Merge branch 'main' into eui-ghost/observability

.buildkite/pipelines/es_serverless/verify_es_serverless_image.yml

@@ -76,7 +76,7 @@ steps:
           queue: n2-4-spot
         depends_on: build
         timeout_in_minutes: 60
-        parallelism: 2
+        parallelism: 4
         retry:
           automatic:
             - exit_status: '*'
@@ -95,6 +95,32 @@ steps:
             - exit_status: '*'
               limit: 1
 
+      - command: .buildkite/scripts/steps/functional/defend_workflows_serverless.sh
+        label: 'Defend Workflows Cypress Tests on Serverless'
+        if: "build.env('SKIP_CYPRESS') != '1' && build.env('SKIP_CYPRESS') != 'true'"
+        agents:
+          queue: n2-4-virt
+        depends_on: build
+        timeout_in_minutes: 60
+        parallelism: 6
+        retry:
+          automatic:
+            - exit_status: '*'
+              limit: 1
+
+      - command: .buildkite/scripts/steps/functional/security_serverless_osquery.sh
+        label: 'Serverless Osquery Cypress Tests'
+        if: "build.env('SKIP_CYPRESS') != '1' && build.env('SKIP_CYPRESS') != 'true'"
+        agents:
+          queue: n2-4-spot
+        depends_on: build
+        timeout_in_minutes: 60
+        parallelism: 6
+        retry:
+          automatic:
+            - exit_status: '*'
+              limit: 1
+
   - wait: ~
 
   - label: ":arrow_up::elastic::arrow_up: Promote docker image"

.buildkite/pipelines/flaky_tests/pipeline.ts

@@ -162,10 +162,11 @@ for (const testSuite of testSuites) {
           `Group configuration was not found in groups.json for the following cypress suite: {${suiteName}}.`
         );
       }
+      const agentQueue = suiteName.includes('defend_workflows') ? 'n2-4-virt' : 'n2-4-spot';
       steps.push({
         command: `.buildkite/scripts/steps/functional/${suiteName}.sh`,
         label: group.name,
-        agents: { queue: 'n2-4-spot' },
+        agents: { queue: agentQueue },
         depends_on: 'build',
         parallelism: testSuite.count,
         concurrency,

.buildkite/pipelines/on_merge.yml

@@ -85,7 +85,7 @@ steps:
       queue: n2-4-spot
     depends_on: build
     timeout_in_minutes: 60
-    parallelism: 4
+    parallelism: 6
     retry:
       automatic:
         - exit_status: '*'
@@ -97,7 +97,7 @@ steps:
       queue: n2-4-spot
     depends_on: build
     timeout_in_minutes: 60
-    parallelism: 2
+    parallelism: 4
     retry:
       automatic:
         - exit_status: '*'
@@ -157,7 +157,7 @@ steps:
       queue: n2-4-virt
     depends_on: build
     timeout_in_minutes: 60
-    parallelism: 6
+    parallelism: 10
     retry:
       automatic:
         - exit_status: '*'
@@ -168,8 +168,8 @@ steps:
     agents:
       queue: n2-4-virt
     depends_on: build
-    timeout_in_minutes: 120
-    parallelism: 2
+    timeout_in_minutes: 60
+    parallelism: 6
     retry:
       automatic:
         - exit_status: '*'
@@ -180,7 +180,7 @@ steps:
     agents:
       queue: n2-4-spot
     depends_on: build
-    timeout_in_minutes: 120
+    timeout_in_minutes: 60
     parallelism: 2
     retry:
       automatic:
@@ -192,7 +192,19 @@ steps:
     agents:
       queue: n2-4-spot
     depends_on: build
-    timeout_in_minutes: 50
+    timeout_in_minutes: 60
+    parallelism: 6
+    retry:
+      automatic:
+        - exit_status: '*'
+          limit: 1
+
+  - command: .buildkite/scripts/steps/functional/security_serverless_osquery.sh
+    label: 'Serverless Osquery Cypress Tests'
+    agents:
+      queue: n2-4-spot
+    depends_on: build
+    timeout_in_minutes: 60
     parallelism: 6
     retry:
       automatic:
@@ -242,7 +254,7 @@ steps:
   - command: .buildkite/scripts/steps/check_types.sh
     label: 'Check Types'
     agents:
-      queue: n2-16-spot
+      queue: n2-2-spot
     timeout_in_minutes: 60
     retry:
       automatic:

.buildkite/pipelines/pull_request/base.yml

@@ -20,7 +20,7 @@ steps:
           limit: 3
 
   - command: .buildkite/scripts/steps/build_api_docs.sh
-    label: 'Build API Docs'
+    label: 'Check Types and Build API Docs'
     agents:
       queue: n2-4-spot
     key: build_api_docs
@@ -63,7 +63,7 @@ steps:
       queue: n2-4-spot
     depends_on: build
     timeout_in_minutes: 60
-    parallelism: 4
+    parallelism: 6
     retry:
       automatic:
         - exit_status: '*'
@@ -75,7 +75,7 @@ steps:
       queue: n2-4-spot
     depends_on: build
     timeout_in_minutes: 60
-    parallelism: 2
+    parallelism: 4
     retry:
       automatic:
         - exit_status: '*'
@@ -135,52 +135,30 @@ steps:
       queue: n2-4-virt
     depends_on: build
     timeout_in_minutes: 60
-    parallelism: 6
+    parallelism: 10
     retry:
       automatic:
         - exit_status: '*'
           limit: 1
 
