|
|
zabbix_export:
|
|
|
version: '7.0'
|
|
|
template_groups:
|
|
|
- uuid: a571c0d144b14fd4a87a9d9b2aa9fcd6
|
|
|
name: Templates/Applications
|
|
|
templates:
|
|
|
- uuid: 884bdbeea93c4be0a11a2c92a5f8adce
|
|
|
template: 'HashiCorp Consul Node by HTTP'
|
|
|
name: 'HashiCorp Consul Node by HTTP'
|
|
|
description: |
|
|
|
Get HashiCorp Consul Node metrics by HTTP agent from metrics endpoint.
|
|
|
|
|
|
Don't forget to change macros {$CONSUL.NODE.API.URL}, {$CONSUL.TOKEN}.
|
|
|
Some metrics may not be collected depending on your HashiCorp Consul instance version and configuration.
|
|
|
More information about metrics you can find in official documentation: https://www.consul.io/docs/agent/telemetry
|
|
|
|
|
|
You can discuss this template or leave feedback on our forum https://www.zabbix.com/forum/zabbix-suggestions-and-feedback
|
|
|
|
|
|
Generated by official Zabbix template tool "Templator" 2.0.0
|
|
|
vendor:
|
|
|
name: Zabbix
|
|
|
version: 7.0-0
|
|
|
groups:
|
|
|
- name: Templates/Applications
|
|
|
items:
|
|
|
- uuid: 9f90fe43daaa43369b000754e1630e41
|
|
|
name: 'Consul: ACL: resolves, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.acl.resolves.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'The number of ACL resolves per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_acl_ResolveToken_count
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: acl
|
|
|
- uuid: 1c969d5d7546444e91e883661d63890b
|
|
|
name: 'Consul: Catalog: deregister, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.catalog.deregister.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'The number of catalog deregister operation per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_catalog_deregister_count
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: catalog
|
|
|
- uuid: 8f01480896f8426688aee08e2ee0fc20
|
|
|
name: 'Consul: Catalog: register, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.catalog.register.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'The number of catalog register operation per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_catalog_register_count
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: catalog
|
|
|
- uuid: dabcb6819c9444a6a287a6458056ef31
|
|
|
name: 'Consul: Number of checks'
|
|
|
type: DEPENDENT
|
|
|
key: consul.checks_number
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: 'Number of checks on current node.'
|
|
|
preprocessing:
|
|
|
- type: JSONPATH
|
|
|
parameters:
|
|
|
- $.Stats.agent.checks
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
master_item:
|
|
|
key: consul.get_node_info
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: consul
|
|
|
- uuid: 8e48706f9bda4689bec45f4a80fcc3cb
|
|
|
name: 'Consul: Number of check monitors'
|
|
|
type: DEPENDENT
|
|
|
key: consul.check_monitors_number
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: 'Number of check monitors on current node.'
|
|
|
preprocessing:
|
|
|
- type: JSONPATH
|
|
|
parameters:
|
|
|
- $.Stats.agent.check_monitors
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
master_item:
|
|
|
key: consul.get_node_info
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: consul
|
|
|
- uuid: 2706adc5e5a64c4480269938e2b90fc1
|
|
|
name: 'Consul: Client RPC, per second'
|
|
|
type: DEPENDENT
|
|
|
key: consul.client_rpc
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: Rps
|
|
|
description: |
|
|
|
Number of times per second whenever a Consul agent in client mode makes an RPC request to a Consul server.
|
|
|
This gives a measure of how much a given agent is loading the Consul servers.
|
|
|
This is only generated by agents in client mode, not Consul servers.
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_client_rpc
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: rpc
|
|
|
- uuid: 3fd30bfd7c324c53a346974c9f38e9db
|
|
|
name: 'Consul: Client RPC failed ,per second'
|
|
|
type: DEPENDENT
|
|
|
key: consul.client_rpc_failed
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: Rps
|
|
|
description: 'Number of times per second whenever a Consul agent in client mode makes an RPC request to a Consul server and fails.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_client_rpc_failed
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: rpc
|
|
|
- uuid: 12b9bbac571b431ea06a13a7154ef673
|
|
|
name: 'Consul: Process CPU seconds, total'
|
|
|
type: DEPENDENT
|
|
|
key: consul.cpu_seconds_total.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: s
|
|
|
description: 'Total user and system CPU time spent in seconds.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- process_cpu_seconds_total
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: cpu
|
|
|
- uuid: 7513b847ac754a25972adb3547a871ca
|
|
|
name: 'Consul: GC pause, p50'
|
|
|
type: DEPENDENT
|
|
|
key: consul.gc_pause.p50
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: s
|
|
|
description: 'The 50 percentile (median) for the number of nanoseconds consumed by stop-the-world garbage collection (GC) pauses since Consul started, in milliseconds.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_runtime_gc_pause_ns{quantile="0.5"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
- type: MULTIPLIER
|
|
|
parameters:
|
|
|
- '1.0E-9'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: gs
|
|
|
- uuid: 3ec74713a835498197e59df962e27bab
|
|
|
name: 'Consul: GC pause, p90'
|
|
|
type: DEPENDENT
|
|
|
key: consul.gc_pause.p90
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: s
|
|
|
description: 'The 90 percentile for the number of nanoseconds consumed by stop-the-world garbage collection (GC) pauses since Consul started, in milliseconds.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_runtime_gc_pause_ns{quantile="0.9"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
- type: MULTIPLIER
|
|
|
parameters:
|
|
|
- '1.0E-9'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: gc
|
|
|
- uuid: 2b3cbe778f1c4d858e43320b8c25960d
|
|
|
name: 'Consul: Get local services'
|
|
|
type: SCRIPT
|
|
|
key: consul.get_local_services
|
|
|
history: '0'
|
|
|
trends: '0'
|
|
|
value_type: TEXT
|
|
|
params: |
|
|
|
var Consul = {
|
|
|
setParams: function (params) {
|
|
|
['api_endpoint', 'token'].forEach(function (field) {
|
|
|
if (typeof params !== 'object' || typeof params[field] === 'undefined' || params[field] === '') {
|
|
|
throw 'Required param is not set: "' + field + '".';
|
|
|
}
|
|
|
});
|
|
|
|
|
|
Consul.params = params;
|
|
|
if (typeof Consul.params.api_endpoint === 'string' && !Consul.params.api_endpoint.endsWith('/')) {
|
|
|
Consul.params.api_endpoint += '/';
|
|
|
}
|
|
|
},
|
|
|
|
|
|
request: function (query) {
|
|
|
var response,
|
|
|
request = new HttpRequest(),
