dynamo/deploy/observability/prometheus.yml

63 lines
2.2 KiB
YAML

# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
global:
scrape_interval: 10s
evaluation_interval: 10s
scrape_configs:
- job_name: 'nats-prometheus-exporter'
scrape_interval: 2s
static_configs:
- targets: ['nats-prometheus-exporter:7777'] # on the "monitoring" network
- job_name: 'etcd-server'
scrape_interval: 2s
static_configs:
- targets: ['etcd-server:2379'] # etcd-server is on the "monitoring" network
- job_name: 'dcgm-exporter'
scrape_interval: 5s
static_configs:
- targets: ['dcgm-exporter:9401'] # on the "monitoring" network
# This is a demo service that needs to be launched manually
# Note that you may need to disable the firewall on your host. On Ubuntu: sudo ufw allow 8000/tcp
# You can also force the port, if the default is different: python -m dynamo.frontend --http-port 8000
- job_name: 'dynamo-frontend'
scrape_interval: 10s
static_configs:
- targets: ['host.docker.internal:8000'] # on the "monitoring" network
# Launch via: DYN_SYSTEM_PORT=8081 dynamo.<backend> ...
# If you want to update the scrape_interval, you may want to also update component.rs's MAX_DELAY
- job_name: 'dynamo-backend'
scrape_interval: 6s
static_configs:
- targets: ['host.docker.internal:8081']
# KVBM leader related metrics
- job_name: 'kvbm-metrics'
scrape_interval: 2s
static_configs:
- targets: ['host.docker.internal:6880']
# Uncomment to see its own Prometheus metrics
# - job_name: 'prometheus'
# scrape_interval: 5s
# static_configs:
# - targets: ['prometheus:9090'] # on the "monitoring" network