6/6.0-beta/compose/config/alarm-settings.yml

# 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:
    indicator-name: service_resp_time
    op: ">"
    threshold: 1000
    period: 10
    count: 3
    silence-period: 5
    message: Response time of service {name} is more than 1000ms in last 3 minutes.
  service_sla_rule:
    # Indicator value need to be long, double or int
    indicator-name: service_sla
    op: "<"
    threshold: 8000
    # The length of time to evaluate the metric
    period: 10
    # How many times after the metric match the condition, will trigger alarm
    count: 2
    # 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 last 2 minutes.
  service_p90_sla_rule:
    # Indicator value need to be long, double or int
    indicator-name: service_p90
    op: ">"
    threshold: 1000
    period: 10
    count: 3
    silence-period: 5
    message: 90% response time of service {name} is lower than 1000ms in last 3 minutes
  service_instance_resp_time_rule:
    indicator-name: service_instance_resp_time
    op: ">"
    threshold: 1000
    period: 10
    count: 2
    silence-period: 5
    message: Response time of service instance {name} is more than 1000ms in last 2 minutes.
#  Active endpoint related metric alarm will cost more memory than service and service instance metric alarm.
#  Because the number of endpoint is much more than service and instance.
#
#  endpoint_avg_rule:
#    indicator-name: endpoint_avg
#    op: ">"
#    threshold: 1000
#    period: 10
#    count: 2
#    silence-period: 5
#    message: Response time of endpoint {name} is more than 1000ms in last 2 minutes.

webhooks:
#  - http://127.0.0.1/notify/
#  - http://127.0.0.1/go-wechat/