|
|
|
url = Consul.params.api_endpoint + query;
|
|
|
|
|
|
request.addHeader('Content-Type: application/json');
|
|
|
request.addHeader('X-Consul-Token: ' + Consul.params.token);
|
|
|
|
|
|
Zabbix.log(4, '[ Consul ] Sending request: ' + url);
|
|
|
response = request.get(url);
|
|
|
|
|
|
Zabbix.log(4, '[ Consul ] Received response with status code ' + request.getStatus() + ': ' + response);
|
|
|
|
|
|
if (response !== null) {
|
|
|
try {
|
|
|
response = JSON.parse(response);
|
|
|
}
|
|
|
catch (error) {
|
|
|
throw 'Failed to parse response received from Consul Agent API.';
|
|
|
}
|
|
|
}
|
|
|
|
|
|
return {
|
|
|
status: request.getStatus(),
|
|
|
response: response
|
|
|
};
|
|
|
},
|
|
|
|
|
|
getServices: function () {
|
|
|
var result = Consul.request('v1/agent/services'),
|
|
|
services = [];
|
|
|
|
|
|
if (typeof result.response !== 'object' || result.status != 200) {
|
|
|
throw 'Cannot get service list from Consul Agent API.';
|
|
|
}
|
|
|
|
|
|
Object.keys(result.response).forEach(function (service) {
|
|
|
services.push(result.response[service]['ID']);
|
|
|
});
|
|
|
|
|
|
return services;
|
|
|
},
|
|
|
|
|
|
getServiceStats: function (service_id) {
|
|
|
var result = Consul.request('v1/agent/health/service/id/' + service_id);
|
|
|
|
|
|
if (typeof result.response !== 'object' || [200, 429, 503].indexOf(result.status) === -1) {
|
|
|
throw 'Cannot get service info from Consul Agent API.';
|
|
|
}
|
|
|
|
|
|
return result.response;
|
|
|
}
|
|
|
}
|
|
|
|
|
|
try {
|
|
|
Consul.setParams(JSON.parse(value));
|
|
|
|
|
|
var services = Consul.getServices(),
|
|
|
result = [];
|
|
|
|
|
|
services.forEach(function (service) {
|
|
|
var service_stats = Consul.getServiceStats(service);
|
|
|
|
|
|
result.push({
|
|
|
'id': service,
|
|
|
'name': service_stats['Service']['Service'],
|
|
|
'status': service_stats['AggregatedStatus'],
|
|
|
'checks': service_stats['Checks'],
|
|
|
'namespace': typeof service_stats['Service']['Namespace'] === 'undefined' ? 'None' : service_stats['Service']['Namespace']
|
|
|
});
|
|
|
});
|
|
|
|
|
|
return JSON.stringify(result);
|
|
|
}
|
|
|
catch (error) {
|
|
|
error += ((String(error).endsWith('.')) ? '' : '.');
|
|
|
Zabbix.log(3, '[ Consul ] ERROR: ' + error);
|
|
|
|
|
|
return JSON.stringify({error: error + ' Check debug log for more information.'});
|
|
|
}
|
|
|
description: 'Get all the services that are registered with the local agent and their status.'
|
|
|
timeout: 15s
|
|
|
parameters:
|
|
|
- name: api_endpoint
|
|
|
value: '{$CONSUL.NODE.API.URL}'
|
|
|
- name: token
|
|
|
value: '{$CONSUL.TOKEN}'
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raw
|
|
|
- uuid: f2fb4c76b4974319846d4773cfb64b0c
|
|
|
name: 'Consul: Get local services check'
|
|
|
type: DEPENDENT
|
|
|
key: consul.get_local_services.check
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
trends: '0'
|
|
|
value_type: CHAR
|
|
|
description: 'Data collection check.'
|
|
|
preprocessing:
|
|
|
- type: JSONPATH
|
|
|
parameters:
|
|
|
- $.error
|
|
|
error_handler: CUSTOM_VALUE
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
master_item:
|
|
|
key: consul.get_local_services
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: status
|
|
|
triggers:
|
|
|
- uuid: 5cf09b213c044033af1d8e1d8821bc38
|
|
|
expression: 'length(last(/HashiCorp Consul Node by HTTP/consul.get_local_services.check))>0'
|
|
|
name: 'Consul: Failed to get local services'
|
|
|
priority: WARNING
|
|
|
description: 'Failed to get local services. Check debug log for more information.'
|
|
|
tags:
|
|
|
- tag: scope
|
|
|
value: availability
|
|
|
- uuid: c0e199969c19444fb68fd8497fcab047
|
|
|
name: 'Consul: Get instance metrics'
|
|
|
type: HTTP_AGENT
|
|
|
key: consul.get_metrics
|
|
|
history: '0'
|
|
|
trends: '0'
|
|
|
value_type: TEXT
|
|
|
description: 'Get raw metrics from Consul instance /metrics endpoint.'
|
|
|
preprocessing:
|
|
|
- type: CHECK_NOT_SUPPORTED
|
|
|
parameters:
|
|
|
- ''
|
|
|
timeout: 15s
|
|
|
url: '{$CONSUL.NODE.API.URL}/v1/agent/metrics?format=prometheus'
|
|
|
headers:
|
|
|
- name: X-Consul-Token
|
|
|
value: '{$CONSUL.TOKEN}'
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: health
|
|
|
- tag: component
|
|
|
value: raw
|
|
|
- uuid: 7e2689de8d78499fb52d718989b7ec8b
|
|
|
name: 'Consul: Get node info'
|
|
|
type: HTTP_AGENT
|
|
|
key: consul.get_node_info
|
|
|
history: '0'
|
|
|
trends: '0'
|
|
|
value_type: TEXT
|
|
|
description: 'Get configuration and member information of the local agent.'
|
|
|
preprocessing:
|
|
|
- type: CHECK_NOT_SUPPORTED
|
|
|
parameters:
|
|
|
- ''
|
|
|
timeout: 15s
|
|
|
url: '{$CONSUL.NODE.API.URL}/v1/agent/self'
|
|
|
headers:
|
|
|
- name: X-Consul-Token
|
|
|
value: '{$CONSUL.TOKEN}'
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raw
|
|
|
- uuid: 2bcd79ab2c0a4ef88c0d2386d9bec1ff
|
|
|
name: 'Consul: Goroutine count'
|
|
|
type: DEPENDENT
|
|
|
key: consul.goroutines
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: 'The number of Goroutines on Consul instance.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- go_goroutines
|
|
|
- value
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: goroutines
|
|
|
- uuid: 6613be65c0794e76a210263810a4692d
|
|
|
name: 'Consul: KV store: apply, p50'
|
|
|
type: DEPENDENT
|
|
|
key: consul.kvs.apply.p50
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 50 percentile (median) for the time it takes to complete an update to the KV store.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_kvs_apply{quantile="0.5"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: kvs
|
|
|
- uuid: 2dc05550018c4d67bab58bd8f86bc365
|
|
|
name: 'Consul: KV store: apply, p90'
|
|
|
type: DEPENDENT
|
|
|
key: consul.kvs.apply.p90
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 90 percentile for the time it takes to complete an update to the KV store.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_kvs_apply{quantile="0.9"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: kvs
|
|
|
- uuid: 978bf96102d0411f8c18e92652a003c4
|
|
|
name: 'Consul: KV store: apply, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.kvs.apply.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'The number of updates to the KV store per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_kvs_apply_count
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: kvs
|
|
|
- uuid: 1b21a53ce7144350af8b50e57c3acf6b
|
|
|
name: 'Consul: Memberlist: degraded'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.degraded
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: |
|
|
|
This metric counts the number of times the Consul agent has performed failure detection on another agent at a slower probe rate.
