Mirroristas/etcd
2
0
Fork 0
mirror of https://github.com/etcd-io/etcd.git synced 2024-09-27 06:25:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Documentation/etcd-mixin: Reformulate alerting rules to use without rather than by (#12122)

Browse Source 
* etcd-mixin: Reformulate alerting rules to use `without` rather than `by`

With aggregations using `by`, all additional target labels that a user
might have configured, are aggregated away. However, those target
labels are useful for e.g. alert routing. With this commit, nothing
should change for vanilla job/instance target labels, but whoever has
more target labels can now still make use of them.

Signed-off-by: beorn7 <beorn@grafana.com>

* etcd-mixin: Parametrize instance labels to aggregate away

Signed-off-by: beorn7 <beorn@grafana.com>
This commit is contained in:
Björn Rabenstein 2020-07-24 01:02:26 +02:00 committed by GitHub
parent d0e4fe56a5
commit c9a5889915
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 21 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
Documentation/etcd-mixin/mixin.libsonnet
View File

@ -1,6 +1,12 @@
{
_config+:: {
etcd_selector: 'job=~".*etcd.*"',
// etcd_instance_labels are the label names that are uniquely
// identifying an instance and need to be aggreated away for alerts
// that are about an etcd cluster as a whole. For example, if etcd
// instances are deployed on K8s, you will likely want to change
// this to 'instance, pod'.
etcd_instance_labels: 'instance',
},
prometheusAlerts+:: {
@ -11,11 +17,11 @@
{
alert: 'etcdMembersDown',
expr: |||
max by (job) (
sum by (job) (up{%(etcd_selector)s} == bool 0)
max without (endpoint) (
sum without (%(etcd_instance_labels)s) (up{%(etcd_selector)s} == bool 0)
or
count by (job,endpoint) (
sum by (job,endpoint,To) (rate(etcd_network_peer_sent_failures_total{%(etcd_selector)s}[1m])) > 0.01
count without (To) (
sum without (%(etcd_instance_labels)s) (rate(etcd_network_peer_sent_failures_total{%(etcd_selector)s}[1m])) > 0.01
)
)
> 0
@ -31,7 +37,7 @@
{
alert: 'etcdInsufficientMembers',
expr: |||
sum(up{%(etcd_selector)s} == bool 1) by (job) < ((count(up{%(etcd_selector)s}) by (job) + 1) / 2)
sum(up{%(etcd_selector)s} == bool 1) without (%(etcd_instance_labels)s) < ((count(up{%(etcd_selector)s}) without (%(etcd_instance_labels)s) + 1) / 2)
||| % $._config,
'for': '3m',
labels: {
@ -57,7 +63,7 @@
{
alert: 'etcdHighNumberOfLeaderChanges',
expr: |||
increase((max by (job) (etcd_server_leader_changes_seen_total{%(etcd_selector)s}) or 0*absent(etcd_server_leader_changes_seen_total{%(etcd_selector)s}))[15m:1m]) >= 4
increase((max without (%(etcd_instance_labels)s) (etcd_server_leader_changes_seen_total{%(etcd_selector)s}) or 0*absent(etcd_server_leader_changes_seen_total{%(etcd_selector)s}))[15m:1m]) >= 4
||| % $._config,
'for': '5m',
labels: {
@ -70,9 +76,9 @@
{
alert: 'etcdHighNumberOfFailedGRPCRequests',
expr: |||
100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) without (grpc_type, grpc_code)
/
sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) BY (job, instance, grpc_service, grpc_method)
sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) without (grpc_type, grpc_code)
> 1
||| % $._config,
'for': '10m',
@ -86,9 +92,9 @@
{
alert: 'etcdHighNumberOfFailedGRPCRequests',
expr: |||
100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) without (grpc_type, grpc_code)
/
sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) BY (job, instance, grpc_service, grpc_method)
sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) without (grpc_type, grpc_code)
> 5
||| % $._config,
'for': '5m',
@ -102,7 +108,7 @@
{
alert: 'etcdGRPCRequestsSlow',
expr: |||
histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{%(etcd_selector)s, grpc_type="unary"}[5m])) by (job, instance, grpc_service, grpc_method, le))
histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{%(etcd_selector)s, grpc_type="unary"}[5m])) without(grpc_type))
> 0.15
||| % $._config,
'for': '10m',
@ -171,8 +177,8 @@
{
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])) without (code) / sum(rate(etcd_http_received_total{%(etcd_selector)s}[5m]))
without (code) > 0.01
||| % $._config,
'for': '10m',
labels: {
@ -185,8 +191,8 @@
{
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])) without (code) / sum(rate(etcd_http_received_total{%(etcd_selector)s}[5m]))
without (code) > 0.05
||| % $._config,
'for': '10m',
labels: {