yihua commented on code in PR #5746: URL: https://github.com/apache/hudi/pull/5746#discussion_r929358584
########## hudi-common/src/main/java/org/apache/hudi/common/config/HoodieMetadataConfig.java: ########## @@ -187,6 +187,26 @@ public final class HoodieMetadataConfig extends HoodieConfig { .sinceVersion("0.11.0") .withDocumentation("Comma-separated list of columns for which column stats index will be built. If not set, all columns will be indexed"); + public static final String COLUMN_STATS_INDEX_PROCESSING_MODE_IN_MEMORY = "in-memory"; + public static final String COLUMN_STATS_INDEX_PROCESSING_MODE_ENGINE = "engine"; + + public static final ConfigProperty<String> COLUMN_STATS_INDEX_PROCESSING_MODE_OVERRIDE = ConfigProperty + .key(METADATA_PREFIX + ".index.column.stats.processing.mode.override") + .noDefaultValue() + .withValidValues(COLUMN_STATS_INDEX_PROCESSING_MODE_IN_MEMORY, COLUMN_STATS_INDEX_PROCESSING_MODE_ENGINE) + .sinceVersion("0.12.0") + .withDocumentation("By default Column Stats Index is automatically determining whether it should be read and processed either" + + "'in-memory' (w/in executing process) or using Spark (on a cluster), based on some factors like the size of the Index " + + "and how many columns are read. This config allows to override this behavior."); + + public static final ConfigProperty<Integer> COLUMN_STATS_INDEX_IN_MEMORY_PROJECTION_THRESHOLD = ConfigProperty + .key(METADATA_PREFIX + ".index.column.stats.inMemory.projection.threshold") + .defaultValue(100000) Review Comment: How fast is it for in-memory? -- 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...@hudi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org