|
|
|
The agent uses its own health metric as an indicator to perform this action.
|
|
|
If its health score is low, it means that the node is healthy, and vice versa.
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_memberlist_degraded
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: health
|
|
|
- uuid: 0a3b25abf7de4212bda5c92c13341593
|
|
|
name: 'Consul: Memberlist: gossip, p90'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.dispatch_log.p90
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'The 90 percentile for the number of gossips (messages) broadcasted to a set of randomly selected nodes.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_memberlist_gossip{quantile="0.9"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: gossip
|
|
|
- uuid: 592fb528d5c14491892c496f7ce9a60b
|
|
|
name: 'Consul: Memberlist: gossip, p50'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.gossip.p50
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 50 for the number of gossips (messages) broadcasted to a set of randomly selected nodes.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_memberlist_gossip{quantile="0.5"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: gossip
|
|
|
- uuid: 32259a799f6949e4be4f7d8722a2dbbe
|
|
|
name: 'Consul: Memberlist: health score'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.health_score
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: |
|
|
|
This metric describes a node's perception of its own health based on how well it is meeting the soft real-time requirements of the protocol.
|
|
|
This metric ranges from 0 to 8, where 0 indicates "totally healthy".
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_memberlist_health_score
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: health
|
|
|
triggers:
|
|
|
- uuid: f964a907c55148bf80991352c7f2ae83
|
|
|
expression: 'max(/HashiCorp Consul Node by HTTP/consul.memberlist.health_score,#3)>{$CONSUL.NODE.HEALTH_SCORE.MAX.HIGH}'
|
|
|
name: 'Consul: Node''s health score is critical'
|
|
|
event_name: 'Consul: Node''s health score is over {$CONSUL.NODE.HEALTH_SCORE.MAX.HIGH}'
|
|
|
priority: AVERAGE
|
|
|
description: |
|
|
|
This metric ranges from 0 to 8, where 0 indicates "totally healthy".
|
|
|
This health score is used to scale the time between outgoing probes, and higher scores translate into longer probing intervals.
|
|
|
For more details see section IV of the Lifeguard paper: https://arxiv.org/pdf/1707.00788.pdf
|
|
|
tags:
|
|
|
- tag: scope
|
|
|
value: availability
|
|
|
- uuid: 1fedc58f33ed4b9797fb37acfceba192
|
|
|
expression: 'max(/HashiCorp Consul Node by HTTP/consul.memberlist.health_score,#3)>{$CONSUL.NODE.HEALTH_SCORE.MAX.WARN}'
|
|
|
name: 'Consul: Node''s health score is warning'
|
|
|
event_name: 'Consul: Node''s health score is too high (over {$CONSUL.NODE.HEALTH_SCORE.MAX.WARN} for 3m)'
|
|
|
priority: WARNING
|
|
|
description: |
|
|
|
This metric ranges from 0 to 8, where 0 indicates "totally healthy".
|
|
|
This health score is used to scale the time between outgoing probes, and higher scores translate into longer probing intervals.
|
|
|
For more details see section IV of the Lifeguard paper: https://arxiv.org/pdf/1707.00788.pdf
|
|
|
dependencies:
|
|
|
- name: 'Consul: Node''s health score is critical'
|
|
|
expression: 'max(/HashiCorp Consul Node by HTTP/consul.memberlist.health_score,#3)>{$CONSUL.NODE.HEALTH_SCORE.MAX.HIGH}'
|
|
|
tags:
|
|
|
- tag: scope
|
|
|
value: availability
|
|
|
- uuid: 1ebba76d809b415488fb0591afeaef6f
|
|
|
name: 'Consul: Memberlist: msg alive'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.msg.alive
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: 'This metric counts the number of alive Consul agents, that the agent has mapped out so far, based on the message information given by the network layer.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_memberlist_msg_alive
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: health
|
|
|
- uuid: 9768a2ce01de4bfe92a17935791b4da4
|
|
|
name: 'Consul: Memberlist: msg dead'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.msg.dead
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: 'This metric counts the number of times a Consul agent has marked another agent to be a dead node.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_memberlist_msg_dead
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: health
|
|
|
- uuid: 43ea04dd91ba4c208e9ad09bbc0016af
|
|
|
name: 'Consul: Memberlist: msg suspect'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.msg.suspect
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: 'The number of times a Consul agent suspects another as failed while probing during gossip protocol.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_memberlist_msg_suspect
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: health
|
|
|
- uuid: 8b3ee806fcf34a46aa61cbfee460d9f7
|
|
|
name: 'Consul: Memberlist: probe node, p50'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.probe_node.p50
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 50 percentile (median) for the time taken to perform a single round of failure detection on a select Consul agent.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_memberlist_probeNode{quantile="0.5"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: memberlist
|
|
|
- uuid: 9a178ba5f7fa4d9a8ecfddfe84257ab6
|
|
|
name: 'Consul: Memberlist: probe node, p90'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.probe_node.p90
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 90 percentile for the time taken to perform a single round of failure detection on a select Consul agent.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_memberlist_probeNode{quantile="0.9"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: memberlist
|
|
|
- uuid: ef688e2ad7494a08a535c019fe19c0a9
|
|
|
name: 'Consul: Memberlist: push pull node, p50'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.push_pull_node.p50
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'The 50 percentile (median) for the number of Consul agents that have exchanged state with this agent.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_memberlist_pushPullNode{quantile="0.5"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: memberlist
|
|
|
- uuid: ae085470652242ba8a2077bebee7a2c7
|
|
|
name: 'Consul: Memberlist: push pull node, p90'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.push_pull_node.p90
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 90 percentile for the number of Consul agents that have exchanged state with this agent.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_memberlist_pushPullNode{quantile="0.9"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: memberlist
|
|
|
- uuid: a5d4e2e589564cc9898537c0a8c6a21a
|
|
|
name: 'Consul: TCP connections, accepted per second'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.tcp_accept
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: Rps
|
|
|
description: 'This metric counts the number of times a Consul agent has accepted an incoming TCP stream connection per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_memberlist_tcp_accept
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: tcp
|
|
|
- uuid: df0a553d811444d1ab767563a1d513a3
|
|
|
name: 'Consul: TCP connections, per second'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.tcp_connect
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: Rps
|
|
|
description: 'This metric counts the number of times a Consul agent has initiated a push/pull sync with an other agent per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_memberlist_tcp_connect
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: tcp
|
|
|
- uuid: ba12a6464199443d8d73164a8dd87f4f
|
|
|
