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

assets,site/content: daily assets regeneration

This commit is contained in:
github-actions[bot] 2021-07-29 03:25:46 +00:00
parent aa2efb024e
commit 1f6e192b9a
5 changed files with 118 additions and 44 deletions

View file

@ -153,7 +153,7 @@ groups:
and ignoring (limit)
(cortex_ingester_instance_limits{limit="max_series"} > 0)
) > 0.7
for: 5m
for: 3h
labels:
severity: warning
- alert: CortexIngesterReachingSeriesLimit
@ -165,7 +165,7 @@ groups:
(cortex_ingester_memory_series / ignoring(limit) cortex_ingester_instance_limits{limit="max_series"})
and ignoring (limit)
(cortex_ingester_instance_limits{limit="max_series"} > 0)
) > 0.8
) > 0.85
for: 5m
labels:
severity: critical

View file

@ -442,10 +442,17 @@ groups:
- name: cortex_scaling_rules
rules:
- expr: |
sum by (cluster, namespace, deployment) (kube_deployment_spec_replicas)
or
sum by (cluster, namespace, deployment) (
label_replace(kube_statefulset_replicas, "deployment", "$1", "statefulset", "(.*)")
label_replace(
kube_deployment_spec_replicas,
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
or
sum by (cluster, namespace, deployment) (
label_replace(kube_statefulset_replicas, "deployment", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")
)
record: cluster_namespace_deployment:actual_replicas:count
- expr: |
@ -517,7 +524,7 @@ groups:
- expr: |
ceil(
(sum by (cluster, namespace) (
cortex_ingester_tsdb_storage_blocks_bytes{job=~".+/ingester"}
cortex_ingester_tsdb_storage_blocks_bytes{job=~".+/ingester.*"}
) / 4)
/
avg by (cluster, namespace) (
@ -531,8 +538,13 @@ groups:
- expr: |
sum by (cluster, namespace, deployment) (
label_replace(
node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
record: cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate
@ -547,8 +559,13 @@ groups:
(
sum by (cluster, namespace, deployment) (
label_replace(
kube_pod_container_resource_requests_cpu_cores,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
kube_pod_container_resource_requests_cpu_cores,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
)
@ -558,8 +575,13 @@ groups:
(
sum by (cluster, namespace, deployment) (
label_replace(
kube_pod_container_resource_requests{resource="cpu"},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
kube_pod_container_resource_requests{resource="cpu"},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
)
@ -578,8 +600,13 @@ groups:
- expr: |
sum by (cluster, namespace, deployment) (
label_replace(
container_memory_usage_bytes,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
container_memory_usage_bytes,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
record: cluster_namespace_deployment:container_memory_usage_bytes:sum
@ -594,8 +621,13 @@ groups:
(
sum by (cluster, namespace, deployment) (
label_replace(
kube_pod_container_resource_requests_memory_bytes,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
kube_pod_container_resource_requests_memory_bytes,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
)
@ -605,8 +637,13 @@ groups:
(
sum by (cluster, namespace, deployment) (
label_replace(
kube_pod_container_resource_requests{resource="memory"},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
kube_pod_container_resource_requests{resource="memory"},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
)

View file

@ -487,7 +487,7 @@ groups:
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"}
) * on(namespace, pod, cluster) group_left() max by (namespace, pod) (
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
)
)
@ -504,7 +504,7 @@ groups:
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"}
) * on(namespace, pod, cluster) group_left() max by (namespace, pod) (
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
)
)
@ -521,7 +521,7 @@ groups:
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"}
) * on(namespace, pod, cluster) group_left() max by (namespace, pod) (
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
)
)
@ -538,7 +538,7 @@ groups:
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"}
) * on(namespace, pod, cluster) group_left() max by (namespace, pod) (
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
)
)