-  - command: .buildkite/scripts/steps/functional/defend_workflows_burn.sh
-    label: 'Defend Workflows Cypress Tests, burning changed specs'
-    agents:
-      queue: n2-4-virt
-    depends_on: build
-    timeout_in_minutes: 60
-    soft_fail: true
-    parallelism: 1
-    retry:
-      automatic: false
-
   - command: .buildkite/scripts/steps/functional/defend_workflows_serverless.sh
     label: 'Defend Workflows Cypress Tests on Serverless'
     agents:
       queue: n2-4-virt
     depends_on: build
-    timeout_in_minutes: 120
-    parallelism: 2
+    timeout_in_minutes: 60
+    parallelism: 6
     retry:
       automatic:
         - exit_status: '*'
           limit: 1
 
-  - command: .buildkite/scripts/steps/functional/defend_workflows_serverless_burn.sh
-    label: 'Defend Workflows Cypress Tests on Serverless, burning changed specs'
-    agents:
-      queue: n2-4-virt
-    depends_on: build
-    timeout_in_minutes: 60
-    soft_fail: true
-    parallelism: 1
-    retry:
-      automatic: false
-
   - command: .buildkite/scripts/steps/functional/threat_intelligence.sh
     label: 'Threat Intelligence Cypress Tests'
     agents:
       queue: n2-4-spot
     depends_on: build
-    timeout_in_minutes: 120
+    timeout_in_minutes: 60
     parallelism: 2
     retry:
       automatic:
@@ -192,40 +170,19 @@ steps:
     agents:
       queue: n2-4-spot
     depends_on: build
-    timeout_in_minutes: 50
+    timeout_in_minutes: 60
     parallelism: 6
     retry:
       automatic:
         - exit_status: '*'
           limit: 1
 
-  - command: .buildkite/scripts/steps/functional/security_solution_burn.sh
-    label: 'Security Solution Cypress tests, burning changed specs'
-    agents:
-      queue: n2-4-spot
-    depends_on: build
-    timeout_in_minutes: 60
-    parallelism: 1
-    retry:
-      automatic: false
-    soft_fail: true
-
-  - command: .buildkite/scripts/steps/functional/osquery_cypress_burn.sh
-    label: 'Osquery Cypress Tests, burning changed specs'
-    agents:
-      queue: n2-4-spot
-    depends_on: build
-    timeout_in_minutes: 50
-    soft_fail: true
-    retry:
-      automatic: false
-
   - command: .buildkite/scripts/steps/functional/security_serverless_osquery.sh
     label: 'Serverless Osquery Cypress Tests'
     agents:
       queue: n2-4-spot
     depends_on: build
-    timeout_in_minutes: 50
+    timeout_in_minutes: 60
     parallelism: 6
     retry:
       automatic:
@@ -275,13 +232,3 @@ steps:
       automatic:
         - exit_status: '-1'
           limit: 3
-
-  - command: .buildkite/scripts/steps/check_types.sh
-    label: 'Check Types'
-    agents:
-      queue: n2-16-spot
-    timeout_in_minutes: 60
-    retry:
-      automatic:
-        - exit_status: '-1'
-          limit: 3

.buildkite/pipelines/pull_request/cypress_burn.yml

@@ -0,0 +1,43 @@
+steps:
+  - command: .buildkite/scripts/steps/functional/defend_workflows_burn.sh
+    label: 'Defend Workflows Cypress Tests, burning changed specs'
+    agents:
+      queue: n2-4-virt
+    depends_on: build
+    timeout_in_minutes: 60
+    soft_fail: true
+    parallelism: 1
+    retry:
+      automatic: false
+
+  - command: .buildkite/scripts/steps/functional/defend_workflows_serverless_burn.sh
+    label: 'Defend Workflows Cypress Tests on Serverless, burning changed specs'
+    agents:
+      queue: n2-4-virt
+    depends_on: build
+    timeout_in_minutes: 60
+    soft_fail: true
+    parallelism: 1
+    retry:
+      automatic: false
+
+  - command: .buildkite/scripts/steps/functional/security_solution_burn.sh
+    label: 'Security Solution Cypress tests, burning changed specs'
+    agents:
+      queue: n2-4-spot
+    depends_on: build
+    timeout_in_minutes: 60
+    parallelism: 1
+    retry:
+      automatic: false
+    soft_fail: true
+
+  - command: .buildkite/scripts/steps/functional/osquery_cypress_burn.sh
+    label: 'Osquery Cypress Tests, burning changed specs'
+    agents:
+      queue: n2-4-spot
+    depends_on: build
+    timeout_in_minutes: 50
+    soft_fail: true
+    retry:
+      automatic: false

