|
|
|
|
@ -1,178 +1,46 @@ |
|
|
|
|
# Set the command-line arguments to pass to the server. |
|
|
|
|
ARGS="-config.file {{config_file}} -storage.local.path {{storage_local_path}} -web.console.libraries {{web_console_libraries}} -web.console.templates {{web_console_templates}}" |
|
|
|
|
ARGS="--config.file {{config_file}} --storage.tsdb.path {{storage_local_path}} --web.console.libraries {{web_console_libraries}} --web.console.templates {{web_console_templates}}" |
|
|
|
|
|
|
|
|
|
# Prometheus supports the following options: |
|
|
|
|
|
|
|
|
|
# -config.file "/etc/prometheus/prometheus.yml" |
|
|
|
|
# Prometheus configuration file name. |
|
|
|
|
# |
|
|
|
|
# == ALERTMANAGER == |
|
|
|
|
# |
|
|
|
|
# -alertmanager.notification-queue-capacity 10000 |
|
|
|
|
# The capacity of the queue for pending alert manager notifications. |
|
|
|
|
# |
|
|
|
|
# -alertmanager.timeout 10s |
|
|
|
|
# Alert manager HTTP API timeout. |
|
|
|
|
# |
|
|
|
|
# -alertmanager.url |
|
|
|
|
# The URL of the alert manager to send notifications to. |
|
|
|
|
# |
|
|
|
|
# == LOG == |
|
|
|
|
# |
|
|
|
|
# -log.format |
|
|
|
|
# If set use a syslog logger or JSON logging. Example: |
|
|
|
|
# logger:syslog?appname=bob&local=7 or logger:stdout?json=true. Defaults to |
|
|
|
|
# stderr. |
|
|
|
|
# |
|
|
|
|
# -log.level "info" |
|
|
|
|
# Only log messages with the given severity or above. Valid levels: |
|
|
|
|
# [debug, info, warn, error, fatal]. |
|
|
|
|
# |
|
|
|
|
# == QUERY == |
|
|
|
|
# |
|
|
|
|
# -query.max-concurrency 20 |
|
|
|
|
# Maximum number of queries executed concurrently. |
|
|
|
|
# |
|
|
|
|
# -query.staleness-delta 5m0s |
|
|
|
|
# Staleness delta allowance during expression evaluations. |
|
|
|
|
# |
|
|
|
|
# -query.timeout 2m0s |
|
|
|
|
# Maximum time a query may take before being aborted. |
|
|
|
|
# |
|
|
|
|
# == STORAGE == |
|
|
|
|
# |
|
|
|
|
# -storage.local.checkpoint-dirty-series-limit 5000 |
|
|
|
|
# If approx. that many time series are in a state that would require |
|
|
|
|
# a recovery operation after a crash, a checkpoint is triggered, even if |
|
|
|
|
# the checkpoint interval hasn't passed yet. A recovery operation requires |
|
|
|
|
# a disk seek. The default limit intends to keep the recovery time below |
|
|
|
|
# 1min even on spinning disks. With SSD, recovery is much faster, so you |
|
|
|
|
# might want to increase this value in that case to avoid overly frequent |
|
|
|
|
# checkpoints. |
|
|
|
|
# |
|
|
|
|
# -storage.local.checkpoint-interval 5m0s |
|
|
|
|
# The period at which the in-memory metrics and the chunks not yet |
|
|
|
|
# persisted to series files are checkpointed. |
|
|
|
|
# |
|
|
|
|
# -storage.local.chunk-encoding-version 1 |
|
|
|
|
# Which chunk encoding version to use for newly created chunks. |
|
|
|
|
# Currently supported is 0 (delta encoding) and 1 (double-delta encoding). |
|
|
|
|
# |
|
|
|
|
# -storage.local.dirty false |
|
|
|
|
# If set, the local storage layer will perform crash recovery even if |
|
|
|
|
# the last shutdown appears to be clean. |
|
|
|
|
# |
|
|
|
|
# -storage.local.index-cache-size.fingerprint-to-metric 10485760 |
|
|
|
|
# The size in bytes for the fingerprint to metric index cache. |
|
|
|
|
# |
|
|
|
|
# -storage.local.index-cache-size.fingerprint-to-timerange 5242880 |
|
|
|
|
# The size in bytes for the metric time range index cache. |
|
|
|
|
# |
|
|
|
|
# -storage.local.index-cache-size.label-name-to-label-values 10485760 |
|
|
|
|
# The size in bytes for the label name to label values index cache. |
|
|
|
|
# |
|
|
|
|
# -storage.local.index-cache-size.label-pair-to-fingerprints 20971520 |
|
|
|
|
# The size in bytes for the label pair to fingerprints index cache. |
|
|
|
|
# |
|
|
|
|
# -storage.local.max-chunks-to-persist 524288 |
|
|
|
|
# How many chunks can be waiting for persistence before sample |
|
