fix(clickhouse): harden R/W path P0–P3 (cleanup, durability, rollups)

Honest TTL cleanup semantics; enqueue-safe dedup with flush retry and writer
metrics; model insert hooks; latest-per-node and hourly metric/openresty
rollups; small-host pool/async defaults, traffic hourly TTL, and UV labeling.
This commit is contained in:
ryan
2026-07-10 10:34:04 +08:00
parent 9b3555c569
commit 160e63558f
37 changed files with 1779 additions and 269 deletions
+12 -2
View File
@@ -117,6 +117,16 @@ func buildOverviewView(ctx context.Context) (*OverviewView, error) {
if err != nil {
return nil, err
}
// Latest-per-node health: dedicated LIMIT 1 BY queries (not a global raw LIMIT).
latestSnapshotRows, err := model.ListOpenFlareLatestMetricSnapshotsSince(ctx, "", since)
if err != nil {
return nil, err
}
latestTrafficRows, err := model.ListOpenFlareLatestRequestReportsSince(ctx, "", since)
if err != nil {
return nil, err
}
// Bounded raw windows remain for distributions and trend fallbacks; trends prefer hourly rollups.
snapshots, err := model.ListOpenFlareMetricSnapshotsSince(ctx, "", since, dashboardOverviewSnapshotLimit)
if err != nil {
return nil, err
@@ -146,8 +156,8 @@ func buildOverviewView(ctx context.Context) (*OverviewView, error) {
var cpuNodeCount int
var memoryNodeCount int
latestSnapshots := observability.LatestMetricSnapshotsByNode(snapshots)
latestTrafficReports := observability.LatestTrafficReportsByNode(reports)
latestSnapshots := observability.LatestMetricSnapshotsByNode(latestSnapshotRows)
latestTrafficReports := observability.LatestTrafficReportsByNode(latestTrafficRows)
activeEventsByNode := observability.ActiveHealthEventsByNode(activeEvents)
for _, node := range nodes {