Move macrobenchmarks to apm-sdks-benchmarks repo

.gitlab-ci.yml

@@ -1,16 +1,19 @@
 include:
   - local: ".gitlab/one-pipeline.locked.yml"
   - local: ".gitlab/benchmarks.yml"
-  - local: ".gitlab/macrobenchmarks.yml"
   - local: ".gitlab/exploration-tests.yml"
   - local: ".gitlab/ci-visibility-tests.yml"
+  - project: 'DataDog/apm-reliability/apm-sdks-benchmarks'
+    file: '.gitlab/ci-java-spring-petclinic.yml'
+    ref: 'sarahchen6/migrate-java-macrobenchmarks'
 
 stages:
   - build
   - publish
   - shared-pipeline
   - benchmarks
-  - macrobenchmarks
+  - java-spring-petclinic-tests
+  - java-spring-petclinic-macrobenchmarks
   - tests
   - exploration-tests
   - ci-visibility-tests

.gitlab/benchmarks/bp-runner.fail-on-breach.yml

@@ -39,7 +39,7 @@ experiments:
           # https://benchmarking.us1.prod.dog/trends?projectId=4&branch=master&trendsTab=per_scenario&scenario=startup%3Apetclinic%3Atracing%3AAgent.start&trendsType=scenario
           - name: "startup:petclinic:tracing:Agent.start"
             thresholds:
-              - execution_time < 1120 ms
+              - execution_time < 1120ms
           # https://benchmarking.us1.prod.dog/trends?projectId=4&branch=master&trendsTab=per_scenario&scenario=startup%3Apetclinic%3Aprofiling%3AAgent.start&trendsType=scenario
           # https://benchmarking.us1.prod.dog/trends?projectId=4&branch=master&trendsTab=per_scenario&scenario=startup%3Apetclinic%3Aappsec%3AAgent.start&trendsType=scenario
           # https://benchmarking.us1.prod.dog/trends?projectId=4&branch=master&trendsTab=per_scenario&scenario=startup%3Apetclinic%3Aiast%3AAgent.start&trendsType=scenario

.gitlab/thresholds/java-spring-petclinic.yml

@@ -0,0 +1,36 @@
+# Thresholds set based on guidance in https://datadoghq.atlassian.net/wiki/x/LgI1LgE#How-to-choose-thresholds-for-pre-release-gates%3F
+
+experiments:
+  - name: Run SLO breach check
+    steps:
+      - name: SLO breach check
+        run: fail_on_breach
+        # https://datadoghq.atlassian.net/wiki/x/LgI1LgE#How-to-choose-a-warning-range-for-pre-release-gates%3F
+        warning_range: 10
+        # File spec
+        #   https://datadoghq.atlassian.net/wiki/x/LgI1LgE#Specification
+        # Measurements
+        #   https://benchmarking.us1.prod.dog/trends?projectId=4&branch=master&trendsTab=per_scenario
+        scenarios:
+          # Note that thresholds there are chosen based the confidence interval with a 10% adjustment.
+
+          # Standard macrobenchmarks
+          # https://benchmarking.us1.prod.dog/trends?projectId=4&branch=master&trendsTab=per_scenario&scenario=normal_operation%2Fonly-tracing&trendsType=scenario
+          - name: normal_operation/only-tracing
+            thresholds:
+              - agg_http_req_duration_p50 < 2.6 ms
+              - agg_http_req_duration_p99 < 8.5 ms
+          # https://benchmarking.us1.prod.dog/trends?projectId=4&branch=master&trendsTab=per_scenario&scenario=normal_operation%2Fotel-latest&trendsType=scenario
+          - name: normal_operation/otel-latest
+            thresholds:
+              - agg_http_req_duration_p50 < 2.5 ms
+              - agg_http_req_duration_p99 < 10 ms
+
+          # https://benchmarking.us1.prod.dog/trends?projectId=4&branch=master&trendsTab=per_scenario&scenario=high_load%2Fonly-tracing&trendsType=scenario
+          - name: high_load/only-tracing
+            thresholds:
+              - throughput > 1100.0 op/s
+          # https://benchmarking.us1.prod.dog/trends?projectId=4&branch=master&trendsTab=per_scenario&scenario=high_load%2Fotel-latest&trendsType=scenario
+          - name: high_load/otel-latest
+            thresholds:
+              - throughput > 1100.0 op/s