Skip to content
Permalink
Branch: master
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
470 lines (364 sloc) 16.4 KB
---
# == COLLECTION ==
# The addresses on which to listen for statsd metrics. These are
# formatted as URLs, with schemes corresponding to valid "network"
# arguments on https://golang.org/pkg/net/#Listen. Currently, only udp,
# tcp(including IPv4 and 6-only) and unixgram(datagram only) schemes are
# supported. This option supersedes the "udp_address" and "tcp_address" options.
statsd_listen_addresses:
- udp://localhost:8126
- tcp://localhost:8126
- unixgram:///tmp/veneur-statsd.sock
# The addresses on which to listen for SSF data. As with
# statsd_listen_addresses, these are formatted as URLs, with schemes
# corresponding to valid "network" arguments on
# https://golang.org/pkg/net/#Listen. Currently, only UDP and Unix
# domain sockets are supported.
# Note: SSF sockets are required to ingest trace data.
# This option supersedes the "ssf_address" option.
ssf_listen_addresses:
- udp://localhost:8128
- unix:///tmp/veneur-ssf.sock
# TLS
# These are only useful in conjunction with TCP listening sockets
# TLS server private key and certificate for encryption (specify both)
# These are the key/certificate contents, not a file path
tls_key: ""
tls_certificate: ""
# Authority certificate: requires clients to be authenticated
tls_authority_certificate: ""
# == BEHAVIOR ==
# Use a static host for forwarding
#forward_address: "http://veneur.example.com"
# Do not add a prefix when setting the forward address for gRPC.
#forward_address: "veneur.example.com"
forward_address: ""
# Whether or not to forward to an upstream Veneur over gRPC. If this is false
# or unset, HTTP will be used.
forward_use_grpc: false
# How often to flush. When flushing to Datadog, changing this
# value when you've already emitted metrics will break your time
# series data.
interval: "10s"
# Veneur can "sychronize" it's flushes with the system clock, flushing at even
# intervals i.e. 0, 10, 20… to align with the `interval`. This is disabled by
# default for now, as it can cause thundering herds in large installations.
synchronize_with_interval: false
# Veneur emits its own metrics; this configures where we send them. It's ok
# to point veneur at itself for metrics consumption!
# This can be host:port combination or a Unix Domain Socket(eg: unix:///tmp/veneur-statsd.sock)
stats_address: "localhost:8126"
# The address on which to listen for HTTP imports and/or healthchecks.
# http_address: "einhorn@0"
http_address: "0.0.0.0:8127"
# The address on which to listen for imports over gRPC.
grpc_address: "0.0.0.0:8128"
# The name of timer metrics that "indicator" spans should be tracked
# under. If this is unset, veneur doesn't report an additional timer
# metric for indicator spans.
indicator_span_timer_name: "indicator_span.duration_ns"
# The name of timer metrics that objectives, derived from indicator
# spans, should be tracked under. If this is unset, veneur doesn't
# report an additional timer metric for indicator spans.
objective_span_timer_name: "objective_span.duration_ns"
# == METRICS CONFIGURATION ==
# Defaults to the os.Hostname()!
hostname: ""
# If true and hostname is "" or absent, don't add the host tag
omit_empty_hostname: false
# Tags supplied here will be added to all metrics and spans ingested by this
# instance. Example:
# tags:
# - "foo:bar"
# - "baz:quz"
tags:
- ""
