Flaky test runner improvements/fixes (elastic#49367)

* Allocate multiple flaky test runner agents as executions grow

* WIP support for deleting kibana install dir during CI

* Add setup script for testing scripts

* Add REMOVE_KIBANA_INSTALL_DIR=1 to flaky test runner

* Change flaky test runner worker processes from 8 to 12

.ci/Jenkinsfile_flaky

@@ -8,26 +8,28 @@ def JOB_PARTS = params.CI_GROUP.split(':')
 def IS_XPACK = JOB_PARTS[0] == 'xpack'
 def JOB = JOB_PARTS[1]
 def CI_GROUP = JOB_PARTS.size() > 2 ? JOB_PARTS[2] : ''
+def EXECUTIONS = params.NUMBER_EXECUTIONS.toInteger()
+def AGENT_COUNT = getAgentCount(EXECUTIONS)
 
 def worker = getWorkerFromParams(IS_XPACK, JOB, CI_GROUP)
 
 def workerFailures = []
 
 currentBuild.displayName += trunc(" ${params.GITHUB_OWNER}:${params.branch_specifier}", 24)
-currentBuild.description = "${params.CI_GROUP}<br />Executions: ${params.NUMBER_EXECUTIONS}"
-
-// Note: If you increase agent count, it will execute NUMBER_EXECUTIONS per agent. It will not divide them up amongst the agents
-// e.g. NUMBER_EXECUTIONS = 25, agentCount = 4 results in 100 total executions
-def agentCount = 1
+currentBuild.description = "${params.CI_GROUP}<br />Agents: ${AGENT_COUNT}<br />Executions: ${params.NUMBER_EXECUTIONS}"
 
 stage("Kibana Pipeline") {
   timeout(time: 180, unit: 'MINUTES') {
     timestamps {
       ansiColor('xterm') {
         def agents = [:]
-        for(def agentNumber = 1; agentNumber <= agentCount; agentNumber++) {
+        for(def agentNumber = 1; agentNumber <= AGENT_COUNT; agentNumber++) {
+          def agentNumberInside = agentNumber
+          def agentExecutions = floor(EXECUTIONS/AGENT_COUNT) + (agentNumber <= EXECUTIONS%AGENT_COUNT ? 1 : 0)
           agents["agent-${agentNumber}"] = {
             catchError {
+              print "Agent ${agentNumberInside} - ${agentExecutions} executions"
+
               kibanaPipeline.withWorkers('flaky-test-runner', {
                 if (!IS_XPACK) {
                   kibanaPipeline.buildOss()
@@ -37,7 +39,7 @@ stage("Kibana Pipeline") {
                 } else {
                   kibanaPipeline.buildXpack()
                 }
-              }, getWorkerMap(agentNumber, params.NUMBER_EXECUTIONS.toInteger(), worker, workerFailures))()
+              }, getWorkerMap(agentNumberInside, agentExecutions, worker, workerFailures))()
             }
           }
         }
@@ -77,17 +79,20 @@ def getWorkerFromParams(isXpack, job, ciGroup) {
   }
 }
 
-def getWorkerMap(agentNumber, numberOfExecutions, worker, workerFailures, maxWorkers = 14) {
+def getWorkerMap(agentNumber, numberOfExecutions, worker, workerFailures, maxWorkerProcesses = 12) {
   def workerMap = [:]
-  def numberOfWorkers = Math.min(numberOfExecutions, maxWorkers)
+  def numberOfWorkers = Math.min(numberOfExecutions, maxWorkerProcesses)
 
   for(def i = 1; i <= numberOfWorkers; i++) {
     def workerExecutions = numberOfExecutions/numberOfWorkers + (i <= numberOfExecutions%numberOfWorkers ? 1 : 0)
 
     workerMap["agent-${agentNumber}-worker-${i}"] = { workerNumber ->
       for(def j = 0; j < workerExecutions; j++) {
         print "Execute agent-${agentNumber} worker-${workerNumber}: ${j}"
-        withEnv(["JOB=agent-${agentNumber}-worker-${workerNumber}-${j}"]) {
+        withEnv([
+          "JOB=agent-${agentNumber}-worker-${workerNumber}-${j}",
+          "REMOVE_KIBANA_INSTALL_DIR=1",
+        ]) {
           catchError {
             try {
               worker(workerNumber)
@@ -104,10 +109,23 @@ def getWorkerMap(agentNumber, numberOfExecutions, worker, workerFailures, maxWor
   return workerMap
 }
 
+def getAgentCount(executions) {
+  // Increase agent count every 24 worker processess, up to 3 agents maximum
+  return Math.min(3, 1 + floor(executions/24))
+}
+
 def trunc(str, length) {
   if (str.size() >= length) {
     return str.take(length) + "..."
   }
 
   return str;
 }
+
+// All of the real rounding/truncating methods are sandboxed
+def floor(num) {
+  return num
+    .toString()
+    .split('\\.')[0]
+    .toInteger()
+}

test/scripts/jenkins_ci_group.sh

@@ -1,14 +1,6 @@
 #!/usr/bin/env bash
 
-set -e
-
-if [[ -z "$IS_PIPELINE_JOB" ]] ; then
-  trap 'node "$KIBANA_DIR/src/dev/failed_tests/cli"' EXIT
-else
-  source src/dev/ci_setup/setup_env.sh
-fi
-
-export TEST_BROWSER_HEADLESS=1
+source test/scripts/jenkins_test_setup.sh
 
 if [[ -z "$IS_PIPELINE_JOB" ]] ; then
   yarn run grunt functionalTests:ensureAllTestsInCiGroup;

test/scripts/jenkins_test_setup.sh

@@ -0,0 +1,17 @@
+set -e
+
+function post_work() {
+  set +e
+
+  if [[ -z "$REMOVE_KIBANA_INSTALL_DIR" && -z "$KIBANA_INSTALL_DIR" && -d "$KIBANA_INSTALL_DIR" ]]; then
+    rm -rf "$REMOVE_KIBANA_INSTALL_DIR"
+  fi
+}
+
+trap 'post_work' EXIT
+
+export TEST_BROWSER_HEADLESS=1
+
+if [[ -n "$IS_PIPELINE_JOB" ]] ; then
+  source src/dev/ci_setup/setup_env.sh
+fi

test/scripts/jenkins_xpack_ci_group.sh

@@ -1,14 +1,6 @@
 #!/usr/bin/env bash
 
-set -e
-
-if [[ -z "$IS_PIPELINE_JOB" ]] ; then
-  trap 'node "$KIBANA_DIR/src/dev/failed_tests/cli"' EXIT
-else
-  source src/dev/ci_setup/setup_env.sh
-fi
-
-export TEST_BROWSER_HEADLESS=1
+source test/scripts/jenkins_test_setup.sh
 
 if [[ -z "$IS_PIPELINE_JOB" ]] ; then
   echo " -> Ensuring all functional tests are in a ciGroup"