assets,site/content: daily assets regeneration

assets/etcd/alerts.yaml

@@ -141,39 +141,6 @@ groups:
     for: 10m
     labels:
       severity: warning
-  - alert: etcdHighNumberOfFailedHTTPRequests
-    annotations:
-      description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
-        instance {{ $labels.instance }}'
-      summary: etcd has high number of failed HTTP requests.
-    expr: |
-      sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) without (code) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
-      without (code) > 0.01
-    for: 10m
-    labels:
-      severity: warning
-  - alert: etcdHighNumberOfFailedHTTPRequests
-    annotations:
-      description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
-        instance {{ $labels.instance }}.'
-      summary: etcd has high number of failed HTTP requests.
-    expr: |
-      sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) without (code) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
-      without (code) > 0.05
-    for: 10m
-    labels:
-      severity: critical
-  - alert: etcdHTTPRequestsSlow
-    annotations:
-      description: etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method
-        }} are slow.
-      summary: etcd instance HTTP requests are slow.
-    expr: |
-      histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))
-      > 0.15
-    for: 10m
-    labels:
-      severity: warning
   - alert: etcdBackendQuotaLowSpace
     annotations:
       message: 'etcd cluster "{{ $labels.job }}": database size exceeds the defined

assets/etcd/dashboards/etcd.json

@@ -1014,7 +1014,9 @@
    "schemaVersion": 13,
    "sharedCrosshair": false,
    "style": "dark",
-   "tags": [ ],
+   "tags": [
+      "etcd-mixin"
+   ],
    "templating": {
       "list": [
          {

assets/prometheus/alerts.yaml

@@ -121,12 +121,12 @@ groups:
       summary: Prometheus fails to send samples to remote storage.
     expr: |
       (
-        rate(prometheus_remote_storage_failed_samples_total{job="prometheus"}[5m])
+        (rate(prometheus_remote_storage_failed_samples_total{job="prometheus"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus"}[5m]))
       /
         (
-          rate(prometheus_remote_storage_failed_samples_total{job="prometheus"}[5m])
+          (rate(prometheus_remote_storage_failed_samples_total{job="prometheus"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus"}[5m]))
         +
-          rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus"}[5m])
+          (rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus"}[5m]) or rate(prometheus_remote_storage_samples_total{job="prometheus"}[5m]))
         )
       )
       * 100

site/content/etcd/_index.md

@@ -215,54 +215,6 @@ labels:
   severity: warning
 {{< /code >}}
  
-##### etcdHighNumberOfFailedHTTPRequests
-
-{{< code lang="yaml" >}}
-alert: etcdHighNumberOfFailedHTTPRequests
-annotations:
-  description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
-    instance {{ $labels.instance }}'
-  summary: etcd has high number of failed HTTP requests.
-expr: |
-  sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) without (code) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
-  without (code) > 0.01
-for: 10m
-labels:
-  severity: warning
-{{< /code >}}
- 
-##### etcdHighNumberOfFailedHTTPRequests
-
-{{< code lang="yaml" >}}
-alert: etcdHighNumberOfFailedHTTPRequests
-annotations:
-  description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
-    instance {{ $labels.instance }}.'
-  summary: etcd has high number of failed HTTP requests.
-expr: |
-  sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) without (code) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
-  without (code) > 0.05
-for: 10m
-labels:
-  severity: critical
-{{< /code >}}
- 
-##### etcdHTTPRequestsSlow
-
-{{< code lang="yaml" >}}
-alert: etcdHTTPRequestsSlow
-annotations:
-  description: etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method
-    }} are slow.
-  summary: etcd instance HTTP requests are slow.
-expr: |
-  histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))
-  > 0.15
-for: 10m
-labels:
-  severity: warning
-{{< /code >}}
- 
 ##### etcdBackendQuotaLowSpace
 
 {{< code lang="yaml" >}}

site/content/prometheus/_index.md

@@ -190,12 +190,12 @@ annotations:
   summary: Prometheus fails to send samples to remote storage.
 expr: |
   (
-    rate(prometheus_remote_storage_failed_samples_total{job="prometheus"}[5m])
+    (rate(prometheus_remote_storage_failed_samples_total{job="prometheus"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus"}[5m]))
   /
     (
-      rate(prometheus_remote_storage_failed_samples_total{job="prometheus"}[5m])
+      (rate(prometheus_remote_storage_failed_samples_total{job="prometheus"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus"}[5m]))
     +
-      rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus"}[5m])
+      (rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus"}[5m]) or rate(prometheus_remote_storage_samples_total{job="prometheus"}[5m]))
     )
   )
   * 100