name: 'Consul: TCP send bytes, per second'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.tcp_sent
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: Bps
|
|
|
description: 'This metric measures the total number of bytes sent by a Consul agent through the TCP protocol per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_memberlist_tcp_sent
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: tcp
|
|
|
- uuid: dde5f5c5c7d44f1dbbcddb4a541f41cc
|
|
|
name: 'Consul: UDP received bytes, per second'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.udp_received
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: Bps
|
|
|
description: 'This metric measures the total number of bytes received by a Consul agent through the UDP protocol per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_memberlist_udp_received
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: udp
|
|
|
- uuid: fa79687f332f4136881577838476c329
|
|
|
name: 'Consul: UDP sent bytes, per second'
|
|
|
type: DEPENDENT
|
|
|
key: consul.memberlist.udp_sent
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: Bps
|
|
|
description: 'This metric measures the total number of bytes sent by a Consul agent through the UDP protocol per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_memberlist_udp_sent
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: udp
|
|
|
- uuid: 59b28123e8154318aca6a283a1b18391
|
|
|
name: 'Consul: Open file descriptors, max'
|
|
|
type: DEPENDENT
|
|
|
key: consul.process_max_fds
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'Maximum number of open file descriptors.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- process_max_fds
|
|
|
- value
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: fds
|
|
|
- uuid: 38ad7b5d43004865bd823f1dae61395a
|
|
|
name: 'Consul: Open file descriptors'
|
|
|
type: DEPENDENT
|
|
|
key: consul.process_open_fds
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'Number of open file descriptors.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- process_open_fds
|
|
|
- value
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: fds
|
|
|
- uuid: 8cb242ddeb7f4a0685c706a24f1f85c5
|
|
|
name: 'Consul: RSS memory usage'
|
|
|
type: DEPENDENT
|
|
|
key: consul.resident_memory_bytes
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: B
|
|
|
description: 'Resident memory size in bytes.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- process_resident_memory_bytes
|
|
|
- value
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: memory
|
|
|
- uuid: ee52c7cd8a4d452d85564a47c44198a6
|
|
|
name: 'Consul: Role'
|
|
|
type: DEPENDENT
|
|
|
key: consul.role
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: 'Role of current Consul agent.'
|
|
|
valuemap:
|
|
|
name: 'Consul Node role'
|
|
|
preprocessing:
|
|
|
- type: JSONPATH
|
|
|
parameters:
|
|
|
- $.Config.Server
|
|
|
- type: BOOL_TO_DECIMAL
|
|
|
parameters:
|
|
|
- ''
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
master_item:
|
|
|
key: consul.get_node_info
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: consul
|
|
|
- uuid: e311c5bdba3e45b68887bc924c7dc206
|
|
|
name: 'Consul: Serf member: failed, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.serf.member.failed.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: |
|
|
|
Increments when an agent is marked dead.
|
|
|
This can be an indicator of overloaded agents, network problems, or configuration errors where agents cannot connect to each other on the required ports.
|
|
|
Shown as events per second.
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_serf_member_failed
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: serf
|
|
|
- uuid: 11ba84beb3494504bd514500ef663cff
|
|
|
name: 'Consul: Serf member: flap, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.serf.member.flap.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: |
|
|
|
Increments when an agent is marked dead and then recovers within a short time period.
|
|
|
This can be an indicator of overloaded agents, network problems, or configuration errors where agents cannot connect to each other on the required ports.
|
|
|
Shown as events per second.
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_serf_member_flap
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: serf
|
|
|
- uuid: f4c224ffb17d49029fef6647dde22c90
|
|
|
name: 'Consul: Serf member: join, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.serf.member.join.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: |
|
|
|
Increments when an agent joins the cluster. If an agent flapped or failed this counter also increments when it re-joins.
|
|
|
Shown as events per second.
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_serf_member_join
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: serf
|
|
|
- uuid: 3264823eb6774c2092b4ffe4638b61a5
|
|
|
name: 'Consul: Serf member: left, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.serf.member.left.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'Increments when an agent leaves the cluster. Shown as events per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_serf_member_left
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: serf
|
|
|
- uuid: 53bb4e76cd1840e8ae9a129d592e202e
|
|
|
name: 'Consul: Serf member: update, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.serf.member.update.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'Increments when a Consul agent updates. Shown as events per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_serf_member_update
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: serf
|
|
|
- uuid: 614e63c6eb254b45a5fb3dbb985c5c3c
|
|
|
name: 'Consul: Number of services'
|
|
|
type: DEPENDENT
|
|
|
key: consul.services_number
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: 'Number of services on current node.'
|
|
|
preprocessing:
|
|
|
- type: JSONPATH
|
|
|
parameters:
|
|
|
- $.Stats.agent.services
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
master_item:
|
|
|
key: consul.get_node_info
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: consul
|
|
|
- uuid: d9988aeda27f4fb09ececcde13efc71a
|
|
|
name: 'Consul: Snapshot: append line, p50'
|
|
|
type: DEPENDENT
|
|
|
key: consul.snapshot.append_line.p50
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 50 percentile (median) for the time taken by the Consul agent to append an entry into the existing log.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_serf_snapshot_appendLine{quantile="0.5"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: snapshot
|
|
|
- uuid: 0b701ec082e64eb19e60650c13cd44fd
|
|
|
name: 'Consul: Snapshot: append line, p90'
|
|
|
type: DEPENDENT
|
|
|
key: consul.snapshot.append_line.p90
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 90 percentile for the time taken by the Consul agent to append an entry into the existing log.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_serf_snapshot_appendLine{quantile="0.9"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: snapshot
|
|
|
- uuid: d56de8b09978421c9703fe327d03a32b
|
|
|
name: 'Consul: Snapshot: append line, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.snapshot.append_line.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'The number of snapshot appendLine operations per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_serf_snapshot_appendLine_count
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: snapshot
|
|
|
- uuid: 12e1a4538f124c4281106b9033b1592d
|
|
|
name: 'Consul: Snapshot: compact, p50'
|
|
|
type: DEPENDENT
|
|
|
key: consul.snapshot.compact.p50
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: |
|
|
|
The 50 percentile (median) for the time taken by the Consul agent to compact a log.
|
|
|
This operation occurs only when the snapshot becomes large enough to justify the compaction.
