From d9d4887d4a7ee8c98d41a1819379032c33cb0067 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Fri, 12 Dec 2025 16:39:53 -0600
Subject: [PATCH 01/23] Add apm-sdks-benchmarks to CI

---
 .gitlab-ci.yml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index e5738260aa3..0bff96f9558 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -4,12 +4,17 @@ include:
   - 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/compare-with-latest-shared-commit'
 
 stages:
   - build
   - publish
   - shared-pipeline
   - benchmarks
+  - java-spring-petclinic-tests
+  - java-spring-petclinic-macrobenchmarks
   - macrobenchmarks
   - tests
   - exploration-tests

From 732aefdb28028163bd0c5de8c60c67574a77ab31 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Fri, 12 Dec 2025 17:02:51 -0600
Subject: [PATCH 02/23] Add thresholds file

---
 .gitlab/thresholds/java-spring-petclinic.yml | 36 ++++++++++++++++++++
 1 file changed, 36 insertions(+)
 create mode 100644 .gitlab/thresholds/java-spring-petclinic.yml

diff --git a/.gitlab/thresholds/java-spring-petclinic.yml b/.gitlab/thresholds/java-spring-petclinic.yml
new file mode 100644
index 00000000000..9064e7bd352
--- /dev/null
+++ b/.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

From 0beddad3001739ff08efe00778c727dd9cf38356 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Fri, 12 Dec 2025 17:10:19 -0600
Subject: [PATCH 03/23] Empty commit to run benchmarks again


From 961090742d827e1574663076274c18a51daf9107 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Fri, 12 Dec 2025 17:20:11 -0600
Subject: [PATCH 04/23] Empty commit to run benchmarks again


From 4fc38a519507cfa2a47c887903dca1ca959b27ce Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Fri, 12 Dec 2025 17:31:04 -0600
Subject: [PATCH 05/23] Empty commit to run benchmarks again


From bb85a00c8b998620ad799883d9904d7140a44611 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Fri, 12 Dec 2025 17:53:16 -0600
Subject: [PATCH 06/23] Empty commit to run benchmarks again


From e6573d03d1870483d78de3dd0cf10deb11d1c3d9 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Fri, 12 Dec 2025 17:58:20 -0600
Subject: [PATCH 07/23] Empty commit to run benchmarks again


From 573ddbc0eb4a15eb40de652c91703a7179f2957b Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Tue, 6 Jan 2026 12:20:38 -0500
Subject: [PATCH 08/23] Run microbenchmarks

---
 .gitlab-ci.yml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index 8417e2ddb2b..d61720ab46b 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -6,7 +6,7 @@ include:
   - local: ".gitlab/ci-visibility-tests.yml"
   - project: 'DataDog/apm-reliability/apm-sdks-benchmarks'
     file: '.gitlab/ci-java-spring-petclinic.yml'
-    ref: 'sarahchen6/compare-with-latest-shared-commit'
+    ref: 'sarahchen6/run-java-microbenchmarks'
 
 stages:
   - build
@@ -15,6 +15,8 @@ stages:
   - benchmarks
   - java-spring-petclinic-tests
   - java-spring-petclinic-macrobenchmarks
+  - java-spring-petclinic-microbenchmarks
+  - java-insecure-bank-microbenchmarks
   - macrobenchmarks
   - tests
   - exploration-tests

From d3ae881e32af573c9fd63aaf4075f689a4ddbd0c Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Tue, 6 Jan 2026 16:53:26 -0500
Subject: [PATCH 09/23] Add infrastructure stage

---
 .gitlab-ci.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index d61720ab46b..da365533bda 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -13,6 +13,7 @@ stages:
   - publish
   - shared-pipeline
   - benchmarks
+  - infrastructure
   - java-spring-petclinic-tests
   - java-spring-petclinic-macrobenchmarks
   - java-spring-petclinic-microbenchmarks

From b28e0fa72aed290ad397928468501f02cdda8d25 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Tue, 6 Jan 2026 16:57:15 -0500
Subject: [PATCH 10/23] Add another stage

---
 .gitlab-ci.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index da365533bda..b90caf0fcdc 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -18,6 +18,7 @@ stages:
   - java-spring-petclinic-macrobenchmarks
   - java-spring-petclinic-microbenchmarks
   - java-insecure-bank-microbenchmarks
+  - generate-slos
   - macrobenchmarks
   - tests
   - exploration-tests

From 177d4280967b0e5e02838a7a8d186ca905fed651 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Tue, 6 Jan 2026 18:10:15 -0500
Subject: [PATCH 11/23] Empty commit to run benchmarks


From 1fb5e0c60a074327abbfa94a9d2d129d77430b85 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Tue, 6 Jan 2026 18:23:44 -0500
Subject: [PATCH 12/23] Empty commit to run benchmarks again


From dbd6c94cd9507756d2af20705dc305fff6f0b3f6 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Wed, 7 Jan 2026 08:59:51 -0500
Subject: [PATCH 13/23] Include insecure bank file

---
 .gitlab-ci.yml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index b90caf0fcdc..bfb8e0e434d 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -7,6 +7,9 @@ include:
   - project: 'DataDog/apm-reliability/apm-sdks-benchmarks'
     file: '.gitlab/ci-java-spring-petclinic.yml'
     ref: 'sarahchen6/run-java-microbenchmarks'
+  - project: 'DataDog/apm-reliability/apm-sdks-benchmarks'
+    file: '.gitlab/ci-java-insecure-bank.yml'
+    ref: 'sarahchen6/run-java-microbenchmarks'
 
 stages:
   - build

From 9a0a7d5ce870f9c947e0d74a3c29f62f510b8810 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Wed, 7 Jan 2026 15:56:53 -0500
Subject: [PATCH 14/23] Empty commit to run benchmarks without full suite


From 22465b74a5a7fdcd236cacc651b4d3eac1567cb4 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Wed, 7 Jan 2026 16:20:34 -0500
Subject: [PATCH 15/23] Empty commit to run benchmarks with updated file


From 63e044f9b6210d9b5d1e34f6b7bb92222164aa6f Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Wed, 7 Jan 2026 17:31:45 -0500
Subject: [PATCH 16/23] Empty commit to run benchmarks again


From b2793639995dc3dd0fb098ecac51d6f5a0c414e4 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Wed, 7 Jan 2026 17:46:22 -0500
Subject: [PATCH 17/23] Empty commit to run benchmarks again


From f50106749e3aec4ab44022adfddff71f9c9e8aae Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Wed, 7 Jan 2026 18:23:56 -0500
Subject: [PATCH 18/23] Empty commit to run benchmarks again...


