Merge branch 'database-monitor' into 'master'

Add Postgres exporter queries configuration file

See merge request !1545

files/gitlab-config-template/gitlab.rb.template

@@ -1330,7 +1330,7 @@ external_url 'GENERATED_EXTERNAL_URL'
 ################################################################################
 # redis_exporter['enable'] = true
-# redis_exporter['log_directory'] = "/var/log/gitlab/redis-exporter"
+# redis_exporter['log_directory'] = '/var/log/gitlab/redis-exporter'
 # redis_exporter['flags'] = {
 #   'redis.addr' => "unix://#{node['gitlab']['gitlab-rails']['redis_socket']}",
 # }
@@ -1344,7 +1344,8 @@ external_url 'GENERATED_EXTERNAL_URL'
 ################################################################################
 # postgres_exporter['enable'] = true
-# postgres_exporter['log_directory'] = "/var/log/gitlab/postgres-exporter"
+# postgres_exporter['home'] = '/var/opt/gitlab/postgres-exporter'
+# postgres_exporter['log_directory'] = '/var/log/gitlab/postgres-exporter'
 # postgres_exporter['flags'] = {}
 # postgres_exporter['listen_address'] = 'localhost:9187'

files/gitlab-cookbooks/gitlab/attributes/default.rb

@@ -917,6 +917,7 @@ default['gitlab']['redis-exporter']['listen_address'] = 'localhost:9121'
 # Postgres exporter
 ###
 default['gitlab']['postgres-exporter']['enable'] = true
+default['gitlab']['postgres-exporter']['home'] = '/var/opt/gitlab/postgres-exporter'
 default['gitlab']['postgres-exporter']['log_directory'] = "/var/log/gitlab/postgres-exporter"
 default['gitlab']['postgres-exporter']['listen_address'] = 'localhost:9187'
 default['gitlab']['postgres-exporter']['env'] = {

files/gitlab-cookbooks/gitlab/libraries/prometheus.rb

@@ -108,9 +108,11 @@ module Prometheus
       default_config = Gitlab['node']['gitlab']['postgres-exporter'].to_hash
       user_config = Gitlab['postgres_exporter']
+      home_directory = user_config['home'] || default_config['home']
       listen_address = user_config['listen_address'] || default_config['listen_address']
       default_config['flags'] = {
         'web.listen-address' => listen_address,
+        'extend.query-path' => File.join(home_directory, 'queries.yaml'),
       }
       default_config['flags'].merge!(user_config['flags']) if user_config.key?('flags')

files/gitlab-cookbooks/gitlab/recipes/postgres-exporter.rb

@@ -19,6 +19,7 @@ account_helper = AccountHelper.new(node)
 postgresql_user = account_helper.postgresql_user
 postgres_exporter_log_dir = node['gitlab']['postgres-exporter']['log_directory']
 postgres_exporter_static_etc_dir = "/opt/gitlab/etc/postgres-exporter"
+postgres_exporter_dir = node['gitlab']['postgres-exporter']['home']
 directory postgres_exporter_log_dir do
   owner postgresql_user
@@ -26,6 +27,12 @@ directory postgres_exporter_log_dir do
   recursive true
 end
+directory postgres_exporter_dir do
+  owner postgresql_user
+  mode '0700'
+  recursive true
+end
+
 env_dir File.join(postgres_exporter_static_etc_dir, 'env') do
   variables node['gitlab']['postgres-exporter']['env']
   restarts ["service[postgres-exporter]"]
@@ -40,6 +47,12 @@ runit_service 'postgres-exporter' do
   log_options node['gitlab']['logging'].to_hash.merge(node['gitlab']['registry'].to_hash)
 end
+template File.join(postgres_exporter_dir, 'queries.yaml') do
+  source 'postgres-queries.yaml'
+  owner postgresql_user
+  mode '0644'
+end
+
 if node['gitlab']['bootstrap']['enable']
   execute "/opt/gitlab/bin/gitlab-ctl start postgres-exporter" do
     retries 20

