Github user mridulm commented on a diff in the pull request: https://github.com/apache/spark/pull/2366#discussion_r17927862 --- Diff: core/src/main/scala/org/apache/spark/storage/BlockManager.scala --- @@ -787,31 +790,111 @@ private[spark] class BlockManager( } /** + * Get peer block managers in the system. + */ + private def getPeers(forceFetch: Boolean): mutable.HashSet[BlockManagerId] = { + cachedPeers.synchronized { + val cachedPeersTtl = conf.getInt("spark.storage.cachedPeersTtl", 60 * 1000) // milliseconds + val timeout = System.currentTimeMillis - lastPeerFetchTime > cachedPeersTtl + if (cachedPeers.isEmpty || forceFetch || timeout) { + cachedPeers.clear() + cachedPeers ++= master.getPeers(blockManagerId).sortBy(_.hashCode) + lastPeerFetchTime = System.currentTimeMillis + logDebug("Fetched peers from master: " + cachedPeers.mkString("[", ",", "]")) + } + } + cachedPeers + } --- End diff -- There is an MT bug here. Since cachedPeers is updated in place, it is possible for 'previous' invocation to be using cachedPeers while the next invocation is clearing/updating it. We can avoid that by overwriting cachedPeers instance variable with result of master.getPeers.
--- 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