Github user kayousterhout commented on a diff in the pull request:
https://github.com/apache/spark/pull/14079#discussion_r86473130
--- Diff:
core/src/main/scala/org/apache/spark/scheduler/BlacklistTracker.scala ---
@@ -17,10 +17,254 @@
package org.apache.spark.scheduler
+import java.util.concurrent.atomic.AtomicReference
+
+import scala.collection.mutable.{ArrayBuffer, HashMap, HashSet}
+
import org.apache.spark.SparkConf
import org.apache.spark.internal.Logging
import org.apache.spark.internal.config
-import org.apache.spark.util.Utils
+import org.apache.spark.util.{Clock, SystemClock, Utils}
+
+/**
+ * BlacklistTracker is designed to track problematic executors and nodes.
It supports blacklisting
+ * executors and nodes across an entire application (with a periodic
expiry). TaskSetManagers add
+ * additional blacklisting of executors and nodes for individual tasks and
stages which works in
+ * concert with the blacklisting here.
+ *
+ * The tracker needs to deal with a variety of workloads, eg.:
+ *
+ * * bad user code -- this may lead to many task failures, but that
should not count against
+ * individual executors
+ * * many small stages -- this may prevent a bad executor for having many
failures within one
+ * stage, but still many failures over the entire application
+ * * "flaky" executors -- they don't fail every task, but are still
faulty enough to merit
+ * blacklisting
+ *
+ * See the design doc on SPARK-8425 for a more in-depth discussion.
+ *
+ * THREADING: As with most helpers of TaskSchedulerImpl, this is not
thread-safe. Though it is
+ * called by multiple threads, callers must already have a lock on the
TaskSchedulerImpl. The
+ * one exception is [[nodeBlacklist()]], which can be called without
holding a lock.
+ */
+private[scheduler] class BlacklistTracker (
+ conf: SparkConf,
+ clock: Clock = new SystemClock()) extends Logging {
+
+ BlacklistTracker.validateBlacklistConfs(conf)
+ private val MAX_FAILURES_PER_EXEC =
conf.get(config.MAX_FAILURES_PER_EXEC)
+ private val MAX_FAILED_EXEC_PER_NODE =
conf.get(config.MAX_FAILED_EXEC_PER_NODE)
+ val BLACKLIST_TIMEOUT_MILLIS = BlacklistTracker.getBlacklistTimeout(conf)
+
+ /**
+ * A map from executorId to information on task failures. Tracks the
time of each task failure,
+ * so that we can avoid blacklisting executors due to failures that are
very far apart. We do not
+ * actively remove from this as soon as tasks hit their timeouts, to
avoid the time it would take
+ * to do so. But it will not grow too large, because as soon as an
executor gets too many
+ * failures, we blacklist the executor and remove its entry here.
+ */
+ private val executorIdToFailureList = new HashMap[String,
ExecutorFailureList]()
+ val executorIdToBlacklistStatus = new HashMap[String,
BlacklistedExecutor]()
+ val nodeIdToBlacklistExpiryTime = new HashMap[String, Long]()
+ /**
+ * An immutable copy of the set of nodes that are currently blacklisted.
Kept in an
+ * AtomicReference to make [[nodeBlacklist()]] thread-safe.
+ */
+ private val _nodeBlacklist = new AtomicReference[Set[String]](Set())
+ /**
+ * Time when the next blacklist will expire. Used as a
+ * shortcut to avoid iterating over all entries in the blacklist when
none will have expired.
+ */
+ var nextExpiryTime: Long = Long.MaxValue
+ /**
+ * Mapping from nodes to all of the executors that have been blacklisted
on that node. We do *not*
+ * remove from this when executors are removed from spark, so we can
track when we get multiple
+ * successive blacklisted executors on one node. Nonetheless, it will
not grow too large because
+ * there cannot be many blacklisted executors on one node, before we
stop requesting more
+ * executors on that node, and we periodically clean up the list of
blacklisted executors.
