diff --git a/nix/host-modules/swarm-grafana.nix b/nix/host-modules/swarm-grafana.nix index 4c4b159b..26c0d8ae 100644 --- a/nix/host-modules/swarm-grafana.nix +++ b/nix/host-modules/swarm-grafana.nix @@ -61,6 +61,7 @@ let [ "agents.json" "authelia.json" + "bao.json" "claude-usage.json" "forge.json" "logstore.json" diff --git a/nix/host-modules/swarm-grafana/dashboards/bao.json b/nix/host-modules/swarm-grafana/dashboards/bao.json new file mode 100644 index 00000000..931f5308 --- /dev/null +++ b/nix/host-modules/swarm-grafana/dashboards/bao.json @@ -0,0 +1,569 @@ +{ + "title": "hyperhive · openbao", + "uid": "hyperhive-bao", + "description": "The swarm's secret store. Two things to know before editing: the metric prefix is vault_, not openbao_ — the fork kept upstream's names, and a panel built on the name you would guess renders perfectly and shows nothing. And a SEALED store emits almost nothing: only the top row works before an operator has run `bao operator init`, everything below it is empty until then and that is the expected reading, not a broken query. Targets are labelled service.name, NOT job; there is no job label in this store. Counters are counts over the dashboard range rather than per-second rates, because a store this quiet rates to exactly zero.", + "editable": true, + "refresh": "1m", + "schemaVersion": 39, + "tags": [ + "hyperhive", + "swarm", + "bao", + "secrets" + ], + "time": { + "from": "now-24h", + "to": "now" + }, + "timezone": "utc", + "version": 1, + "templating": { + "list": [] + }, + "panels": [ + { + "id": 1, + "type": "stat", + "title": "Seal state", + "description": "SEALED means the store is up but refusing every read — the state it boots into, and the state it returns to on restart unless auto-unseal is configured. The max() is load-bearing: once unsealed there are two vault_core_unsealed series and the cluster=\"\" one stays 0 forever, so a bare selector reads SEALED on a healthy store.", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 0, + "y": 0 + }, + "targets": [ + { + "refId": "A", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "max(vault_core_unsealed{\"service.name\"=\"bao\"})", + "instant": true, + "legendFormat": "seal" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { + "mode": "thresholds" + }, + "mappings": [ + { + "type": "value", + "options": { + "0": { + "text": "SEALED", + "color": "red", + "index": 0 + }, + "1": { + "text": "unsealed", + "color": "green", + "index": 1 + } + } + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red", + "value": null + }, + { + "color": "green", + "value": 1 + } + ] + } + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "background", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + } + }, + { + "id": 2, + "type": "stat", + "title": "Uptime", + "description": "Time since the openbao process started. Read it beside the seal state: a restart re-seals the store, so a short uptime and a SEALED panel are one event rather than two problems.", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 6, + "y": 0 + }, + "targets": [ + { + "refId": "A", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "time() - process_start_time_seconds{\"service.name\"=\"bao\"}", + "instant": true, + "legendFormat": "uptime" + } + ], + "fieldConfig": { + "defaults": { + "unit": "s", + "decimals": 0, + "color": { + "mode": "fixed", + "fixedColor": "text" + }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + } + }, + { + "id": 3, + "type": "stat", + "title": "Goroutines", + "description": "A Go runtime metric, so it is present even while sealed — which makes it the panel that distinguishes a store with nothing to say from a scrape that is not arriving at all. No data here means the collector is not reaching the metrics listener.", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 12, + "y": 0 + }, + "targets": [ + { + "refId": "A", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "go_goroutines{\"service.name\"=\"bao\"}", + "instant": true, + "legendFormat": "goroutines" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { + "mode": "fixed", + "fixedColor": "text" + }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + } + }, + { + "id": 4, + "type": "stat", + "title": "Requests (range)", + "description": "vault_core_handle_request_count over the dashboard range — every API call the store served, unseal attempts included. The summary's _count series, not the summary itself. Zero on a sealed store, and zero is the honest answer there rather than an absent panel.", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 18, + "y": 0 + }, + "targets": [ + { + "refId": "A", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "sum(increase(vault_core_handle_request_count{\"service.name\"=\"bao\"}[$__range])) or vector(0)", + "instant": true, + "legendFormat": "requests" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { + "mode": "fixed", + "fixedColor": "text" + }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + } + }, + { + "id": 10, + "type": "stat", + "title": "Seal operations (range)", + "description": "Encrypt and decrypt calls against the seal wrapper — on this swarm a TPM through PKCS#11, so each one is a round trip to hardware. These are counters with no _total suffix. A climbing decrypt count with a flat request count means something is re-reading the barrier rather than serving clients.", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "gridPos": { + "h": 4, + "w": 12, + "x": 0, + "y": 4 + }, + "targets": [ + { + "refId": "A", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "sum(increase(vault_seal_encrypt{\"service.name\"=\"bao\"}[$__range])) or vector(0)", + "instant": true, + "legendFormat": "encrypt" + }, + { + "refId": "B", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "sum(increase(vault_seal_decrypt{\"service.name\"=\"bao\"}[$__range])) or vector(0)", + "instant": true, + "legendFormat": "decrypt" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { + "mode": "palette-classic" + }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value_and_name", + "justifyMode": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + } + }, + { + "id": 11, + "type": "stat", + "title": "Raft peers", + "description": "Voting members of the store's raft cluster. This swarm runs a single node, so 1 is the expected value and anything else means a peer was added — or that this node no longer sees itself as part of the cluster it stores data for.", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "gridPos": { + "h": 4, + "w": 12, + "x": 12, + "y": 4 + }, + "targets": [ + { + "refId": "A", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "vault_raft_peers{\"service.name\"=\"bao\"}", + "instant": true, + "legendFormat": "peers" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { + "mode": "fixed", + "fixedColor": "text" + }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + } + }, + { + "id": 20, + "type": "timeseries", + "title": "Request latency", + "description": "Quantiles openbao computes itself — a summary, so the store picked the buckets and a histogram_quantile() is neither needed nor possible here. Units are MILLISECONDS: vault's timers report ms, and reading them as seconds understates the store by three orders of magnitude.", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 8 + }, + "targets": [ + { + "refId": "A", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "vault_core_handle_request{\"service.name\"=\"bao\",quantile=\"0.99\"}", + "legendFormat": "p99" + }, + { + "refId": "B", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "vault_core_handle_request{\"service.name\"=\"bao\",quantile=\"0.5\"}", + "legendFormat": "p50" + } + ], + "fieldConfig": { + "defaults": { + "unit": "ms", + "decimals": 1, + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineWidth": 1, + "fillOpacity": 0, + "showPoints": "never", + "spanNulls": false, + "axisSoftMin": 0 + } + }, + "overrides": [] + }, + "options": { + "legend": { + "displayMode": "list", + "placement": "bottom", + "showLegend": true, + "calcs": [] + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + } + }, + { + "id": 21, + "type": "timeseries", + "title": "Leases", + "description": "Outstanding leases, and the irrevocable ones beside them. The second line should sit at zero: an irrevocable lease is one the store gave up trying to revoke, so a credential somewhere outlives what issued it and no amount of waiting will clean it up.", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 8 + }, + "targets": [ + { + "refId": "A", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "vault_expire_num_leases{\"service.name\"=\"bao\"}", + "legendFormat": "leases" + }, + { + "refId": "B", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "vault_expire_num_irrevocable_leases{\"service.name\"=\"bao\"}", + "legendFormat": "irrevocable" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineWidth": 1, + "fillOpacity": 10, + "showPoints": "never", + "spanNulls": false, + "axisSoftMin": 0 + } + }, + "overrides": [] + }, + "options": { + "legend": { + "displayMode": "list", + "placement": "bottom", + "showLegend": true, + "calcs": [] + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + } + }, + { + "id": 30, + "type": "timeseries", + "title": "Heap in use", + "description": "go_memstats_heap_inuse_bytes. Present while sealed, so it is a live line even on a store that is serving nothing — a sawtooth is normal Go behaviour, a monotonic climb on an idle store is not.", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "gridPos": { + "h": 6, + "w": 24, + "x": 0, + "y": 16 + }, + "targets": [ + { + "refId": "A", + "datasource": { + "type": "prometheus", + "uid": "@datasourceUid@" + }, + "expr": "go_memstats_heap_inuse_bytes{\"service.name\"=\"bao\"}", + "legendFormat": "heap" + } + ], + "fieldConfig": { + "defaults": { + "unit": "bytes", + "decimals": 1, + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineWidth": 1, + "fillOpacity": 10, + "showPoints": "never", + "spanNulls": false, + "axisSoftMin": 0 + } + }, + "overrides": [] + }, + "options": { + "legend": { + "displayMode": "list", + "placement": "bottom", + "showLegend": true, + "calcs": [] + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + } + } + ] +}