Vantage/vantage-app
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Monitor grath zoom

Browse Source
This commit is contained in:
mrhid6
2026-08-24 10:58:50 +00:00
parent 2fab784ba7
commit 22b99ff895
11 changed files with 395 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
server/cmd/main.go
+8 -4
View File
@@ -51,10 +51,10 @@ import (
// @name Authorization
// @description An API token, sent as "Bearer vt_…". Scoped and optionally expiring.
// @securityDefinitions.apikey esoAuth
// @in header
// @name Authorization
// @description The External Secrets read token, rotated under Settings. It reaches /api/secrets/{group}/values and nothing else. It is a different credential from an API token, and the two must never be substituted for one another.
// @securityDefinitions.apikey esoAuth
// @in header
// @name Authorization
// @description The External Secrets read token, rotated under Settings. It reaches /api/secrets/{group}/values and nothing else. It is a different credential from an API token, and the two must never be substituted for one another.
func main() {
mongoURI := getEnv("MONGO_URI", "mongodb://localhost:27017")
@@ -162,6 +162,10 @@ func runSchemaSetup() {
log.Printf("warning: failed to ensure workflow indexes: %v", err)
}
if err := services.EnsureMonitorSampleIndexes(); err != nil {
log.Printf("warning: failed to ensure monitor sample indexes: %v", err)
}
if err := services.EnsureVulnIndexes(); err != nil {
log.Printf("warning: failed to ensure vuln indexes: %v", err)
}
server/internal/api/docs/openapi.json
+91
View File
@@ -1119,6 +1119,26 @@
},
"type": "object"
},
"models.MonitorSample": {
"properties": {
"at": {
"type": "string"
},
"instance_id": {
"type": "string"
},
"latency_ms": {
"type": "integer"
},
"monitor_id": {
"type": "string"
},
"up": {
"type": "boolean"
}
},
"type": "object"
},
"models.MonitorState": {
"properties": {
"cert_expiry_at": {
@@ -4345,6 +4365,77 @@
]
}
},
"/monitors/{id}/samples": {
"get": {
"description": "Raw check results for the last `minutes` minutes, oldest first. Samples expire after 48 hours; use the uptime rollups for longer ranges.",
"parameters": [
{
"description": "Monitor ID",
"in": "path",
"name": "id",
"required": true,
"schema": {
"type": "string"
}
},
{
"description": "Window in minutes (default 60, max 2880)",
"in": "query",
"name": "minutes",
"schema": {
"type": "integer"
}
}
],
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"items": {
"$ref": "#/components/schemas/models.MonitorSample"
},
"type": "array"
}
}
},
"description": "OK"
},
"404": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/api.ErrorResponse"
}
}
},
"description": "Not Found"
},
"500": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/api.ErrorResponse"
}
}
},
"description": "Internal Server Error"
}
},
"security": [
{
"cookieAuth": []
},
{
"bearerAuth": []
}
],
"summary": "Get a monitor's individual check results",
"tags": [
"monitors"
]
}
},
"/monitors/{id}/uptime": {
"get": {
"description": "Hourly rollups for the last 30 days.",
server/internal/api/monitors.go
+45
View File
@@ -2,6 +2,7 @@ package api
import (
"net/http"
"strconv"
"time"
"gitea.hostxtra.co.uk/mrhid6/vantage/server/internal/auth"
@@ -19,6 +20,7 @@ func registerMonitorRoutes(g *gin.RouterGroup) {
g.DELETE("/monitors/:id", deleteMonitor)
g.GET("/monitors/:id/incidents", getMonitorIncidents)
g.GET("/monitors/:id/uptime", getMonitorUptime)
g.GET("/monitors/:id/samples", getMonitorSamples)
}
// listMonitors godoc
@@ -221,6 +223,49 @@ func getMonitorIncidents(c *gin.Context) {
c.JSON(http.StatusOK, incidents)
}
// getMonitorSamples godoc
//
// @Summary Get a monitor's individual check results
// @Description Raw check results for the last `minutes` minutes, oldest first. Samples expire after 48 hours; use the uptime rollups for longer ranges.
// @Tags monitors
// @Produce json
// @Param id path string true "Monitor ID"
// @Param minutes query int false "Window in minutes (default 60, max 2880)"
// @Success 200 {array} models.MonitorSample
// @Failure 404 {object} ErrorResponse
// @Failure 500 {object} ErrorResponse
// @Security cookieAuth
// @Security bearerAuth
// @Router /monitors/{id}/samples [get]
func getMonitorSamples(c *gin.Context) {
m, err := services.GetMonitor(auth.InstanceID(c), c.Param("id"))
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
if m == nil {
c.JSON(http.StatusNotFound, gin.H{"error": "monitor not found"})
return
}
// Clamped rather than rejected: the window is a view setting, and the only
// honest answer past the TTL is the shorter window anyway.
minutes := 60
if raw := c.Query("minutes"); raw != "" {
if n, convErr := strconv.Atoi(raw); convErr == nil && n > 0 {
minutes = n
}
}
if max := int(services.MonitorSampleTTL.Minutes()); minutes > max {
minutes = max
}
samples, err := services.MonitorSamples(auth.InstanceID(c), c.Param("id"), time.Now().Add(-time.Duration(minutes)*time.Minute))
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
c.JSON(http.StatusOK, samples)
}
// getMonitorUptime godoc
//
// @Summary Get a monitor's uptime rollups
server/internal/api/scopes.go
+1
View File
@@ -100,6 +100,7 @@ var routeScopes = map[string]string{
"DELETE /api/monitors/:id": "monitors:write",
"GET /api/monitors/:id/incidents": "monitors:read",
"GET /api/monitors/:id/uptime": "monitors:read",
"GET /api/monitors/:id/samples": "monitors:read",
// Channel routes, registered by registerChannelRoutes. Channels exist to
// serve alerts, so they share the monitors scope rather than getting their
server/internal/models/monitor.go
+15
View File
@@ -71,6 +71,21 @@ type Incident struct {
Cause string `bson:"cause,omitempty" json:"cause,omitempty"`
}
// MonitorSample is one check result, kept only long enough to draw the
// sub-hour views of the history chart. Rollup remains the durable record: a
// sample expires by TTL, a rollup does not.
