mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-08-18 21:26:56 +00:00
Chris LuandGitHub
c194924d13
The dashboard charted one summed disk-usage line, so a step in the total gave no hint which cluster moved. A new panel stacks each cluster's daily size as its own band: the top of the stack is the fleet total, each band is one cluster, and the clusters past the twentieth are summed into an "other" band so the stack still adds up to the total. The series is built from the per-cluster daily histories and served by /api/cluster-sizes. Clusters report roughly once a day at no fixed hour, so a day with no report carries the previous value forward — dropping it to zero would sag the total every day as the clusters that have not reported yet fall out from under it. A cluster that stops reporting past the active window ends at its last sample instead of holding capacity forever. Ranking is by the most recent day, tie-broken on cluster id so the colors do not shuffle between refreshes. Hover and click resolve to the band under the pointer: Chart.js's builtin interaction modes match the nearest line, which on a stack of thin bands is rarely the band being pointed at. Clicking one fills the per-cluster history lookup below it.
67 lines
2.0 KiB
Go
67 lines
2.0 KiB
Go
package storage
|
|
|
|
import (
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/telemetry/proto"
|
|
)
|
|
|
|
// confirmDays is how many distinct UTC days a cluster must have reported
|
|
// on before it counts as confirmed in the aggregated stats.
|
|
const confirmDays = 2
|
|
|
|
// activeDays is how recently a cluster must have reported to count as active.
|
|
const activeDays = 7
|
|
|
|
// HistorySample is one retained data point of a cluster's daily reports.
|
|
// Tags are kept short because thousands of samples end up in the state file.
|
|
type HistorySample struct {
|
|
Ts int64 `json:"ts"` // unix seconds the report was received
|
|
TotalDiskBytes uint64 `json:"disk"`
|
|
TotalVolumeCount int32 `json:"volumes"`
|
|
VolumeServerCount int32 `json:"servers"`
|
|
}
|
|
|
|
// appendHistory records the report as the cluster's sample for the day,
|
|
// replacing an earlier sample from the same UTC day. Callers must hold s.mu.
|
|
func (s *PrometheusStorage) appendHistory(data *proto.TelemetryData, receivedAt time.Time) {
|
|
sample := HistorySample{
|
|
Ts: receivedAt.Unix(),
|
|
TotalDiskBytes: data.TotalDiskBytes,
|
|
TotalVolumeCount: data.TotalVolumeCount,
|
|
VolumeServerCount: data.VolumeServerCount,
|
|
}
|
|
h := s.histories[data.TopologyId]
|
|
if n := len(h); n > 0 && sameUTCDay(h[n-1].Ts, sample.Ts) {
|
|
h[n-1] = sample
|
|
} else {
|
|
h = append(h, sample)
|
|
}
|
|
s.histories[data.TopologyId] = h
|
|
}
|
|
|
|
func sameUTCDay(a, b int64) bool {
|
|
ta, tb := time.Unix(a, 0).UTC(), time.Unix(b, 0).UTC()
|
|
return ta.Year() == tb.Year() && ta.YearDay() == tb.YearDay()
|
|
}
|
|
|
|
// GetHistory returns the cluster's samples from the last `days` days.
|
|
// The second return value reports whether the cluster is known at all.
|
|
func (s *PrometheusStorage) GetHistory(clusterId string, days int) ([]HistorySample, bool) {
|
|
s.mu.RLock()
|
|
defer s.mu.RUnlock()
|
|
|
|
h, ok := s.histories[clusterId]
|
|
if !ok {
|
|
return nil, false
|
|
}
|
|
cutoff := time.Now().AddDate(0, 0, -days).Unix()
|
|
samples := make([]HistorySample, 0, len(h))
|
|
for _, sample := range h {
|
|
if sample.Ts >= cutoff {
|
|
samples = append(samples, sample)
|
|
}
|
|
}
|
|
return samples, true
|
|
}
|