Add ability for parallel Jenkins multi-arch builds

Trigger all jenkins builds (adding them to jenkins queue) and then parallel wait on them. We control the concurrency by the number of executors per arch (or if we add multiple machines that match the build label).

Author: yosifkit

Jenkinsfile.build

@@ -1,15 +1,18 @@
 // one job per arch (for now) that just builds "the top thing" (triggered by the meta-update job)
 properties([
-	disableConcurrentBuilds(),
 	disableResume(),
 	durabilityHint('PERFORMANCE_OPTIMIZED'),
 	parameters([
+		string(name: 'identifier', trim: true),
 		string(name: 'buildId', trim: true),
 	]),
 ])
 
 env.BASHBREW_ARCH = env.JOB_NAME.minus('/build').split('/')[-1] // "windows-amd64", "arm64v8", etc
 env.BUILD_ID = params.buildId
+if (params.identifier) {
+	currentBuild.displayName = params.identifier + ' (#' + currentBuild.number + ')'
+}
 
 node('multiarch-' + env.BASHBREW_ARCH) { ansiColor('xterm') {
 	stage('Checkout') {

Jenkinsfile.trigger

@@ -102,69 +102,98 @@ if (breakEarly) { return } // thanks Jenkins...
 
 // new data to be added to the past-jobs.json
 // { lastTime: unixTimestamp, url: "" }
-def buildCompletionData = [:]
+buildCompletionData = [:]
 
-for (buildObj in queue) {
-	stage(buildObj.identifier) {
-		//def json = writeJSON(json: buildObj, returnText: true)
-		//echo(json) // for debugging/data purposes
+// list of closures that we can use to wait for the jobs on.
+def waitQueue = [:]
+def addToWait(identifier, buildId, externalizableId) {
+	return {
+		// "catchError" to set "stageResult" :(
+		catchError(message: 'Build of "' + identifier + '" failed', buildResult: 'UNSTABLE', stageResult: 'FAILURE') {
+			stage(identifier) {
+				def res = waitForBuild(
+					runId: externalizableId,
+					propagateAbort: true, // allow cancelling this job to cancel all the triggered jobs
+				)
+				buildCompletionData[buildId] = [
+					lastTime: (res.startTimeInMillis + res.duration) / 1000, // convert to seconds
+					url: res.absoluteUrl,
+				]
+				if (res.result != 'SUCCESS') {
+					// set stage result via catchError
+					error(res.result)
+				}
+			}
+		}
+	}
+}
+
+// stage to wrap up all the build job triggers that get waited on later
+stage('trigger') {
+	for (int i = 0; i < queue.size(); i++) {
+		def buildObj = queue[i]
 
 		// "catchError" to set "stageResult" :(
 		catchError(message: 'Build of "' + buildObj.identifier + '" failed', buildResult: 'UNSTABLE', stageResult: 'FAILURE') {
 			if (buildObj.gha_payload) {
-				node {
-					withEnv([
-						'payload=' + buildObj.gha_payload,
-					]) {
-						withCredentials([
-							string(
-								variable: 'GH_TOKEN',
-								credentialsId: 'github-access-token-docker-library-bot-meta',
-							),
+				stage(buildObj.identifier) {
+					node {
+						withEnv([
+							'payload=' + buildObj.gha_payload,
 						]) {
-							sh '''
-								set -u +x
-
-								# https://docs.github.com/en/free-pro-team@latest/rest/actions/workflows?apiVersion=2022-11-28#create-a-workflow-dispatch-event
-								curl -fL \
-									-X POST \
-									-H 'Accept: application/vnd.github+json' \
-									-H "Authorization: Bearer $GH_TOKEN" \
-									-H 'X-GitHub-Api-Version: 2022-11-28' \
-									https://api.github.com/repos/docker-library/meta/actions/workflows/build.yml/dispatches \
-									-d "$payload"
-							'''
+							withCredentials([
+								string(
+									variable: 'GH_TOKEN',
+									credentialsId: 'github-access-token-docker-library-bot-meta',
+								),
+							]) {
+								sh '''
+									set -u +x
+
+									# https://docs.github.com/en/free-pro-team@latest/rest/actions/workflows?apiVersion=2022-11-28#create-a-workflow-dispatch-event
+									curl -fL \
+										-X POST \
+										-H 'Accept: application/vnd.github+json' \
+										-H "Authorization: Bearer $GH_TOKEN" \
+										-H 'X-GitHub-Api-Version: 2022-11-28' \
+										https://api.github.com/repos/docker-library/meta/actions/workflows/build.yml/dispatches \
+										-d "$payload"
+								'''
+							}
 						}
+						// record that GHA was triggered (for tracking continued triggers that fail to push an image)
+						buildCompletionData[buildObj.buildId] = [
+							lastTime: System.currentTimeMillis() / 1000, // convert to seconds
+							url: currentBuild.absoluteUrl,
+						]
 					}
-					// record that GHA was triggered (for tracking continued triggers that fail to push an image)
-					buildCompletionData[buildObj.buildId] = [
-						lastTime: System.currentTimeMillis() / 1000, // convert to seconds
-						url: currentBuild.absoluteUrl,
-					]
 				}
 			} else {
+				// why not parallel these build() invocations?
+				// jenkins parallel closures get started in a randomish order, ruining our sorted queue
 				def res = build(
 					job: 'build',
 					parameters: [
+						string(name: 'identifier', value: buildObj.identifier),
 						string(name: 'buildId', value: buildObj.buildId),
 					],
 					propagate: false,
-					quietPeriod: 5, // seconds
+					// trigger these quickly so they all get added to Jenkins queue in "queue" order
+					quietPeriod: 0, // seconds
+					// we'll wait on them after they are all queued
+					waitForStart: true,
 				)
-				// record the job failure
-				buildCompletionData[buildObj.buildId] = [
-					lastTime: (res.startTimeInMillis + res.duration) / 1000, // convert to seconds
-					url: res.absoluteUrl,
-				]
-				if (res.result != 'SUCCESS') {
-					// set stage result via catchError
-					error(res.result)
-				}
+				waitQueue[buildObj.identifier] = addToWait(buildObj.identifier, buildObj.buildId, res.externalizableId)
 			}
 		}
 	}
 }
 
+// wait on all the 'build' jobs that were queued
+if (waitQueue.size() > 0) {
+	parallel waitQueue
+}
+
 // save currentJobs so we can use it next run as pastJobs
 node {
 	def buildCompletionDataJson = writeJSON(json: buildCompletionData, returnText: true)