From fc79182c310adfcba4ab3b360f9f6e493b1835d2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=90=B4=E6=99=9F=20Wu=20Sheng?= <wu.sheng@foxmail.com>
Date: Mon, 3 Dec 2018 22:58:23 +0800
Subject: [PATCH] Make endpoint alarm setting not active in default (#1998)

---
 docker/config/alarm-settings.yml              | 62 +++++++++++++------
 .../src/main/assembly/alarm-settings.yml      | 19 +++---
 2 files changed, 55 insertions(+), 26 deletions(-)

diff --git a/docker/config/alarm-settings.yml b/docker/config/alarm-settings.yml
index 9ea69756b..eab440737 100644
--- a/docker/config/alarm-settings.yml
+++ b/docker/config/alarm-settings.yml
@@ -17,28 +17,54 @@
 # Sample alarm rules.
 rules:
   # Rule unique name, must be ended with `_rule`.
-#  endpoint_percent_rule:
-#    # Indicator value need to be long, double or int
-#    indicator-name: endpoint_percent
-#    threshold: 75
-#    op: <
-#    # The length of time to evaluate the metric
-#    period: 10
-#    # How many times after the metric match the condition, will trigger alarm
-#    count: 3
-#    # How many times of checks, the alarm keeps silence after alarm triggered, default as same as period.
-#    silence-period: 10
-#    message: Successful rate of endpoint {name} is lower than 75%
   service_resp_time_rule:
     indicator-name: service_resp_time
-    # [Optional] Default, match all services in this indicator
-    include-names:
-      - dubbox-provider
-      - dubbox-consumer
-    threshold: 1000
     op: ">"
+    threshold: 1000
     period: 10
-    count: 1
+    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/
diff --git a/oap-server/server-starter/src/main/assembly/alarm-settings.yml b/oap-server/server-starter/src/main/assembly/alarm-settings.yml
index 9ee76e2fe..eab440737 100644
--- a/oap-server/server-starter/src/main/assembly/alarm-settings.yml
+++ b/oap-server/server-starter/src/main/assembly/alarm-settings.yml
@@ -54,14 +54,17 @@ rules:
     count: 2
     silence-period: 5
     message: Response time of service instance {name} is more than 1000ms in last 2 minutes.
-  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.
+#  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/