Export tier metrics via Prometheus (#13413)

e.g
```
minio_cluster_ilm_transitioned_bytes{server="minio3:9000",tier="S3TIER-1"} 1.36317772e+08
minio_cluster_ilm_transitioned_bytes{server="minio3:9000",tier="S3TIER-2"} 2892
minio_cluster_ilm_transitioned_bytes{server="minio3:9000",tier="STANDARD"}
1.3631488e+08

minio_cluster_ilm_transitioned_objects{server="minio3:9000",tier="S3TIER-1"} 1
minio_cluster_ilm_transitioned_objects{server="minio3:9000",tier="S3TIER-2"} 0
minio_cluster_ilm_transitioned_objects{server="minio3:9000",tier="STANDARD"} 1

minio_cluster_ilm_transitioned_versions{server="minio3:9000",tier="S3TIER-1"} 3
minio_cluster_ilm_transitioned_versions{server="minio3:9000",tier="S3TIER-2"} 2
minio_cluster_ilm_transitioned_versions{server="minio3:9000",tier="STANDARD"} 1
```
This commit is contained in:
Krishnan Parthasarathi 2022-02-08 12:45:28 -08:00 committed by GitHub
parent 9890f579f8
commit 0ee2933234
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 86 additions and 1 deletions

View File

@ -48,6 +48,7 @@ func init() {
getMinioHealingMetrics(),
getNodeHealthMetrics(),
getClusterStorageMetrics(),
getClusterTierMetrics(),
}
peerMetricsGroups = []*MetricsGroup{
@ -181,6 +182,10 @@ const (
expiryPendingTasks MetricName = "expiry_pending_tasks"
transitionPendingTasks MetricName = "transition_pending_tasks"
transitionActiveTasks MetricName = "transition_active_tasks"
transitionedBytes MetricName = "transitioned_bytes"
transitionedObjects MetricName = "transitioned_objects"
transitionedVersions MetricName = "transitioned_versions"
)
const (
@ -1605,13 +1610,90 @@ func getBucketUsageMetrics() *MetricsGroup {
HistogramBucketLabel: "range",
VariableLabels: map[string]string{"bucket": bucket},
})
}
return
})
return mg
}
func getClusterTransitionedBytesMD() MetricDescription {
return MetricDescription{
Namespace: clusterMetricNamespace,
Subsystem: ilmSubsystem,
Name: transitionedBytes,
Help: "Total bytes transitioned to a tier",
Type: gaugeMetric,
}
}
func getClusterTransitionedObjectsMD() MetricDescription {
return MetricDescription{
Namespace: clusterMetricNamespace,
Subsystem: ilmSubsystem,
Name: transitionedObjects,
Help: "Total number of objects transitioned to a tier",
Type: gaugeMetric,
}
}
func getClusterTransitionedVersionsMD() MetricDescription {
return MetricDescription{
Namespace: clusterMetricNamespace,
Subsystem: ilmSubsystem,
Name: transitionedVersions,
Help: "Total number of versions transitioned to a tier",
Type: gaugeMetric,
}
}
func getClusterTierMetrics() *MetricsGroup {
mg := &MetricsGroup{
cacheInterval: 10 * time.Second,
}
mg.RegisterRead(func(ctx context.Context) (metrics []Metric) {
if globalTierConfigMgr.Empty() {
return
}
objLayer := newObjectLayerFn()
if objLayer == nil || globalIsGateway {
return
}
dui, err := loadDataUsageFromBackend(GlobalContext, objLayer)
if err != nil {
return
}
// data usage has not captured any data yet.
if dui.LastUpdate.IsZero() {
return
}
// e.g minio_cluster_ilm_transitioned_bytes{tier="S3TIER-1"}=136314880
// minio_cluster_ilm_transitioned_objects{tier="S3TIER-1"}=1
// minio_cluster_ilm_transitioned_versions{tier="S3TIER-1"}=3
for tier, st := range dui.TierStats.Tiers {
metrics = append(metrics, Metric{
Description: getClusterTransitionedBytesMD(),
Value: float64(st.TotalSize),
VariableLabels: map[string]string{"tier": tier},
})
metrics = append(metrics, Metric{
Description: getClusterTransitionedObjectsMD(),
Value: float64(st.NumObjects),
VariableLabels: map[string]string{"tier": tier},
})
metrics = append(metrics, Metric{
Description: getClusterTransitionedVersionsMD(),
Value: float64(st.NumVersions),
VariableLabels: map[string]string{"tier": tier},
})
}
return metrics
})
return mg
}
func getLocalStorageMetrics() *MetricsGroup {
mg := &MetricsGroup{
cacheInterval: 10 * time.Second,

View File

@ -27,6 +27,9 @@ These metrics can be from any MinIO server once per collection.
| `minio_cluster_capacity_usable_total_bytes` | Total usable capacity online in the cluster. |
| `minio_cluster_nodes_offline_total` | Total number of MinIO nodes offline. |
| `minio_cluster_nodes_online_total` | Total number of MinIO nodes online. |
| `minio_cluster_ilm_transitioned_bytes` | Total bytes transitioned to a tier |
| `minio_cluster_ilm_transitioned_objects` | Total number of objects transitioned to a tier |
| `minio_cluster_ilm_transitioned_versions` | Total number of versions transitioned to a tier |
| `minio_heal_objects_error_total` | Objects for which healing failed in current self healing run |
| `minio_heal_objects_heal_total` | Objects healed in current self healing run |
| `minio_heal_objects_total` | Objects scanned in current self healing run |