# Tags listed here will be excluded from sinks. A pipe ("|") delimiter
# can be used to specify the name of a sink, in which case the tag will
# only be excluded from that one sink.
# Sinks must support this behavior by providing a SetExcludedTags method,
# or the exclusion rule will not be applied.
tags_exclude:
- "nonce"
- "host_env|signalfx"
# Set to floating point values that you'd like to output percentiles for from
# histograms.
percentiles:
- 0.5
- 0.75
- 0.99
# Aggregations you'd like to output for histograms. Possible values can be any
# or all of:
# - `min`: the minimum value in the histogram during the flush period
# - `max`: the maximum value in the histogram during the flush period
# - `median`: the median value in the histogram during the flush period
# - `avg`: the average value in the histogram during the flush period
# - `count`: the number of values added to the histogram during the flush period
# - `sum`: the sum of all values added to the histogram during the flush period
# - `hmean`: the harmonic mean of the all the values added to the histogram during the flush period
aggregates:
- "min"
- "max"
- "count"
# == DEPRECATED ==
# This configuration has been replaced by datadog_flush_max_per_body.
flush_max_per_body: 0
# This configuration has been replaced by datadog_span_buffer_size.
ssf_buffer_size: 0
# This has been replaced by lightstep_access_token
trace_lightstep_access_token: ""
# This has been replaced by lightstep_collector_host
trace_lightstep_collector_host: ""
# This has been replaced by lightstep_reconnect_period
trace_lightstep_reconnect_period: ""
# This has been replaced by lightstep_maximum_spans
trace_lightstep_maximum_spans: 0
# This has been replaced by lightstep_num_clients
trace_lightstep_num_clients: 0
# == PERFORMANCE ==
# Adjusts the number of metrics workers across which Veneur will
# distribute aggregation. More decreases contention but has
# diminishing returns. The default value is 1, no parallel ingestion
# of metrics.
num_workers: 96
# Adjusts the number of listening goroutines on any UDP listener
# (statsd and SSF). Numbers larger than 1 will enable the use of
# SO_REUSEPORT, so make sure this is supported on your platform!
num_readers: 1
# Adjusts the number of span workers across which Veneur will
# distribute span ingestion. The default value is 1, no parallel
# ingestion of spans.
num_span_workers: 10
# Adjusts the number of spans that can be accomodated before the span
# ingestion buffer blocks. This is good to tweak when you're seeing
# spiky span ingestion patterns and a lot of spans get dropped. This
# corresponds directly to a Go channel's capacity, for which the
# default is zero (unbuffered).
span_channel_capacity: 100
# == LIMITS ==
# How big of a buffer to allocate for incoming metrics. Metrics longer than this
# will be truncated!
metric_max_length: 4096
# How big of a buffer to allocate for incoming traces.
trace_max_length_bytes: 16384
# The size of the buffer we'll use to buffer socket reads. Tune this if you
# you think Veneur needs more room to keep up with all packets.
read_buffer_size_bytes: 2097152
# == DIAGNOSTICS ==
# Sets the log level to DEBUG
debug: false
# Log (at level DEBUG) information about every ingested span. Be
# careful with this setting in a real deployment - it is extremely
# verbose.
debug_ingested_spans: false
# Log (at level DEBUG) information about every batch of flushed
# metrics. Be careful with this setting in a real deployment - it is
# extremely verbose.
debug_flushed_metrics: false
# runtime.SetMutexProfileFraction
# The fraction of mutex contention events that are reported in the mutex profile.
# On average, 1/n events are reported, so higher numbers will sample fewer events.
# Default (0) disables mutex profiling altogether.
mutex_profile_fraction: 0
# runtime.SetBlockProfileRate.
# The fraction of goroutine blocking events that are reported in the blocking profile.
# On average, one blocking event will be sampled for every N nanoseconds spent blocked.
# Default (0) disables block profiling altogether.
block_profile_rate: 0
# Providing a Sentry DSN here will send internal exceptions to Sentry
sentry_dsn: ""
# Enables Go profiling
enable_profiling: false
# == SINKS ==
# == Datadog ==
# Datadog can be a sink for metrics, events, service checks and trace spans.
# Hostname to send Datadog data to.
datadog_api_hostname: https://app.datadoghq.com
# API key for acessing Datadog
datadog_api_key: "farts"
# How many metrics to include in the body of each POST to Datadog. Veneur
# will post multiple times in parallel if the limit is exceeded.
datadog_flush_max_per_body: 25000
# Hostname to send Datadog trace data to.
datadog_trace_api_address: ""
