### SSH define service { use generic-service service_description SSH - pageable hostgroup_name pageable_servers check_command check_ssh contact_groups page_admins } define service { use generic-service service_description SSH hostgroup_name not_pageable_servers check_command check_ssh contact_groups admins } define service { use generic-service service_description SSH for flaky machines hostgroup_name flaky_servers check_command check_ssh normal_check_interval 2 retry_check_interval 2 max_check_attempts 5 contact_groups admins } ### Disk usage define service { use generic-service service_description Disk usage - pageable hostgroup_name pageable_servers check_command check_remote_disk!20%!10% contact_groups ops_message } define service { use generic-service service_description Disk usage hostgroup_name not_pageable_servers check_command check_remote_disk!20%!10% contact_groups ops_message } define service { use generic-service service_description Disk usage for flaky machines hostgroup_name flaky_servers check_command check_remote_disk!20%!10% normal_check_interval 2 retry_check_interval 2 max_check_attempts 5 contact_groups admins } ### System updates define service { use generic-service service_description Debian update availability hostgroup_name all check_command check_debian_packages!22 contact_groups admins } ### NTP define service { use generic-service service_description Check AWS NTP time hostgroup_name aws_host check_command check_ntp_time!22!169.254.169.123 max_check_attempts 3 contact_groups admins } define service { use generic-service service_description Check non-AWS NTP time hostgroup_name non_aws_host check_command check_ntp_time!22!pool.ntp.org max_check_attempts 5 contact_groups admins } ### Service groups #### Application frontends define service { use generic-service service_description HTTPS hostgroup_name prod_frontends, fullstack check_command check_https_status contact_groups page_admins } define service { use generic-service service_description HTTPS hostgroup_name staging_frontends check_command check_https_status contact_groups ops_message } define service { use generic-service service_description Check send receive time hostgroup_name prod_frontends, fullstack check_command check_send_receive_time!22 max_check_attempts 2 contact_groups page_admins } define service { use generic-service service_description Check send receive time hostgroup_name staging_frontends check_command check_send_receive_time!22 max_check_attempts 2 contact_groups ops_message } define service { use generic-service service_description Check analytics state hostgroup_name prod_frontends check_command check_analytics_state!22 max_check_attempts 2 contact_groups admins } #### PostgreSQL define service { use generic-service service_description Check PostgreSQL connection hostgroup_name postgresql check_command check_postgres!zulip!nagios!connection contact_groups page_admins } define service { use generic-service service_description Check PostgreSQL autovac_freeze hostgroup_name postgresql check_command check_postgres_alert_args!zulip!nagios!autovac_freeze!101%!105% contact_groups admins } define service { use generic-service service_description Check PostgreSQL backends hostgroup_name postgresql check_command check_postgres!zulip!nagios!backends contact_groups admins } define service { use generic-service service_description Check PostgreSQL disabled triggers hostgroup_name postgresql check_command check_postgres!zulip!nagios!disabled_triggers contact_groups admins } define service { use generic-service service_description Check PostgreSQL hitratio hostgroup_name postgresql check_command check_postgres!zulip!nagios!hitratio contact_groups admins } # define service { # use generic-service # service_description Check PostgreSQL locks # hostgroup_name postgresql # check_command check_postgres_alert_args!zulip!nagios!locks!400!600 # contact_groups admins # } define service { use generic-service service_description Check PostgreSQL query_time hostgroup_name postgresql check_command check_postgres_alert_args!zulip!nagios!query_time!20 seconds!40 seconds contact_groups admins } define service { use generic-service service_description Check PostgreSQL sequence hostgroup_name postgresql check_command check_postgres!zulip!nagios!sequence contact_groups admins } define service { use generic-service service_description Check PostgreSQL timesync hostgroup_name postgresql check_command check_postgres!zulip!nagios!timesync contact_groups admins } # define service { # use generic-service # service_description Check PostgreSQL txn_idle # hostgroup_name postgresql # check_command check_postgres_alert_args!zulip!nagios!txn_idle!20 seconds!40 seconds # contact_groups admins # } define service { use generic-service service_description Check PostgreSQL txn_time hostgroup_name postgresql check_command check_postgres_alert_args!zulip!nagios!txn_time!20 seconds!40 seconds contact_groups admins } define service { use generic-service service_description Check FTS update log length hostgroup_name postgresql_primary check_command check_fts_update_log