From 9da26aafd7522658057c84fe42d9252e901875ee Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Thu, 8 Jan 2026 09:56:02 -0500
Subject: [PATCH 19/23] Empty commit to run benchmarks again again


From 3d8f8c0fd68221d51e03ca80a83a7a77447bf8c9 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Tue, 13 Jan 2026 17:21:51 -0500
Subject: [PATCH 20/23] Empty commit to run benchmarks


From fb618b482fb3e56223017b873207402707890d05 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Wed, 14 Jan 2026 14:50:42 -0500
Subject: [PATCH 21/23] Try deleting microbenchmarks

---
 benchmark/Dockerfile                          | 103 ------------------
 benchmark/README.MD                           |  29 -----
 benchmark/benchmarks.sh                       |  42 -------
 benchmark/dacapo/benchmark.json               |  45 --------
 benchmark/dacapo/run.sh                       |  41 -------
 benchmark/load/insecure-bank/k6.js            |  76 -------------
 benchmark/load/insecure-bank/start-servers.sh |  28 -----
 benchmark/load/petclinic/k6.js                |  61 -----------
 benchmark/load/petclinic/start-servers.sh     |  28 -----
 benchmark/load/run.sh                         |  77 -------------
 benchmark/run.sh                              |  43 --------
 .../startup/insecure-bank/benchmark.json      |  22 ----
 benchmark/startup/petclinic/benchmark.json    |  34 ------
 benchmark/startup/run.sh                      |   5 -
 benchmark/utils/k6.js                         |  21 ----
 benchmark/utils/run-k6-load-test.sh           |  21 ----
 benchmark/utils/run-on-server-ready.sh        |  11 --
 benchmark/utils/run-sirun-benchmarks.sh       |  41 -------
 benchmark/utils/update-java-version.sh        |   5 -
 19 files changed, 733 deletions(-)
 delete mode 100644 benchmark/Dockerfile
 delete mode 100644 benchmark/README.MD
 delete mode 100755 benchmark/benchmarks.sh
 delete mode 100644 benchmark/dacapo/benchmark.json
 delete mode 100755 benchmark/dacapo/run.sh
 delete mode 100644 benchmark/load/insecure-bank/k6.js
 delete mode 100755 benchmark/load/insecure-bank/start-servers.sh
 delete mode 100644 benchmark/load/petclinic/k6.js
 delete mode 100755 benchmark/load/petclinic/start-servers.sh
 delete mode 100755 benchmark/load/run.sh
 delete mode 100755 benchmark/run.sh
 delete mode 100644 benchmark/startup/insecure-bank/benchmark.json
 delete mode 100644 benchmark/startup/petclinic/benchmark.json
 delete mode 100755 benchmark/startup/run.sh
 delete mode 100644 benchmark/utils/k6.js
 delete mode 100755 benchmark/utils/run-k6-load-test.sh
 delete mode 100755 benchmark/utils/run-on-server-ready.sh
 delete mode 100755 benchmark/utils/run-sirun-benchmarks.sh
 delete mode 100755 benchmark/utils/update-java-version.sh