# The size of the ring buffer used for retaining spans during a flush interval.
datadog_span_buffer_size: 16384
# == SignalFx ==
# SignalFx can be a sink for metrics and events.
# The API token to use, either always, or if no
# signalfx_per_tag_api_keys match
signalfx_api_key: "abc123"
# Where to send metrics
signalfx_endpoint_base: "https://ingest.signalfx.com"
# The tag we'll add to each metric that contains the hostname we came from
signalfx_hostname_tag: "host"
# The tag that we'll (optionally) use to look up values in
# signalfx_per_tag_api_keys. If this is empty, the SignalFX sink uses
# only signalfx_api_key.
signalfx_vary_key_by: host_operator
# If signalfx_vary_key_by is set, and matches one of the keys in here,
# use the value as the signalfx api token. If this is empty, only
# signalfx_api_key is used to submit metrics.
signalfx_per_tag_api_keys:
# metrics tagged with host_operator:cory will be submitted with api
# key "farts_in_a_general_direction"
- name: "cory"
api_key: "farts_in_a_general_direction"
# metrics tagged with host_operator:asf will be submitted with api
# key "definitely_no_farts"
- name: "asf"
api_key: "definitely_no_farts"
# A list of metric *prefixes* to drop. Note that this is not the whole string
# and not a regexp. Just a prefix. Any metrics that have this prefix as a name
# (not a tag!) will be dropped before sending to SignalFx.
signalfx_metric_name_prefix_drops:
- ""
# A list of tag `key:value` *prefixes* pairs to drop. Note that this is not the
# whole string and not a regexp. Just a prefix. You can use it in a few ways:
# * `foo:` will match any tag key, so you can ignore the value
# * `foo:bar` will match the key and value (well, unless there's `foo:barsnort`)
# * `foo` to matching things like `foobar:gorch` and `foofart:fighter`
signalfx_metric_tag_prefix_drops:
- ""
# The maximum number of datapoints in a single HTTP request to
# signalfx. On flush time, if veneur would flush more than the number
# configured here, it breaks the flushes apart into batches of this
# configured max size and submits them in parallel HTTP requests. If
# set to zero (the default), veneur makes a single HTTP request per
# signalfx flush endpoint.
signalfx_flush_max_per_body: 0
# == AWS X-Ray ==
# X-Ray can be a sink for trace spans.
# If present, X-Ray will be enabled as a tracing sink
xray_address: "localhost:2000"
# Sample rate in percent (as an integer)
# This should ideally be a floating point number, but at the time this was
# written, gojson interpreted whole-number floats in yaml as integers.
# The sink will hash the trace id of the span such that all Veneur instances
# will sample the same segments by using the trace id as input for a checksum.
xray_sample_percentage: 100
# All tags are sent as (unindexed) Metadata to X-ray. Up to 50 tags per trace
# (not per span) can be indexed as Annotations for search. Tag keys specified here
# will be provided as Annotations
xray_annotation_tags:
- ""
# == LightStep ==
# LightStep can be a sink for trace spans.
# If present, lightstep will be enabled as a tracing sink
# and this access token will be used
# Access token for accessing LightStep
lightstep_access_token: ""
# Host to send trace data to
lightstep_collector_host: ""
# How often LightStep should reconnect to collectors. If your workload is
# imbalanced — some veneur instances see more spans than others — then you may
# want to reconnect more often.
lightstep_reconnect_period: "5m"