.buildkite/pipelines/quality-gates/pipeline.tests-production.yaml

@@ -3,7 +3,7 @@
 # A failure in this pipeline build will prevent further progression to the subsequent stage.
 
 steps:
-  - label: ":pipeline::kibana::seedling: Trigger SLO check"
+  - label: ":kibana: SLO check"
     trigger: "serverless-quality-gates" # https://buildkite.com/elastic/serverless-quality-gates
     build:
       message: "${BUILDKITE_MESSAGE} (triggered by pipeline.tests-production.yaml)"
@@ -13,7 +13,7 @@ steps:
         CHECK_SLO_TAG: kibana
     soft_fail: true
 
-  - label: ":pipeline::rocket::seedling: Trigger control-plane e2e tests"
+  - label: ":rocket: control-plane e2e tests"
     if: build.env("ENVIRONMENT") == "production-canary"
     trigger: "ess-k8s-production-e2e-tests" # https://buildkite.com/elastic/ess-k8s-production-e2e-tests
     build:
@@ -25,3 +25,6 @@ steps:
   - label: ":cookie: 24h bake time before continuing promotion"
     if: build.env("ENVIRONMENT") == "production-canary"
     command: "sleep 86400"
+    agents:
+      # How long can this agent live for in minutes - 25 hours
+      instanceMaxAge: 1500

.buildkite/pipelines/quality-gates/pipeline.tests-qa.yaml

@@ -3,7 +3,7 @@
 # A failure in this pipeline build will prevent further progression to the subsequent stage.
 
 steps:
-  - label: ":pipeline::kibana::seedling: Trigger Kibana Serverless Tests for ${ENVIRONMENT}"
+  - label: ":kibana: Kibana Serverless Tests for ${ENVIRONMENT}"
     trigger: appex-qa-serverless-kibana-ftr-tests # https://buildkite.com/elastic/appex-qa-serverless-kibana-ftr-tests
     soft_fail: true # Remove this before release or when tests stabilize
     build:
@@ -12,8 +12,8 @@ steps:
         EC_ENV: qa
         EC_REGION: aws-eu-west-1
       message: "${BUILDKITE_MESSAGE} (triggered by pipeline.tests-qa.yaml)"
-  
-  # TODO: Uncomment this code when the integration is ready. 
+
+  # TODO: Uncomment this code when the integration is ready.
   # - label: ":pipeline::female-detective::seedling: Trigger Security Solution quality gate script"
   #   trigger: security-serverless-quality-gate # https://buildkite.com/elastic/security-serverless-quality-gate
   #   soft_fail: true # Remove this when tests are fixed
@@ -22,15 +22,14 @@ steps:
   #       ENVIRONMENT: ${ENVIRONMENT}
   #     message: "${BUILDKITE_MESSAGE} (triggered by pipeline.tests-qa.yaml)"
 
-  - label: ":pipeline::ship::seedling: Trigger Fleet serverless smoke tests for ${ENVIRONMENT}"
+  - label: ":ship: Fleet serverless smoke tests for ${ENVIRONMENT}"
     trigger: fleet-smoke-tests # https://buildkite.com/elastic/fleet-smoke-tests
-    soft_fail: true # Remove this before release
     build:
       env:
         ENVIRONMENT: ${ENVIRONMENT}
       message: "${BUILDKITE_MESSAGE} (triggered by pipeline.tests-qa.yaml)"
 
-  - label: ":pipeline::rocket::seedling: Trigger control-plane e2e tests"
+  - label: ":rocket: control-plane e2e tests"
     trigger: "ess-k8s-qa-e2e-tests-daily" # https://buildkite.com/elastic/ess-k8s-qa-e2e-tests-daily
     build:
       env:

.buildkite/pipelines/quality-gates/pipeline.tests-staging.yaml

@@ -3,15 +3,15 @@
 # A failure in this pipeline build will prevent further progression to the subsequent stage.
 
 steps:
-  - label: ":pipeline::rocket::seedling: Trigger control-plane e2e tests"
+  - label: ":rocket: control-plane e2e tests"
     trigger: "ess-k8s-staging-e2e-tests" # https://buildkite.com/elastic/ess-k8s-staging-e2e-tests
     build:
       env:
         REGION_ID: aws-us-east-1
         NAME_PREFIX: ci_test_kibana-promotion_
       message: "${BUILDKITE_MESSAGE} (triggered by pipeline.tests-staging.yaml)"
 
-  - label: ":pipeline::kibana::seedling: Trigger Kibana Serverless Tests for ${ENVIRONMENT}"
+  - label: ":kibana: Kibana Serverless Tests for ${ENVIRONMENT}"
     trigger: appex-qa-serverless-kibana-ftr-tests # https://buildkite.com/elastic/appex-qa-serverless-kibana-ftr-tests
     soft_fail: true # Remove this before release or when tests stabilize
     build: