mirrors/monitoring-mixins-website
1
0
Fork 0
mirror of https://github.com/monitoring-mixins/website.git synced 2024-12-14 11:37:31 +00:00
Code Activity

assets,site/content: daily assets regeneration

Browse source
This commit is contained in:
github-actions[bot] 2021-03-05 03:27:06 +00:00
parent 61d1f2ec9f
commit cc4aed9d81
5 changed files with 30 additions and 30 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
assets/ceph/alerts.yaml
View file

@ -80,27 +80,27 @@ groups:
rules:
- alert: CephOSDCriticallyFull
annotations:
description: Utilization of back-end storage device {{ $labels.ceph_daemon }}
has crossed 85% on host {{ $labels.hostname }}. Immediately free up some space
or expand the storage cluster or contact support.
description: Utilization of storage device {{ $labels.ceph_daemon }} of device_class
type {{$labels.device_class}} has crossed 80% on host {{ $labels.hostname
}}. Immediately free up some space or add capacity of type {{$labels.device_class}}.
message: Back-end storage device is critically full.
severity_level: error
storage_type: ceph
expr: |
(ceph_osd_metadata * on (ceph_daemon) group_left() (ceph_osd_stat_bytes_used / ceph_osd_stat_bytes)) >= 0.85
(ceph_osd_metadata * on (ceph_daemon) group_right(device_class) (ceph_osd_stat_bytes_used / ceph_osd_stat_bytes)) >= 0.80
for: 40s
labels:
severity: critical
- alert: CephOSDNearFull
annotations:
description: Utilization of back-end storage device {{ $labels.ceph_daemon }}
has crossed 75% on host {{ $labels.hostname }}. Free up some space or expand
the storage cluster or contact support.
description: Utilization of storage device {{ $labels.ceph_daemon }} of device_class
type {{$labels.device_class}} has crossed 75% on host {{ $labels.hostname
}}. Immediately free up some space or add capacity of type {{$labels.device_class}}.
message: Back-end storage device is nearing full.
severity_level: warning
storage_type: ceph
expr: |
(ceph_osd_metadata * on (ceph_daemon) group_left() (ceph_osd_stat_bytes_used / ceph_osd_stat_bytes)) >= 0.75
(ceph_osd_metadata * on (ceph_daemon) group_right(device_class) (ceph_osd_stat_bytes_used / ceph_osd_stat_bytes)) >= 0.75
for: 40s
labels:
severity: warning

2
assets/ceph/rules.yaml
View file

@ -5,7 +5,7 @@ groups:
kube_node_status_condition{condition="Ready",job="kube-state-metrics",status="true"} * on (node) group_right() max(label_replace(ceph_disk_occupation{job="rook-ceph-mgr"},"node","$1","exported_instance","(.*)")) by (node)
record: cluster:ceph_node_down:join_kube
- expr: |
avg(max by(instance) (label_replace(label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "instance", "$1", "exported_instance", "(.*)"), "device", "$1", "device", "/dev/(.*)") * on(instance, device) group_right() (irate(node_disk_read_time_seconds_total[1m]) + irate(node_disk_write_time_seconds_total[1m]) / (clamp_min(irate(node_disk_reads_completed_total[1m]), 1) + irate(node_disk_writes_completed_total[1m])))))
avg(topk by (ceph_daemon) (1, label_replace(label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "instance", "$1", "exported_instance", "(.*)"), "device", "$1", "device", "/dev/(.*)")) * on(instance, device) group_right(ceph_daemon) topk by (instance,device) (1,(irate(node_disk_read_time_seconds_total[1m]) + irate(node_disk_write_time_seconds_total[1m]) / (clamp_min(irate(node_disk_reads_completed_total[1m]), 1) + irate(node_disk_writes_completed_total[1m])))))
record: cluster:ceph_disk_latency:join_ceph_node_disk_irate1m
- name: telemeter.rules
rules:

12
assets/kubernetes/rules.yaml
View file

@ -535,9 +535,9 @@ groups:
)
record: node_namespace_pod_container:container_memory_swap
- expr: |
sum by (namespace) (
sum by (namespace, pod) (
max by (namespace, pod, container) (
sum by (namespace, cluster) (
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"}
) * on(namespace, pod) group_left() max by (namespace, pod) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
@ -546,9 +546,9 @@ groups:
)
record: namespace:kube_pod_container_resource_requests_memory_bytes:sum
- expr: |
sum by (namespace) (
sum by (namespace, pod) (
max by (namespace, pod, container) (
sum by (namespace, cluster) (
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"}
) * on(namespace, pod) group_left() max by (namespace, pod) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1

