Commit Graph

7502 Commits

Author SHA1 Message Date
e3e5f18f26 [Fix](Json type) correct cast result for json type (#34764) 2024-05-18 18:40:17 +08:00
e66dd58860 [Improve](inverted index) improve performance by introducing bulk contains for bitmap in _build_index_result_column (#34831) 2024-05-18 18:38:04 +08:00
9b5028785d [fix](prepare) fix datetimev2 return err when binary_row_format (#34662)
fix datetimev2 return err when binary_row_format. before pr, Backend return datetimev2 alwary by to_string.
fix datatimev2 return metadata loss scale.
2024-05-18 18:37:41 +08:00
eb7eaee386 [fix](function) money format (#34680) 2024-05-18 18:35:29 +08:00
db273d578f [Fix](tablet id) use int64_t instead of int32_t or uint32_t for tablet_id (#34962) 2024-05-18 18:34:05 +08:00
0febfc10e4 [Fix](inverted index) fix wrong fs in inverted_index_file_writer (#34903) 2024-05-18 18:30:10 +08:00
dff6171546 [fix](auto inc) db_id and table_id should be int64_t instead of int32_t (#34912) 2024-05-18 18:29:59 +08:00
4b96f9834f [fix](move-memtable) change brpc connection type to single (#34883) 2024-05-18 18:29:20 +08:00
849eeb39e9 [fix](load) skip sending cancel rpc if VNodeChannel is not inited (#34897) 2024-05-18 18:29:10 +08:00
1e53a2a81d [Improve](inverted index) improve query performance by not using output index result column (#34281) 2024-05-18 18:18:12 +08:00
6b1c441258 [fix](group_commit) Wal reader should check block length to avoid reading empty block (#34792) 2024-05-18 18:17:56 +08:00
6c515e0c76 [fix](group commit) Make compatibility issues on serializing and deserializing wal file more clear (#34793) 2024-05-18 18:12:43 +08:00
80dd027ce2 [opt](join) For left semi/anti join without mark join conjunct and without other conjucnts, stop probing after matching one row (#34703) 2024-05-18 18:08:50 +08:00
876248aa4e [fix](function) json_object can not input null value (#34591) 2024-05-18 18:00:48 +08:00
691f3c5ee7 [Performance](Variant) Improve load performance for variant type (#33890)
1. remove phmap for padding rows
2. add SimpleFieldVisitorToScarlarType for short circuit type deducing
3. correct type coercion for conflict types bettween integers
4. improve nullable column performance
5. remove shared_ptr dependancy for DataType use TypeIndex instead
6. Optimization by caching the order of fields (which is almost always the same)
and a quick check to match the next expected field, instead of searching the hash table.

benchmark:
In clickbench data, load performance:
12m36.799s ->7m10.934s about 43% latency reduce

In variant_p2/performance.groovy:
3min44s20 -> 1min15s80 about 66% latency reducy
2024-05-18 17:58:33 +08:00
4ba15b27ca simple fix for cancel core block dep is released when call 2024-05-16 06:32:21 +08:00
e74b17c761 [Fix](Row store) support decimal256 type (#34887) 2024-05-15 19:01:18 +08:00
1a24895257 [opt](routine-load) optimize routine load task thread pool and related param(#32282) (#34896) 2024-05-15 12:42:02 +08:00
2cbe6740a5 [fix](reader) avoid be coredump in block reader in abnormal situation (#34878) 2024-05-15 12:38:40 +08:00
1f0c45204b [fix](iceberg) read the primary key columns if hasing equality delete (#34884)
backport: #34835
2024-05-15 11:37:25 +08:00
02084fd91f [fix](iceberg_orc)Fixed the bug that the iceberg reader did not perform position delete when reading the orc file without a predicate. (#34814) (#34882)
bp #34814
2024-05-15 11:31:29 +08:00
e13ce905cf [Fix](hive-writer) Fix hive partition update file size and remove redundant column names. (#34651) (#34885)
Backport #34651.
2024-05-15 11:23:32 +08:00
c7134faea9 [Fix](outfile) Fix the timing of setting the _is_closed flag in Parquet/ORC writer (#34668) 2024-05-15 10:28:22 +08:00
d5ab2787ba [Fix](function) fix pad functions behaviour of empty pad string (#34796)
fix pad functions behaviour of empty pad string
2024-05-15 10:28:09 +08:00
0b4d814598 [fix](decimal) Fix wrong result produced by decimal128 multiply (#34825)
* [fix](decimal) Fix wrong result produced by decimal128 multiply

* update
2024-05-14 23:34:11 +08:00
4dd5379951 [bugfix](hive)fix error for writing to hive for 2.1 (#34518)
mirror #34520
2024-05-14 23:27:29 +08:00
5ece07ab8c [faultinjection](test) add some fault injection in pipeline task method 2024-05-14 15:01:32 +08:00
9491b7d422 [fix](iceberg) prevent coredump if read position delete file failed (#34802) 2024-05-14 14:03:33 +08:00
95b05928fd [fix](compaction) fix time series compaction merge empty rowsets priority #34562 (#34765) 2024-05-14 09:10:09 +08:00
0ae1b9c70a [chore](remove code) Remove dragonbox related (#34528)
* Revert "[refactor](mysql result format) use new serde framework to tuple convert (#25006)"

This reverts commit e5ef0aa6d439c3f9b1f1fe5bc89c9ea6a71d4019.