diff --git a/benchmark/Dockerfile b/benchmark/Dockerfile
deleted file mode 100644
index 0279186478a..00000000000
--- a/benchmark/Dockerfile
+++ /dev/null
@@ -1,103 +0,0 @@
-# Petclinic download and compilation stage
-FROM eclipse-temurin:17-jammy as petclinic
-
-ARG SPRING_PETCLINIC_COMMIT=cefaf55dd124d0635abfe857c3c99a3d3ea62017
-
-RUN apt-get update \
-  && apt-get -y install git  \
-  && apt-get -y clean \
-  && rm -rf /var/lib/apt/lists/*
-
-RUN set -eux;\
-  git init spring-petclinic;\
-  cd spring-petclinic;\
-  git remote add origin https://github.com/spring-projects/spring-petclinic.git;\
-  git fetch --depth 1 origin ${SPRING_PETCLINIC_COMMIT};\
-  git checkout ${SPRING_PETCLINIC_COMMIT};\
-  ./mvnw dependency:go-offline
-
-RUN cd spring-petclinic \
-  && ./mvnw package -Dmaven.test.skip=true \
-  && cp target/*.jar /spring-petclinic.jar
-
-
-# Insecure bank download and compilation stage
-FROM eclipse-temurin:17-jammy as insecure-bank
-
-RUN apt-get update \
-  && apt-get -y install git  \
-  && apt-get -y clean \
-  && rm -rf /var/lib/apt/lists/*
-
-RUN git clone --depth 1 --branch malvarez/spring-boot --single-branch https://github.com/hdiv/insecure-bank.git \
-  && cd insecure-bank \
-  && ./gradlew -q dependencies
-
-RUN cd insecure-bank \
-  && ./gradlew bootWar \
-  && cp build/libs/*.war /insecure-bank.war
-
-# Dacapo download
-FROM debian:bookworm-slim as dacapo
-RUN apt-get update \
-  && apt-get -y install wget unzip \
-  && apt-get -y clean \
-  && rm -rf /var/lib/apt/lists/*
-
-ARG DACAPO_VERSION=23.11-chopin
-# The data for the big benchmarks is removed too ensure the final docker image is not too big
-RUN wget -nv -O dacapo.zip https://download.dacapobench.org/chopin/dacapo-$DACAPO_VERSION.zip \
-	&& mkdir /dacapo \
-	&& unzip dacapo.zip -d /dacapo/ \
-	&& rm -rf /dacapo/dacapo-$DACAPO_VERSION/dat/luindex \
-	&& rm -rf /dacapo/dacapo-$DACAPO_VERSION/dat/lusearch \
-	&& rm -rf /dacapo/dacapo-$DACAPO_VERSION/dat/graphchi \
-	&& rm dacapo.zip
-
-FROM debian:bookworm-slim
-
-RUN apt-get update \
-  && apt-get -y install git curl wget procps gettext-base \
-  && apt-get -y clean \
-  && rm -rf /var/lib/apt/lists/*
-
-COPY --from=eclipse-temurin:8-jammy /opt/java/openjdk /usr/lib/jvm/8
-COPY --from=eclipse-temurin:11-jammy /opt/java/openjdk /usr/lib/jvm/11
-COPY --from=eclipse-temurin:17-jammy /opt/java/openjdk /usr/lib/jvm/17
-
-RUN rm -rf \
-    /usr/lib/jvm/*/man \
-    /usr/lib/jvm/*/src.zip \
-    /usr/lib/jvm/*/lib/src.zip \
-    /usr/lib/jvm/*/demo \
-    /usr/lib/jvm/*/sample
-
-ENV JAVA_8_HOME=/usr/lib/jvm/8
-ENV JAVA_11_HOME=/usr/lib/jvm/11
-ENV JAVA_17_HOME=/usr/lib/jvm/17
-ENV JAVA_HOME=${JAVA_8_HOME}
-ENV PATH=${PATH}:${JAVA_HOME}/bin
-
-ARG SIRUN_VERSION=0.1.11
-RUN wget -O sirun.tar.gz https://github.com/DataDog/sirun/releases/download/v$SIRUN_VERSION/sirun-v$SIRUN_VERSION-x86_64-unknown-linux-musl.tar.gz \
-	&& tar -xzf sirun.tar.gz \
-	&& rm sirun.tar.gz \
-  && mv sirun /usr/bin/sirun
-
-ARG K6_VERSION=0.45.1
-RUN wget -O k6.tar.gz https://github.com/grafana/k6/releases/download/v$K6_VERSION/k6-v$K6_VERSION-linux-amd64.tar.gz \
-	&& tar --strip-components=1 -xzf k6.tar.gz \
-	&& rm k6.tar.gz \
-  && mv k6 /usr/bin/k6
-
-RUN mkdir -p /app
-
-COPY --from=petclinic /spring-petclinic.jar /app/spring-petclinic.jar
-ENV PETCLINIC=/app/spring-petclinic.jar
-
-COPY --from=insecure-bank /insecure-bank.war /app/insecure-bank.war
-ENV INSECURE_BANK=/app/insecure-bank.war
-
-COPY --from=dacapo /dacapo/ /app/
-ARG DACAPO_VERSION=23.11-chopin
-ENV DACAPO=/app/dacapo-$DACAPO_VERSION.jar
diff --git a/benchmark/README.MD b/benchmark/README.MD
deleted file mode 100644
index 30f3bbcf864..00000000000
--- a/benchmark/README.MD
+++ /dev/null
@@ -1,29 +0,0 @@
-# Benchmarks
-
-This directory contains different types of benchmarks.
-
-## Running Benchmarks via Docker
-
-Docker allows the execution of benchmarks without needing to install and configure your development environment. For example, package installation and installation of sirun are performed automatically.
-
-In order to run benchmarks using Docker, issue the following command from the `benchmark/` folder of this project:
-
-```sh
-./run.sh
-```
-
-If you run into storage errors (e.g. running out of disk space), try removing all unused Docker containers, networks, and images with `docker system prune -af` before running the script again. Once finished, the reports will be available in the `benchmark/reports/` folder. Note that the script can take ~40 minutes to run.
-
-### Running specific benchmarks
-
-If you want to run only a specific category of benchmarks, you can do so via arguments:
-
-1. Run startup benchmarks
-```sh
-./run.sh startup [application]?
-```
-
-2. Run load benchmarks
-```sh
-./run.sh load [application]?
-```
diff --git a/benchmark/benchmarks.sh b/benchmark/benchmarks.sh
deleted file mode 100755
index 0b245038afa..00000000000
--- a/benchmark/benchmarks.sh
+++ /dev/null
@@ -1,42 +0,0 @@
-#!/usr/bin/env bash
-set -eu
-
-readonly SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
-export TRACER_DIR="${SCRIPT_DIR}/.."
-export REPORTS_DIR="${SCRIPT_DIR}/reports"
-export UTILS_DIR="${SCRIPT_DIR}/utils"
-export SHELL_UTILS_DIR="${UTILS_DIR}/shell"
-export K6_UTILS_DIR="${UTILS_DIR}/k6"
-export TRACER="${SCRIPT_DIR}/tracer/dd-java-agent.jar"
-export NO_AGENT_VARIANT="no_agent"
-
-run_benchmarks() {
-  local type=$1
-  if [[ -d "${type}" ]] && [[ -f "${type}/run.sh" ]]; then
-    cd "${type}"
-    ./run.sh "$@"
-    cd "${SCRIPT_DIR}"
-  fi
-}
-
-# Find or rebuild tracer to be used in the benchmarks
-if [[ ! -f "${TRACER}" ]]; then
-  mkdir -p "${SCRIPT_DIR}/tracer"
-  cd "${TRACER_DIR}"
-  readonly TRACER_VERSION=$(./gradlew properties -q | grep "version:" | awk '{print $2}')
-  readonly TRACER_COMPILED="${SCRIPT_DIR}/../dd-java-agent/build/libs/dd-java-agent-${TRACER_VERSION}.jar"
-  if [[ ! -f "${TRACER_COMPILED}" ]]; then
-    echo "Tracer not found, starting gradle compile ..."
-    ./gradlew assemble
-  fi
-  cp "${TRACER_COMPILED}" "${TRACER}"
-  cd "${SCRIPT_DIR}"
-fi
-
-if [[ "$#" == '0' ]]; then
-  for type in 'startup' 'load' 'dacapo'; do
-    run_benchmarks "$type"