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_serf_snapshot_compact{quantile="0.5"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: snapshot
|
|
|
- uuid: c55de444dd30484eb116abfd6f28a9a0
|
|
|
name: 'Consul: Snapshot: compact, p90'
|
|
|
type: DEPENDENT
|
|
|
key: consul.snapshot.compact.p90
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: |
|
|
|
The 90 percentile for the time taken by the Consul agent to compact a log.
|
|
|
This operation occurs only when the snapshot becomes large enough to justify the compaction.
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_serf_snapshot_compact{quantile="0.9"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: snapshot
|
|
|
- uuid: 586be345685b4f0dbbb31f2062bebc01
|
|
|
name: 'Consul: Snapshot: compact, rate'
|
|
|
type: DEPENDENT
|
|
|
key: consul.snapshot.compact.rate
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'The number of snapshot compact operations per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_serf_snapshot_compact_count
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: snapshot
|
|
|
- uuid: 777e8cdd1cfc4f4bba613ef08320f1bb
|
|
|
name: 'Consul: Version'
|
|
|
type: DEPENDENT
|
|
|
key: consul.version
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
trends: '0'
|
|
|
value_type: CHAR
|
|
|
description: 'Version of Consul agent.'
|
|
|
preprocessing:
|
|
|
- type: JSONPATH
|
|
|
parameters:
|
|
|
- $.Config.Version
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
master_item:
|
|
|
key: consul.get_node_info
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: consul
|
|
|
triggers:
|
|
|
- uuid: fa78d269c01548a083085a3a98e5a59b
|
|
|
expression: 'last(/HashiCorp Consul Node by HTTP/consul.version,#1)<>last(/HashiCorp Consul Node by HTTP/consul.version,#2) and length(last(/HashiCorp Consul Node by HTTP/consul.version))>0'
|
|
|
name: 'Consul: Version has been changed'
|
|
|
event_name: 'Consul: Version has changed (new version: {ITEM.VALUE})'
|
|
|
priority: INFO
|
|
|
description: 'Consul version has changed. Acknowledge to close the problem manually.'
|
|
|
manual_close: 'YES'
|
|
|
tags:
|
|
|
- tag: scope
|
|
|
value: notice
|
|
|
- uuid: 62c0bb503c084f9da10f1be3c716608b
|
|
|
name: 'Consul: Virtual memory size'
|
|
|
type: DEPENDENT
|
|
|
key: consul.virtual_memory_bytes
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: B
|
|
|
description: 'Virtual memory size in bytes.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- process_virtual_memory_bytes
|
|
|
- value
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: memory
|
|
|
discovery_rules:
|
|
|
- uuid: 565c42fc4e444433aaafd656813b82f7
|
|
|
name: 'HTTP API methods discovery'
|
|
|
type: DEPENDENT
|
|
|
key: consul.http_api_discovery
|
|
|
delay: '0'
|
|
|
description: 'Discovery HTTP API methods specific metrics.'
|
|
|
item_prototypes:
|
|
|
- uuid: 4bdb2007bada4840aa453630e701059c
|
|
|
name: 'Consul: HTTP request: ["{#HTTP_METHOD}"], p50'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.http.api.p50["{#HTTP_METHOD}"]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 50 percentile (median) of how long it takes to service the given HTTP request for the given verb.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_api_http{method = "{#HTTP_METHOD}", quantile = "0.5"}'
|
|
|
- function
|
|
|
- sum
|
|
|
error_handler: DISCARD_VALUE
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: api
|
|
|
- tag: verb
|
|
|
value: '{#HTTP_METHOD}'
|
|
|
- uuid: 537b455889d54deab7ada216a89f1cb2
|
|
|
name: 'Consul: HTTP request: ["{#HTTP_METHOD}"], p90'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.http.api.p90["{#HTTP_METHOD}"]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 90 percentile of how long it takes to service the given HTTP request for the given verb.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_api_http{method = "{#HTTP_METHOD}", quantile = "0.9"}'
|
|
|
- function
|
|
|
- sum
|
|
|
error_handler: DISCARD_VALUE
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: api
|
|
|
- tag: verb
|
|
|
value: '{#HTTP_METHOD}'
|
|
|
- uuid: 53cdb47018df434381f7fc3e401a4dee
|
|
|
name: 'Consul: HTTP request: ["{#HTTP_METHOD}"], rate'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.http.api.rate["{#HTTP_METHOD}"]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: Rps
|
|
|
description: 'The number of HTTP request for the given verb per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_api_http_count{method = "{#HTTP_METHOD}"}'
|
|
|
- function
|
|
|
- sum
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: api
|
|
|
- tag: verb
|
|
|
value: '{#HTTP_METHOD}'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_TO_JSON
|
|
|
parameters:
|
|
|
- 'consul_api_http{method =~ ".*"}'
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- |
|
|
|
var lookup = {},
|
|
|
result = [];
|
|
|
|
|
|
JSON.parse(value).forEach(function (item) {
|
|
|
var http_method = item.labels.method;
|
|
|
if (!(lookup[http_method])) {
|
|
|
lookup[http_method] = 1;
|
|
|
result.push({ "{#HTTP_METHOD}": http_method });
|
|
|
}
|
|
|
})
|
|
|
|
|
|
return JSON.stringify(result);
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
- uuid: dd87920ea8184ec793229878407a0993
|
|
|
name: 'Local node services discovery'
|
|
|
type: DEPENDENT
|
|
|
key: consul.node_services_lld
|
|
|
delay: '0'
|
|
|
filter:
|
|
|
conditions:
|
|
|
- macro: '{#SERVICE_NAME}'
|
|
|
value: '{$CONSUL.LLD.FILTER.LOCAL_SERVICE_NAME.MATCHES}'
|
|
|
formulaid: A
|
|
|
- macro: '{#SERVICE_NAME}'
|
|
|
value: '{$CONSUL.LLD.FILTER.LOCAL_SERVICE_NAME.NOT_MATCHES}'
|
|
|
operator: NOT_MATCHES_REGEX
|
|
|
formulaid: B
|
|
|
- macro: '{#SERVICE_NAMESPACE}'
|
|
|
value: '{$CONSUL.LLD.FILTER.SERVICE_NAMESPACE.MATCHES}'
|
|
|
formulaid: C
|
|
|
- macro: '{#SERVICE_NAMESPACE}'
|
|
|
value: '{$CONSUL.LLD.FILTER.SERVICE_NAMESPACE.NOT_MATCHES}'
|
|
|
operator: NOT_MATCHES_REGEX
|
|
|
formulaid: D
|
|
|
description: 'Discover metrics for services that are registered with the local agent.'
