Github user andrewor14 commented on a diff in the pull request:
https://github.com/apache/spark/pull/2436#discussion_r17695418
--- Diff: core/src/main/scala/org/apache/spark/deploy/master/Master.scala
---
@@ -491,14 +491,13 @@ private[spark] class Master(
val shuffledAliveWorkers = Random.shuffle(workers.toSeq.filter(_.state
== WorkerState.ALIVE))
val aliveWorkerNum = shuffledAliveWorkers.size
var curPos = 0
+ var stopPos = aliveWorkerNum
for (driver <- waitingDrivers.toList) { // iterate over a copy of
waitingDrivers
// We assign workers to each waiting driver in a round-robin
fashion. For each driver, we
// start from the last worker that was assigned a driver, and
continue onwards until we have
// explored all alive workers.
- curPos = (curPos + 1) % aliveWorkerNum
- val startPos = curPos
--- End diff --
I still don't understand what you mean. The behavior we want here is this:
for each driver, we start from the position where the last driver left off, and
we want to loop through each worker at most once (i.e. we don't want to exit
the loop as soon as we have looked at `numWorkersAlive`). If the last driver's
last visited index is N, then we still start from N + 1 because we keep track
of the position `curPos`. `numWorkersVisited` is a counter, not an index into
`shuffledWorkers`. Does that make sense?
---
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]