-  done
-else
-  run_benchmarks "$@"
-fi
diff --git a/benchmark/dacapo/benchmark.json b/benchmark/dacapo/benchmark.json
deleted file mode 100644
index ec0ca767f43..00000000000
--- a/benchmark/dacapo/benchmark.json
+++ /dev/null
@@ -1,45 +0,0 @@
-{
-  "name": "dacapo_${BENCHMARK}",
-  "setup": "bash -c \"mkdir -p ${OUTPUT_DIR}/${VARIANT}\"",
-  "run": "bash -c \"java ${JAVA_OPTS} -jar ${DACAPO} --converge --scratch-directory=${OUTPUT_DIR}/${VARIANT}/scratch --latency-csv ${BENCHMARK} &> ${OUTPUT_DIR}/${VARIANT}/dacapo.log\"",
-  "timeout": 150,
-  "iterations": 1,
-  "variants": {
-    "${NO_AGENT_VARIANT}": {
-      "env": {
-        "VARIANT": "${NO_AGENT_VARIANT}",
-        "JAVA_OPTS": ""
-      }
-    },
-    "tracing": {
-      "env": {
-        "VARIANT": "tracing",
-        "JAVA_OPTS": "-javaagent:${TRACER}"
-      }
-    },
-    "profiling": {
-      "env": {
-        "VARIANT": "profiling",
-        "JAVA_OPTS": "-javaagent:${TRACER} -Ddd.profiling.enabled=true"
-      }
-    },
-    "appsec": {
-      "env": {
-        "VARIANT": "appsec",
-        "JAVA_OPTS": "-javaagent:${TRACER} -Ddd.appsec.enabled=true -Ddd.iast.enabled=false"
-      }
-    },
-    "iast": {
-      "env": {
-        "VARIANT": "iast",
-        "JAVA_OPTS": "-javaagent:${TRACER} -Ddd.iast.enabled=true"
-      }
-    },
-    "iast_GLOBAL": {
-      "env": {
-        "VARIANT": "iast_GLOBAL",
-        "JAVA_OPTS": "-javaagent:${TRACER} -Ddd.iast.enabled=true -Ddd.iast.context.mode=GLOBAL"
-      }
-    }
-  }
-}
diff --git a/benchmark/dacapo/run.sh b/benchmark/dacapo/run.sh
deleted file mode 100755
index ece44f9e5f0..00000000000
--- a/benchmark/dacapo/run.sh
+++ /dev/null
@@ -1,41 +0,0 @@
-#!/usr/bin/env bash
-set -eu
-
-source "${UTILS_DIR}/update-java-version.sh" 11
-
-function message() {
-  echo "$(date +"%T"): $1"
-}
-
-run_benchmark() {
-  local type=$1
-
-  message "dacapo benchmark: ${type} started"
-
-  # export the benchmark
-  export BENCHMARK="${type}"
-
-  # create output folder for the test
-  export OUTPUT_DIR="${REPORTS_DIR}/dacapo/${type}"
-  mkdir -p "${OUTPUT_DIR}"
-
-  # substitute environment variables in the json file
-  benchmark=$(mktemp)
-  # shellcheck disable=SC2046
-  # shellcheck disable=SC2016
-  envsubst "$(printf '${%s} ' $(env | cut -d'=' -f1))" <benchmark.json >"${benchmark}"
-
-  # run the sirun test
-  sirun "${benchmark}" &>"${OUTPUT_DIR}/${type}.json"
-
-  message "dacapo benchmark: ${type} finished"
-}
-
-if [ "$#" == '2' ]; then
-  run_benchmark "$2"
-else
-  for benchmark in biojava tomcat ; do
-    run_benchmark "${benchmark}"
-  done
-fi
-
diff --git a/benchmark/load/insecure-bank/k6.js b/benchmark/load/insecure-bank/k6.js
deleted file mode 100644
index 2dd800fa7e5..00000000000
--- a/benchmark/load/insecure-bank/k6.js
+++ /dev/null
@@ -1,76 +0,0 @@
-import http from 'k6/http';
-import {checkResponse, isOk, isRedirect} from "../../utils/k6.js";
-
-const variants = {
-  "no_agent": {
-    "APP_URL": 'http://localhost:8080',
-  },
-  "tracing": {
-    "APP_URL": 'http://localhost:8081',
-  },
-  "profiling": {
-    "APP_URL": 'http://localhost:8082',
-  },
-  "iast": {
-    "APP_URL": 'http://localhost:8083',
-  },
-  "iast_GLOBAL": {
-    "APP_URL": 'http://localhost:8084',
-  },
-  "iast_FULL": {
-    "APP_URL": 'http://localhost:8085',
-  },
-}
-
-export const options = function (variants) {
-  let scenarios = {};
-  for (const variant of Object.keys(variants)) {
-    scenarios[`load--insecure-bank--${variant}--warmup`] = {
-      executor: 'constant-vus',  // https://grafana.com/docs/k6/latest/using-k6/scenarios/executors/#all-executors
-      vus: 5,
-      duration: '165s',
-      gracefulStop: '2s',
-      env: {
-        "APP_URL": variants[variant]["APP_URL"]
-      }
-    };
-
-    scenarios[`load--insecure-bank--${variant}--high_load`] = {
-      executor: 'constant-vus',
-      vus: 5,
-      startTime: '167s',
-      duration: '15s',
-      gracefulStop: '2s',
-      env: {
-        "APP_URL": variants[variant]["APP_URL"]
-      }
-    };
-  }
-
-  return {
-    discardResponseBodies: true,
-    scenarios,
-  }
-}(variants);
-
-export default function () {
-
-  // login form
-  const loginResponse = http.post(`${__ENV.APP_URL}/login`, {
-    username: 'john',
-    password: 'test'
-  }, {
-    redirects: 0
-  });
-  checkResponse(loginResponse, isRedirect);
-
-  // dashboard
-  const dashboard = http.get(`${__ENV.APP_URL}/dashboard`);
-  checkResponse(dashboard, isOk);
-
-  // logout
-  const logout = http.get(`${__ENV.APP_URL}/j_spring_security_logout`, {
-    redirects: 0
-  });
-  checkResponse(logout, isRedirect);
-}
diff --git a/benchmark/load/insecure-bank/start-servers.sh b/benchmark/load/insecure-bank/start-servers.sh
deleted file mode 100755
index 4cae95567f2..00000000000
--- a/benchmark/load/insecure-bank/start-servers.sh
+++ /dev/null
@@ -1,28 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-
-start_server() {
-  local VARIANT=$1
-  local JAVA_OPTS=$2
-
-  if [ -n "$CI_JOB_TOKEN" ]; then
-    # Inside BP, so we can assume 24 CPU cores available and set CPU affinity
-    CPU_AFFINITY_APP=$3
-  else
-    CPU_AFFINITY_APP=""
-  fi
-
-  mkdir -p "${LOGS_DIR}/${VARIANT}"
-  ${CPU_AFFINITY_APP}java ${JAVA_OPTS} -Xms3G -Xmx3G -jar ${INSECURE_BANK} &> ${LOGS_DIR}/${VARIANT}/insecure-bank.log &PID=$!
-  echo "${CPU_AFFINITY_APP}java ${JAVA_OPTS} -Xms3G -Xmx3G -jar ${INSECURE_BANK} &> ${LOGS_DIR}/${VARIANT}/insecure-bank.log [PID=$PID]"
-}
-
-start_server "no_agent" "-Dserver.port=8080" "taskset -c 47 " &
-start_server "tracing" "-javaagent:${TRACER} -Dserver.port=8081" "taskset -c 46 " &
-start_server "profiling" "-javaagent:${TRACER} -Ddd.profiling.enabled=true -Dserver.port=8082" "taskset -c 45 " &
-start_server "iast" "-javaagent:${TRACER} -Ddd.iast.enabled=true -Dserver.port=8083" "taskset -c 44 " &
-start_server "iast_GLOBAL" "-javaagent:${TRACER} -Ddd.iast.enabled=true -Ddd.iast.context.mode=GLOBAL -Dserver.port=8084" "taskset -c 43 " &
-start_server "iast_FULL" "-javaagent:${TRACER} -Ddd.iast.enabled=true -Ddd.iast.detection.mode=FULL -Dserver.port=8085" "taskset -c 42 " &
-
-wait
