@cryptotaxi247 / netdata-1 / commits / 2555dccae

health: add python.d/go.d jobs last_collected_secs alarms (#11168)

Ilya Mashchenko committed May 24, 2021 at 14:42 UTC 2555dccae77ebe4ac132c13feca610be1dd26857
33 files changed +16 -530
health/Makefile.am
+2 -13
@@ -25,9 +25,7 @@ install-exec-local:
25 healthconfigdir=$(libconfigdir)/health.d
26 dist_healthconfig_DATA = \
27 health.d/adaptec_raid.conf \
28 - health.d/am2320.conf \
28 health.d/anomalies.conf \
30 - health.d/apache.conf \
29 health.d/apcupsd.conf \
30 health.d/backend.conf \
31 health.d/bcache.conf \
@@ -39,7 +37,6 @@ dist_healthconfig_DATA = \
37 health.d/cgroups.conf \
38 health.d/cpu.conf \
39 health.d/cockroachdb.conf \
42 - health.d/couchdb.conf \
40 health.d/disks.conf \
41 health.d/dnsmasq_dhcp.conf \
42 health.d/dns_query.conf \
@@ -51,6 +48,7 @@ dist_healthconfig_DATA = \
48 health.d/ioping.conf \
49 health.d/fronius.conf \
50 health.d/gearman.conf \
51 + health.d/go.d.plugin.conf \
52 health.d/haproxy.conf \
53 health.d/hdfs.conf \
54 health.d/httpcheck.conf \
@@ -59,26 +57,19 @@ dist_healthconfig_DATA = \
57 health.d/ipmi.conf \
58 health.d/isc_dhcpd.conf \
59 health.d/kubelet.conf \
62 - health.d/lighttpd.conf \
60 health.d/linux_power_supply.conf \
61 health.d/load.conf \
62 health.d/mdstat.conf \
63 health.d/megacli.conf \
64 health.d/memcached.conf \
65 health.d/memory.conf \
69 - health.d/mongodb.conf \
66 health.d/mysql.conf \
71 - health.d/named.conf \
67 health.d/net.conf \
68 health.d/netfilter.conf \
74 - health.d/nginx.conf \
75 - health.d/nginx_plus.conf \
69 health.d/pihole.conf \
77 - health.d/phpfpm.conf \
70 health.d/portcheck.conf \
79 - health.d/postgres.conf \
71 health.d/processes.conf \
81 - health.d/pulsar.conf \
72 + health.d/python.d.plugin.conf \
73 health.d/qos.conf \
74 health.d/ram.conf \
75 health.d/redis.conf \
@@ -86,7 +77,6 @@ dist_healthconfig_DATA = \
77 health.d/riakkv.conf \
78 health.d/scaleio.conf \
79 health.d/softnet.conf \
89 - health.d/squid.conf \
80 health.d/stiebeleltron.conf \
81 health.d/synchronization.conf \
82 health.d/swap.conf \
@@ -107,6 +97,5 @@ dist_healthconfig_DATA = \
97 health.d/wmi.conf \
98 health.d/x509check.conf \
99 health.d/zfs.conf \
110 - health.d/zookeeper.conf \
100 health.d/dbengine.conf \
101 $(NULL)
health/health.d/am2320.conf deleted
-15
@@ -1,15 +0,0 @@
1 -# make sure am2320 is sending stats
2 -
3 - template: am2320_last_collected_secs
4 - on: am2320.temperature
5 - class: Other
6 -component: Sensors
7 - type: Latency
8 - calc: $now - $last_collected_t
9 - units: seconds ago
10 - every: 10s
11 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
12 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
13 - delay: down 5m multiplier 1.5 max 1h
14 - info: number of seconds since the last successful data collection
15 - to: webmaster
health/health.d/cockroachdb.conf
-16
@@ -1,20 +1,4 @@
1
2 -# Availability
3 -
4 - template: cockroachdb_last_collected_secs
5 - on: cockroachdb.live_nodes
6 - class: Database
7 -component: CockroachDB
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: dba
17 -
2 # Capacity
3
4 template: cockroachdb_used_storage_capacity
health/health.d/couchdb.conf deleted
-16
@@ -1,16 +0,0 @@
1 -
2 -# make sure couchdb is running
3 -
4 - template: couchdb_last_collected_secs
5 - on: couchdb.request_methods
6 - class: Database
7 -component: CouchDB
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: dba
health/health.d/gearman.conf
-14
@@ -1,17 +1,3 @@
1 -# make sure Gearman is running
2 - template: gearman_last_collected_secs
3 - on: gearman.total_jobs
4 - class: Computing
5 -component: Gearman
6 - type: Latency
7 - calc: $now - $last_collected_t
8 - units: seconds ago
9 - every: 10s
10 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
11 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
12 - delay: down 5m multiplier 1.5 max 1h
13 - info: number of seconds since the last successful data collection