//
// It carries no message. The failure text is on the incident, and a document
// per check is the one place in this schema where a few bytes multiply by the
// check rate.
type MonitorSample struct {
InstanceID string `bson:"instance_id" json:"instance_id"`
MonitorID string `bson:"monitor_id" json:"monitor_id"`
At time.Time `bson:"at" json:"at"`
Up bool `bson:"up" json:"up"`
LatencyMs int `bson:"latency_ms" json:"latency_ms"`
}
type Rollup struct {
InstanceID string `bson:"instance_id" json:"instance_id"`
MonitorID string `bson:"monitor_id" json:"monitor_id"`
server/internal/services/migrate_instance.go
+1
View File
@@ -36,6 +36,7 @@ var ScopedCollections = []string{
"monitors",
"incidents",
"monitor_rollups",
"monitor_samples",
"notification_channels",
"console_sessions",
"audit_logs",
server/internal/services/monitors.go
+37
View File
@@ -221,6 +221,7 @@ func DeleteMonitor(instanceID, monitorID string) error {
}
db.Col("incidents").DeleteMany(ctx, bson.M{"monitor_id": monitorID, "instance_id": instanceID})
db.Col("monitor_rollups").DeleteMany(ctx, bson.M{"monitor_id": monitorID, "instance_id": instanceID})
db.Col("monitor_samples").DeleteMany(ctx, bson.M{"monitor_id": monitorID, "instance_id": instanceID})
return nil
}
@@ -258,6 +259,31 @@ func UptimeRollups(instanceID, monitorID string, since time.Time) ([]models.Roll
return out, nil
}
// MaxMonitorSamples bounds one range read. At the 10s floor, 48h is 17,280
// checks; the chart buckets them anyway, so a cap costs nothing visible and
// stops one monitor pulling a megabyte of JSON per poll.
const MaxMonitorSamples = 6000
// MonitorSamples returns individual check results since a point in time,
// oldest first. Samples older than MonitorSampleTTL have expired, so an early
// `since` silently returns a shorter window rather than an error — the caller
// draws the gap.
func MonitorSamples(instanceID, monitorID string, since time.Time) ([]models.MonitorSample, error) {
ctx, cancel := monCtx()
defer cancel()
cur, err := db.Col("monitor_samples").Find(ctx,
bson.M{"monitor_id": monitorID, "instance_id": instanceID, "at": bson.M{"$gte": since}},
options.Find().SetSort(bson.M{"at": 1}).SetLimit(MaxMonitorSamples))
if err != nil {
return nil, err
}
var out []models.MonitorSample
if err := cur.All(ctx, &out); err != nil {
return nil, err
}
return out, nil
}
func IngestResult(instanceID, runner, monitorID string, res checker.Result) error {
if instanceID == "" {
return errors.New("instance id required")
@@ -328,6 +354,17 @@ func ingestResult(instanceID, runner, monitorID string, res checker.Result) erro
up = 1
}
/* The sample is the same result at full resolution, expiring by TTL. It is
written next to the rollup rather than instead of it: the rollup is what
survives, the sample is what the sub-hour views read. */
db.Col("monitor_samples").InsertOne(ctx, models.MonitorSample{
InstanceID: m.InstanceID,
MonitorID: monitorID,
At: now,
Up: res.Up,
LatencyMs: res.LatencyMs,
})
db.Col("monitor_rollups").UpdateOne(ctx,
bson.M{"monitor_id": monitorID, "period_start": bucket},
bson.M{
server/internal/services/monitorsampleindexes.go
+42
View File
@@ -0,0 +1,42 @@
package services
import (
"context"
"log"
"time"
"gitea.hostxtra.co.uk/mrhid6/vantage/server/internal/db"
"go.mongodb.org/mongo-driver/v2/bson"
"go.mongodb.org/mongo-driver/v2/mongo"
"go.mongodb.org/mongo-driver/v2/mongo/options"
)
// MonitorSampleTTL is how long an individual check result is kept.
//
// It matches the longest range the chart draws from samples rather than the
// longest range it draws at all: 24h and 48h come from the hourly rollups,
// which are permanent. Keeping samples past the window that reads them would
// only grow the collection.
const MonitorSampleTTL = 48 * time.Hour
// EnsureMonitorSampleIndexes declares the sample range index and its TTL.
//
// Warn rather than fatal, like the other history indexes — but note the TTL is
// not an optimisation: without it nothing ever removes a sample, and the
// collection grows at the fleet's total check rate forever. A boot that logs
// this warning needs following up.
func EnsureMonitorSampleIndexes() error {
ctx := context.Background()
idx := []mongo.IndexModel{
// Every read is a range scan over this key.
{Keys: bson.D{{Key: "instance_id", Value: 1}, {Key: "monitor_id", Value: 1}, {Key: "at", Value: 1}}},
// Expiry is Mongo's job: a sweeper would be another leader-scoped loop
// doing what the server already does for free.
{Keys: bson.D{{Key: "at", Value: 1}}, Options: options.Index().SetExpireAfterSeconds(int32(MonitorSampleTTL.Seconds()))},
}
if _, err := db.Col("monitor_samples").Indexes().CreateMany(ctx, idx); err != nil {
log.Printf("warning: monitor_samples indexes: %v", err)
}
return nil
}