contact_groups admins } define service { use generic-service service_description Check PostgreSQL replication lag hostgroup_name postgresql_primary, postgresql_replica check_command check_postgresql_replication_lag contact_groups admins } #### Redis define service { use generic-service service_description Check redis service # Both redis and frontends hostgroups, since frontends SSH proxy redis to themselves hostgroup_name prod_frontends, fullstack, redis check_command check_redis_ssh!22 max_check_attempts 3 contact_groups page_admins } define service { use generic-service service_description Check redis service hostgroup_name staging_frontends check_command check_redis_ssh!22 max_check_attempts 3 contact_groups ops_message } #### RabbitMQ / queue workers define service { use generic-service service_description Check RabbitMQ queue sizes hostgroup_name prod_frontends, fullstack check_command check_rabbitmq_queues!22 # Workaround weird checks 40s after first error causing alerts # from a single failure because cron hasn't run again yet max_check_attempts 3 contact_groups page_admins_and_warn_czo } define service { use generic-service service_description Check RabbitMQ queue sizes hostgroup_name staging_frontends check_command check_rabbitmq_queues!22 # Workaround weird checks 40s after first error causing alerts # from a single failure because cron hasn't run again yet max_check_attempts 3 contact_groups ops_message } define service { name rabbitmq-consumer-service use generic-service service_description RabbitMQ consumer check template hostgroup_name frontends # Workaround weird checks 40s after first error causing alerts # from a single failure because cron hasn't run again yet max_check_attempts 3 contact_groups admins register 0 } define service { use rabbitmq-consumer-service service_description Check RabbitMQ notify_tornado consumers hostgroup_name prod_frontends, fullstack check_command check_rabbitmq_consumers!notify_tornado contact_groups page_admins } define service { use rabbitmq-consumer-service service_description Check RabbitMQ notify_tornado consumers hostgroup_name staging_frontends check_command check_rabbitmq_consumers!notify_tornado contact_groups admins } define service { use rabbitmq-consumer-service service_description Check RabbitMQ deferred_work consumers check_command check_rabbitmq_consumers!deferred_work } define service { use rabbitmq-consumer-service service_description Check RabbitMQ digest digest_emails consumers check_command check_rabbitmq_consumers!digest_emails } define service { use rabbitmq-consumer-service service_description Check RabbitMQ email_mirror consumers check_command check_rabbitmq_consumers!email_mirror } define service { use rabbitmq-consumer-service service_description Check RabbitMQ email_senders consumers check_command check_rabbitmq_consumers!email_senders } define service { use rabbitmq-consumer-service service_description Check RabbitMQ deferred_email_senders consumers check_command check_rabbitmq_consumers!deferred_email_senders } define service { use rabbitmq-consumer-service service_description Check RabbitMQ embed_links consumers check_command check_rabbitmq_consumers!embed_links } define service { use rabbitmq-consumer-service service_description Check RabbitMQ embedded_bots consumers check_command check_rabbitmq_consumers!embedded_bots } define service { use rabbitmq-consumer-service service_description Check RabbitMQ missedmessage_emails consumers check_command check_rabbitmq_consumers!missedmessage_emails } define service { use rabbitmq-consumer-service service_description Check RabbitMQ missedmessage_mobile_notifications consumers check_command check_rabbitmq_consumers!missedmessage_mobile_notifications } define service { use rabbitmq-consumer-service service_description Check RabbitMQ outgoing_webhooks consumers check_command check_rabbitmq_consumers!outgoing_webhooks } define service { use rabbitmq-consumer-service service_description Check RabbitMQ soft_reactivation consumers check_command check_rabbitmq_consumers!soft_reactivation } define service { use rabbitmq-consumer-service service_description Check RabbitMQ thumbnail consumers check_command check_rabbitmq_consumers!thumbnail } define service { use rabbitmq-consumer-service service_description Check RabbitMQ user_activity consumers check_command check_rabbitmq_consumers!user_activity } define service { use rabbitmq-consumer-service service_description Check RabbitMQ user_activity_interval consumers check_command check_rabbitmq_consumers!user_activity_interval } define service { use generic-service service_description Check worker memory usage hostgroup_name frontends check_command check_worker_memory contact_groups admins } define service { use generic-service service_description Check for queue worker errors. hostgroup_name frontends check_command check_queue_worker_errors!22 contact_groups admins } ### Smokescreen define service { use generic-service service_description Check Smokescreen proxy hostgroup_name smokescreen check_command check_proxy_status contact_groups page_admins }