|
|
|
item_prototypes:
|
|
|
- uuid: 44b0f82769d244d6a20b9ce0b5cc5cb6
|
|
|
name: 'Consul: ["{#SERVICE_NAME}"]: Aggregated status'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.service.aggregated_state["{#SERVICE_ID}"]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
discover: NO_DISCOVER
|
|
|
description: 'Aggregated values of all health checks for the service instance.'
|
|
|
valuemap:
|
|
|
name: 'Consul health state'
|
|
|
preprocessing:
|
|
|
- type: JSONPATH
|
|
|
parameters:
|
|
|
- '$[?(@.id == "{#SERVICE_ID}")].status.first()'
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- |
|
|
|
var state = ['passing', 'warning', 'critical'];
|
|
|
|
|
|
return state.indexOf(value.trim()) === -1 ? 255 : state.indexOf(value.trim());
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
master_item:
|
|
|
key: consul.get_local_services
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: service
|
|
|
- tag: namespace
|
|
|
value: '{#SERVICE_NAMESPACE}'
|
|
|
- tag: service
|
|
|
value: '{#SERVICE_NAME}'
|
|
|
trigger_prototypes:
|
|
|
- uuid: 661551e1e9e94b25b7bd6ea876640b6d
|
|
|
expression: 'last(/HashiCorp Consul Node by HTTP/consul.service.aggregated_state["{#SERVICE_ID}"]) = 2'
|
|
|
name: 'Consul: Aggregated status is ''critical'''
|
|
|
event_name: 'Consul: Node''s health score is over {$CONSUL.NODE.HEALTH_SCORE.MAX.HIGH}'
|
|
|
priority: AVERAGE
|
|
|
description: 'Aggregated state of service on the local agent is ''critical''.'
|
|
|
tags:
|
|
|
- tag: scope
|
|
|
value: availability
|
|
|
- uuid: 724f6a5e16f64a779a71ad9a9378fb60
|
|
|
expression: 'last(/HashiCorp Consul Node by HTTP/consul.service.aggregated_state["{#SERVICE_ID}"]) = 1'
|
|
|
name: 'Consul: Aggregated status is ''warning'''
|
|
|
priority: WARNING
|
|
|
description: 'Aggregated state of service on the local agent is ''warning''.'
|
|
|
tags:
|
|
|
- tag: scope
|
|
|
value: availability
|
|
|
- uuid: 20a0ec9e059548a192c9c37bd7aeaaed
|
|
|
name: 'Consul: ["{#SERVICE_NAME}"]: Check ["{#SERVICE_CHECK_NAME}"]: Output'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.service.check.output["{#SERVICE_ID}/{#SERVICE_CHECK_ID}"]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
trends: '0'
|
|
|
discover: NO_DISCOVER
|
|
|
value_type: CHAR
|
|
|
description: 'Current output of health check for the service.'
|
|
|
valuemap:
|
|
|
name: 'Consul health state'
|
|
|
preprocessing:
|
|
|
- type: JSONPATH
|
|
|
parameters:
|
|
|
- '$[?(@.id == "{#SERVICE_ID}")].checks[?(@.CheckID == "{#SERVICE_CHECK_ID}")].Output.first()'
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
master_item:
|
|
|
key: consul.get_local_services
|
|
|
tags:
|
|
|
- tag: check
|
|
|
value: '{#SERVICE_CHECK_NAME}'
|
|
|
- tag: component
|
|
|
value: service
|
|
|
- tag: namespace
|
|
|
value: '{#SERVICE_NAMESPACE}'
|
|
|
- tag: service
|
|
|
value: '{#SERVICE_NAME}'
|
|
|
- uuid: 3b67eb4df3dc4d9b9f4ab4c35a592367
|
|
|
name: 'Consul: ["{#SERVICE_NAME}"]: Check ["{#SERVICE_CHECK_NAME}"]: Status'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.service.check.state["{#SERVICE_ID}/{#SERVICE_CHECK_ID}"]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
discover: NO_DISCOVER
|
|
|
description: 'Current state of health check for the service.'
|
|
|
valuemap:
|
|
|
name: 'Consul health state'
|
|
|
preprocessing:
|
|
|
- type: JSONPATH
|
|
|
parameters:
|
|
|
- '$[?(@.id == "{#SERVICE_ID}")].checks[?(@.CheckID == "{#SERVICE_CHECK_ID}")].Status.first()'
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- |
|
|
|
var state = ['passing', 'warning', 'critical'];
|
|
|
|
|
|
return state.indexOf(value.trim()) === -1 ? 255 : state.indexOf(value.trim());
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
master_item:
|
|
|
key: consul.get_local_services
|
|
|
tags:
|
|
|
- tag: check
|
|
|
value: '{#SERVICE_CHECK_NAME}'
|
|
|
- tag: component
|
|
|
value: service
|
|
|
- tag: namespace
|
|
|
value: '{#SERVICE_NAMESPACE}'
|
|
|
- tag: service
|
|
|
value: '{#SERVICE_NAME}'
|
|
|
master_item:
|
|
|
key: consul.get_local_services
|
|
|
preprocessing:
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- |
|
|
|
var data = JSON.parse(value),
|
|
|
result = [];
|
|
|
|
|
|
if (data.length === 0) {
|
|
|
return '[]'
|
|
|
};
|
|
|
data.forEach(function (service) {
|
|
|
|
|
|
result.push({
|
|
|
'{#TYPE}': 'aggregated_status',
|
|
|
'{#SERVICE_NAME}': service.name,
|
|
|
'{#SERVICE_ID}': service.id,
|
|
|
'{#SERVICE_NAMESPACE}': service.namespace
|
|
|
});
|
|
|
|
|
|
if (service['checks'] !== 0) {
|
|
|
service['checks'].forEach(function (check) {
|
|
|
result.push({
|
|
|
'{#TYPE}': 'service_check',
|
|
|
'{#SERVICE_NAME}': service.name,
|
|
|
'{#SERVICE_ID}': service.id,
|
|
|
'{#SERVICE_NAMESPACE}': service.namespace,
|
|
|
'{#SERVICE_CHECK_ID}': check["CheckID"],
|
|
|
'{#SERVICE_CHECK_NAME}': check["Name"]
|
|
|
});
|
|
|
});
|
|
|
}
|
|
|
|
|
|
});
|
|
|
|
|
|
return JSON.stringify(result)
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
overrides:
|
|
|
- name: 'aggregated status'
|
|
|
step: '1'
|
|
|
filter:
|
|
|
conditions:
|
|
|
- macro: '{#TYPE}'
|
|
|
value: aggregated_status
|
|
|
formulaid: A
|
|
|
operations:
|
|
|
- operationobject: ITEM_PROTOTYPE
|
|
|
operator: LIKE
|
|
|
value: 'Aggregated status'
|
|
|
discover: DISCOVER
|
|
|
- operationobject: ITEM_PROTOTYPE
|
|
|
operator: LIKE
|
|
|
value: State
|
|
|
discover: DISCOVER
|
|
|
- name: checks
|
|
|
step: '2'
|
|
|
filter:
|
|
|
conditions:
|
|
|
- macro: '{#TYPE}'
|
|
|
value: service_check
|
|
|
formulaid: A
|
|
|
operations:
|
|
|
- operationobject: ITEM_PROTOTYPE
|
|
|
operator: LIKE
|
|
|
value: Check
|
|
|
discover: DISCOVER
|
|
|
- uuid: 6ff39fd6911945b2baa9b762d5a86df2
|
|
|
name: 'Raft leader metrics discovery'
|
|
|
type: DEPENDENT
|
|
|
key: consul.raft.leader.discovery
|
|
|
delay: '0'
|
|
|
description: 'Discover raft metrics for leader nodes.'
