mirror of
https://github.com/temporalio/temporal.git
synced 2026-08-30 18:41:49 -07:00
c19b51a743
## What changed? <!-- Describe what has changed in this PR --> Added Grafana Tempo - an OTEL collector - to the developer setup. Since we're already using Grafana, Tempo seemed like a logical choice. ## Why? <!-- Tell your future self why have you made these changes --> It allows developers to see all the RPC calls they are making (e.g. when running the server locally or a functional test). Tempo allows filtering by workflow ID. _(note that not _all_ places are tagged yet, but lots of them)_ ## How did you test it? <!-- How have you verified this change? Tested locally? Added a unit test? Checked in staging env? --> ``` make start-grafana-tempo make OTEL=true start ``` ``` tctl --ns default namespace register tctl wf start --tq test --wid test -wt test ``` <img width="3352" alt="image" src="https://github.com/user-attachments/assets/5809691a-da32-4a04-8e80-700f8acd47e5" /> And running a functional test from the IDE: <img width="3346" alt="image" src="https://github.com/user-attachments/assets/061bfaf3-0a34-4b4e-a06c-497dfa3a948a" /> ## Potential risks <!-- Assuming the worst case, what can be broken when deploying this change to production? --> ## Documentation <!-- Have you made sure this change doesn't falsify anything currently stated in `docs/`? If significant new behavior is added, have you described that in `docs/`? --> Updated docs/development/tracing.md ## Is hotfix candidate? <!-- Is this PR a hotfix candidate or does it require a notification to be sent to the broader community? (Yes/No) -->
83 lines
2.5 KiB
YAML
83 lines
2.5 KiB
YAML
# Copied from https://github.com/grafana/tempo/blob/main/example/docker-compose/local/tempo.yaml
|
|
|
|
stream_over_http_enabled: true
|
|
server:
|
|
http_listen_port: 3200
|
|
log_level: info
|
|
|
|
cache:
|
|
background:
|
|
writeback_goroutines: 5
|
|
caches:
|
|
- roles:
|
|
- frontend-search
|
|
memcached:
|
|
host: memcached:11211
|
|
|
|
query_frontend:
|
|
search:
|
|
duration_slo: 5s
|
|
throughput_bytes_slo: 1.073741824e+09
|
|
metadata_slo:
|
|
duration_slo: 5s
|
|
throughput_bytes_slo: 1.073741824e+09
|
|
trace_by_id:
|
|
duration_slo: 100ms
|
|
metrics:
|
|
max_duration: 120h # maximum duration of a metrics query, increase for local setups
|
|
query_backend_after: 5m
|
|
duration_slo: 5s
|
|
throughput_bytes_slo: 1.073741824e+09
|
|
|
|
distributor:
|
|
receivers: # this configuration will listen on all ports and protocols that tempo is capable of.
|
|
jaeger: # the receives all come from the OpenTelemetry collector. more configuration information can
|
|
protocols: # be found there: https://github.com/open-telemetry/opentelemetry-collector/tree/main/receiver
|
|
thrift_http: #
|
|
grpc: # for a production deployment you should only enable the receivers you need!
|
|
thrift_binary:
|
|
thrift_compact:
|
|
zipkin:
|
|
otlp:
|
|
protocols:
|
|
http:
|
|
grpc:
|
|
opencensus:
|
|
|
|
ingester:
|
|
max_block_duration: 5m # cut the headblock when this much time passes. this is being set for demo purposes and should probably be left alone normally
|
|
|
|
compactor:
|
|
compaction:
|
|
block_retention: 24h # overall Tempo trace retention. set for demo purposes
|
|
|
|
metrics_generator:
|
|
registry:
|
|
external_labels:
|
|
source: tempo
|
|
cluster: docker-compose
|
|
storage:
|
|
path: /var/tempo/generator/wal
|
|
remote_write:
|
|
- url: http://prometheus:9090/api/v1/write
|
|
send_exemplars: true
|
|
traces_storage:
|
|
path: /var/tempo/generator/traces
|
|
processor:
|
|
local_blocks:
|
|
filter_server_spans: false
|
|
flush_to_storage: true
|
|
|
|
storage:
|
|
trace:
|
|
backend: local # backend configuration to use
|
|
wal:
|
|
path: /var/tempo/wal # where to store the wal locally
|
|
local:
|
|
path: /var/tempo/blocks
|
|
|
|
overrides:
|
|
defaults:
|
|
metrics_generator:
|
|
processors: [service-graphs, span-metrics, local-blocks] # enables metrics generator
|
|
generate_native_histograms: both |