74 lines
3.4 KiB
YAML
74 lines
3.4 KiB
YAML
# Licensed to the Apache Software Foundation (ASF) under one
|
|
# or more contributor license agreements. See the NOTICE file
|
|
# distributed with this work for additional information
|
|
# regarding copyright ownership. The ASF licenses this file
|
|
# to you under the Apache License, Version 2.0 (the
|
|
# "License"); you may not use this file except in compliance
|
|
# with the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
# Sample alarm rules.
|
|
rules:
|
|
# Rule unique name, must be ended with `_rule`.
|
|
service_resp_time_rule:
|
|
# A MQE expression, the result type must be `SINGLE_VALUE` and the root operation of the expression must be a Compare Operation
|
|
# which provides `1`(true) or `0`(false) result. When the result is `1`(true), the alarm will be triggered.
|
|
expression: sum(service_resp_time > 1000) >= 3
|
|
period: 10
|
|
silence-period: 5
|
|
message: Response time of service {name} is more than 1000ms in 3 minutes of last 10 minutes.
|
|
# service_resp_time_rule:
|
|
# expression: avg(service_resp_time) > 1000
|
|
# period: 10
|
|
# silence-period: 5
|
|
# message: Avg response time of service {name} is more than 1000ms in last 10 minutes.
|
|
service_sla_rule:
|
|
expression: sum(service_sla < 8000) >= 2
|
|
# The length of time to evaluate the metrics
|
|
period: 10
|
|
# How many times of checks, the alarm keeps silence after alarm triggered, default as same as period.
|
|
silence-period: 3
|
|
message: Successful rate of service {name} is lower than 80% in 2 minutes of last 10 minutes
|
|
service_resp_time_percentile_rule:
|
|
expression: sum(service_percentile{p='50,75,90,95,99'} > 1000) >= 3
|
|
period: 10
|
|
silence-period: 5
|
|
message: Percentile response time of service {name} alarm in 3 minutes of last 10 minutes, due to more than one condition of p50 > 1000, p75 > 1000, p90 > 1000, p95 > 1000, p99 > 1000
|
|
service_instance_resp_time_rule:
|
|
expression: sum(service_instance_resp_time > 1000) >= 2
|
|
period: 10
|
|
silence-period: 5
|
|
message: Response time of service instance {name} is more than 1000ms in 2 minutes of last 10 minutes
|
|
database_access_resp_time_rule:
|
|
expression: sum(database_access_resp_time > 1000) >= 2
|
|
period: 10
|
|
message: Response time of database access {name} is more than 1000ms in 2 minutes of last 10 minutes
|
|
endpoint_relation_resp_time_rule:
|
|
expression: sum(endpoint_relation_resp_time > 1000) >= 2
|
|
period: 10
|
|
message: Response time of endpoint relation {name} is more than 1000ms in 2 minutes of last 10 minutes
|
|
# Active endpoint related metrics alarm will cost more memory than service and service instance metrics alarm.
|
|
# Because the number of endpoint is much more than service and instance.
|
|
#
|
|
# endpoint_resp_time_rule:
|
|
# expression: sum(endpoint_resp_time > 1000) >= 2
|
|
# period: 10
|
|
# silence-period: 5
|
|
# message: Response time of endpoint {name} is more than 1000ms in 2 minutes of last 10 minutes
|
|
|
|
#hooks:
|
|
# webhook:
|
|
# default:
|
|
# is-default: true
|
|
# urls:
|
|
# - http://127.0.0.1/notify/
|
|
# - http://127.0.0.1/go-wechat/
|
|
|