# The LightStep client has internal throttling to prevent you overwhelming
# things. Anything that exceeds this many spans in the reporting period
# — which is a minimum of 500ms and maxmium 2.5s at the time of this writing
# — will be dropped. In other words, you can only submit this many spans per
# flush! If left at zero, veneur will set the maximum to the size of
# `ssf_buffer_size`.
lightstep_maximum_spans: 0
# Multiple clients can be used to load-balance spans cross multiple collectors,
# improving span indexing success rates.
# If missing (or set to zero), it will default
# to a minimum of one client
lightstep_num_clients: 1
# == Kafka ==
# Comma-delimited list of brokers suitable for Sarama's [NewAsyncProducer](https://godoc.org/github.com/Shopify/sarama#NewAsyncProducer)
# in the form hostname:port, such as localhost:9092
kafka_broker: ""
# Name of the topic we'll be publishing checks to
kafka_check_topic: "veneur_checks"
# Name of the topic we'll be publishing events to
kafka_event_topic: "veneur_events"
# Name of the topic we'll be publishing metrics to
kafka_metric_topic: ""
# Name of the topic we'll be publishing spans to
kafka_span_topic: "veneur_spans"
# Name of a tag to hash on for sampling; if empty, spans are sampled based off
# of traceID
kafka_span_sample_tag: ""
# Sample rate in percent (as an integer)
# This should ideally be a floating point number, but at the time this was
# written, gojson interpreted whole-number floats in yaml as integers.
kafka_span_sample_rate_percent: 100
kafka_metric_buffer_bytes: 0
kafka_metric_buffer_messages: 0
kafka_metric_buffer_frequency: ""
kafka_span_serialization_format: "protobuf"
# The type of partitioner to use.
kafka_partitioner: "hash"
# What type of acks to require for metrics? One of none, local or all.
kafka_metric_require_acks: "all"
# What type of acks to require for span? One of none, local or all.
kafka_span_require_acks: "all"
kafka_span_buffer_bytes: 0
kafka_span_buffer_mesages: 0
kafka_span_buffer_frequency: ""
# The number of retries before giving up.
kafka_retry_max: 0
# == Falconer ==
#
# Falconer (https://github.com/stripe/falconer) is an ephemeral (in-memory)
# trace data sink. Veneur relays data to Falconer via gRPC.
falconer_address: "falconer.service.consul"
# == Splunk ==
#
# Veneur can feed spans to splunk through the HTTP Event Consumer
# (HEC) interface
# See also http://dev.splunk.com/view/event-collector/SP-CAAAE6M
# The URL to use for a connection to the splunk
splunk_hec_address: "https://localhost:8088"
# The authentication token veneur will use to authenticate to the HEC
splunk_hec_token: "00000000-0000-0000-0000-000000000000"
# (optional) The number of spans to submit in a single request to the
# Splunk HEC endpoint. If unset, defaults to 100 (the recommended
# maximum event count per batch according to Splunk).
splunk_hec_batch_size: 100
# (optional) The maximum number of parallel submissions to do to the
# splunk HEC endpoint. Must be greater than 0. If this setting is
# omitted, defaults to 1.
splunk_hec_submission_workers: 3
# (optional) server name set on the TLS configuration. This is useful
# if the host you're reaching identifies with a different name than on
# the URL.
splunk_hec_tls_validate_hostname: "some-other-hostname"
# (optional) The maximum amount of time to wait before timing out
# sending a batch of spans to the Splunk HEC. If omitted / set to 0,
# sending batches happens without a timeout.
splunk_hec_send_timeout: "10ms"
# (optional) The maximum amount of time to wait before timing out
# ingesting a single span to the Splunk HEC sink. If omitted / set to
# 0, ingestion will wait indefintely until the span can be ingested.
splunk_hec_ingest_timeout: "10ms"
# (optional) The fraction of traces that are chosen to be reported to
# Splunk. On average, 1/N traces will be chosen to be reported to
# Splunk. Setting this value to 1 or 0 disables sampling, reporting
# all spans from all traces to Splunk. Sampling is performed on the
# trace ID, so either all spans from a given trace will be reported,
# or none will. Spans get excluded from sampling if they have
# indicator=true set, or if they have a trace ID of 0.
splunk_span_sample_rate: 10
# (optional) The maximum duration to keep an HEC submission HTTP
# request. After this duration, veneur will close & re-open the HTTP
# connection even if less than `splunk_hec_batch_size` have been
# ingested. This defaults to the flush `interval` setting (10s).
splunk_hec_max_connection_lifetime: "10s"
# (optional) The maximum (random) amount of jitter to add to
# splunk_hec_max_connection_lifetime. This can help reduce the number
# of submission workers that close & re-open their HTTP connections at
# the same time. If set to 0, there will be no jitter.
splunk_hec_connection_lifetime_jitter: "10s"
# == PLUGINS ==
# == S3 Output ==
# Include these if you want to archive data to S3
aws_access_key_id: ""
aws_secret_access_key: ""
aws_region: ""
aws_s3_bucket: ""
# == LocalFile Output ==
# Include this if you want to archive data to a local file (which should then be rotated/cleaned)
flush_file: ""
You can’t perform that action at this time.
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session.