hubgeter opened a new pull request, #58532:
URL: https://github.com/apache/doris/pull/58532
### What problem does this PR solve?
Related PR: #57771
Problem Summary:
Fixed a core issue when reading Hudi Parquet format tables with the
`hoodie.properties` `hoodie.datasource.write.drop.partition.columns=false`.
```
*** SIGSEGV address not mapped to object (@0x18) received by PID 12234 (TID
38368 OR 0x7f0bd279e640) from PID 24; stack trace: ***
11:01:31 0# doris::signal::(anonymous
namespace)::FailureSignalHandler(int, siginfo_t*, void*) at
/home/zcp/repo_center/doris_master/doris/be/src/common/signal_handler.h:420
11:01:31 1# PosixSignals::chained_handler(int, siginfo*, void*) [clone
.part.0] in /usr/lib/jvm/java-17-openjdk-amd64/lib/server/libjvm.so
11:01:31 2# JVM_handle_linux_signal in
/usr/lib/jvm/java-17-openjdk-amd64/lib/server/libjvm.so
11:01:31 3# 0x00007F18963FB520 in /lib/x86_64-linux-gnu/libc.so.6
11:01:31 4# std::_Function_handler<bool
(doris::vectorized::ParquetPredicate::PageIndexStat**, int),
doris::vectorized::ParquetReader::_process_page_index_filter(tparquet::RowGroup
const&, doris::vectorized::RowGroupReader::RowGroupIndex const&,
std::vector<std::unique_ptr<doris::MutilColumnBlockPredicate,
std::default_delete<doris::MutilColumnBlockPredicate> >,
std::allocator<std::unique_ptr<doris::MutilColumnBlockPredicate,
std::default_delete<doris::MutilColumnBlockPredicate> > > > const&,
doris::segment_v2::RowRanges*)::$_1>::_M_invoke(std::_Any_data const&,
doris::vectorized::ParquetPredicate::PageIndexStat**&&, int&&) at
/usr/local/ldb-toolchain-v0.26/bin/../lib/gcc/x86_64-pc-linux-gnu/15/include/g++-v15/bits/std_function.h:292
11:01:31 5# doris::InListPredicateBase<(doris::PrimitiveType)2,
(doris::PredicateType)7, doris::HybridSet<(doris::PrimitiveType)2,
doris::FixedContainer<bool, 1ul>,
doris::vectorized::PredicateColumnType<(doris::PrimitiveType)2> >
>::evaluate_and(doris::vectorized::ParquetPredicate::CachedPageIndexStat*,
doris::segment_v2::RowRanges*) const at
/home/zcp/repo_center/doris_master/doris/be/src/olap/in_list_predicate.h:345
11:01:31 6#
doris::AndBlockColumnPredicate::evaluate_and(doris::vectorized::ParquetPredicate::CachedPageIndexStat*,
doris::segment_v2::RowRanges*) const at
/home/zcp/repo_center/doris_master/doris/be/src/olap/block_column_predicate.cpp:148
11:01:31 7#
doris::vectorized::ParquetReader::_process_page_index_filter(tparquet::RowGroup
const&, doris::vectorized::RowGroupReader::RowGroupIndex const&,
std::vector<std::unique_ptr<doris::MutilColumnBlockPredicate,
std::default_delete<doris::MutilColumnBlockPredicate> >,
std::allocator<std::unique_ptr<doris::MutilColumnBlockPredicate,
std::default_delete<doris::MutilColumnBlockPredicate> > > > const&,
doris::segment_v2::RowRanges*) in
/mnt/hdd01/ci/doris-deploy-master-local/be/lib/doris_be
11:01:31 8#
doris::vectorized::ParquetReader::_process_min_max_bloom_filter(doris::vectorized::RowGroupReader::RowGroupIndex
const&, tparquet::RowGroup const&,
std::vector<std::unique_ptr<doris::MutilColumnBlockPredicate,
std::default_delete<doris::MutilColumnBlockPredicate> >,
std::allocator<std::unique_ptr<doris::MutilColumnBlockPredicate,
std::default_delete<doris::MutilColumnBlockPredicate> > > > const&,
doris::segment_v2::RowRanges*) at
/home/zcp/repo_center/doris_master/doris/be/src/vec/exec/format/parquet/vparquet_reader.cpp:1082
11:01:31 9# doris::vectorized::ParquetReader::_next_row_group_reader() in
/mnt/hdd01/ci/doris-deploy-master-local/be/lib/doris_be
11:01:31 10#
doris::vectorized::ParquetReader::get_next_block(doris::vectorized::Block*,
unsigned long*, bool*) at
/home/zcp/repo_center/doris_master/doris/be/src/vec/exec/format/parquet/vparquet_reader.cpp:598
11:01:31 11#
doris::vectorized::HudiReader::get_next_block_inner(doris::vectorized::Block*,
unsigned long*, bool*) at
/home/zcp/repo_center/doris_master/doris/be/src/vec/exec/format/table/hudi_reader.cpp:29
11:01:31 12#
doris::vectorized::TableFormatReader::get_next_block(doris::vectorized::Block*,
unsigned long*, bool*) at
/home/zcp/repo_center/doris_master/doris/be/src/vec/exec/format/table/table_format_reader.h:82
11:01:31 13#
doris::vectorized::FileScanner::_get_block_wrapped(doris::RuntimeState*,
doris::vectorized::Block*, bool*) at
/home/zcp/repo_center/doris_master/doris/be/src/vec/exec/scan/file_scanner.cpp:472
```
### Release note
None
### Check List (For Author)
- Test <!-- At least one of them must be included. -->
- [ ] Regression test
- [ ] Unit Test
- [ ] Manual test (add detailed scripts or steps below)
- [x] No need to test or manual test. Explain why:
- [ ] This is a refactor/code format and no logic has been changed.
- [x] Previous test can cover this change.
- [ ] No code files have been changed.
- [ ] Other reason <!-- Add your reason? -->
- Behavior changed:
- [x] No.
- [ ] Yes. <!-- Explain the behavior change -->
- Does this need documentation?
- [x] No.
- [ ] Yes. <!-- Add document PR link here. eg:
https://github.com/apache/doris-website/pull/1214 -->
### Check List (For Reviewer who merge this PR)
- [ ] Confirm the release note
- [ ] Confirm test cases
- [ ] Confirm document
- [ ] Add branch pick label <!-- Add branch pick label that this PR should
merge into -->
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]