+ */
+ val nodeToBlacklistedExecs = new HashMap[String, HashSet[String]]()
+
+ /**
+ * Un-blacklists executors and nodes that have been blacklisted for at
least
+ * BLACKLIST_TIMEOUT_MILLIS
+ */
+ def applyBlacklistTimeout(): Unit = {
+ val now = clock.getTimeMillis()
+ // quickly check if we've got anything to expire from blacklist -- if
not, avoid doing any work
+ if (now > nextExpiryTime) {
+ // Apply the timeout to blacklisted nodes and executors
+ val execsToUnblacklist =
executorIdToBlacklistStatus.filter(_._2.expiryTime < now).keys
+ if (execsToUnblacklist.nonEmpty) {
+ // Un-blacklist any executors that have been blacklisted longer
than the blacklist timeout.
+ logInfo(s"Removing executors $execsToUnblacklist from blacklist
because the blacklist " +
+ s"for those executors has timed out")
+ execsToUnblacklist.foreach { exec =>
+ val status = executorIdToBlacklistStatus.remove(exec).get
+ val failedExecsOnNode = nodeToBlacklistedExecs(status.node)
+ failedExecsOnNode.remove(exec)
+ if (failedExecsOnNode.isEmpty) {
+ nodeToBlacklistedExecs.remove(status.node)
+ }
+ }
+ }
+ val nodesToUnblacklist = nodeIdToBlacklistExpiryTime.filter(_._2 <
now).keys
+ if (nodesToUnblacklist.nonEmpty) {
+ // Un-blacklist any nodes that have been blacklisted longer than
the blacklist timeout.
+ logInfo(s"Removing nodes $nodesToUnblacklist from blacklist
because the blacklist " +
+ s"has timed out")
+ nodesToUnblacklist.foreach { node =>
nodeIdToBlacklistExpiryTime.remove(node) }
+ _nodeBlacklist.set(nodeIdToBlacklistExpiryTime.keySet.toSet)
+ }
+ updateNextExpiryTime()
+ }
+ }
+
+ private def updateNextExpiryTime(): Unit = {
+ // we don't need to check nodeIdToBlacklistExpiryTime because that
will always share an
+ // expiry time with some blacklisted executor. In other words, the
next node expiry time
+ // will never be before the next executor blacklist time.
+ if (executorIdToBlacklistStatus.nonEmpty) {
+ nextExpiryTime = executorIdToBlacklistStatus.map{_._2.expiryTime}.min
+ } else {
+ nextExpiryTime = Long.MaxValue
+ }
+ }
+
+
+ def updateBlacklistForSuccessfulTaskSet(
+ stageId: Int,
+ stageAttemptId: Int,
+ failuresByExec: HashMap[String, ExecutorFailuresInTaskSet]): Unit = {
+ // if any tasks failed, we count them towards the overall failure
count for the executor at
+ // this point.
+ val now = clock.getTimeMillis()
+ val expiryTime = now + BLACKLIST_TIMEOUT_MILLIS
+ failuresByExec.foreach { case (exec, failuresInTaskSet) =>
+ val allFailuresOnOneExecutor =
+ executorIdToFailureList.getOrElseUpdate(exec, new
ExecutorFailureList)
+ // Apply the timeout to individual tasks. This is to prevent
one-off failures that are very
+ // spread out in time (and likely have nothing to do with problems
on the executor) from
+ // triggering blacklisting. However, note that we do *not* remove
executors and nodes from
+ // the blacklist as we expire individual task failures -- each have
their own timeout. Eg.,
+ // suppose:
+ // * timeout = 10, maxFailuresPerExec = 2
+ // * Task 1 fails on exec 1 at time 0
+ // * Task 2 fails on exec 1 at time 5
+ // --> exec 1 is blacklisted from time 5 - 15.
+ // This is to simplify the implementation, as well as keep the
behavior easier to understand
+ // for the end user.
