS_PROMETHEUS}"
402 "hiddenSeries": false,
415 "nullPointMode": "null",
417 "alertThreshold": true
420 "pluginVersion": "10.2.0",
424 "seriesOverrides": [],
427 "steppedLine": false,
431 "type": "prometheus",
432 "uid": "${DS_PROMETHEUS}"
434 "expr": "sum(rate(arvados_keepstore_volume_operations{}[1m])) without (operation,device_id)",
436 "legendFormat": "{{instance}}",
442 "title": "Keepstore volume operations rate/second",
446 "value_type": "individual"
456 "$$hashKey": "object:982",
463 "$$hashKey": "object:983",
479 "type": "prometheus",
480 "uid": "${DS_PROMETHEUS}"
496 "hiddenSeries": false,
509 "nullPointMode": "null as zero",
511 "alertThreshold": true
514 "pluginVersion": "10.2.0",
518 "seriesOverrides": [],
521 "steppedLine": false,
525 "type": "prometheus",
526 "uid": "${DS_PROMETHEUS}"
528 "expr": "arvados_dispatchcloud_queue_entries{}",
530 "legendFormat": "{{instance_type}} {{state}}",
535 "type": "prometheus",
536 "uid": "${DS_PROMETHEUS}"
538 "expr": "arvados_dispatchcloud_containers_allocated_not_started{}",
540 "legendFormat": "allocated, not started",
545 "type": "prometheus",
546 "uid": "${DS_PROMETHEUS}"
548 "expr": "arvados_dispatchcloud_containers_not_allocated_over_quota{}",
550 "legendFormat": "not allocated, over quota",
556 "title": "Queue: # containers per {state, instance type}",
560 "value_type": "individual"
570 "$$hashKey": "object:4306",
577 "$$hashKey": "object:4307",
593 "type": "prometheus",
594 "uid": "${DS_PROMETHEUS}"
610 "hiddenSeries": false,
623 "nullPointMode": "null",
625 "alertThreshold": true
628 "pluginVersion": "10.2.0",
632 "seriesOverrides": [],
635 "steppedLine": false,
639 "type": "prometheus",
640 "uid": "${DS_PROMETHEUS}"
642 "expr": "arvados_keepstore_bufferpool_inuse_buffers{}",
644 "legendFormat": "{{instance}}",
650 "title": "Keepstore buffers in use",
654 "value_type": "individual"
664 "$$hashKey": "object:929",
671 "$$hashKey": "object:930",
687 "type": "prometheus",
688 "uid": "${DS_PROMETHEUS}"
698 "hiddenSeries": false,
711 "nullPointMode": "null as zero",
713 "alertThreshold": true
716 "pluginVersion": "10.2.0",
720 "seriesOverrides": [],
723 "steppedLine": false,
727 "type": "prometheus",
728 "uid": "${DS_PROMETHEUS}"
730 "expr": "arvados_dispatchcloud_containers_longest_wait_time_seconds{}",
732 "legendFormat": "Longest wait time",
737 "type": "prometheus",
738 "uid": "${DS_PROMETHEUS}"
740 "expr": "rate(arvados_dispatchcloud_containers_time_from_queue_to_crunch_run_seconds_sum{}[10m]) / rate(arvados_dispatchcloud_containers_time_from_queue_to_crunch_run_seconds_count{}[10m])",
742 "legendFormat": "avg wait time [10m]",
748 "title": "Container wait times",
752 "value_type": "individual"
762 "$$hashKey": "object:138",
769 "$$hashKey": "object:139",
785 "type": "prometheus",
786 "uid": "${DS_PROMETHEUS}"
802 "hiddenSeries": false,
815 "nullPointMode": "null",
817 "alertThreshold": true
820 "pluginVersion": "10.2.0",
824 "seriesOverrides": [],
827 "steppedLine": false,
831 "type": "prometheus",
832 "uid": "${DS_PROMETHEUS}"
834 "expr": "arvados_keep_total_bytes{}",
836 "legendFormat": "Total stored",
841 "type": "prometheus",
842 "uid": "${DS_PROMETHEUS}"
844 "expr": "arvados_keep_overreplicated_bytes{}",
846 "legendFormat": "Overreplicated",
851 "type": "prometheus",
852 "uid": "${DS_PROMETHEUS}"
854 "expr": "arvados_keep_underreplicated_bytes{}",
856 "legendFormat": "Underreplicated",
