Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/15852#discussion_r88581369
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/CompactibleFileStreamLog.scala
---
@@ -245,4 +284,25 @@ object CompactibleFileStreamLog {
def nextCompactionBatchId(batchId: Long, compactInterval: Long): Long = {
(batchId + compactInterval + 1) / compactInterval * compactInterval - 1
}
+
+ /**
+ * Derives a compact interval from the latest compact batch id and
+ * a default compact interval.
+ */
+ def deriveCompactInterval(defaultInterval: Int, latestCompactBatchId:
Int) : Int = {
+ if (latestCompactBatchId + 1 <= defaultInterval) {
+ latestCompactBatchId + 1
+ } else if (defaultInterval < (latestCompactBatchId + 1) / 2) {
+ // Find the first divisor >= default compact interval
+ def properDivisors(min: Int, n: Int) =
+ (min to n/2).view.filter(i => n % i == 0) :+ n
+
+ properDivisors(defaultInterval, latestCompactBatchId + 1).head
+ }
+ else {
--- End diff --
nit: move `else {` to the above line.
---
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]
