In this release, Doris Team has fixed more than 170 issues or performance improvement since 1.1.1. This release is a bugfix release on 1.1 and all users are encouraged to upgrade to this release.
Features
New MemTracker
Introduced new MemTracker for both vectorized engine and non-vectorized engine which is more accurate.
Add API for showing current queries and kill query
Support read/write emoji of UTF16 via ODBC Table
Improvements
Data Lake related improvements
-
Improved HDFS ORC File scan performance about 300%. #11501
-
Support HDFS HA mode when query Iceberg table.
-
Support query Hive data created by Apache Tez
-
Add Ali OSS as Hive external support.
Add support for string and text type in Spark Load
Add reuse block in non-vectorized engine and have 50% performance improvement in some cases. #11392
Improve like or regex performance
Disable tcmalloc's aggressive_memory_decommit
It will have 40% performance gains in load or query.
Currently it is a config, you can change it by set config tc_enable_aggressive_memory_decommit.
Bug Fix
Some issues about FE that will cause FE failure or data corrupt.
-
Add reserved disk config to avoid too many reserved BDB-JE files.(Serious) In an HA environment, BDB JE will retains as many reserved files. The BDB-je log doesn't delete until approaching a disk limit.
-
Fix fatal bug in BDB-JE which will cause FE replica could not start correctly or data corrupted. (Serious)
Fe will hang on waitFor_rpc during query and BE will hang in high concurrent scenarios.
A fatal issue in vectorized storage engine which will cause wrong result. (Serious)
Lots of planner related issues that will cause BE core or in abnormal state.
#12080 #12075 #12040 #12003 #12007 #11971 #11933 #11861 #11859 #11855 #11837 #11834 #11821 #11782 #11723 #11569
