Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[SPARK-32975] [K8S] Ensure driver is ready before executors start #32739

Closed
wants to merge 1 commit into from
Closed

[SPARK-32975] [K8S] Ensure driver is ready before executors start #32739

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions ...es/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsAllocator.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ package org.apache.spark.scheduler.cluster.k8s

import java.time.Instant
import java.util.concurrent.ConcurrentHashMap
import java.util.concurrent.TimeUnit
import java.util.concurrent.atomic.{AtomicInteger, AtomicLong}

import scala.collection.JavaConverters._
Expand Down Expand Up @@ -61,6 +62,8 @@ private[spark] class ExecutorPodsAllocator(
podAllocationDelay * 5,
conf.get(KUBERNETES_ALLOCATION_EXECUTOR_TIMEOUT))

private val driverPodReadinessTimeout = 5

private val executorIdleTimeout = conf.get(DYN_ALLOCATION_EXECUTOR_IDLE_TIMEOUT) * 1000

private val namespace = conf.get(KUBERNETES_NAMESPACE)
Expand Down Expand Up @@ -345,6 +348,16 @@ private[spark] class ExecutorPodsAllocator(
s"ResourceProfile Id: $resourceProfileId, target: $expected running: $running.")
// Check reusable PVCs for this executor allocation batch
val reusablePVCs = getReusablePVCs(applicationId, pvcsInUse)
// wait until the driver pod is ready to ensure executors can connect to driver svc
if (numExecutorsToAllocate > 0) {
try {
kubernetesClient.pods().inNamespace(namespace).withName(kubernetesDriverPodName.get).
waitUntilReady(driverPodReadinessTimeout, TimeUnit.MINUTES)
} catch {
case e: InterruptedException =>
logWarning(s"Timeout waiting for driver pod ${kubernetesDriverPodName.get} get ready")
}
}
for ( _ <- 0 until numExecutorsToAllocate) {
val newExecutorId = EXECUTOR_ID_COUNTER.incrementAndGet()
val executorConf = KubernetesConf.createExecutorConf(
Expand Down