xzj7019 commented on code in PR #27259:
URL: https://github.com/apache/doris/pull/27259#discussion_r1398634610
##########
fe/fe-core/src/main/java/org/apache/doris/nereids/cost/CostModelV1.java:
##########
@@ -299,12 +303,41 @@ public Cost visitPhysicalHashJoin(
0
);
}
- return CostV1.of(context.getSessionVariable(), leftRowCount +
rightRowCount + outputRowCount,
+ return CostV1.of(context.getSessionVariable(),
+ (leftRowCount + rightRowCount + outputRowCount)
+ * skewPenalty(physicalHashJoin, probeStats,
buildStats, totalInstanceNumber),
rightRowCount,
0
);
}
+ private double skewPenalty(PhysicalHashJoin<? extends Plan, ? extends
Plan> physicalHashJoin,
+ Statistics probeStats,
+ Statistics buildStats,
+ int totalInstanceNumber) {
+ double penalty = 1.0;
+ for (Expression conj : physicalHashJoin.getHashJoinConjuncts()) {
+ EqualTo eq = (EqualTo) JoinUtils.swapEqualToForChildrenOrder(
+ (EqualTo) conj, physicalHashJoin.left().getOutputSet());
+ ColumnStatistic leftColStats =
probeStats.findColumnStatistics(eq.left());
+ if (leftColStats != null && !leftColStats.isUnKnown()) {
+ if (leftColStats.ndv < beNumber) {
+ penalty = totalInstanceNumber / Math.max(1.0,
leftColStats.ndv);
+ break;
+ }
+ }
+
+ ColumnStatistic rightColStats =
buildStats.findColumnStatistics(eq.right());
+ if (rightColStats != null && !rightColStats.isUnKnown()) {
+ if (rightColStats.ndv < beNumber) {
+ penalty = totalInstanceNumber / Math.max(1.0,
leftColStats.ndv);
Review Comment:
right side also depends on leftColStats?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For additional commands, e-mail: commits-h...@doris.apache.org
