gitlab-org--gitlab-foss/lib/gitlab/prometheus_client.rb

200 lines
6.1 KiB
Ruby
Raw Normal View History

# frozen_string_literal: true
module Gitlab
# Helper methods to interact with Prometheus network services & resources
class PrometheusClient
include Gitlab::Utils::StrongMemoize
2018-02-23 12:58:40 -05:00
Error = Class.new(StandardError)
ConnectionError = Class.new(Gitlab::PrometheusClient::Error)
UnexpectedResponseError = Class.new(Gitlab::PrometheusClient::Error)
2018-02-23 12:58:40 -05:00
QueryError = Class.new(Gitlab::PrometheusClient::Error)
HEALTHY_RESPONSE = "Prometheus is Healthy.\n"
2018-02-23 12:58:40 -05:00
# Target number of data points for `query_range`.
# Please don't exceed the limit of 11000 data points
# See https://github.com/prometheus/prometheus/blob/91306bdf24f5395e2601773316945a478b4b263d/web/api/v1/api.go#L347
QUERY_RANGE_DATA_POINTS = 600
# Minimal value of the `step` parameter for `query_range` in seconds.
QUERY_RANGE_MIN_STEP = 60
# Key translation between RestClient and Gitlab::HTTP (HTTParty)
RESTCLIENT_GITLAB_HTTP_KEYMAP = {
ssl_cert_store: :cert_store
}.freeze
attr_reader :api_url, :options
private :api_url, :options
def initialize(api_url, options = {})
@api_url = api_url.chomp('/')
@options = options
end
def ping
json_api_get('query', query: '1')
end
def healthy?
response_body = handle_management_api_response(get(health_url, {}))
# From Prometheus docs: This endpoint always returns 200 and should be used to check Prometheus health.
response_body == HEALTHY_RESPONSE
end
def ready?
response = get(ready_url, {})
# From Prometheus docs: This endpoint returns 200 when Prometheus is ready to serve traffic (i.e. respond to queries).
response.code == 200
rescue StandardError => e
raise PrometheusClient::UnexpectedResponseError, "#{e.message}"
end
def proxy(type, args)
path = api_path(type)
get(path, args)
rescue Gitlab::HTTP::ResponseError => ex
raise PrometheusClient::ConnectionError, "Network connection error" unless ex.response && ex.response.try(:code)
handle_querying_api_response(ex.response)
end
2017-05-09 00:15:34 -04:00
def query(query, time: Time.now)
get_result('vector') do
json_api_get('query', query: query, time: time.to_f)
end
end
def query_range(query, start_time: 8.hours.ago, end_time: Time.now)
start_time = start_time.to_f
end_time = end_time.to_f
step = self.class.compute_step(start_time, end_time)
get_result('matrix') do
json_api_get(
'query_range',
query: query,
start: start_time,
end: end_time,
step: step
)
end
end
# Queries Prometheus with the given aggregate query and groups the results by mapping
# metric labels to their respective values.
#
# @return [Hash] mapping labels to their aggregate numeric values, or the empty hash if no results were found
def aggregate(aggregate_query, time: Time.now, transform_value: :to_f)
response = query(aggregate_query, time: time)
response.to_h do |result|
key = block_given? ? yield(result['metric']) : result['metric']
_timestamp, value = result['value']
[key, value.public_send(transform_value)] # rubocop:disable GitlabSecurity/PublicSend
end
end
2017-06-05 15:00:57 -04:00
def label_values(name = '__name__')
json_api_get("label/#{name}/values")
end
def series(*matches, start_time: 8.hours.ago, end_time: Time.now)
json_api_get('series', 'match': matches, start: start_time.to_f, end: end_time.to_f)
end
def self.compute_step(start_time, end_time)
diff = end_time - start_time
step = (diff / QUERY_RANGE_DATA_POINTS).ceil
[QUERY_RANGE_MIN_STEP, step].max
end
def health_url
"#{api_url}/-/healthy"
end
def ready_url
"#{api_url}/-/ready"
end
private
def api_path(type)
[api_url, 'api', 'v1', type].join('/')
end
def json_api_get(type, args = {})
path = api_path(type)
response = get(path, args)
handle_querying_api_response(response)
rescue Gitlab::HTTP::ResponseError => ex
raise PrometheusClient::ConnectionError, "Network connection error" unless ex.response && ex.response.try(:code)
handle_querying_api_response(ex.response)
end
def gitlab_http_key(key)
RESTCLIENT_GITLAB_HTTP_KEYMAP[key] || key
end
def mapped_options
options.keys.to_h { |k| [gitlab_http_key(k), options[k]] }
end
def http_options
strong_memoize(:http_options) do
{ follow_redirects: false }.merge(mapped_options)
