Align metric names with Prometheus naming conventions
Use base units, export cumulative values as _total counters, update docs, dashboards and rules.
This commit is contained in:
@@ -20,7 +20,7 @@ groups:
|
||||
|
||||
- alert: PveGuestCpuSaturated
|
||||
expr: |-
|
||||
pve_vm_cpu_usage > 0.95 or pve_ct_cpu_usage > 0.95
|
||||
pve_vm_cpu_usage_ratio > 0.95 or pve_ct_cpu_usage_ratio > 0.95
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -74,7 +74,7 @@ groups:
|
||||
|
||||
- alert: PveNodeCpuSaturated
|
||||
expr: |-
|
||||
pve_node_cpu_usage > 0.95
|
||||
pve_node_cpu_usage_ratio > 0.95
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -99,8 +99,8 @@ groups:
|
||||
|
||||
- alert: PveClusterClockSkew
|
||||
expr: |-
|
||||
max by (cluster) (pve_node_localtime)
|
||||
- min by (cluster) (pve_node_localtime) > 15
|
||||
max by (cluster) (pve_node_localtime_seconds)
|
||||
- min by (cluster) (pve_node_localtime_seconds) > 15
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
@@ -113,9 +113,9 @@ groups:
|
||||
- alert: PveNodeSubscriptionExpiringSoon
|
||||
expr: |-
|
||||
(
|
||||
pve_node_subscription_nextduedate > time()
|
||||
pve_node_subscription_next_due_timestamp_seconds > time()
|
||||
and
|
||||
pve_node_subscription_nextduedate < time() + (30 * 24 * 60 * 60)
|
||||
pve_node_subscription_next_due_timestamp_seconds < time() + (30 * 24 * 60 * 60)
|
||||
)
|
||||
and on (cluster, node)
|
||||
(pve_node_subscription_status == 1)
|
||||
@@ -147,7 +147,7 @@ groups:
|
||||
|
||||
- alert: PveNodeDiskWearout
|
||||
expr: |-
|
||||
pve_node_disk_wearout < 5
|
||||
pve_node_disk_wearout_percent < 5
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
@@ -242,7 +242,7 @@ groups:
|
||||
|
||||
- alert: PveNodeZfsReadErrors
|
||||
expr: |-
|
||||
pve_node_zfs_read_errors > 0
|
||||
pve_node_zfs_read_errors_total > 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -255,7 +255,7 @@ groups:
|
||||
|
||||
- alert: PveNodeZfsWriteErrors
|
||||
expr: |-
|
||||
pve_node_zfs_write_errors > 0
|
||||
pve_node_zfs_write_errors_total > 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -268,7 +268,7 @@ groups:
|
||||
|
||||
- alert: PveNodeZfsChecksumErrors
|
||||
expr: |-
|
||||
pve_node_zfs_checksum_errors > 0
|
||||
pve_node_zfs_checksum_errors_total > 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -284,12 +284,12 @@ groups:
|
||||
(
|
||||
sum by (cluster, node) (
|
||||
(
|
||||
pve_vm_mem_total_bytes
|
||||
pve_vm_memory_total_bytes
|
||||
and on (cluster, node, vmid, name) (pve_vm_state == 1)
|
||||
)
|
||||
or
|
||||
(
|
||||
pve_ct_mem_total_bytes
|
||||
pve_ct_memory_total_bytes
|
||||
and on (cluster, node, vmid, name) (pve_ct_state == 1)
|
||||
)
|
||||
)
|
||||
@@ -400,9 +400,9 @@ groups:
|
||||
|
||||
- alert: PveNodeDiskWearoutWarning
|
||||
expr: |-
|
||||
(pve_node_disk_wearout < 20)
|
||||
(pve_node_disk_wearout_percent < 20)
|
||||
and
|
||||
(pve_node_disk_wearout >= 5)
|
||||
(pve_node_disk_wearout_percent >= 5)
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -417,9 +417,9 @@ groups:
|
||||
|
||||
- alert: PveGuestMemoryHigh
|
||||
expr: |-
|
||||
pve_vm_mem_used_bytes / pve_vm_mem_total_bytes > 0.90
|
||||
pve_vm_memory_used_bytes / pve_vm_memory_total_bytes > 0.90
|
||||
or
|
||||
pve_ct_mem_used_bytes / pve_ct_mem_total_bytes > 0.90
|
||||
pve_ct_memory_used_bytes / pve_ct_memory_total_bytes > 0.90
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -433,9 +433,9 @@ groups:
|
||||
|
||||
- alert: PveGuestDiskFillingUp
|
||||
expr: |-
|
||||
pve_vm_disk_usage_bytes / pve_vm_disk_size_bytes > 0.90
|
||||
pve_vm_disk_used_bytes / pve_vm_disk_size_bytes > 0.90
|
||||
or
|
||||
pve_ct_disk_usage_bytes / pve_ct_disk_size_bytes > 0.90
|
||||
pve_ct_disk_used_bytes / pve_ct_disk_size_bytes > 0.90
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -461,9 +461,9 @@ groups:
|
||||
|
||||
- alert: PveVmDiskErrorsIncreasing
|
||||
expr: |-
|
||||
delta(pve_vm_disk_failed_rd_ops[10m]) > 0
|
||||
increase(pve_vm_disk_failed_read_operations_total[10m]) > 0
|
||||
or
|
||||
delta(pve_vm_disk_failed_wr_ops[10m]) > 0
|
||||
increase(pve_vm_disk_failed_write_operations_total[10m]) > 0
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
@@ -476,7 +476,7 @@ groups:
|
||||
|
||||
- alert: PveNodeClockDrift
|
||||
expr: |-
|
||||
abs(pve_node_time - time()) > 60
|
||||
abs(pve_node_time_seconds - time()) > 60
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -489,7 +489,7 @@ groups:
|
||||
|
||||
- alert: PveNodeRestarted
|
||||
expr: |-
|
||||
resets(pve_node_uptime[15m]) > 0
|
||||
resets(pve_node_uptime_seconds[15m]) > 0
|
||||
for: 0m
|
||||
labels:
|
||||
severity: info
|
||||
@@ -501,8 +501,8 @@ groups:
|
||||
|
||||
- alert: PveCollectorSlow
|
||||
expr: |-
|
||||
rate(pve_metrics_collection_latency_ms_sum[5m])
|
||||
/ rate(pve_metrics_collection_latency_ms_count[5m]) > 5000
|
||||
rate(pve_metrics_collection_duration_seconds_sum[5m])
|
||||
/ rate(pve_metrics_collection_duration_seconds_count[5m]) > 5
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -510,7 +510,7 @@ groups:
|
||||
summary: PVE exporter collector is slow.
|
||||
description: >-
|
||||
Collector {{ $labels.collector }} has taken an average of
|
||||
{{ printf "%.0f" $value }} ms per successful run for at least ten
|
||||
{{ printf "%.1f" $value }} s per successful run for at least ten
|
||||
minutes.
|
||||
|
||||
- alert: PveExporterDown
|
||||
|
||||
Reference in New Issue
Block a user