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

removed checks that keep giving false positives. #10796

Closed
wants to merge 1 commit into from
Closed

removed checks that keep giving false positives. #10796

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
32 changes: 0 additions & 32 deletions Documentation/etcd-mixin/mixin.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,38 +47,6 @@
message: 'etcd cluster "{{ $labels.job }}": instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last 30 minutes.',
},
},
{
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
||| % $._config,
'for': '10m',
labels: {
severity: 'warning',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.',
},
},
{
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
||| % $._config,
'for': '5m',
labels: {
severity: 'critical',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.',
},
},
{
alert: 'etcdGRPCRequestsSlow',
expr: |||
Expand Down
26 changes: 0 additions & 26 deletions Documentation/op-guide/etcd3_alert.rules
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,32 +41,6 @@ ANNOTATIONS {
# gRPC request alerts
# ===================

# 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
FOR 10m
LABELS {
severity = "warning"
}
ANNOTATIONS {
summary = "a high number of gRPC requests are failing",
description = "{{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}",
}

# 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
FOR 5m
LABELS {
severity = "critical"
}
ANNOTATIONS {
summary = "a high number of gRPC requests are failing",
description = "{{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}",
}

# alert if the 99th percentile of gRPC method calls take more than 150ms
ALERT GRPCRequestsSlow
IF histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job="etcd",grpc_type="unary"}[5m])) by (grpc_service, grpc_method, le)) > 0.15
Expand Down
24 changes: 0 additions & 24 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 @@ -29,30 +29,6 @@ groups:
for: 15m
labels:
severity: warning
- alert: etcdHighNumberOfFailedGRPCRequests
annotations:
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
for: 10m
labels:
severity: warning
- alert: etcdHighNumberOfFailedGRPCRequests
annotations:
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
for: 5m
labels:
severity: critical
- alert: etcdGRPCRequestsSlow
annotations:
message: 'etcd cluster "{{ $labels.job }}": gRPC requests to {{ $labels.grpc_method
Expand Down