Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Documentation: Fix etcdHighNumberOfFailedGRPCRequests rules return NaN value #10629

Closed
wants to merge 1 commit into from
Closed

Documentation: Fix etcdHighNumberOfFailedGRPCRequests rules return NaN value #10629

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 12 additions & 10 deletions Documentation/etcd-mixin/mixin.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,9 +51,9 @@
alert: 'etcdHighNumberOfFailedGRPCRequests',
expr: |||
100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
/
sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) BY (job, instance, grpc_service, grpc_method)
> 1
/ sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) BY (job, instance, grpc_service, grpc_method) > 0
or sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method) > bool 0
> 1
||| % $._config,
'for': '10m',
labels: {
Expand All @@ -67,9 +67,9 @@
alert: 'etcdHighNumberOfFailedGRPCRequests',
expr: |||
100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
/
sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) BY (job, instance, grpc_service, grpc_method)
> 5
/ sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) BY (job, instance, grpc_service, grpc_method) > 0
or sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method) > bool 0
> 5
||| % $._config,
'for': '5m',
labels: {
Expand Down Expand Up @@ -151,8 +151,9 @@
{
alert: 'etcdHighNumberOfFailedHTTPRequests',
expr: |||
sum(rate(etcd_http_failed_total{%(etcd_selector)s, code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{%(etcd_selector)s}[5m]))
BY (method) > 0.01
sum(rate(etcd_http_failed_total{%(etcd_selector)s, code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{%(etcd_selector)s}[5m])) BY (method)
or sum(rate(etcd_http_failed_total{%(etcd_selector)s, code!="404"}[5m])) BY (method) > bool 0
> 0.01
||| % $._config,
'for': '10m',
labels: {
Expand All @@ -165,8 +166,9 @@
{
alert: 'etcdHighNumberOfFailedHTTPRequests',
expr: |||
sum(rate(etcd_http_failed_total{%(etcd_selector)s, code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{%(etcd_selector)s}[5m]))
BY (method) > 0.05
sum(rate(etcd_http_failed_total{%(etcd_selector)s, code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{%(etcd_selector)s}[5m])) BY (method)
or sum(rate(etcd_http_failed_total{%(etcd_selector)s, code!="404"}[5m])) BY (method) > bool 0
> 0.05
||| % $._config,
'for': '10m',
labels: {
Expand Down
8 changes: 6 additions & 2 deletions Documentation/op-guide/etcd3_alert.rules
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,9 @@ ANNOTATIONS {
# alert if more than 1% of gRPC method calls have failed within the last 5 minutes
ALERT HighNumberOfFailedGRPCRequests
IF 100 * (sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m]))
/ sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m]))) > 1
/ sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m]))) > 0
or sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) > bool 0
> 1
FOR 10m
LABELS {
severity = "warning"
Expand All @@ -57,7 +59,9 @@ ANNOTATIONS {
# alert if more than 5% of gRPC method calls have failed within the last 5 minutes
ALERT HighNumberOfFailedGRPCRequests
IF 100 * (sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m]))
/ sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m]))) > 5
/ sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m]))) > 0
or sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) > bool 0
> 5
FOR 5m
LABELS {
severity = "critical"
Expand Down
26 changes: 14 additions & 12 deletions Documentation/op-guide/etcd3_alert.rules.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,10 +34,10 @@ groups:
message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{
$labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
expr: |
100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
/
sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method)
> 1
sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
/ sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method) > 0
or sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method) > bool 0
> 1
for: 10m
labels:
severity: warning
Expand All @@ -46,10 +46,10 @@ groups:
message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{
$labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
expr: |
100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
/
sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method)
> 5
sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
/ sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method) > 0
or sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method) > bool 0
> 5
for: 5m
labels:
severity: critical
Expand Down Expand Up @@ -107,8 +107,9 @@ groups:
message: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
instance {{ $labels.instance }}'
expr: |
sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
BY (method) > 0.01
sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m])) BY (method) > 0
or sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) > bool 0
> 0.01
for: 10m
labels:
severity: warning
Expand All @@ -117,8 +118,9 @@ groups:
message: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
instance {{ $labels.instance }}.'
expr: |
sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
BY (method) > 0.05
sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m])) BY (method) > 0
or sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) > bool 0
> 0.05
for: 10m
labels:
severity: critical
Expand Down