# Telegraf Configuration for gNMI Streaming Telemetry
# Collects interface counters and data rates from IOS-XR routers

[global_tags]

[agent]
  interval = "10s"
  round_interval = true
  metric_batch_size = 1000
  metric_buffer_limit = 10000
  collection_jitter = "0s"
  flush_interval = "10s"
  flush_jitter = "0s"
  precision = "0s"

###############################################################################
#                            INPUT PLUGINS                                    #
###############################################################################

## gNMI targets — driven by environment variables so the telemetry fleet can
## scale without editing this file. Set in .env:
##   GNMI_ADDRESSES — quoted, comma-separated host:port list, e.g.
##     GNMI_ADDRESSES="10.0.0.1:57400", "10.0.0.2:57400"
##   GNMI_USERNAME / GNMI_PASSWORD — gNMI credentials (uniform across the fleet)
## Every target must have gNMI/grpc enabled and be reachable on the gRPC port.
[[inputs.gnmi]]
  addresses = [ ${GNMI_ADDRESSES} ]
  username = "${GNMI_USERNAME}"
  password = "${GNMI_PASSWORD}"

  ## No TLS (lab environment)
  enable_tls = false

  ## Use json_ietf encoding (supported by IOS-XR 24.3.1)
  encoding = "json_ietf"

  ## Redial in case of failures after
  redial = "10s"

  ## OpenConfig interface counters (bytes, packets, errors, discards)
  [[inputs.gnmi.subscription]]
    name = "interface_counters"
    origin = "openconfig-interfaces"
    path = "/interfaces/interface/state/counters"
    subscription_mode = "sample"
    sample_interval = "10s"

  ## OpenConfig interface state (admin/oper status, description, type)
  [[inputs.gnmi.subscription]]
    name = "interface_state"
    origin = "openconfig-interfaces"
    path = "/interfaces/interface/state"
    subscription_mode = "sample"
    sample_interval = "30s"

## Docker container resource metrics — CPU, memory (incl. limit + %), network,
## and block IO for every obmp-* container. Surfaces resource pressure (e.g. a
## container approaching its mem_limit) before it OOM-crashes.
[[inputs.docker]]
  endpoint = "unix:///var/run/docker.sock"
  gather_services = false
  container_name_include = ["obmp-*"]
  perdevice = false
  total = true
  timeout = "10s"

## Host filesystem usage — free/used space on the volumes holding the
## Postgres data, Kafka, InfluxDB and the OpenBMP data root. The host root is
## bind-mounted read-only at /hostfs and HOST_MOUNT_PREFIX / HOST_PROC (set in
## docker-compose.yml) point the plugin at the host, not the container.
[[inputs.disk]]
  interval = "60s"
  ignore_fs = ["tmpfs", "devtmpfs", "devfs", "overlay", "aufs", "squashfs", "ramfs", "nsfs", "iso9660"]

## PostgreSQL database + table sizes — tracks RIB growth, which expands
## sharply once the full-table GoBGP feed is ingesting (~1M routes).
[[inputs.postgresql_extensible]]
  interval = "60s"
  address = "host=localhost port=5432 user=openbmp password=${POSTGRES_PASSWORD} dbname=openbmp sslmode=disable"
  [[inputs.postgresql_extensible.query]]
    sqlquery = "SELECT datname, pg_database_size(datname) AS bytes FROM pg_database WHERE datname = 'openbmp'"
    measurement = "postgresql_db_size"
    tagvalue = "datname"
  [[inputs.postgresql_extensible.query]]
    sqlquery = "SELECT c.relname AS tablename, pg_total_relation_size(c.oid) AS bytes FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace WHERE n.nspname = 'public' AND c.relkind = 'r' ORDER BY 2 DESC LIMIT 20"
    measurement = "postgresql_table_size"
    tagvalue = "tablename"

###############################################################################
#                            OUTPUT PLUGINS                                   #
###############################################################################

[[outputs.influxdb_v2]]
  urls = ["http://localhost:8086"]
  token = "${INFLUXDB_TOKEN}"
  organization = "openbmp"
  bucket = "telemetry"