|
|
|
# ingestion will be throttled. Many chunks waiting to be persisted will |
|
|
|
|
# increase the checkpoint size. |
|
|
|
|
# |
|
|
|
|
# -storage.local.memory-chunks 1048576 |
|
|
|
|
# How many chunks to keep in memory. While the size of a chunk is |
|
|
|
|
# 1kiB, the total memory usage will be significantly higher than this value |
|
|
|
|
# * 1kiB. Furthermore, for various reasons, more chunks might have to be |
|
|
|
|
# kept in memory temporarily. Sample ingestion will be throttled if the |
|
|
|
|
# configured value is exceeded by more than 10%. |
|
|
|
|
# |
|
|
|
|
# -storage.local.path "/var/lib/prometheus/metrics" |
|
|
|
|
# Base path for metrics storage. |
|
|
|
|
# |
|
|
|
|
# -storage.local.pedantic-checks false |
|
|
|
|
# If set, a crash recovery will perform checks on each series file. |
|
|
|
|
# This might take a very long time. |
|
|
|
|
# |
|
|
|
|
# -storage.local.retention 360h0m0s |
|
|
|
|
# How long to retain samples in the local storage. |
|
|
|
|
# |
|
|
|
|
# -storage.local.series-file-shrink-ratio 0.1 |
|
|
|
|
# A series file is only truncated (to delete samples that have |
|
|
|
|
# exceeded the retention period) if it shrinks by at least the provided |
|
|
|
|
# ratio. This saves I/O operations while causing only a limited storage |
|
|
|
|
# space overhead. If 0 or smaller, truncation will be performed even for a |
|
|
|
|
# single dropped chunk, while 1 or larger will effectively prevent any |
|
|
|
|
# truncation. |
|
|
|
|
# |
|
|
|
|
# -storage.local.series-sync-strategy "adaptive" |
|
|
|
|
# When to sync series files after modification. Possible values: |
|
|
|
|
# 'never', 'always', 'adaptive'. Sync'ing slows down storage performance |
|
|
|
|
# but reduces the risk of data loss in case of an OS crash. With the |
|
|
|
|
# 'adaptive' strategy, series files are sync'd for as long as the storage |
|
|
|
|
# is not too much behind on chunk persistence. |
|
|
|
|
# |
|
|
|
|
# -storage.remote.graphite-address |
|
|
|
|
# The host:port of the remote Graphite server to send samples to. |
|
|
|
|
# None, if empty. |
|
|
|
|
# |
|
|
|
|
# -storage.remote.graphite-prefix |
|
|
|
|
# The prefix to prepend to all metrics exported to Graphite. None, if |
|
|
|
|
# empty. |
|
|
|
|
# |
|
|
|
|
# -storage.remote.graphite-transport "tcp" |
|
|
|
|
# Transport protocol to use to communicate with Graphite. 'tcp', if |
|
|
|
|
# empty. |
|
|
|
|
# |
|
|
|
|
# -storage.remote.influxdb-url |
|
|
|
|
# The URL of the remote InfluxDB server to send samples to. None, if |
|
|
|
|
# empty. |
|
|
|
|
# |
|
|
|
|
# -storage.remote.influxdb.database "prometheus" |
|
|
|
|
# The name of the database to use for storing samples in InfluxDB. |
|
|
|
|
# |
|
|
|
|
# -storage.remote.influxdb.retention-policy "default" |
|
|
|
|
# The InfluxDB retention policy to use. |
|
|
|
|
# |
|
|
|
|
# -storage.remote.influxdb.username |
|
|
|
|
# The username to use when sending samples to InfluxDB. The |
|
|
|
|
# corresponding password must be provided via the INFLUXDB_PW environment |
|
|
|
|
# variable. |
|
|
|
|
# |
|
|
|
|
# -storage.remote.opentsdb-url |
|
|
|
|
# The URL of the remote OpenTSDB server to send samples to. None, if |
|
|
|
|
# empty. |
|
|
|
|
# |
|
|
|
|
# -storage.remote.timeout 30s |
|
|
|
|
# The timeout to use when sending samples to the remote storage. |
|
|
|
|
# |
|
|
|
|
# == WEB == |
|
|
|
|
# |
|
|
|
|
# -web.console.libraries "/etc/prometheus/console_libraries" |
|
|
|
|
# Path to the console library directory. |
|
|
|
|
# |
|
|
|
|
# -web.console.templates "/etc/prometheus/consoles" |
|
|
|
|
# Path to the console template directory, available at /consoles. |
|
|
|
|
# |
|
|
|
|
# -web.enable-remote-shutdown false |
|
|
|
|
# Enable remote service shutdown. |
|
|
|
|
# |
|
|
|
|
# -web.external-url |
|
|
|
|