14 - to: sysadmin
1
2 template: gearman_workers_queued
3 on: gearman.single_job
health/health.d/go.d.plugin.conf renamed
+7 -7
@@ -1,11 +1,12 @@
1
2 -# make sure nginx_plus is running
2 +# make sure go.d.plugin data collection job is running
3
4 - template: nginx_plus_last_collected_secs
5 - on: nginx_plus.requests_total
6 - class: Web Server
7 -component: NGINX Plus
8 - type: Latency
4 + template: go.d_job_last_collected_secs
5 + on: netdata.go_plugin_execution_time
6 + class: Netdata
7 +component: go.d.plugin
8 + type: Error
9 + module: *
10 calc: $now - $last_collected_t
11 units: seconds ago
12 every: 10s
@@ -14,4 +15,3 @@ component: NGINX Plus
15 delay: down 5m multiplier 1.5 max 1h
16 info: number of seconds since the last successful data collection
17 to: webmaster
17 -
health/health.d/hdfs.conf
-17
@@ -1,21 +1,4 @@
1
2 -# make sure hdfs is running
3 -
4 - template: hdfs_last_collected_secs
5 - on: hdfs.heap_memory
6 - class: Storage
7 -component: HDFS
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: webmaster
17 -
18 -
2 # Common
3
4 template: hdfs_capacity_usage
health/health.d/httpcheck.conf
-14
@@ -1,17 +1,3 @@
1 - template: httpcheck_last_collected_secs
2 - families: *
3 - on: httpcheck.status
4 - class: Other
5 -component: HTTP endpoint
6 - type: Latency
7 - calc: $now - $last_collected_t
8 - every: 10s
9 - units: seconds ago
10 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
11 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
12 - delay: down 5m multiplier 1.5 max 1h
13 - info: number of seconds since the last successful data collection
14 - to: sysadmin
1
2 # This is a fast-reacting no-notification alarm ideal for custom dashboards or badges
3 template: httpcheck_web_service_up
health/health.d/lighttpd.conf deleted
-17
@@ -1,17 +0,0 @@
1 -
2 -# make sure lighttpd is running
3 -
4 - template: lighttpd_last_collected_secs
5 - on: lighttpd.requests
6 - class: Web Server
7 -component: Lighttpd
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: webmaster
17 -
health/health.d/memcached.conf
-17
@@ -1,21 +1,4 @@
1
2 -# make sure memcached is running
3 -
4 - template: memcached_last_collected_secs
5 - on: memcached.cache
6 - class: KV Storage
7 -component: Memcached
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: dba
17 -
18 -
2 # detect if memcached cache is full
3
4 template: memcached_cache_memory_usage
health/health.d/mongodb.conf deleted
-16
@@ -1,16 +0,0 @@
1 -
2 -# make sure mongodb is running
3 -
4 - template: mongodb_last_collected_secs
5 - on: mongodb.read_operations
6 - class: Database
7 -component: MongoDB
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: dba
health/health.d/mysql.conf
-18
@@ -1,22 +1,4 @@
1
2 -# make sure mysql is running
3 -
4 - template: mysql_last_collected_secs
5 - on: mysql.queries
6 - class: Database
7 -component: MySQL
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: dba
17 -
18 -
19 -# -----------------------------------------------------------------------------
2 # slow queries
3
4 template: mysql_10s_slow_queries
health/health.d/named.conf deleted
-17
@@ -1,17 +0,0 @@
1 -
2 -# make sure named is running
3 -
4 - template: named_last_collected_secs
5 - on: named.global_queries
6 - class: DNS
7 -component: BIND
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: domainadmin
17 -
health/health.d/nginx.conf deleted
-17
@@ -1,17 +0,0 @@
1 -
2 -# make sure nginx is running
3 -
4 - template: nginx_last_collected_secs
5 - on: nginx.requests
6 - class: Web Server
7 -component: NGINX
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: webmaster
17 -
health/health.d/phpfpm.conf deleted
-17
@@ -1,17 +0,0 @@
1 -
2 -# make sure phpfpm is running
3 -
4 - template: phpfpm_last_collected_secs
5 - on: phpfpm.requests
6 - class: Web Server
7 -component: PHP-FPM
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: webmaster
17 -
health/health.d/pihole.conf
-16
@@ -1,20 +1,4 @@
1
2 -# Make sure Pi-hole is responding.