+ allFailuresOnOneExecutor.dropFailuresWithTimeoutBefore(now)
+ allFailuresOnOneExecutor.addFailures(stageId, stageAttemptId,
failuresInTaskSet)
+ val newTotal = allFailuresOnOneExecutor.numUniqueTaskFailures
+
+ if (newTotal >= MAX_FAILURES_PER_EXEC) {
+ logInfo(s"Blacklisting executor id: $exec because it has
$newTotal" +
+ s" task failures in successful task sets")
+ val node = failuresInTaskSet.node
+ executorIdToBlacklistStatus.put(exec, BlacklistedExecutor(node,
expiryTime))
+ executorIdToFailureList.remove(exec)
+ updateNextExpiryTime()
+
+ // In addition to blacklisting the executor, we also update the
data for failures on the
+ // node, and potentially put the entire node into a blacklist as
well.
+ val blacklistedExecsOnNode =
nodeToBlacklistedExecs.getOrElseUpdate(node, HashSet[String]())
+ blacklistedExecsOnNode += exec
+ if (blacklistedExecsOnNode.size >= MAX_FAILED_EXEC_PER_NODE) {
+ logInfo(s"Blacklisting node $node because it has
${blacklistedExecsOnNode.size} " +
+ s"executors blacklisted: ${blacklistedExecsOnNode}")
+ nodeIdToBlacklistExpiryTime.put(node, expiryTime)
+ _nodeBlacklist.set(nodeIdToBlacklistExpiryTime.keySet.toSet)
+ }
+ }
+ }
+ }
+
+ def isExecutorBlacklisted(executorId: String): Boolean = {
+ executorIdToBlacklistStatus.contains(executorId)
+ }
+
+ /**
+ * Get the full set of nodes that are blacklisted. Unlike other methods
in this class, this *IS*
+ * thread-safe -- no lock required on a taskScheduler.
+ */
+ def nodeBlacklist(): Set[String] = {
+ _nodeBlacklist.get()
+ }
+
+ def isNodeBlacklisted(node: String): Boolean = {
+ nodeIdToBlacklistExpiryTime.contains(node)
+ }
+
+ def handleRemovedExecutor(executorId: String): Unit = {
+ // We intentionally do not clean up executors that are already
blacklisted in nodeToFailedExecs,
+ // so that if another executor on the same node gets blacklisted, we
can blacklist the entire
+ // node. We also can't clean up executorIdToBlacklistStatus, so we
can eventually remove
+ // the executor after the timeout. Despite not clearing those
structures here, we don't expect
+ // they will grow too big since you won't get too many executors on
one node, and the timeout
+ // will clear it up periodically in any case.
+ executorIdToFailureList -= executorId
+ }
+
+
+ /**
+ * Tracks all failures for one executor (that have not passed the
timeout). Designed to
+ * efficiently remove failures that are older than the timeout, and
query for the number of unique
+ * failed tasks.
+ * In general we actually expect this to be extremely small, since it
won't contain more than the
+ * maximum number of task failures before an executor is failed (default
2).
+ */
+ private[scheduler] final class ExecutorFailureList extends Logging {
+
+ private case class TaskId(stage: Int, stageAttempt: Int, taskIndex:
Int)
+
+ /**
+ * All failures on this executor in successful task sets, sorted by
time ascending.
+ */
+ private var failures = ArrayBuffer[(TaskId, Long)]()
+
+ def addFailures(
+ stage: Int,
+ stageAttempt: Int,
+ failuresInTaskSet: ExecutorFailuresInTaskSet): Unit = {
+ // The new failures may interleave with the old ones, so rebuild the
failures in sorted order.
+ // This shouldn't be expensive because if there were a lot of
failures, the executor would
+ // have been blacklisted.
+ if (failuresInTaskSet.taskToFailureCountAndExpiryTime.nonEmpty) {
+ failuresInTaskSet.taskToFailureCountAndExpiryTime.foreach { case
(taskIdx, (_, time)) =>
+ failures += ((TaskId(stage, stageAttempt, taskIdx), time))
--- End diff --
would it make sense to store the TaskId in taskToFailureCountAndExpiryTime
rather than storing the index, since that's what's eventually needed anyway,
and then maybe an existing TaskId object can be re-used?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
