Github user kayousterhout commented on a diff in the pull request: https://github.com/apache/spark/pull/14079#discussion_r92075850 --- Diff: core/src/main/scala/org/apache/spark/scheduler/BlacklistTracker.scala --- @@ -17,10 +17,275 @@ 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 clean up the list of blacklisted executors once an executor has + * been blacklisted for BLACKLIST_TIMEOUT_MILLIS. + */ + 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") + nodeIdToBlacklistExpiryTime --= nodesToUnblacklist + _nodeBlacklist.set(nodeIdToBlacklistExpiryTime.keySet.toSet) + } + updateNextExpiryTime() + } + } + + private def updateNextExpiryTime(): Unit = { + val execMinExpiry = if (executorIdToBlacklistStatus.nonEmpty) { + executorIdToBlacklistStatus.map{_._2.expiryTime}.min + } else { + Long.MaxValue + } + val nodeMinExpiry = if (nodeIdToBlacklistExpiryTime.nonEmpty) { + nodeIdToBlacklistExpiryTime.values.min + } else { + Long.MaxValue + } + nextExpiryTime = math.min(execMinExpiry, nodeMinExpiry) + } + + + 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 --- End diff -- To mitigate part of my confusion in the comment above (about which expiry times are used where), what about moving this to line 154 (right before "// If this..."), which is closer to where it's used, and renaming to the more verbose expiryTimeForNewBlacklists or similar?
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org