|
|
|
item_prototypes:
|
|
|
- uuid: 440e2a259cd64b918ebfb607961da2c8
|
|
|
name: 'Consul: Autopilot healthy'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.autopilot.healthy[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'Tracks the overall health of the local server cluster. 1 if all servers are healthy, 0 if one or more are unhealthy.'
|
|
|
valuemap:
|
|
|
name: 'Consul Autopilot healthy'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_autopilot_healthy
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: health
|
|
|
- uuid: 2e4fd6c5aac84054aef867fc9d8cb3c5
|
|
|
name: 'Consul: Raft state: commit time, p50'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.commit_time.p50[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 50 percentile (median) time it takes to commit a new entry to the raft log on the leader, in milliseconds.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_raft_commitTime{quantile="0.5"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
- uuid: 9428c07a23364967aef060cf3303b996
|
|
|
name: 'Consul: Raft state: commit time, p90'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.commit_time.p90[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 90 percentile time it takes to commit a new entry to the raft log on the leader, in milliseconds.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_raft_commitTime{quantile="0.9"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
- uuid: d54c97e8c4204f8c9f79911440f1bd13
|
|
|
name: 'Consul: Raft state: commit, rate'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.commit_time.rate[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: Rps
|
|
|
description: 'The number of commits a new entry to the Raft log on the leader per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_raft_commitTime_count
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
- uuid: 3c56ebe6e022430e861488873ac6f716
|
|
|
name: 'Consul: Raft state: dispatch log, p50'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.dispatch_log.p50[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 50 percentile (median) time it takes for the leader to write log entries to disk, in milliseconds.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_raft_leader_dispatchLog{quantile="0.5"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
- uuid: fd1e6c33254b467f8355491dc96889eb
|
|
|
name: 'Consul: Raft state: dispatch log, p90'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.dispatch_log.p90[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 90 percentile time it takes for the leader to write log entries to disk, in milliseconds.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_raft_leader_dispatchLog{quantile="0.9"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
- uuid: bc73aeda20a543ac957d1531f25fd5a9
|
|
|
name: 'Consul: Raft state: dispatch log, rate'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.dispatch_log.rate[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
description: 'The number of times a Raft leader writes a log to disk per second.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_raft_leader_dispatchLog_count
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
- uuid: 526a787732224555adde561ec86844fb
|
|
|
name: 'Consul: Raft state: leader last contact, p50'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.leader_last_contact.p50[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 50 percentile (median) of how long it takes a leader node to communicate with followers during a leader lease check, in milliseconds.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_raft_leader_lastContact{quantile="0.5"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
- uuid: 1ae3d9e4647b4972b1572946a2794715
|
|
|
name: 'Consul: Raft state: leader last contact, p90'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.leader_last_contact.p90[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: ms
|
|
|
description: 'The 90 percentile of how long it takes a leader node to communicate with followers during a leader lease check, in milliseconds.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- 'consul_raft_leader_lastContact{quantile="0.9"}'
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- 'return (isNaN(value)) ? 0 : value;'
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
master_item:
|
|
|
key: consul.get_node_info
|
|
|
preprocessing:
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- |
|
|
|
return JSON.stringify(JSON.parse(value)["Stats"]["leader"] === true
|
|
|
? [{'{#SINGLETON}': ''}] : []);
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
- uuid: f7dfc3d88f5440bea02080205d3f0a9b
|
|
|
name: 'Raft server metrics discovery'
|
|
|
type: DEPENDENT
|
|
|
key: consul.raft.server.discovery
|
|
|
delay: '0'
|
|
|
description: 'Discover raft metrics for server nodes.'
|
|
|
item_prototypes:
|
|
|
- uuid: 428f1d7924634383aabcd5b37f561a41
|
|
|
name: 'Consul: Raft: apply, rate'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.apply.rate[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
value_type: FLOAT
|
|
|
units: Rps
|
|
|
description: |
|
|
|
Incremented whenever a leader first passes a message into the Raft commit process (called an Apply operation).
|
|
|
This metric describes the arrival rate of new logs into Raft per second.
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_raft_apply
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
- type: CHANGE_PER_SECOND
|
|
|
parameters:
|
|
|
- ''
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
- uuid: 25dd098b98124fa8a9518963c8b4e5ce
|
|
|
name: 'Consul: Raft state'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.state[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
trends: '0'
|
|
|
value_type: CHAR
|
|
|
description: 'Current state of Consul agent.'
|
|
|
preprocessing:
|
|
|
- type: JSONPATH
|
|
|
parameters:
|
|
|
- $.Stats.raft.state
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
master_item:
|
|
|
key: consul.get_node_info
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
- uuid: 7b030c4eac68464e8c454577ab0f0f53
|
|
|
name: 'Consul: Raft state: candidate'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.state_candidate[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: 'The number of initiated leader elections.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_raft_state_candidate
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
- uuid: e89157e341d8409c96e31a9d541a7fe8
|
|
|
name: 'Consul: Raft state: leader'
|
|
|
type: DEPENDENT
|
|
|
key: 'consul.raft.state_leader[{#SINGLETON}]'
|
|
|
delay: '0'
|
|
|
history: 7d
|
|
|
description: 'Increments when a server becomes a leader.'
