jcoffey-dev
bcb9a01cd6
The demo had 75k generic records across eight host-0N/service pairs, one dashboard, one alert rule, and -- because nothing ever called AgentControl.CheckIn -- a completely empty Agents page. /hack/demo-simulator replaces the generic data with a fictional but coherent fleet: 14 hosts running nginx, an API tier, workers, Postgres, Redis, mail, Linux journals and Windows event logs, whose messages and attributes look like what those services actually write. It backfills a week (~370k records, ~20s) and then keeps running. Running continuously is the point, not an implementation detail. Three things the demo has to show are only true if data keeps arriving: the Agents page marks a host stale once check-ins stop, alert rules evaluate over trailing windows and would freeze in one state against a static dataset, and any "last 15 minutes" view is empty on data that stopped growing overnight. It also emits metrics/heartbeats and answers CheckIn faithfully enough that the remote-config editor's pending -> applied transition works end to end. Seeded incidents give the data something to find: an api-02 outage with matching slow queries on db-01, 5xx at the edge and cascading job failures; an SSH probe burst; a spam wave; a disk filling up; and one decommissioned host left deliberately stale. /hack/demo-seed holds the rest of the deployment -- the nightly reset, eight dashboards (64 panels, every viz type but line), eleven alert rules across three notification targets, and the systemd unit. Rule thresholds are calibrated against what the simulator actually produces: the first pass had four rules whose thresholds the traffic could never reach and one that fired during normal operation. No line charts: dashboard panels reject the raw-SQL escape hatch, and the pipe language has no time-bucketing, so a real time axis isn't expressible today. Noted in demo-seed/README.md rather than papered over.
113 lines
3.1 KiB
JSON
113 lines
3.1 KiB
JSON
{
|
|
"name": "Infrastructure",
|
|
"description": "Agent-reported CPU, memory, and disk for every host in the fleet",
|
|
"default_earliest": "-6h",
|
|
"default_latest": "now",
|
|
"panels": [
|
|
{
|
|
"title": "Metric samples",
|
|
"query": "cairnobs.metrics=true | stats count",
|
|
"viz_type": "single_stat",
|
|
"position_x": 0,
|
|
"position_y": 0,
|
|
"width": 4,
|
|
"height": 3,
|
|
"query_language": "spl",
|
|
"sort_order": 0
|
|
},
|
|
{
|
|
"title": "Peak CPU (%)",
|
|
"query": "cairnobs.metrics=true | stats max(cpu_percent) as max_cpu_percent",
|
|
"viz_type": "single_stat",
|
|
"position_x": 4,
|
|
"position_y": 0,
|
|
"width": 4,
|
|
"height": 3,
|
|
"query_language": "spl",
|
|
"sort_order": 1
|
|
},
|
|
{
|
|
"title": "Agent heartbeats",
|
|
"query": "cairnobs.heartbeat=true | stats count",
|
|
"viz_type": "single_stat",
|
|
"position_x": 8,
|
|
"position_y": 0,
|
|
"width": 4,
|
|
"height": 3,
|
|
"query_language": "spl",
|
|
"sort_order": 2
|
|
},
|
|
{
|
|
"title": "Average CPU by host",
|
|
"query": "cairnobs.metrics=true | stats avg(cpu_percent) as avg_cpu_percent by host | sort -avg_cpu_percent",
|
|
"viz_type": "bar",
|
|
"position_x": 0,
|
|
"position_y": 3,
|
|
"width": 6,
|
|
"height": 5,
|
|
"viz_config": {
|
|
"x_column": "host",
|
|
"value_column": "avg_cpu_percent"
|
|
},
|
|
"query_language": "spl",
|
|
"sort_order": 3
|
|
},
|
|
{
|
|
"title": "Disk used by host (bytes)",
|
|
"query": "cairnobs.metrics=true | stats max(disk_used_bytes) as disk_used_bytes by host | sort -disk_used_bytes | head 12",
|
|
"viz_type": "top_n",
|
|
"position_x": 6,
|
|
"position_y": 3,
|
|
"width": 6,
|
|
"height": 5,
|
|
"viz_config": {
|
|
"label_column": "host",
|
|
"value_column": "disk_used_bytes"
|
|
},
|
|
"query_language": "spl",
|
|
"sort_order": 4
|
|
},
|
|
{
|
|
"title": "Memory used by host (bytes)",
|
|
"query": "cairnobs.metrics=true | stats max(mem_used_bytes) as mem_used_bytes by host | sort -mem_used_bytes",
|
|
"viz_type": "bar",
|
|
"position_x": 0,
|
|
"position_y": 8,
|
|
"width": 6,
|
|
"height": 5,
|
|
"viz_config": {
|
|
"x_column": "host",
|
|
"value_column": "mem_used_bytes"
|
|
},
|
|
"query_language": "spl",
|
|
"sort_order": 5
|
|
},
|
|
{
|
|
"title": "Heartbeats by host",
|
|
"query": "cairnobs.heartbeat=true | stats count by host | sort -count",
|
|
"viz_type": "bar",
|
|
"position_x": 6,
|
|
"position_y": 8,
|
|
"width": 6,
|
|
"height": 5,
|
|
"viz_config": {
|
|
"x_column": "host",
|
|
"value_column": "count"
|
|
},
|
|
"query_language": "spl",
|
|
"sort_order": 6
|
|
},
|
|
{
|
|
"title": "Latest sample per host",
|
|
"query": "cairnobs.metrics=true | stats max(uptime_seconds) as uptime_seconds, avg(cpu_percent) as avg_cpu_percent, max(cpu_cores) as cores by host | sort -avg_cpu_percent",
|
|
"viz_type": "table",
|
|
"position_x": 0,
|
|
"position_y": 13,
|
|
"width": 12,
|
|
"height": 6,
|
|
"query_language": "spl",
|
|
"sort_order": 7
|
|
}
|
|
]
|
|
}
|