files/gitlab-cookbooks/gitlab/templates/default/postgres-queries.yaml

+pg_replication:
+  query: "SELECT EXTRACT(EPOCH FROM (now() - pg_last_xact_replay_timestamp()))::INT as lag"
+  metrics:
+    - lag:
+        usage: "GAUGE"
+        description: "Replication lag behind master in seconds"
+
+pg_postmaster:
+  query: "SELECT pg_postmaster_start_time as start_time_seconds from pg_postmaster_start_time()"
+  metrics:
+    - start_time_seconds:
+        usage: "GAUGE"
+        description: "Time at which postmaster started"
+
+pg_settings_shared_buffers:
+  query: "SELECT 8192*setting::bigint as bytes from pg_settings where name = 'shared_buffers'"
+  metrics:
+    - bytes:
+        usage: "GAUGE"
+        description: "Size of shared_buffers"
+
+pg_settings_checkpoint:
+  query: "select (select setting::int from pg_settings where name = 'checkpoint_segments') as segments, (select setting::int from pg_settings where name = 'checkpoint_timeout') as timeout_seconds, (select setting::float from pg_settings where name = 'checkpoint_completion_target') as completion_target"
+  metrics:
+    - segments:
+        usage: "GAUGE"
+        description: "Number of checkpoint segments"
+    - timeout_seconds:
+        usage: "GAUGE"
+        description: "Checkpoint timeout in seconds"
+    - completion_target:
+        usage: "GAUGE"
+        description: "Checkpoint completion target, ranging from 0 to 1"
+
+pg_stat_user_tables:
+  query: "SELECT schemaname, relname, seq_scan, seq_tup_read, idx_scan, idx_tup_fetch, n_tup_ins, n_tup_upd, n_tup_del, n_tup_hot_upd, n_live_tup, n_dead_tup, n_mod_since_analyze, last_vacuum, last_autovacuum, last_analyze, last_autoanalyze, vacuum_count, autovacuum_count, analyze_count, autoanalyze_count FROM pg_stat_user_tables"
+  metrics:
+    - schemaname:
+        usage: "LABEL"
+        description: "Name of the schema that this table is in"
+    - relname:
+        usage: "LABEL"
+        description: "Name of this table"
+    - seq_scan:
+        usage: "COUNTER"
+        description: "Number of sequential scans initiated on this table"
+    - seq_tup_read:
+        usage: "COUNTER"
+        description: "Number of live rows fetched by sequential scans"
+    - idx_scan:
+        usage: "COUNTER"
+        description: "Number of index scans initiated on this table"
+    - idx_tup_fetch:
+        usage: "COUNTER"
+        description: "Number of live rows fetched by index scans"
+    - n_tup_ins:
+        usage: "COUNTER"
+        description: "Number of rows inserted"
+    - n_tup_upd:
+        usage: "COUNTER"
+        description: "Number of rows updated"
+    - n_tup_del:
+        usage: "COUNTER"
+        description: "Number of rows deleted"
+    - n_tup_hot_upd:
+        usage: "COUNTER"
+        description: "Number of rows HOT updated (i.e., with no separate index update required)"
+    - n_live_tup:
+        usage: "GAUGE"
+        description: "Estimated number of live rows"
+    - n_dead_tup:
+        usage: "GAUGE"
+        description: "Estimated number of dead rows"
+    - n_mod_since_analyze:
+        usage: "GAUGE"
+        description: "Estimated number of rows changed since last analyze"
+    - last_vacuum:
+        usage: "GAUGE"
+        description: "Last time at which this table was manually vacuumed (not counting VACUUM FULL)"
+    - last_autovacuum:
+        usage: "GAUGE"
+        description: "Last time at which this table was vacuumed by the autovacuum daemon"
+    - last_analyze:
+        usage: "GAUGE"
+        description: "Last time at which this table was manually analyzed"
+    - last_autoanalyze:
+        usage: "GAUGE"
+        description: "Last time at which this table was analyzed by the autovacuum daemon"
+    - vacuum_count:
+        usage: "COUNTER"
+        description: "Number of times this table has been manually vacuumed (not counting VACUUM FULL)"