View file

@ -243,7 +243,7 @@ expr: |
and ignoring (limit)
(cortex_ingester_instance_limits{limit="max_series"} > 0)
) > 0.7
for: 5m
for: 3h
labels:
severity: warning
{{< /code >}}
@ -260,7 +260,7 @@ expr: |
(cortex_ingester_memory_series / ignoring(limit) cortex_ingester_instance_limits{limit="max_series"})
and ignoring (limit)
(cortex_ingester_instance_limits{limit="max_series"} > 0)
) > 0.8
) > 0.85
for: 5m
labels:
severity: critical
@ -2075,10 +2075,17 @@ record: cluster_namespace_job:cortex_distributor_received_samples:rate5m
{{< code lang="yaml" >}}
expr: |
sum by (cluster, namespace, deployment) (kube_deployment_spec_replicas)
or
sum by (cluster, namespace, deployment) (
label_replace(kube_statefulset_replicas, "deployment", "$1", "statefulset", "(.*)")
label_replace(
kube_deployment_spec_replicas,
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
or
sum by (cluster, namespace, deployment) (
label_replace(kube_statefulset_replicas, "deployment", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")
)
record: cluster_namespace_deployment:actual_replicas:count
{{< /code >}}
@ -2185,7 +2192,7 @@ record: cluster_namespace_deployment_reason:required_replicas:count
expr: |
ceil(
(sum by (cluster, namespace) (
cortex_ingester_tsdb_storage_blocks_bytes{job=~".+/ingester"}
cortex_ingester_tsdb_storage_blocks_bytes{job=~".+/ingester.*"}
) / 4)
/
avg by (cluster, namespace) (
@ -2204,8 +2211,13 @@ record: cluster_namespace_deployment_reason:required_replicas:count
expr: |
sum by (cluster, namespace, deployment) (
label_replace(
node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
record: cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate
@ -2226,8 +2238,13 @@ expr: |
(
sum by (cluster, namespace, deployment) (
label_replace(
kube_pod_container_resource_requests_cpu_cores,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
kube_pod_container_resource_requests_cpu_cores,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
)
@ -2237,8 +2254,13 @@ expr: |
(
sum by (cluster, namespace, deployment) (
label_replace(
kube_pod_container_resource_requests{resource="cpu"},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
kube_pod_container_resource_requests{resource="cpu"},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
)
@ -2267,8 +2289,13 @@ record: cluster_namespace_deployment_reason:required_replicas:count
expr: |
sum by (cluster, namespace, deployment) (
label_replace(
container_memory_usage_bytes,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
container_memory_usage_bytes,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
record: cluster_namespace_deployment:container_memory_usage_bytes:sum
@ -2289,8 +2316,13 @@ expr: |
(
sum by (cluster, namespace, deployment) (
label_replace(
kube_pod_container_resource_requests_memory_bytes,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
kube_pod_container_resource_requests_memory_bytes,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
)
@ -2300,8 +2332,13 @@ expr: |
(
sum by (cluster, namespace, deployment) (
label_replace(
kube_pod_container_resource_requests{resource="memory"},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
label_replace(
kube_pod_container_resource_requests{resource="memory"},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
)
)
)

View file

@ -1754,7 +1754,7 @@ expr: |
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"}
) * on(namespace, pod, cluster) group_left() max by (namespace, pod) (
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
)
)
@ -1781,7 +1781,7 @@ expr: |
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"}
) * on(namespace, pod, cluster) group_left() max by (namespace, pod) (
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
)
)
@ -1808,7 +1808,7 @@ expr: |
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"}
) * on(namespace, pod, cluster) group_left() max by (namespace, pod) (
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
)
)
@ -1835,7 +1835,7 @@ expr: |
sum by (namespace, pod, cluster) (
max by (namespace, pod, container, cluster) (
kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"}
) * on(namespace, pod, cluster) group_left() max by (namespace, pod) (
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
kube_pod_status_phase{phase=~"Pending|Running"} == 1
)
)