infraio commented on a change in pull request #2663:
URL: https://github.com/apache/hbase/pull/2663#discussion_r543113766
##########
File path:
hbase-server/src/main/java/org/apache/hadoop/hbase/regionserver/StoreScanner.java
##########
@@ -130,6 +132,13 @@
*/
public static final String HBASE_CELLS_SCANNED_PER_HEARTBEAT_CHECK =
"hbase.cells.scanned.per.heartbeat.check";
+ /**
+ * The number of bytes after which we decide if to do only next() or continue
+ * with seek(). Currently it defaults to the STORESCANNER_PREAD_MAX_BYTES
config
+ * To disable this feature put a value < 0.
+ */
+ public static final String HBASE_SWITCH_TO_NEXT_AFTER_BYTES_READ =
Review comment:
I check your example in PPT. What this PR want to reduce is the compare
times of "matcher.compareKeyForNextRow(nextIndexedKey, cell)", right?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