# The URL under which Prometheus is externally reachable (for |
|
|
|
|
# example, if Prometheus is served via a reverse proxy). Used for |
|
|
|
|
# generating relative and absolute links back to Prometheus itself. If the |
|
|
|
|
# URL has a path portion, it will be used to prefix all HTTP endpoints |
|
|
|
|
# served by Prometheus. If omitted, relevant URL components will be derived |
|
|
|
|
# automatically. |
|
|
|
|
# |
|
|
|
|
# -web.listen-address ":9090" |
|
|
|
|
# Address to listen on for the web interface, API, and telemetry. |
|
|
|
|
# |
|
|
|
|
# -web.local-assets "/usr/share/prometheus/web/" |
|
|
|
|
# Path to static assets/templates directory. |
|
|
|
|
# |
|
|
|
|
# -web.telemetry-path "/metrics" |
|
|
|
|
# Path under which to expose metrics. |
|
|
|
|
# |
|
|
|
|
# -web.user-assets |
|
|
|
|
# Path to static asset directory, available at /user. |
|
|
|
|
# |
|
|
|
|
# usage: prometheus [<flags>] |
|
|
|
|
# |
|
|
|
|
# The Prometheus monitoring server |
|
|
|
|
# |
|
|
|
|
# Flags: |
|
|
|
|
# -h, --help Show context-sensitive help (also try --help-long and --help-man). |
|
|
|
|
# --version Show application version. |
|
|
|
|
# --config.file="prometheus.yml" |
|
|
|
|
# Prometheus configuration file path. |
|
|
|
|
# --web.listen-address="0.0.0.0:9090" |
|
|
|
|
# Address to listen on for UI, API, and telemetry. |
|
|
|
|
# --web.read-timeout=5m Maximum duration before timing out read of the request, and closing idle connections. |
|
|
|
|
# --web.max-connections=512 Maximum number of simultaneous connections. |
|
|
|
|
# --web.external-url=<URL> The URL under which Prometheus is externally reachable (for example, if Prometheus is served via a reverse proxy). Used for generating relative and absolute links back to Prometheus itself. If the URL has a |
|
|
|
|
# path portion, it will be used to prefix all HTTP endpoints served by Prometheus. If omitted, relevant URL components will be derived automatically. |
|
|
|
|
# --web.route-prefix=<path> Prefix for the internal routes of web endpoints. Defaults to path of --web.external-url. |
|
|
|
|
# --web.user-assets=<path> Path to static asset directory, available at /user. |
|
|
|
|
# --web.enable-lifecycle Enable shutdown and reload via HTTP request. |
|
|
|
|
# --web.enable-admin-api Enables API endpoints for admin control actions. |
|
|
|
|
# --web.console.templates="consoles" |
|
|
|
|
# Path to the console template directory, available at /consoles. |
|
|
|
|
# --web.console.libraries="console_libraries" |
|
|
|
|
# Path to the console library directory. |
|
|
|
|
# --storage.tsdb.path="data/" |
|
|
|
|
# Base path for metrics storage. |
|
|
|
|
# --storage.tsdb.min-block-duration=2h |
|
|
|
|
# Minimum duration of a data block before being persisted. |
|
|
|
|
# --storage.tsdb.max-block-duration=<duration> |
|
|
|
|
# Maximum duration compacted blocks may span. (Defaults to 10% of the retention period) |
|
|
|
|
# --storage.tsdb.retention=15d |
|
|
|
|
# How long to retain samples in the storage. |
|
|
|
|
# --storage.tsdb.no-lockfile |
|
|
|
|
# Do not create lockfile in data directory. |
|
|
|
|
# --alertmanager.notification-queue-capacity=10000 |
|
|
|
|
# The capacity of the queue for pending alert manager notifications. |
|
|
|
|
# --alertmanager.timeout=10s |
|
|
|
|
# Timeout for sending alerts to Alertmanager. |
|
|
|
|
# --query.lookback-delta=5m The delta difference allowed for retrieving metrics during expression evaluations. |
|
|
|
|
# --query.timeout=2m Maximum time a query may take before being aborted. |
|
|
|
|
# --query.max-concurrency=20 |
|
|
|
|
# Maximum number of queries executed concurrently. |
|
|
|
|
# --log.level=info Only log messages with the given severity or above. One of: [debug, info, warn, error] |
|
|
|
|
# |
|
|
|
|
|
Ricardo Hernandez
5 years ago
committed by
GitHub