diff --git a/benchmark/load/petclinic/k6.js b/benchmark/load/petclinic/k6.js
deleted file mode 100644
index debeab10a8e..00000000000
--- a/benchmark/load/petclinic/k6.js
+++ /dev/null
@@ -1,61 +0,0 @@
-import http from 'k6/http';
-import {checkResponse, isOk} from "../../utils/k6.js";
-
-const variants = {
-  "no_agent": {
-    "APP_URL": 'http://localhost:8080',
-  },
-  "tracing": {
-    "APP_URL": 'http://localhost:8081',
-  },
-  "profiling": {
-    "APP_URL": 'http://localhost:8082',
-  },
-  "appsec": {
-    "APP_URL": 'http://localhost:8083',
-  },
-  "iast": {
-    "APP_URL": 'http://localhost:8084',
-  },
-  "code_origins": {
-    "APP_URL": 'http://localhost:8085',
-  }
-}
-
-export const options = function (variants) {
-  const scenarios = {};
-  for (const variant of Object.keys(variants)) {
-    scenarios[`load--petclinic--${variant}--warmup`] = {
-      executor: 'constant-vus',  // https://grafana.com/docs/k6/latest/using-k6/scenarios/executors/#all-executors
-      vus: 5,
-      duration: '165s',
-      gracefulStop: '2s',
-      env: {
-        "APP_URL": variants[variant]["APP_URL"]
-      }
-    };
-
-    scenarios[`load--petclinic--${variant}--high_load`] = {
-      executor: 'constant-vus',
-      vus: 5,
-      startTime: '167s',
-      duration: '15s',
-      gracefulStop: '2s',
-      env: {
-        "APP_URL": variants[variant]["APP_URL"]
-      }
-    };
-  }
-
-  return {
-    discardResponseBodies: true,
-    scenarios,
-  }
-}(variants);
-
-export default function () {
-
-  // find owner
-  const ownersList = http.get(`${__ENV.APP_URL}/owners?lastName=`);
-  checkResponse(ownersList, isOk);
-}
diff --git a/benchmark/load/petclinic/start-servers.sh b/benchmark/load/petclinic/start-servers.sh
deleted file mode 100755
index 1ebbb4e0418..00000000000
--- a/benchmark/load/petclinic/start-servers.sh
+++ /dev/null
@@ -1,28 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-
-start_server() {
-  local VARIANT=$1
-  local JAVA_OPTS=$2
-
-  if [ -n "$CI_JOB_TOKEN" ]; then
-    # Inside BP, so we can assume 24 CPU cores available and set CPU affinity
-    CPU_AFFINITY_APP=$3
-  else
-    CPU_AFFINITY_APP=""
-  fi
-
-  mkdir -p "${LOGS_DIR}/${VARIANT}"
-  ${CPU_AFFINITY_APP}java ${JAVA_OPTS} -Xms2G -Xmx2G -jar ${PETCLINIC} &> ${LOGS_DIR}/${VARIANT}/petclinic.log &PID=$!
-  echo "${CPU_AFFINITY_APP}java ${JAVA_OPTS} -Xms2G -Xmx2G -jar ${PETCLINIC} &> ${LOGS_DIR}/${VARIANT}/petclinic.log [PID=$!]"
-}
-
-start_server "no_agent" "-Dserver.port=8080" "taskset -c 31-32 " &
-start_server "tracing" "-javaagent:${TRACER} -Dserver.port=8081" "taskset -c 33-34 " &
-start_server "profiling" "-javaagent:${TRACER} -Ddd.profiling.enabled=true -Dserver.port=8082" "taskset -c 35-36 " &
-start_server "appsec" "-javaagent:${TRACER} -Ddd.appsec.enabled=true -Dserver.port=8083" "taskset -c 37-38 " &
-start_server "iast" "-javaagent:${TRACER} -Ddd.iast.enabled=true -Dserver.port=8084" "taskset -c 39-40 " &
-start_server "code_origins" "-javaagent:${TRACER} -Ddd.code.origin.for.spans.enabled=true -Dserver.port=8085" "taskset -c 41-42 " &
-
-wait
diff --git a/benchmark/load/run.sh b/benchmark/load/run.sh
deleted file mode 100755
index 5f2f265b045..00000000000
--- a/benchmark/load/run.sh
+++ /dev/null
@@ -1,77 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-
-function message() {
-  echo "$(date +"%T"): $1"
-}
-
-function healthcheck() {
-  local url=$1
-
-  while true; do
-    if [[ $(curl -fso /dev/null -w "%{http_code}" "${url}") = 200 ]]; then
-      break
-    fi
-  done
-}
-
-type=$1
-
-if [ -n "$CI_JOB_TOKEN" ]; then
-  # Inside BP, so we can assume 24 CPU cores on the second socket available and set CPU affinity
-  export CPU_AFFINITY_K6="taskset -c 24-27 "
-else
-  export CPU_AFFINITY_K6=""
-fi
-
-source "${UTILS_DIR}/update-java-version.sh" 17
-
-for app in *; do
-  if [[ ! -d "${app}" ]]; then
-    continue
-  fi
-
-  message "${type} benchmark: ${app} started"
-
-  export OUTPUT_DIR="${REPORTS_DIR}/${type}/${app}"
-  mkdir -p ${OUTPUT_DIR}
-
-  export LOGS_DIR="${ARTIFACTS_DIR}/${type}/${app}"
-  mkdir -p ${LOGS_DIR}
-
-  # Using profiler variants for healthcheck as they are the slowest
-  if [ "${app}" == "petclinic" ]; then
-    HEALTHCHECK_URL=http://localhost:8082
-    REPETITIONS_COUNT=2
-  elif [ "${app}" == "insecure-bank" ]; then
-    HEALTHCHECK_URL=http://localhost:8082/login
-    REPETITIONS_COUNT=2
-  else
-    echo "Unknown app ${app}"
-    exit 1
-  fi
-
-  for i in $(seq 1 $REPETITIONS_COUNT); do
-    bash -c "${UTILS_DIR}/../${type}/${app}/start-servers.sh" &
-
-    echo "Waiting for serves to start..."
-    if [ "${app}" == "petclinic" ]; then
-      for port in $(seq 8080 8085); do
-        healthcheck http://localhost:$port
-      done
-    elif [ "${app}" == "insecure-bank" ]; then
-      for port in $(seq 8080 8085); do
-        healthcheck http://localhost:$port/login
-      done
-    fi
-    echo "Servers are up!"
-
-    (
-      cd ${app} &&
-      bash -c "${CPU_AFFINITY_K6}${UTILS_DIR}/run-k6-load-test.sh 'pkill java'"
-    )
-  done
-
-  message "${type} benchmark: ${app} finished"
-done
diff --git a/benchmark/run.sh b/benchmark/run.sh
deleted file mode 100755
index bcd3649e9a0..00000000000
--- a/benchmark/run.sh
+++ /dev/null
@@ -1,43 +0,0 @@
-#!/usr/bin/env bash
-set -eu
-
-readonly SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)"
-readonly INITIAL_DIR="$(pwd)"
-readonly TRACER="${SCRIPT_DIR}/tracer/dd-java-agent.jar"
-
-cd "${SCRIPT_DIR}"
-
-# Build container image
-echo "Building base image ..."
-docker build \
-  -t dd-trace-java/benchmark \
-  .
-
-# Find or rebuild tracer to be used in the benchmarks
-if [[ ! -f "${TRACER}" ]]; then
-  mkdir -p "${SCRIPT_DIR}/tracer"
-  cd "${SCRIPT_DIR}/.."
-  readonly TRACER_VERSION=$(./gradlew properties -q | grep "version:" | awk '{print $2}')
-  readonly TRACER_COMPILED="${SCRIPT_DIR}/../dd-java-agent/build/libs/dd-java-agent-${TRACER_VERSION}.jar"
-  if [ ! -f "${TRACER_COMPILED}" ]; then
-    echo "Tracer not found, starting gradle compile ..."
-    ./gradlew assemble
-  fi
-  cp "${TRACER_COMPILED}" "${TRACER}"
-  cd "${SCRIPT_DIR}"
-fi
-
-# Trigger benchmarks
-echo "Running benchmarks ..."
