From e7cd7fffbf4b297e54438c1378f0b9aa2c98523b Mon Sep 17 00:00:00 2001 From: Ramkrishna Date: Tue, 23 Aug 2016 10:53:33 +0530 Subject: [PATCH] HBASE-16444 CellUtil#estimatedSerializedSizeOfKey() should consider KEY_INFRASTRUCTURE_SIZ (Ram) --- .../java/org/apache/hadoop/hbase/CellUtil.java | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/hbase-common/src/main/java/org/apache/hadoop/hbase/CellUtil.java b/hbase-common/src/main/java/org/apache/hadoop/hbase/CellUtil.java index ff6ad90bd60..be5006915ea 100644 --- a/hbase-common/src/main/java/org/apache/hadoop/hbase/CellUtil.java +++ b/hbase-common/src/main/java/org/apache/hadoop/hbase/CellUtil.java @@ -526,6 +526,7 @@ public final class CellUtil { } /** + * Estimate based on keyvalue's serialization format. * @param cell * @return Estimate of the cell size in bytes. * @deprecated please use estimatedSerializedSizeOf(Cell) @@ -549,7 +550,7 @@ public final class CellUtil { return getSumOfCellElementLengths(cell) + // Use the KeyValue's infrastructure size presuming that another implementation would have // same basic cost. - KeyValue.KEY_INFRASTRUCTURE_SIZE + + KeyValue.ROW_LENGTH_SIZE + KeyValue.FAMILY_LENGTH_SIZE + // Serialization is probably preceded by a length (it is in the KeyValueCodec at least). Bytes.SIZEOF_INT; } @@ -573,10 +574,17 @@ public final class CellUtil { KeyValue.TIMESTAMP_TYPE_SIZE; } + /** + * Calculates the serialized key size. We always serialize in the KeyValue's serialization + * format. + * @param cell the cell for which the key size has to be calculated. + * @return the key size + */ public static int estimatedSerializedSizeOfKey(final Cell cell) { if (cell instanceof KeyValue) return ((KeyValue)cell).getKeyLength(); - // This will be a low estimate. Will do for now. - return getSumOfCellKeyElementLengths(cell); + return cell.getRowLength() + cell.getFamilyLength() + + cell.getQualifierLength() + + KeyValue.KEY_INFRASTRUCTURE_SIZE; } /**