Squashed commit of the following: commit 22e1cb8f4b98f71d21026f69aa3e68d79946d6ae Merge: 766a42a9639 e966c6aea25 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Fri Feb 23 21:30:46 2018 +0100 Merge remote-tracking branch 'upstream/master' into 38783-add-cluster-metrics.yml # Conflicts: # app/controllers/projects/prometheus/metrics_controller.rb # app/controllers/projects/prometheus_controller.rb # app/models/project_services/prometheus_service.rb # lib/gitlab/prometheus/queries/query_additional_metrics.rb # spec/controllers/projects/prometheus/metrics_controller_spec.rb # spec/models/project_services/prometheus_service_spec.rb commit 766a42a96393f502d439c1f0beb0b6cfb2c228d4 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Fri Feb 23 17:58:45 2018 +0100 Move prometheus adapter to app/models/concerns commit ca84eed49811cf3064a2e5ea611af1c947c590d7 Merge: 66702099586 cb504cedc2a Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Fri Feb 23 15:36:03 2018 +0100 Merge remote-tracking branch 'upstream/backport_custom_metrics_ce_components' into 38783-add-cluster-metrics.yml + fix failing tests # Conflicts: # app/controllers/projects/prometheus_controller.rb # app/models/project_services/prometheus_service.rb # lib/gitlab/prometheus/queries/query_additional_metrics.rb # spec/models/project_services/prometheus_service_spec.rb commit cb504cedc2a6e353ffb56833334681e3da09fc14 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Fri Feb 23 14:46:15 2018 +0100 Fix prometheus_service found by find_or_initialize_service commit 928b84c72c2c4c46e1785b9a943c1822a137de16 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 22 23:15:11 2018 +0100 additional metrics and backported tests commit 41291383b4b6976af94eaf9e1a7b2e2a172310e7 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 22 21:57:45 2018 +0100 Introduce Metrics controller and retire prometheus controller commit 6e7492e4c7ffa9d8621f09198071bc14be875976 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 22 21:46:37 2018 +0100 Backport PrometheusClient::Error and all->common_metrics rename commit 66702099586c864a7f78970a0ee0dd9f3c2beeef Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 22 20:23:03 2018 +0100 fix failing tests commit ce921ea723cde61b2441ba98c9aca97606c719c8 Author: Mike Greiling <mike@pixelcog.com> Date: Wed Feb 21 23:47:30 2018 -0600 add labels to cluster metrics commit 993830c6892e4fbf53d3f72da00002d642c7e9b2 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 22 01:20:49 2018 +0100 Fix formatting probelms and few small tests commit 66ee65d8e3f747c90d986bc3056178422156bc8e Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 22 01:08:03 2018 +0100 stop using in deployment tests environment.id commit 62c91978d15f0369988521363dae24bd7510d68d Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 22 01:06:33 2018 +0100 fix prometheus_controller and adapter tests commit 977b1d34c1d03c7233582e8328f85caf634895ed Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 22 00:19:39 2018 +0100 finish up active? -> can_query? rename commit e614f7daee58a9758d83ba3efe1649c8b80bc1e2 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Wed Feb 21 23:51:33 2018 +0100 deployment prometheus adapter tests fix commit ebd726c114a6026fef0adf3eba6ee1972530148a Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Wed Feb 21 21:40:40 2018 +0100 Move environment dependant tests to environment commit 6d31311cd3729c29233283dded70e03a4a9a3c97 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Wed Feb 21 20:40:24 2018 +0100 update monitoring service and move adding dpeloyment_time to deployment model commit 60b6bf391ab36846dce122bc6b0c5196a186267c Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Wed Feb 21 20:15:46 2018 +0100 adjust deployment spec and prometheus specs commit 6681662cf1c028aff2ff94aa0501732cb7119ba1 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 22:30:20 2018 +0100 Revert changes to reactive caching commit e282f86c45a056889f57d3f7fd23a81c88efff6a Merge: 5751c73df59 6844a2df873 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 22:08:17 2018 +0100 Merge remote-tracking branch 'upstream/master' into 38783-add-cluster-metrics.yml commit 5751c73df59d0a03840a1b4b71b0637670f971a6 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 22:07:43 2018 +0100 rename active? to can_query? and cleanup environment prometheus router commit 3f3c6e1d33dcd9315979daf26a95f2aab83a7de9 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 21:51:43 2018 +0100 