From 0ae909fedf9bcdcf0c8110ff9714c06c239e76fa Mon Sep 17 00:00:00 2001 From: Victor Lyuboslavsky <2685025+getvictor@users.noreply.github.com> Date: Thu, 29 Jan 2026 10:18:02 -0600 Subject: [PATCH] Updated loadtest OTEL config to match dogfood (#38991) **Related issue:** Resolves #36494 I tried this with loadtest. --- .../signoz/otel-collector-values.yaml | 100 ++++++++++++++---- 1 file changed, 81 insertions(+), 19 deletions(-) diff --git a/infrastructure/loadtesting/terraform/signoz/otel-collector-values.yaml b/infrastructure/loadtesting/terraform/signoz/otel-collector-values.yaml index 0b80c3d3e5..b97be1d529 100644 --- a/infrastructure/loadtesting/terraform/signoz/otel-collector-values.yaml +++ b/infrastructure/loadtesting/terraform/signoz/otel-collector-values.yaml @@ -1,12 +1,66 @@ # OTEL Collector configuration overrides for production stability -# These settings fix ClickHouse timeout issues by adding proper timeouts, -# retry logic, and sending queues. +# Fully explicit config matching dogfood structure otelCollector: # Enable low cardinality exception grouping to reduce exception noise lowCardinalityExceptionGrouping: true config: + connectors: + signozmeter: + metrics_flush_interval: 1h + dimensions: + - name: service.name + - name: deployment.environment + - name: host.name + + receivers: + otlp: + protocols: + grpc: + endpoint: 0.0.0.0:4317 + max_recv_msg_size_mib: 16 + http: + endpoint: 0.0.0.0:4318 + jaeger: + protocols: + grpc: + endpoint: 0.0.0.0:14250 + thrift_http: + endpoint: 0.0.0.0:14268 + + processors: + batch: + send_batch_size: 2000 + timeout: 5s + batch/meter: + send_batch_max_size: 25000 + send_batch_size: 20000 + timeout: 1s + memory_limiter: + check_interval: 1s + limit_mib: 11264 + spike_limit_mib: 512 + signozspanmetrics/delta: + metrics_exporter: signozclickhousemetrics + latency_histogram_buckets: [100us, 1ms, 2ms, 6ms, 10ms, 50ms, 100ms, 250ms, 500ms, 1000ms, 1400ms, 2000ms, 5s, 10s, 20s, 40s, 60s] + dimensions_cache_size: 100000 + dimensions: + - name: service.namespace + default: default + - name: deployment.environment + default: default + - name: signoz.collector.id + aggregation_temporality: AGGREGATION_TEMPORALITY_DELTA + + extensions: + health_check: + endpoint: 0.0.0.0:13133 + zpages: + endpoint: localhost:55679 + pprof: + endpoint: localhost:1777 + exporters: # Logs exporter with balanced queue sizes for throughput and memory clickhouselogsexporter: @@ -20,7 +74,8 @@ otelCollector: enabled: true num_consumers: 10 queue_size: 10000 - + signozclickhousemetrics: + timeout: 45s # Traces exporter must handle spans after tail_sampling clickhousetraces: timeout: 120s @@ -42,23 +97,30 @@ otelCollector: initial_interval: 5s max_interval: 30s max_elapsed_time: 300s - - processors: - # Optimized batch processor to send data more frequently - # Smaller batches reduce memory pressure - batch: - send_batch_size: 2000 - timeout: 5s - - # Memory limiter to prevent out-of-memory by applying back pressure - memory_limiter: - check_interval: 1s - limit_mib: 11264 - spike_limit_mib: 512 + signozclickhousemeter: + timeout: 45s + sending_queue: + enabled: false service: + telemetry: + logs: + encoding: json + extensions: [health_check, zpages, pprof] pipelines: traces: - processors: - - memory_limiter - - batch + receivers: [otlp, jaeger] + processors: [memory_limiter, signozspanmetrics/delta, batch] + exporters: [clickhousetraces, metadataexporter, signozmeter] + metrics: + receivers: [otlp] + processors: [batch] + exporters: [metadataexporter, signozclickhousemetrics, signozmeter] + logs: + receivers: [otlp] + processors: [memory_limiter, batch] + exporters: [clickhouselogsexporter, metadataexporter, signozmeter] + metrics/meter: + receivers: [signozmeter] + processors: [batch/meter] + exporters: [signozclickhousemeter]