-docker run --rm \
-  -v "${HOME}/.gradle":/home/benchmark/.gradle:delegated \
-  -v "${PWD}/..":/tracer:delegated \
-  -w /tracer/benchmark \
-  -e GRADLE_OPTS="-Dorg.gradle.daemon=false" \
-  --entrypoint=./benchmarks.sh \
-  --name dd-trace-java-benchmark \
-  --cap-add SYS_ADMIN \
-  dd-trace-java/benchmark \
-  "$@"
-
-cd "${INITIAL_DIR}"
diff --git a/benchmark/startup/insecure-bank/benchmark.json b/benchmark/startup/insecure-bank/benchmark.json
deleted file mode 100644
index 17c69a50847..00000000000
--- a/benchmark/startup/insecure-bank/benchmark.json
+++ /dev/null
@@ -1,22 +0,0 @@
-{
-  "name": "startup_insecure-bank",
-  "setup": "bash -c \"mkdir -p ${OUTPUT_DIR}/${VARIANT}\"",
-  "service": "bash -c \"${UTILS_DIR}/run-on-server-ready.sh http://localhost:8080/login 'pkill java'\"",
-  "run": "bash -c \"java -javaagent:${TRACER} -Ddd.benchmark.enabled=true -Ddd.benchmark.output.dir=${OUTPUT_DIR}/${VARIANT} ${JAVA_OPTS} -jar ${INSECURE_BANK} &> ${OUTPUT_DIR}/${VARIANT}/insecure-bank.log\"",
-  "iterations": 10,
-  "timeout": 60,
-  "variants": {
-    "tracing": {
-      "env": {
-        "VARIANT": "tracing",
-        "JAVA_OPTS": ""
-      }
-    },
-    "iast": {
-      "env": {
-        "VARIANT": "iast",
-        "JAVA_OPTS": "-Ddd.iast.enabled=true"
-      }
-    }
-  }
-}
diff --git a/benchmark/startup/petclinic/benchmark.json b/benchmark/startup/petclinic/benchmark.json
deleted file mode 100644
index 23713c38469..00000000000
--- a/benchmark/startup/petclinic/benchmark.json
+++ /dev/null
@@ -1,34 +0,0 @@
-{
-  "name": "startup_petclinic",
-  "setup": "bash -c \"mkdir -p ${OUTPUT_DIR}/${VARIANT}\"",
-  "service": "bash -c \"${UTILS_DIR}/run-on-server-ready.sh http://localhost:8080 'pkill java'\"",
-  "run": "bash -c \"java -javaagent:${TRACER} -Ddd.benchmark.enabled=true -Ddd.benchmark.output.dir=${OUTPUT_DIR}/${VARIANT} ${JAVA_OPTS} -jar ${PETCLINIC} &> ${OUTPUT_DIR}/${VARIANT}/petclinic.log\"",
-  "iterations": 10,
-  "timeout": 60,
-  "variants": {
-    "tracing": {
-      "env": {
-        "VARIANT": "tracing",
-        "JAVA_OPTS": ""
-      }
-    },
-    "profiling": {
-      "env": {
-        "VARIANT": "profiling",
-        "JAVA_OPTS": "-Ddd.profiling.enabled=true"
-      }
-    },
-    "appsec": {
-      "env": {
-        "VARIANT": "appsec",
-        "JAVA_OPTS": "-Ddd.appsec.enabled=true"
-      }
-    },
-    "iast": {
-      "env": {
-        "VARIANT": "iast",
-        "JAVA_OPTS": "-Ddd.iast.enabled=true"
-      }
-    }
-  }
-}
diff --git a/benchmark/startup/run.sh b/benchmark/startup/run.sh
deleted file mode 100755
index 432c65d3fd5..00000000000
--- a/benchmark/startup/run.sh
+++ /dev/null
@@ -1,5 +0,0 @@
-#!/usr/bin/env bash
-set -eu
-
-source "${UTILS_DIR}/update-java-version.sh" 17
-"${UTILS_DIR}/run-sirun-benchmarks.sh" "$@"
diff --git a/benchmark/utils/k6.js b/benchmark/utils/k6.js
deleted file mode 100644
index aa5147ae3c8..00000000000
--- a/benchmark/utils/k6.js
+++ /dev/null
@@ -1,21 +0,0 @@
-import {check} from 'k6';
-
-export function checkResponse(response) {
-  const checks = Array.prototype.slice.call(arguments, 1);
-  const reduced = checks.reduce((result, current) => Object.assign(result, current), {});
-  check(response, reduced);
-}
-
-export const isOk = {
-  'is OK': r => r.status === 200
-};
-
-export const isRedirect = {
-  'is redirect': r => r.status >= 300 && r.status < 400
-};
-
-export function bodyContains(text) {
-  return {
-    'body contains': r => r.body.includes(text)
-  }
-}
diff --git a/benchmark/utils/run-k6-load-test.sh b/benchmark/utils/run-k6-load-test.sh
deleted file mode 100755
index d3415f54eef..00000000000
--- a/benchmark/utils/run-k6-load-test.sh
+++ /dev/null
@@ -1,21 +0,0 @@
-#!/usr/bin/env bash
-set -eu
-
-command=$1
-exit_code=0
-
-cleanup() {
-  # run the exit command
-  bash -c "${command}"
-  exit $exit_code
-}
-
-trap cleanup EXIT ERR INT TERM
-
-echo "Starting k6 load test, logs are recorded into ${LOGS_DIR}/k6.log..."
-
-# run the k6 benchmark and store the result as JSON
-k6 run k6.js --out "json=${OUTPUT_DIR}/k6_$(date +%s).json" > "${LOGS_DIR}/k6.log" 2>&1
-exit_code=$?
-
-echo "k6 load test done !!!"
diff --git a/benchmark/utils/run-on-server-ready.sh b/benchmark/utils/run-on-server-ready.sh
deleted file mode 100755
index 2aad5aa9f70..00000000000
--- a/benchmark/utils/run-on-server-ready.sh
+++ /dev/null
@@ -1,11 +0,0 @@
-#!/usr/bin/env bash
-set -eu
-
-url=$1
-command=$2
-# wait for an HTTP server to come up and runs the selected command
-while true; do
-  if [[ $(curl -fso /dev/null -w "%{http_code}" "${url}") = 200 ]]; then
-    bash -c "${command}"
-  fi
-done
diff --git a/benchmark/utils/run-sirun-benchmarks.sh b/benchmark/utils/run-sirun-benchmarks.sh
deleted file mode 100755
index c0bc732dcfa..00000000000
--- a/benchmark/utils/run-sirun-benchmarks.sh
+++ /dev/null
@@ -1,41 +0,0 @@
-#!/usr/bin/env bash
-set -eu
-
-function message() {
-  echo "$(date +"%T"): $1"
-}
-
-run_benchmark() {
-  local type=$1
-  local app=$2
-  if [[ -d "${app}" ]] && [[ -f "${app}/benchmark.json" ]]; then
-
-    message "${type} benchmark: ${app} started"
-    cd "${app}"
-
-    # create output folder for the test
-    export OUTPUT_DIR="${REPORTS_DIR}/${type}/${app}"
-    mkdir -p "${OUTPUT_DIR}"
-
-    # substitute environment variables in the json file
-    benchmark=$(mktemp)
-    # shellcheck disable=SC2046
-    # shellcheck disable=SC2016
-    envsubst "$(printf '${%s} ' $(env | cut -d'=' -f1))" <benchmark.json >"${benchmark}"
-
-    # run the sirun test
-    sirun "${benchmark}" &>"${OUTPUT_DIR}/${app}.json"
-
-    message "${type} benchmark: ${app} finished"
-
-    cd ..
-  fi
-}
-
-if [ "$#" == '2' ]; then
-  run_benchmark "$@"
-else
-  for folder in *; do
-    run_benchmark "$1" "${folder}"
-  done
-fi
diff --git a/benchmark/utils/update-java-version.sh b/benchmark/utils/update-java-version.sh
deleted file mode 100755
index 3d76603e0ef..00000000000
--- a/benchmark/utils/update-java-version.sh
+++ /dev/null
@@ -1,5 +0,0 @@
-readonly target=$1
-readonly NEW_PATH=$(echo "${PATH}" | sed -e "s@/usr/lib/jvm/[[:digit:]]\+@/usr/lib/jvm/${target}@g")
-export PATH="${NEW_PATH}"
-
-java --version

