Enhance API and UI for incident management and live updates
- Added a new endpoint `/api/agg/incidents` to provide a normalized snapshot of incidents for fleet triage, including severity and recommended actions. - Implemented live event streaming via `/api/live/events` for real-time updates on fleet status and incidents, enhancing observability. - Updated the Web UI to include dedicated sections for incidents and live updates, improving user navigation and access to critical information. - Enhanced API documentation to reflect new endpoints and their functionalities, ensuring clarity for developers and users.
This commit is contained in:
@@ -0,0 +1,154 @@
|
||||
package aggregate
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
type statsSummaryLite struct {
|
||||
ConnectionsBadTotal uint64 `json:"connections_bad_total"`
|
||||
ConnectionsTotal uint64 `json:"connections_total"`
|
||||
}
|
||||
|
||||
func BuildIncidents(ctx context.Context, h *Handler, aliases []string) (IncidentsData, bool) {
|
||||
out := IncidentsData{Items: make([]IncidentItem, 0)}
|
||||
partial := false
|
||||
|
||||
fleet := FetchFleetStatus(ctx, h.Client, h.Parsed, aliases)
|
||||
if fleet.ServersFailed > 0 {
|
||||
partial = true
|
||||
}
|
||||
|
||||
for _, s := range fleet.Servers {
|
||||
if !s.OK {
|
||||
severity := SeverityWarning
|
||||
if !s.HealthOK && !s.SystemInfoOK {
|
||||
severity = SeverityCritical
|
||||
}
|
||||
out.Items = append(out.Items, IncidentItem{
|
||||
ID: fmt.Sprintf("node_degraded:%s", s.Alias),
|
||||
Kind: "node_degraded",
|
||||
Severity: severity,
|
||||
Status: IncidentStatusFiring,
|
||||
Title: fmt.Sprintf("Нода %s degraded", s.Alias),
|
||||
Summary: "health/system_info не прошли полностью",
|
||||
AffectedAliases: []string{s.Alias},
|
||||
Actions: []IncidentAction{
|
||||
{Label: "Открыть ноду", Href: "/servers/" + s.Alias},
|
||||
{Label: "Runtime", Href: "/servers/" + s.Alias + "/runtime"},
|
||||
},
|
||||
})
|
||||
}
|
||||
if s.Health != nil && s.Health.ReadOnly {
|
||||
out.Items = append(out.Items, IncidentItem{
|
||||
ID: fmt.Sprintf("node_read_only:%s", s.Alias),
|
||||
Kind: "node_read_only",
|
||||
Severity: SeverityWarning,
|
||||
Status: IncidentStatusFiring,
|
||||
Title: fmt.Sprintf("Нода %s в read_only", s.Alias),
|
||||
Summary: "API ноды не принимает mutating операции",
|
||||
AffectedAliases: []string{s.Alias},
|
||||
Actions: []IncidentAction{
|
||||
{Label: "Users", Href: "/servers/" + s.Alias + "/users"},
|
||||
{Label: "Security", Href: "/servers/" + s.Alias + "/security"},
|
||||
},
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
for _, alias := range aliases {
|
||||
data, meta := FetchTelemtGET[statsSummaryLite](ctx, h.Client, h.Parsed, alias, "stats/summary")
|
||||
if !meta.OK {
|
||||
partial = true
|
||||
continue
|
||||
}
|
||||
if data.ConnectionsBadTotal >= 10000 {
|
||||
out.Items = append(out.Items, IncidentItem{
|
||||
ID: fmt.Sprintf("bad_connections_high:%s", alias),
|
||||
Kind: "bad_connections_high",
|
||||
Severity: SeverityCritical,
|
||||
Status: IncidentStatusFiring,
|
||||
Title: fmt.Sprintf("Высокий bad connections на %s", alias),
|
||||
Summary: "Резкий рост ошибок клиентских соединений",
|
||||
AffectedAliases: []string{alias},
|
||||
MetricName: "connections_bad_total",
|
||||
MetricValue: float64(data.ConnectionsBadTotal),
|
||||
MetricThreshold: 10000,
|
||||
Actions: []IncidentAction{
|
||||
{Label: "Node dashboard", Href: "/servers/" + alias},
|
||||
},
|
||||
})
|
||||
} else if data.ConnectionsBadTotal >= 1000 {
|
||||
out.Items = append(out.Items, IncidentItem{
|
||||
ID: fmt.Sprintf("bad_connections_warn:%s", alias),
|
||||
Kind: "bad_connections_warn",
|
||||
Severity: SeverityWarning,
|
||||
Status: IncidentStatusFiring,
|
||||
Title: fmt.Sprintf("Рост bad connections на %s", alias),
|
||||
Summary: "Наблюдается рост ошибок клиентских соединений",
|
||||
AffectedAliases: []string{alias},
|
||||
MetricName: "connections_bad_total",
|
||||
MetricValue: float64(data.ConnectionsBadTotal),
|
||||
MetricThreshold: 1000,
|
||||
Actions: []IncidentAction{
|
||||
{Label: "Node dashboard", Href: "/servers/" + alias},
|
||||
},
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
sort.Slice(out.Items, func(i, j int) bool {
|
||||
if severityWeight(out.Items[i].Severity) != severityWeight(out.Items[j].Severity) {
|
||||
return severityWeight(out.Items[i].Severity) > severityWeight(out.Items[j].Severity)
|
||||
}
|
||||
return strings.Compare(out.Items[i].ID, out.Items[j].ID) < 0
|
||||
})
|
||||
|
||||
out.Total = len(out.Items)
|
||||
for _, it := range out.Items {
|
||||
switch it.Severity {
|
||||
case SeverityCritical:
|
||||
out.CriticalTotal++
|
||||
case SeverityWarning:
|
||||
out.WarningTotal++
|
||||
default:
|
||||
out.InfoTotal++
|
||||
}
|
||||
}
|
||||
return out, partial
|
||||
}
|
||||
|
||||
func severityWeight(s IncidentSeverity) int {
|
||||
switch s {
|
||||
case SeverityCritical:
|
||||
return 3
|
||||
case SeverityWarning:
|
||||
return 2
|
||||
case SeverityInfo:
|
||||
return 1
|
||||
default:
|
||||
return 0
|
||||
}
|
||||
}
|
||||
|
||||
func BuildLiveEnvelope(ctx context.Context, h *Handler, aliases []string) map[string]any {
|
||||
inc, partial := BuildIncidents(ctx, h, aliases)
|
||||
status := "healthy"
|
||||
if inc.CriticalTotal > 0 {
|
||||
status = "critical"
|
||||
} else if inc.WarningTotal > 0 {
|
||||
status = "degraded"
|
||||
}
|
||||
return map[string]any{
|
||||
"type": "live_snapshot",
|
||||
"timestamp": time.Now().UTC().Format(time.RFC3339Nano),
|
||||
"status": status,
|
||||
"partial": partial,
|
||||
"incidents": inc.Items,
|
||||
"counts": map[string]int{"total": inc.Total, "critical": inc.CriticalTotal, "warning": inc.WarningTotal, "info": inc.InfoTotal},
|
||||
"aliases_used": aliases,
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user