+    - autovacuum_count:
+        usage: "COUNTER"
+        description: "Number of times this table has been vacuumed by the autovacuum daemon"
+    - analyze_count:
+        usage: "COUNTER"
+        description: "Number of times this table has been manually analyzed"
+    - autoanalyze_count:
+        usage: "COUNTER"
+        description: "Number of times this table has been analyzed by the autovacuum daemon"
+
+pg_stat_statements:
+  query: |
+    SELECT
+      pg_authid.rolname as user,
+      pg_database.datname as database,
+      pg_stat_statements.queryid,
+      left(pg_stat_statements.query,250) as query,
+      pg_stat_statements.calls,
+      pg_stat_statements.total_time as time_milliseconds,
+      pg_stat_statements.rows,
+      pg_stat_statements.shared_blks_hit,
+      pg_stat_statements.shared_blks_read,
+      pg_stat_statements.shared_blks_dirtied,
+      pg_stat_statements.shared_blks_written,
+      pg_stat_statements.temp_blks_read,
+      pg_stat_statements.temp_blks_written
+      FROM pg_stat_statements
+      JOIN pg_authid
+        ON pg_authid.oid = pg_stat_statements.userid
+      JOIN pg_database
+        ON pg_database.oid = pg_stat_statements.dbid
+  metrics:
+    - user:
+        usage: "LABEL"
+        description: "The user who executed the statement"
+    - dbid:
+        usage: "LABEL"
+        description: "The database in which the statement was executed"
+    - queryid:
+        usage: "LABEL"
+        description: "Internal hash code, computed from the statement's parse tree"
+    - query:
+        usage: "LABEL"
+        description: "Text of a representative statement (first 250 characters)"
+    - calls:
+        usage: "COUNTER"
+        description: "Number of times executed"
+    - time_milliseconds:
+        usage: "COUNTER"
+        description: "Total time spent in the statement, in milliseconds"
+    - rows:
+        usage: "COUNTER"
+        description: "Total number of rows retrieved or affected by the statement"
+    - shared_blks_hit:
+        usage: "COUNTER"
+        description: "Total number of shared block cache hits by the statement"
+    - shared_blks_read:
+        usage: "COUNTER"
+        description: "Total number of shared blocks read by the statement"
+    - shared_blks_dirtied:
+        usage: "COUNTER"
+        description: "Total number of shared blocks dirtied by the statement"
+    - shared_blks_written:
+        usage: "COUNTER"
+        description: "Total number of shared blocks written by the statement"
+    - temp_blks_read:
+        usage: "COUNTER"
+        description: "Total number of temp blocks read by the statement"
+    - temp_blks_written:
+        usage: "COUNTER"
+        description: "Total number of temp blocks written by the statement"

spec/chef/recipes/postgres_exporter_spec.rb

@@ -50,6 +50,11 @@ describe 'gitlab::postgres-exporter' do
         .with_content(/exec svlogd -tt \/var\/log\/gitlab\/postgres-exporter/)
     end
+    it 'creates the queries.yaml file' do
+      expect(chef_run).to render_file('/var/opt/gitlab/postgres-exporter/queries.yaml')
+        .with_content(/pg_replication:/)
+    end
+
     it 'creates default set of directories' do
       expect(chef_run).to create_directory('/var/log/gitlab/postgres-exporter').with(
         owner: 'gitlab-psql',
@@ -60,7 +65,10 @@ describe 'gitlab::postgres-exporter' do
     it 'sets default flags' do
       expect(chef_run).to render_file('/opt/gitlab/sv/postgres-exporter/run')
-        .with_content(/web.listen-address=localhost:9187/)
+        .with_content { |content|
+          expect(content).to match(/web.listen-address=localhost:9187/)
+          expect(content).to match(/extend.query-path=\/var\/opt\/gitlab\/postgres-exporter\/queries.yaml/)
+        }
     end
   end