From 1e14390719cc9e79cc67272a50e7e0bf95b38d87 Mon Sep 17 00:00:00 2001 From: Pratyaksh Sharma Date: Wed, 20 Nov 2019 19:46:27 +0530 Subject: [PATCH] [HUDI-350]: updated default value of config.getCleanerCommitsRetained() in javadocs --- .../main/java/org/apache/hudi/io/HoodieCleanHelper.java | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/hudi-client/src/main/java/org/apache/hudi/io/HoodieCleanHelper.java b/hudi-client/src/main/java/org/apache/hudi/io/HoodieCleanHelper.java index fbc87b950..f82bb6e06 100644 --- a/hudi-client/src/main/java/org/apache/hudi/io/HoodieCleanHelper.java +++ b/hudi-client/src/main/java/org/apache/hudi/io/HoodieCleanHelper.java @@ -174,12 +174,13 @@ public class HoodieCleanHelper> implements Seri * Selects the versions for file for cleaning, such that it *

* - Leaves the latest version of the file untouched - For older versions, - It leaves all the commits untouched which - * has occured in last config.getCleanerCommitsRetained() commits - It leaves ONE commit before this + * has occurred in last config.getCleanerCommitsRetained() commits - It leaves ONE commit before this * window. We assume that the max(query execution time) == commit_batch_time * config.getCleanerCommitsRetained(). - * This is 12 hours by default. This is essential to leave the file used by the query thats running for the max time. + * This is 5 hours by default (assuming ingestion is running every 30 minutes). This is essential to leave the file + * used by the query that is running for the max time. *

* This provides the effect of having lookback into all changes that happened in the last X commits. (eg: if you - * retain 24 commits, and commit batch time is 30 mins, then you have 12 hrs of lookback) + * retain 10 commits, and commit batch time is 30 mins, then you have 5 hrs of lookback) *

* This policy is the default. */