|
|
|
preprocessing:
|
|
|
- type: PROMETHEUS_PATTERN
|
|
|
parameters:
|
|
|
- consul_raft_state_leader
|
|
|
- value
|
|
|
- ''
|
|
|
error_handler: DISCARD_VALUE
|
|
|
master_item:
|
|
|
key: consul.get_metrics
|
|
|
tags:
|
|
|
- tag: component
|
|
|
value: raft
|
|
|
master_item:
|
|
|
key: consul.get_node_info
|
|
|
preprocessing:
|
|
|
- type: JAVASCRIPT
|
|
|
parameters:
|
|
|
- |
|
|
|
return JSON.stringify(JSON.parse(value)["Config"]["Server"] === true
|
|
|
? [{'{#SINGLETON}': ''}] : []);
|
|
|
- type: DISCARD_UNCHANGED_HEARTBEAT
|
|
|
parameters:
|
|
|
- 3h
|
|
|
tags:
|
|
|
- tag: class
|
|
|
value: software
|
|
|
- tag: target
|
|
|
value: consul
|
|
|
macros:
|
|
|
- macro: '{$CONSUL.LLD.FILTER.LOCAL_SERVICE_NAME.MATCHES}'
|
|
|
value: '.*'
|
|
|
description: 'Filter of discoverable discovered services on local node.'
|
|
|
- macro: '{$CONSUL.LLD.FILTER.LOCAL_SERVICE_NAME.NOT_MATCHES}'
|
|
|
value: 'CHANGE IF NEEDED'
|
|
|
description: 'Filter to exclude discovered services on local node.'
|
|
|
- macro: '{$CONSUL.LLD.FILTER.SERVICE_NAMESPACE.MATCHES}'
|
|
|
value: '.*'
|
|
|
description: 'Filter of discoverable discovered service by namespace on local node. Enterprise only, in case of Open Source version Namespace will be set to ''None''.'
|
|
|
- macro: '{$CONSUL.LLD.FILTER.SERVICE_NAMESPACE.NOT_MATCHES}'
|
|
|
value: 'CHANGE IF NEEDED'
|
|
|
description: 'Filter to exclude discovered service by namespace on local node. Enterprise only, in case of Open Source version Namespace will be set to ''None''.'
|
|
|
- macro: '{$CONSUL.NODE.API.URL}'
|
|
|
value: 'http://localhost:8500'
|
|
|
description: 'Consul instance URL.'
|
|
|
- macro: '{$CONSUL.NODE.HEALTH_SCORE.MAX.HIGH}'
|
|
|
value: '4'
|
|
|
description: 'Maximum acceptable value of node''s health score for AVERAGE trigger expression.'
|
|
|
- macro: '{$CONSUL.NODE.HEALTH_SCORE.MAX.WARN}'
|
|
|
value: '2'
|
|
|
description: 'Maximum acceptable value of node''s health score for WARNING trigger expression.'
|
|
|
- macro: '{$CONSUL.OPEN.FDS.MAX.WARN}'
|
|
|
value: '90'
|
|
|
description: 'Maximum percentage of used file descriptors.'
|
|
|
- macro: '{$CONSUL.TOKEN}'
|
|
|
value: '<PUT YOUR AUTH TOKEN>'
|
|
|
description: 'Consul auth token.'
|
|
|
valuemaps:
|
|
|
- uuid: 92638a6d5a9347edb011a8c999a9895e
|
|
|
name: 'Consul Autopilot healthy'
|
|
|
mappings:
|
|
|
- value: '0'
|
|
|
newvalue: Unhealthy
|
|
|
- value: '1'
|
|
|
newvalue: Healthy
|
|
|
- uuid: 1f966e7c41134551870c82f013f0b2cd
|
|
|
name: 'Consul health state'
|
|
|
mappings:
|
|
|
- value: '0'
|
|
|
newvalue: passing
|
|
|
- value: '1'
|
|
|
newvalue: warning
|
|
|
- value: '2'
|
|
|
newvalue: critical
|
|
|
- value: '255'
|
|
|
newvalue: unknown
|
|
|
- uuid: 8d8f7d7e37a44fe8ac590147f621cb4c
|
|
|
name: 'Consul Node role'
|
|
|
mappings:
|
|
|
- value: '0'
|
|
|
newvalue: Agent
|
|
|
- value: '1'
|
|
|
newvalue: Server
|
|
|
triggers:
|
|
|
- uuid: 9e1a0b7f49844d1db525d00d5f1060f0
|
|
|
expression: 'min(/HashiCorp Consul Node by HTTP/consul.process_open_fds,5m)/last(/HashiCorp Consul Node by HTTP/consul.process_max_fds)*100>{$CONSUL.OPEN.FDS.MAX.WARN}'
|
|
|
name: 'Consul: Current number of open files is too high'
|
|
|
event_name: 'Consul: Current number of open files is too high (over {$CONSUL.OPEN.FDS.MAX.WARN}% for 5m)'
|
|
|
priority: WARNING
|
|
|
description: '"Heavy file descriptor usage (i.e., near the process’s file descriptor limit) indicates a potential file descriptor exhaustion issue."'
|
|
|
tags:
|
|
|
- tag: scope
|
|
|
value: capacity
|
|
|
graphs:
|
|
|
- uuid: 2411147c0f4a425394a64fcd3dc231f0
|
|
|
name: 'Consul: Catalog operations'
|
|
|
graph_items:
|
|
|
- color: 199C0D
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.catalog.register.rate
|
|
|
- sortorder: '1'
|
|
|
color: F63100
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.catalog.deregister.rate
|
|
|
- uuid: 929c2527abaf447f9909003e6a43d799
|
|
|
name: 'Consul: File descriptors'
|
|
|
graph_items:
|
|
|
- drawtype: GRADIENT_LINE
|
|
|
color: 199C0D
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.process_open_fds
|
|
|
- sortorder: '1'
|
|
|
drawtype: BOLD_LINE
|
|
|
color: F63100
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.process_max_fds
|
|
|
- uuid: 6a987c1499f145ff8b68281f4fef3424
|
|
|
name: 'Consul: Memory usage'
|
|
|
graph_items:
|
|
|
- color: 199C0D
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.virtual_memory_bytes
|
|
|
- sortorder: '1'
|
|
|
color: F63100
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.resident_memory_bytes
|
|
|
- uuid: ba792478fe3140709a06a852560307fd
|
|
|
name: 'Consul: Serf member operations'
|
|
|
graph_items:
|
|
|
- color: 199C0D
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.serf.member.update.rate
|
|
|
- sortorder: '1'
|
|
|
color: F63100
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.serf.member.left.rate
|
|
|
- sortorder: '2'
|
|
|
color: 00611C
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.serf.member.join.rate
|
|
|
- sortorder: '3'
|
|
|
color: F7941D
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.serf.member.failed.rate
|
|
|
- sortorder: '4'
|
|
|
color: FC6EA3
|
|
|
item:
|
|
|
host: 'HashiCorp Consul Node by HTTP'
|
|
|
key: consul.serf.member.flap.rate
|