861 "type": "prometheus",
862 "uid": "${DS_PROMETHEUS}"
864 "expr": "arvados_keep_lost_bytes{}",
866 "legendFormat": "Lost",
872 "title": "Total bytes by type",
876 "value_type": "individual"
886 "$$hashKey": "object:304",
888 "format": "decbytes",
895 "$$hashKey": "object:305",
911 "type": "prometheus",
912 "uid": "${DS_PROMETHEUS}"
922 "hiddenSeries": false,
935 "nullPointMode": "null as zero",
937 "alertThreshold": true
940 "pluginVersion": "10.2.0",
944 "seriesOverrides": [],
947 "steppedLine": false,
951 "type": "prometheus",
952 "uid": "${DS_PROMETHEUS}"
954 "expr": "rate(arvados_dispatchcloud_instances_time_to_ssh_seconds_sum{}[10m]) / rate(arvados_dispatchcloud_instances_time_to_ssh_seconds_count{}[10m])",
957 "legendFormat": "ssh",
962 "type": "prometheus",
963 "uid": "${DS_PROMETHEUS}"
965 "expr": "rate(arvados_dispatchcloud_instances_time_to_ready_for_container_seconds_sum{}[10m]) / rate(arvados_dispatchcloud_instances_time_to_ready_for_container_seconds_count{}[10m])",
967 "legendFormat": "ready",
973 "title": "Instance time to ... avg [10m]",
977 "value_type": "individual"
987 "$$hashKey": "object:113",
994 "$$hashKey": "object:114",
1010 "type": "prometheus",
1011 "uid": "${DS_PROMETHEUS}"
1021 "hiddenSeries": false,
1034 "nullPointMode": "null",
1036 "alertThreshold": true
1038 "percentage": false,
1039 "pluginVersion": "10.2.0",
1043 "seriesOverrides": [],
1046 "steppedLine": false,
1050 "type": "prometheus",
1051 "uid": "${DS_PROMETHEUS}"
1053 "expr": "arvados_concurrent_requests{}",
1055 "legendFormat": "{{instance}}",
1061 "title": "Concurrent requests",
1065 "value_type": "individual"
1075 "$$hashKey": "object:109",
1082 "$$hashKey": "object:110",
1098 "type": "prometheus",
1099 "uid": "${DS_PROMETHEUS}"
1115 "hiddenSeries": false,
1128 "nullPointMode": "null as zero",
1130 "alertThreshold": true
1132 "percentage": false,
1133 "pluginVersion": "10.2.0",
1137 "seriesOverrides": [],
1140 "steppedLine": false,
1144 "type": "prometheus",
1145 "uid": "${DS_PROMETHEUS}"
1147 "expr": "arvados_dispatchcloud_boot_outcomes{}",
1149 "legendFormat": "{{outcome}}",
1155 "title": "Boot outcomes",
1159 "value_type": "individual"
1169 "$$hashKey": "object:921",
1176 "$$hashKey": "object:922",
1192 "type": "prometheus",
1193 "uid": "${DS_PROMETHEUS}"
1209 "hiddenSeries": false,
1222 "nullPointMode": "null as zero",
1224 "alertThreshold": true
1226 "percentage": false,
1227 "pluginVersion": "10.2.0",
1231 "seriesOverrides": [],
1234 "steppedLine": false,
1238 "type": "prometheus",
1239 "uid": "${DS_PROMETHEUS}"
1241 "expr": "sum(arvados_dispatchcloud_instances_price{})",
1243 "intervalFactor": 10,
1244 "legendFormat": "cost ($)",
1254 "value_type": "individual"
1264 "$$hashKey": "object:623",
1266 "label": "$ / hour",
1272 "$$hashKey": "object:624",
1288 "type": "prometheus",
1289 "uid": "${DS_PROMETHEUS}"
1305 "hiddenSeries": false,
1318 "nullPointMode": "null as zero",
1320 "alertThreshold": true
1322 "percentage": false,
1323 "pluginVersion": "10.2.0",
1327 "seriesOverrides": [],
1330 "steppedLine": false,
1334 "type": "prometheus",
1335 "uid": "${DS_PROMETHEUS}"
1337 "expr": "arvados_dispatchcloud_instances_disappeared{}",
1339 "legendFormat": "{{state}}",
1345 "title": "instance state before disappearance",
1349 "value_type": "individual"
1359 "$$hashKey": "object:1025",
1366 "$$hashKey": "object:1026",