From 698e89e682ebc53ce7df65c318005678955bf4d0 Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Wed, 14 Jan 2026 14:56:28 -0500
Subject: [PATCH 22/23] Comment out local benchmarks

---
 .gitlab/benchmarks.yml      | 144 ++++++++++++++++++------------------
 .gitlab/macrobenchmarks.yml |  12 +--
 2 files changed, 78 insertions(+), 78 deletions(-)

diff --git a/.gitlab/benchmarks.yml b/.gitlab/benchmarks.yml
index 28aef7ad58b..2d817d2df58 100644
--- a/.gitlab/benchmarks.yml
+++ b/.gitlab/benchmarks.yml
@@ -30,82 +30,82 @@
     UPSTREAM_BRANCH: $CI_COMMIT_REF_NAME # The branch or tag name for which project is built.
     UPSTREAM_COMMIT_SHA: $CI_COMMIT_SHA # The commit revision the project is built for.
 
-benchmarks-startup:
-  extends: .benchmarks
-  script:
-    - !reference [ .benchmarks, script ]
-    - ./steps/capture-hardware-software-info.sh
-    - ./steps/run-benchmarks.sh startup
-    - ./steps/analyze-results.sh startup
+# benchmarks-startup:
+#   extends: .benchmarks
+#   script:
+#     - !reference [ .benchmarks, script ]
+#     - ./steps/capture-hardware-software-info.sh
+#     - ./steps/run-benchmarks.sh startup
+#     - ./steps/analyze-results.sh startup
 
-benchmarks-load:
-  extends: .benchmarks
-  script:
-    - !reference [ .benchmarks, script ]
-    - ./steps/capture-hardware-software-info.sh
-    - ./steps/run-benchmarks.sh load
-    - ./steps/analyze-results.sh load
+# benchmarks-load:
+#   extends: .benchmarks
+#   script:
+#     - !reference [ .benchmarks, script ]
+#     - ./steps/capture-hardware-software-info.sh
+#     - ./steps/run-benchmarks.sh load
+#     - ./steps/analyze-results.sh load
 
-benchmarks-dacapo:
-  extends: .benchmarks
-  script:
-    - !reference [ .benchmarks, script ]
-    - ./steps/capture-hardware-software-info.sh
-    - ./steps/run-benchmarks.sh dacapo
-    - ./steps/analyze-results.sh dacapo
+# benchmarks-dacapo:
+#   extends: .benchmarks
+#   script:
+#     - !reference [ .benchmarks, script ]
+#     - ./steps/capture-hardware-software-info.sh
+#     - ./steps/run-benchmarks.sh dacapo
+#     - ./steps/analyze-results.sh dacapo
 
