Ottomata has uploaded a new change for review.
https://gerrit.wikimedia.org/r/72096
Change subject: Reenabling kafka too many produce requests icinga check.
......................................................................
Reenabling kafka too many produce requests icinga check.
Change-Id: I5a0db0ab6eac217a761958b57790715a247001c8
---
M manifests/misc/analytics.pp
M templates/icinga/checkcommands.cfg.erb
2 files changed, 19 insertions(+), 4 deletions(-)
git pull ssh://gerrit.wikimedia.org:29418/operations/puppet
refs/changes/96/72096/1
diff --git a/manifests/misc/analytics.pp b/manifests/misc/analytics.pp
index cf598fa..46fc0c0 100644
--- a/manifests/misc/analytics.pp
+++ b/manifests/misc/analytics.pp
@@ -30,9 +30,18 @@
# Set up icinga monitoring of Kafka broker server produce requests per
second.
# If this drops too low, trigger an alert
# for this udp2log instance.
- monitor_service { "kakfa-broker-ProduceRequestsPerSecond":
- description =>
"kafka_network_SocketServerStats.ProduceRequestsPerSecond",
- check_command =>
"check_kafka_broker_produce_requests!2!1",
+ monitor_service { "kakfa-broker-ProduceRequestsPerSecond_min":
+ description =>
"kafka_network_SocketServerStats.ProduceRequestsPerSecond_min",
+ check_command =>
"check_kafka_broker_produce_requests_min!5!1",
+ contact_group => "analytics",
+ }
+
+ # Set up icinga monitoring of Kafka broker server produce requests per
second.
+ # If this drops too low, trigger an alert
+ # for this udp2log instance.
+ monitor_service { "kakfa-broker-ProduceRequestsPerSecond_max":
+ description =>
"kafka_network_SocketServerStats.ProduceRequestsPerSecond_max",
+ check_command =>
"check_kafka_broker_produce_requests_max!15!20",
contact_group => "analytics",
}
}
diff --git a/templates/icinga/checkcommands.cfg.erb
b/templates/icinga/checkcommands.cfg.erb
index b156f7e..c569665 100644
--- a/templates/icinga/checkcommands.cfg.erb
+++ b/templates/icinga/checkcommands.cfg.erb
@@ -617,9 +617,15 @@
# Analytics Kraken checks
# Check that Kafka Brokers are getting ProduceRequests.
define command{
- command_name check_kafka_broker_produce_requests
+ command_name check_kafka_broker_produce_requests_min
command_line $USER1$/check_ganglios_generic_value -H $HOSTADDRESS$
-m kafka_network_SocketServerStats.ProduceRequestsPerSecond -w $ARG1$ -c $ARG2$
-o lt
}
+# Check that Kafka Brokers are not getting too many ProduceRequests.
+define command{
+ command_name check_kafka_broker_produce_requests_max
+ command_line $USER1$/check_ganglios_generic_value -H $HOSTADDRESS$
-m kafka_network_SocketServerStats.ProduceRequestsPerSecond -w $ARG1$ -c $ARG2$
-o gt
+}
+
# Alerts for data loss in Kraken HDFS.
define command{
--
To view, visit https://gerrit.wikimedia.org/r/72096
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: I5a0db0ab6eac217a761958b57790715a247001c8
Gerrit-PatchSet: 1
Gerrit-Project: operations/puppet
Gerrit-Branch: production
Gerrit-Owner: Ottomata <[email protected]>
_______________________________________________
MediaWiki-commits mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