1382 "type": "prometheus",
1383 "uid": "${DS_PROMETHEUS}"
1399 "hiddenSeries": false,
1412 "nullPointMode": "null as zero",
1414 "alertThreshold": true
1416 "percentage": false,
1417 "pluginVersion": "10.2.0",
1421 "seriesOverrides": [],
1424 "steppedLine": false,
1428 "type": "prometheus",
1429 "uid": "${DS_PROMETHEUS}"
1431 "expr": "arvados_dispatchcloud_instances_price{}",
1433 "intervalFactor": 10,
1434 "legendFormat": "{{category}}",
1440 "title": "Cost by node state",
1444 "value_type": "individual"
1454 "$$hashKey": "object:574",
1456 "label": "$ / hour",
1462 "$$hashKey": "object:575",
1478 "type": "prometheus",
1479 "uid": "${DS_PROMETHEUS}"
1489 "hiddenSeries": false,
1502 "nullPointMode": "null as zero",
1504 "alertThreshold": true
1506 "percentage": false,
1507 "pluginVersion": "10.2.0",
1511 "seriesOverrides": [],
1514 "steppedLine": false,
1518 "type": "prometheus",
1519 "uid": "${DS_PROMETHEUS}"
1521 "expr": "rate(arvados_dispatchcloud_instances_time_from_shutdown_request_to_disappearance_seconds_sum{}[10m]) / rate(arvados_dispatchcloud_instances_time_from_shutdown_request_to_disappearance_seconds_count{}[10m])",
1523 "legendFormat": "shutdown to disappearance",
1529 "title": "Instances time from shutdown to disappearance avg[10m]",
1533 "value_type": "individual"
1543 "$$hashKey": "object:450",
1550 "$$hashKey": "object:451",
1566 "type": "prometheus",
1567 "uid": "${DS_PROMETHEUS}"
1583 "hiddenSeries": false,
1596 "nullPointMode": "null as zero",
1598 "alertThreshold": true
1600 "percentage": false,
1601 "pluginVersion": "10.2.0",
1605 "seriesOverrides": [],
1608 "steppedLine": false,
1612 "type": "prometheus",
1613 "uid": "${DS_PROMETHEUS}"
1615 "expr": "arvados_dispatchcloud_instances_total{}",
1618 "legendFormat": "{{instance_type}} : {{category}}",
1624 "$$hashKey": "object:540",
1625 "colorMode": "critical",
1633 "title": "Nodes by state",
1637 "value_type": "individual"
1647 "$$hashKey": "object:723",
1654 "$$hashKey": "object:724",
1670 "type": "prometheus",
1671 "uid": "${DS_PROMETHEUS}"
1681 "hiddenSeries": false,
1694 "nullPointMode": "null as zero",
1696 "alertThreshold": true
1698 "percentage": false,
1699 "pluginVersion": "10.2.0",
1703 "seriesOverrides": [],
1706 "steppedLine": false,
1710 "type": "prometheus",
1711 "uid": "${DS_PROMETHEUS}"
1713 "expr": "rate(arvados_dispatchcloud_instances_run_probe_duration_seconds_sum{}[10m]) / rate(arvados_dispatchcloud_instances_run_probe_duration_seconds_count{}[10m])",
1715 "legendFormat": "{{outcome}}",
1721 "title": "run probe duration avg[10m]",
1725 "value_type": "individual"
1735 "$$hashKey": "object:125",
1742 "$$hashKey": "object:126",
1758 "type": "prometheus",
1759 "uid": "${DS_PROMETHEUS}"
1769 "hiddenSeries": false,
1782 "nullPointMode": "null",
1784 "alertThreshold": true
1786 "percentage": false,
1787 "pluginVersion": "10.2.0",
1791 "seriesOverrides": [],
1794 "steppedLine": false,
1798 "type": "prometheus",
1799 "uid": "${DS_PROMETHEUS}"
1801 "expr": "delta(arvados_dispatchcloud_instances_run_probe_duration_seconds_count{}[1m])",
1804 "legendFormat": "{{outcome}}",
1810 "title": "run probe count by outcome -- delta[1m]",
1814 "value_type": "individual"
1824 "$$hashKey": "object:149",
1831 "$$hashKey": "object:150",
1844 "schemaVersion": 38,
1854 "refresh_intervals": [
1867 "title": "Arvados cluster overview",
1868 "uid": "ArvadosClusterOverviewDashboard",