-benchmarks-post-results:
-  extends: .benchmarks
-  tags: ["arch:amd64"]
-  script:
-    - !reference [ .benchmarks, script ]
-    - ./steps/upload-results-to-s3.sh
-    - ./steps/post-pr-comment.sh
-  needs:
-    - job: benchmarks-startup
-      artifacts: true
-    - job: benchmarks-load
-      artifacts: true
-    - job: benchmarks-dacapo
-      artifacts: true
+# benchmarks-post-results:
+#   extends: .benchmarks
+#   tags: ["arch:amd64"]
+#   script:
+#     - !reference [ .benchmarks, script ]
+#     - ./steps/upload-results-to-s3.sh
+#     - ./steps/post-pr-comment.sh
+#   needs:
+#     - job: benchmarks-startup
+#       artifacts: true
+#     - job: benchmarks-load
+#       artifacts: true
+#     - job: benchmarks-dacapo
+#       artifacts: true
 
-check-big-regressions:
-  extends: .benchmarks
-  needs:
-    - job: benchmarks-startup
-      artifacts: true
-    - job: benchmarks-dacapo
-      artifacts: true
-  when: on_success
-  tags: ["arch:amd64"]
-  rules:
-    - if: '$POPULATE_CACHE'
-      when: never
-    - if: '$CI_COMMIT_BRANCH =~ /backport-pr-/'
-      when: never
-    - if: '$CI_COMMIT_BRANCH !~ /^(master|release\/)/'
-      when: on_success
-    - when: never
-  # ARTIFACTS_DIR /go/src/github.com/DataDog/apm-reliability/dd-trace-java/reports/
-  # need to convert them
-  script:
-    - !reference [ .benchmarks, script ]
-    - | 
-      for benchmarkType in startup dacapo; do
-          find "$ARTIFACTS_DIR/$benchmarkType" -name "benchmark-baseline.json" -o -name "benchmark-candidate.json" | while read file; do
-            relpath="${file#$ARTIFACTS_DIR/$benchmarkType/}"
-            prefix="${relpath%/benchmark-*}" # Remove the trailing /benchmark-(baseline|candidate).json
-            prefix="${prefix#./}" # Remove any leading ./
-            prefix="${prefix//\//-}" # Replace / with -
-            case "$file" in
-              *benchmark-baseline.json) type="baseline" ;;
-              *benchmark-candidate.json) type="candidate" ;;
-            esac
-            echo "Moving $file to $ARTIFACTS_DIR/${type}-${prefix}.converted.json"
-            cp "$file" "$ARTIFACTS_DIR/${type}-${prefix}.converted.json"
-          done
-      done
-    - bp-runner $CI_PROJECT_DIR/.gitlab/benchmarks/bp-runner.fail-on-regression.yml --debug
+# check-big-regressions:
+#   extends: .benchmarks
+#   needs:
+#     - job: benchmarks-startup
+#       artifacts: true
+#     - job: benchmarks-dacapo
+#       artifacts: true
+#   when: on_success
+#   tags: ["arch:amd64"]
+#   rules:
+#     - if: '$POPULATE_CACHE'
+#       when: never
+#     - if: '$CI_COMMIT_BRANCH =~ /backport-pr-/'
+#       when: never
+#     - if: '$CI_COMMIT_BRANCH !~ /^(master|release\/)/'
+#       when: on_success
+#     - when: never
+#   # ARTIFACTS_DIR /go/src/github.com/DataDog/apm-reliability/dd-trace-java/reports/
+#   # need to convert them
+#   script:
+#     - !reference [ .benchmarks, script ]
+#     - | 
+#       for benchmarkType in startup dacapo; do
+#           find "$ARTIFACTS_DIR/$benchmarkType" -name "benchmark-baseline.json" -o -name "benchmark-candidate.json" | while read file; do
+#             relpath="${file#$ARTIFACTS_DIR/$benchmarkType/}"
+#             prefix="${relpath%/benchmark-*}" # Remove the trailing /benchmark-(baseline|candidate).json
+#             prefix="${prefix#./}" # Remove any leading ./
+#             prefix="${prefix//\//-}" # Replace / with -
+#             case "$file" in
+#               *benchmark-baseline.json) type="baseline" ;;
+#               *benchmark-candidate.json) type="candidate" ;;
+#             esac
+#             echo "Moving $file to $ARTIFACTS_DIR/${type}-${prefix}.converted.json"
+#             cp "$file" "$ARTIFACTS_DIR/${type}-${prefix}.converted.json"
+#           done
+#       done
+#     - bp-runner $CI_PROJECT_DIR/.gitlab/benchmarks/bp-runner.fail-on-regression.yml --debug
 
 .dsm-kafka-benchmarks:
   stage: benchmarks
diff --git a/.gitlab/macrobenchmarks.yml b/.gitlab/macrobenchmarks.yml
index b1c5681fb5b..151dcf496e4 100644
--- a/.gitlab/macrobenchmarks.yml
+++ b/.gitlab/macrobenchmarks.yml
@@ -92,12 +92,12 @@ check-slo-breaches:
       artifacts: true
     - job: otel-latest
       artifacts: true
-    - job: benchmarks-startup
-      artifacts: true
-    - job: benchmarks-load
-      artifacts: true
-    - job: benchmarks-dacapo
-      artifacts: true
+    # - job: benchmarks-startup
+    #   artifacts: true
+    # - job: benchmarks-load
+    #   artifacts: true
+    # - job: benchmarks-dacapo
+    #   artifacts: true
   script:
     # macrobenchmarks are located here, files are already in "converted" format
     - export ARTIFACTS_DIR="$(pwd)/platform/artifacts/" && mkdir -p "${ARTIFACTS_DIR}"

From c3597911d523f088ae48baf24b6b097699bcb48a Mon Sep 17 00:00:00 2001
From: Sarah Chen <sarah.chen@datadoghq.com>
Date: Fri, 16 Jan 2026 15:49:38 -0500
Subject: [PATCH 23/23] Change stage names

---
 .gitlab-ci.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index 706ca302dad..6c1bf1f5156 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -19,8 +19,8 @@ stages:
   - infrastructure
   - java-spring-petclinic-tests
   - java-spring-petclinic-macrobenchmarks
-  - java-spring-petclinic-microbenchmarks
-  - java-insecure-bank-microbenchmarks
+  - java-startup-microbenchmarks
+  - java-load-microbenchmarks
   - generate-slos
   - macrobenchmarks
   - tests