* run buildall

* MORE

* FIX
2024-05-13 22:16:57 +08:00
cdc950f2c3 [improvement](spill) improve spill log printing 2024-05-12 19:33:27 +08:00
7a172a55ab [fix](memory) Fix prune all LRU Cache based on number #34601 (#34736) 2024-05-12 11:47:53 +08:00
ca9eb56233 [Fix](functions) fix strcmp return value #34565 2024-05-12 09:49:38 +08:00
a8be47f3ff [fix](fs) Close local file writer when downloading via broker fs (#34714) 2024-05-12 09:45:24 +08:00
cadbbdd2c0 [fix](config) for compatibility issue of log dir config (#34734)
* [fix](config) for compatibility issue of log dir config

* 1
2024-05-12 09:44:50 +08:00
e23a89f0da fix compile error 2024-05-11 15:36:06 +08:00
14d0433a76 [improve](path gc) Execute path gc interval adaptive to disk size (#34538) 2024-05-11 15:04:35 +08:00
719e50f353 [fix](json function) fix failed when json_exists_path use not null input (#34289) 2024-05-11 15:04:35 +08:00
Pxl
1ff4dc8f85 [Bug](runtime-filter) fix coredump won change_null_to_true when argument column is not null… (#34602)
fix coredump won change_null_to_true when argument column is not nullable
2024-05-11 15:04:35 +08:00
659f7ef2af [refactor](Nereids)refactor runtime filter generator (#34275) (#34696)
this pr revert the modification on clucene introduced by pr #34682
2024-05-11 12:04:41 +08:00
8c237e82a3 [Bug](exec) fix intersections/differences bug (#34675) 2024-05-11 11:45:31 +08:00
58c19e33b3 [fix](round) Fix incorrect decimal scale inference in round functions (#34471)
* FIX NEEDED

* FORMAT

* FORMAT

* FIX TEST
2024-05-11 11:42:12 +08:00
0a79c547ff [Refactor](Sink) Remove is_append mode in table sink (#34684)
Remove the is_append mode from the sink component due to the following reasons:
1. The performance improvement from this mode is relatively minor, approximately 10%, as demonstrated in previous benchmarks.
2. The mode complicates maintenance. It requires a separate data writing path to avoid copying, which increases complexity and poses a risk of potential data loss.

I've already test the compability with previous version
2024-05-11 11:20:10 +08:00
7ba66c5890 [branch-2.1](routine-load) do not schedule task when there is no data (#34654) 2024-05-11 11:01:18 +08:00
dd1b54cf62 [pick](nereids)Runtime filter pushdown refactor for branch-2.1 (#34682)
* [refactor](Nereids)refactor runtime filter generator (#34275)

1. unify the process of generating rf for hash join and for nested loop join
2. fix some bugs in generating rf
3. remove some duplicated check

(cherry picked from commit 07267faac0d9c6ef3bb1fd4ee101b4c761c8a2f2)

* [refactor](nereids) do not deny a runtime filter by removing an entry in aliasMap (#34559)

in current version, there are 2 approaches to verify whether a join condition can be used to generate a runtime filter, they are
1. remove the output slot from aliasMap
2. pushDownVisitor.visit(...) return false
the 1st approach has some drawbacks, we prefer to the 2ed approach.
In this pr, all the cases are handled by the 2ed approach, and remove the related code for the 1st approach.

(cherry picked from commit a29082bf31e66efa2df193b38347e610f2bf7464)

* rebase
2024-05-11 09:44:24 +08:00
Pxl
e2ea54c0a7 [Improvement](sink) remove unused check on string's write_column_to_mysql (#34491)
remove unused check on string's write_column_to_mysql
2024-05-10 22:13:05 +08:00
aa684d85d7 [Bug](Variant) fix rapidjson::Allocator may cause mem allocate issue when build with DENABLE_CLANG_COVERAGE (#34150) 2024-05-10 22:12:00 +08:00
853dbdcb00 [Feature](PreparedStatement) implement general server side prepared (#33807) 2024-05-10 22:10:11 +08:00
5271042a7d [bugfix](gccompile) fix gcc compile error (#34546)
Co-authored-by: yiguolei <yiguolei@gmail.com>
2024-05-10 22:06:00 +08:00
95593f8e19 [config](move-memtable) support HTTP header load_stream_per_node in stream load (#34444) 2024-05-10 22:05:35 +08:00