18
site/content/ceph/_index.md
View file

@ -131,14 +131,14 @@ labels:
{{< code lang="yaml" >}}
alert: CephOSDCriticallyFull
annotations:
description: Utilization of back-end storage device {{ $labels.ceph_daemon }} has
crossed 85% on host {{ $labels.hostname }}. Immediately free up some space or
expand the storage cluster or contact support.
description: Utilization of storage device {{ $labels.ceph_daemon }} of device_class
type {{$labels.device_class}} has crossed 80% on host {{ $labels.hostname }}.
Immediately free up some space or add capacity of type {{$labels.device_class}}.
message: Back-end storage device is critically full.
severity_level: error
storage_type: ceph
expr: |
(ceph_osd_metadata * on (ceph_daemon) group_left() (ceph_osd_stat_bytes_used / ceph_osd_stat_bytes)) >= 0.85
(ceph_osd_metadata * on (ceph_daemon) group_right(device_class) (ceph_osd_stat_bytes_used / ceph_osd_stat_bytes)) >= 0.80
for: 40s
labels:
severity: critical
@ -149,14 +149,14 @@ labels:
{{< code lang="yaml" >}}
alert: CephOSDNearFull
annotations:
description: Utilization of back-end storage device {{ $labels.ceph_daemon }} has
crossed 75% on host {{ $labels.hostname }}. Free up some space or expand the storage
cluster or contact support.
description: Utilization of storage device {{ $labels.ceph_daemon }} of device_class
type {{$labels.device_class}} has crossed 75% on host {{ $labels.hostname }}.
Immediately free up some space or add capacity of type {{$labels.device_class}}.
message: Back-end storage device is nearing full.
severity_level: warning
storage_type: ceph
expr: |
(ceph_osd_metadata * on (ceph_daemon) group_left() (ceph_osd_stat_bytes_used / ceph_osd_stat_bytes)) >= 0.75
(ceph_osd_metadata * on (ceph_daemon) group_right(device_class) (ceph_osd_stat_bytes_used / ceph_osd_stat_bytes)) >= 0.75
for: 40s
labels:
severity: warning
@ -408,7 +408,7 @@ record: cluster:ceph_node_down:join_kube
{{< code lang="yaml" >}}
expr: |
avg(max by(instance) (label_replace(label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "instance", "$1", "exported_instance", "(.*)"), "device", "$1", "device", "/dev/(.*)") * on(instance, device) group_right() (irate(node_disk_read_time_seconds_total[1m]) + irate(node_disk_write_time_seconds_total[1m]) / (clamp_min(irate(node_disk_reads_completed_total[1m]), 1) + irate(node_disk_writes_completed_total[1m])))))
avg(topk by (ceph_daemon) (1, label_replace(label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "instance", "$1", "exported_instance", "(.*)"), "device", "$1", "device", "/dev/(.*)")) * on(instance, device) group_right(ceph_daemon) topk by (instance,device) (1,(irate(node_disk_read_time_seconds_total[1m]) + irate(node_disk_write_time_seconds_total[1m]) / (clamp_min(irate(node_disk_reads_completed_total[1m]), 1) + irate(node_disk_writes_completed_total[1m])))))
record: cluster:ceph_disk_latency:join_ceph_node_disk_irate1m
{{< /code >}}

12
site/content/kubernetes/_index.md
View file

@ -1890,9 +1890,9 @@ record: node_namespace_pod_container:container_memory_swap
{{< code lang="yaml" >}}
expr: |
sum by (namespace) (
sum by (namespace, pod) (
max by (namespace, pod, container) (
sum by (namespace, cluster) (
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"}
) * on(namespace, pod) group_left() max by (namespace, pod) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
@ -1906,9 +1906,9 @@ record: namespace:kube_pod_container_resource_requests_memory_bytes:sum
{{< code lang="yaml" >}}
expr: |
sum by (namespace) (
sum by (namespace, pod) (
max by (namespace, pod, container) (
sum by (namespace, cluster) (
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"}
) * on(namespace, pod) group_left() max by (namespace, pod) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1