3 -
4 - template: pihole_last_collected_secs
5 - on: pihole.dns_queries_total
6 - class: Ad Filtering
7 -component: Pi-hole
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: webmaster
17 -
2 # Blocked DNS queries.
3
4 template: pihole_blocked_queries
health/health.d/portcheck.conf
-14
@@ -1,17 +1,3 @@
1 - template: portcheck_last_collected_secs
2 - families: *
3 - on: portcheck.status
4 - class: Other
5 -component: TCP endpoint
6 - type: Latency
7 - calc: $now - $last_collected_t
8 - every: 10s
9 - units: seconds ago
10 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
11 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
12 - delay: down 5m multiplier 1.5 max 1h
13 - info: number of seconds since the last successful data collection
14 - to: sysadmin
1
2 # This is a fast-reacting no-notification alarm ideal for custom dashboards or badges
3 template: portcheck_service_reachable
health/health.d/postgres.conf deleted
-16
@@ -1,16 +0,0 @@
1 -
2 -# make sure postgres is running
3 -
4 - template: postgres_last_collected_secs
5 - on: postgres.db_stat_transactions
6 - class: Database
7 -component: PostgreSQL
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: dba
health/health.d/pulsar.conf deleted
-16
@@ -1,16 +0,0 @@
1 -
2 -# Availability
3 -
4 - template: pulsar_last_collected_secs
5 - on: pulsar.broker_components
6 - class: Messaging
7 -component: Pulsar
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: sysadmin
health/health.d/python.d.plugin.conf renamed
+7 -7
@@ -1,11 +1,12 @@
1
2 -# make sure apache is running
2 +# make sure python.d.plugin data collection job is running
3
4 - template: apache_last_collected_secs
5 - on: apache.requests
6 - class: Web Server
7 -component: Apache
8 - type: Latency
4 + template: python.d_job_last_collected_secs
5 + on: netdata.pythond_runtime
6 + class: Netdata
7 +component: python.d.plugin
8 + type: Error
9 + module: *
10 calc: $now - $last_collected_t
11 units: seconds ago
12 every: 10s
@@ -14,4 +15,3 @@ component: Apache
15 delay: down 5m multiplier 1.5 max 1h
16 info: number of seconds since the last successful data collection
17 to: webmaster
17 -
health/health.d/redis.conf
-16
@@ -1,20 +1,4 @@
1
2 -# make sure redis is running
3 -
4 - template: redis_last_collected_secs
5 - on: redis.operations
6 - class: KV Storage
7 -component: Redis
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: dba
17 -
2 template: redis_bgsave_broken
3 families: *
4 on: redis.bgsave_health
health/health.d/retroshare.conf
-15
@@ -1,18 +1,3 @@
1 -# make sure RetroShare is running
2 -
3 - template: retroshare_last_collected_secs
4 - on: retroshare.peers
5 - class: Data Sharing
6 -component: Retroshare
7 - type: Latency
8 - calc: $now - $last_collected_t
9 - units: seconds ago
10 - every: 10s
11 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
12 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
13 - delay: down 5m multiplier 1.5 max 1h
14 - info: number of seconds since the last successful data collection
15 - to: sysadmin
1
2 # make sure the DHT is fine when active
3
health/health.d/riakkv.conf
-14
@@ -1,17 +1,3 @@
1 -# Ensure that Riak is running. template: riak_last_collected_secs
2 - template: riakkv_last_collected_secs
3 - on: riak.kv.throughput
4 - class: Database
5 -component: Riak KV
6 - type: Latency
7 - calc: $now - $last_collected_t
8 - units: seconds ago
9 - every: 10s
10 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
11 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
12 - delay: down 5m multiplier 1.5 max 1h
13 - info: number of seconds since the last successful data collection
14 - to: dba
1
2 # Warn if a list keys operation is running.
3 template: riakkv_list_keys_active
health/health.d/scaleio.conf
-16
@@ -1,20 +1,4 @@
1
2 -# make sure scaleio is running
3 -
4 - template: scaleio_last_collected_secs
5 - on: scaleio.system_capacity_total
6 - class: Storage
7 -component: ScaleIO
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: sysadmin
17 -
2 # make sure Storage Pool capacity utilization is under limit
3
4 template: scaleio_storage_pool_capacity_utilization
health/health.d/squid.conf deleted
-17
@@ -1,17 +0,0 @@
1 -
2 -# make sure squid is running
3 -
4 - template: squid_last_collected_secs
5 - on: squid.clients_requests
6 - class: Web Proxy
7 -component: Squid
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: proxyadmin
17 -
health/health.d/unbound.conf
-16
@@ -1,20 +1,4 @@
1
2 -# make sure unbound is running
3 -
4 - template: unbound_last_collected_secs
5 - on: unbound.queries
6 - class: DNS
7 -component: Unbound
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: sysadmin
17 -
2 # make sure there is no overwritten/dropped queries in the request-list
3
4 template: unbound_request_list_overwritten
health/health.d/vcsa.conf
-16
@@ -1,20 +1,4 @@
1
2 -# make sure vcsa is running and responding
3 -
4 - template: vcsa_last_collected_secs
5 - on: vcsa.system_health
6 - class: Virtual Machine
7 -component: VMware vCenter
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: sysadmin
17 -
2 # Overall system health:
3 # - 0: all components are healthy.