Fix tests, and only use prometheus service if its active commit 6345838bac584c213b665d334252ccab202cb271 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 16:24:27 2018 +0100 Fix typo commit 7a585d32afe8da050b5615b1d036a550e06479f5 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 15:29:40 2018 +0100 Cluster id is not required commit e6af62afb11fa380f6aff1c31a81bcc9bab3b1eb Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 15:15:46 2018 +0100 Result transformation support commit f3b1bd7c67894f44efe33591ddb70093bd620c03 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 15:07:07 2018 +0100 Fix rubocop warning and exten cluster query timeframe commit be77947cea64261a4d3dead33c3c57f413a9880c Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 14:42:47 2018 +0100 Fix additional metrics test commit eb3922e16221abe16f59fae1c38122f227643343 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 14:34:44 2018 +0100 rename prometheus adapter methods commit 045476cd08b21593818b274ae8a44d19b705523f Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 13:19:36 2018 +0100 Make prometheus adapter a module commit f2daf050d8c689f72c4c61207930bc53c331f12e Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 20 12:00:44 2018 +0100 refactoring wip commit 52e4ef5587794e811dc10a0f2dca522342a865da Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Sun Feb 18 20:25:55 2018 +0100 cleanup prometheus adapter concept commit 3887365faab9dfcd9c00bcfc501d09ac62431a03 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Sun Feb 18 19:22:11 2018 +0100 Refactor out deployment id, Rename PrometheusQuerier to PrometheusAdapter commit aa2fc2df57bd72c9a5e94f66d1f1e23990be6c3f Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Fri Feb 16 23:59:54 2018 +0100 Refactor prometheus client commit e43c1ca9d9874d6cf1569f40fa1aca158d9d5d91 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 15 20:24:45 2018 +0100 Use initial version of cluster_metrics.yml commit 867821ce0b2609ebf8994220aa8e3a94d66a01e0 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 15 05:24:14 2018 +0100 Fix querying cluster metrics commit 1601e002a064cbb10ffe110a19433c5662858f1d Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 15 04:49:03 2018 +0100 Queues for unicersal querier commit 5db198fdc925c0223be24939b76da1d544dd569c Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 15 03:35:17 2018 +0100 refactor reactive caching and prometheus querying commit b0fc00e8c9d21e961ef44b0129103e2a62928b52 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Thu Feb 15 00:12:03 2018 +0100 Add generic query additional metrics commit ffe76e6a9ba196bccff22c4880e0384959ad5e48 Author: Pawel Chojnacki <pawel@chojnacki.ws> Date: Tue Feb 13 15:40:15 2018 +0100 Cluster Metric yml initial + Remove cluster query + remove cluster_metrics.yml + Prometheus adapter tests
2018-02-23 15:33:33 -05:00
end
end
def get(path, args)
Gitlab::HTTP.get(path, { query: args }.merge(http_options) )
rescue SocketError
raise PrometheusClient::ConnectionError, "Can't connect to #{api_url}"
rescue OpenSSL::SSL::SSLError
raise PrometheusClient::ConnectionError, "#{api_url} contains invalid SSL data"
rescue Errno::ECONNREFUSED
raise PrometheusClient::ConnectionError, 'Connection refused'
end
def handle_management_api_response(response)
if response.code == 200
response.body
else
raise PrometheusClient::UnexpectedResponseError, "#{response.code} - #{response.body}"
end
end
def handle_querying_api_response(response)
response_code = response.try(:code)
response_body = response.try(:body)
raise PrometheusClient::UnexpectedResponseError, "#{response_code} - #{response_body}" unless response_code
json_data = parse_json(response_body) if [200, 400].include?(response_code)
2018-01-03 21:13:54 -05:00
case response_code
when 200
json_data['data'] if response['status'] == 'success'
when 400
2018-02-23 12:58:40 -05:00
raise PrometheusClient::QueryError, json_data['error'] || 'Bad data received'
else
raise PrometheusClient::UnexpectedResponseError, "#{response_code} - #{response_body}"
end
end
def get_result(expected_type)
data = yield
data['result'] if data['resultType'] == expected_type
end
def parse_json(response_body)
Gitlab::Json.parse(response_body, legacy_mode: true)
rescue JSON::ParserError
raise PrometheusClient::UnexpectedResponseError, 'Parsing response failed'
end
end
end