4 # - 1: one or more components might become overloaded soon.
health/health.d/vernemq.conf
-16
@@ -1,20 +1,4 @@
1
2 -# Availability
3 -
4 - template: vernemq_last_collected_secs
5 - on: vernemq.node_uptime
6 - class: Messaging
7 -component: VerneMQ
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: sysadmin
17 -
2 # Socket errors
3
4 template: vernemq_socket_errors
health/health.d/web_log.conf
-35
@@ -1,22 +1,4 @@
1
2 -# make sure we can collect web log data
3 -
4 - template: last_collected_secs
5 - on: web_log.response_codes
6 - class: Web Server
7 -component: Web log
8 - type: Latency
9 - families: *
10 - calc: $now - $last_collected_t
11 - units: seconds ago
12 - every: 10s
13 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
14 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
15 - delay: down 5m multiplier 1.5 max 1h
16 - info: number of seconds since the last successful data collection
17 - to: webmaster
18 -
19 -
2 # -----------------------------------------------------------------------------
3 # high level response code alarms
4
@@ -231,23 +213,6 @@ component: Web log
213
214 # ---------------------------------------------------GO-VERSION---------------------------------------------------------
215
234 -# make sure we can collect web log data
235 -
236 - template: web_log_last_collected_secs
237 - on: web_log.requests
238 - class: Web Server
239 -component: Web log
240 - type: Latency
241 - families: *
242 - calc: $now - $last_collected_t
243 - units: seconds ago
244 - every: 10s
245 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
246 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
247 - delay: down 5m multiplier 1.5 max 1h
248 - info: number of seconds since the last successful data collection
249 - to: webmaster
250 -
216 # unmatched lines
217
218 # the following alarms trigger only when there are enough data.
health/health.d/whoisquery.conf
-17
@@ -1,21 +1,4 @@
1
2 -# make sure whoisquery is running
3 -
4 - template: whoisquery_last_collected_secs
5 - on: whoisquery.time_until_expiration
6 - class: Other
7 -component: WHOIS
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 60s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: webmaster
17 -
18 -
2 template: whoisquery_days_until_expiration
3 on: whoisquery.time_until_expiration
4 class: Other
health/health.d/wmi.conf
-18
@@ -1,22 +1,4 @@
1
2 -# you can disable an alarm notification by setting the 'to' line to: silent
3 -
4 -## Availability
5 -
6 - template: wmi_last_collected_secs
7 - on: cpu.collector_duration
8 - class: Windows
9 -component: Availability
10 - type: Latency
11 - calc: $now - $last_collected_t
12 - units: seconds ago
13 - every: 10s
14 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
15 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
16 - delay: down 5m multiplier 1.5 max 1h
17 - info: number of seconds since the last successful data collection
18 - to: sysadmin
19 -
2 ## CPU
3
4 template: wmi_10min_cpu_usage
health/health.d/x509check.conf
-17
@@ -1,21 +1,4 @@
1
2 -# make sure x509check is running
3 -
4 - template: x509check_last_collected_secs
5 - on: x509check.time_until_expiration
6 - class: Certificates
7 -component: x509 certificates
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 60s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: webmaster
17 -
18 -
2 template: x509check_days_until_expiration
3 on: x509check.time_until_expiration
4 class: Certificates
health/health.d/zookeeper.conf deleted
-17
@@ -1,17 +0,0 @@
1 -
2 -# make sure zookeeper is running
3 -
4 - template: zookeeper_last_collected_secs
5 - on: zookeeper.requests
6 - class: KV Storage
7 -component: ZooKeeper
8 - type: Latency
9 - calc: $now - $last_collected_t
10 - units: seconds ago
11 - every: 10s
12 - warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13 - crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14 - delay: down 5m multiplier 1.5 max 1h
15 - info: number of seconds since the last successful data collection
16 - to: webmaster
17 -