This is an automated email from the ASF dual-hosted git repository.
yiguolei pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/master by this push:
new 7b270d1ae9 [Fix](mutli-catalog) Fix orc reader crashed when hdfs
reading error by catching exception. (#22193)
7b270d1ae9 is described below
commit 7b270d1ae9b8ca76ac613141ac820301d513835c
Author: Qi Chen <[email protected]>
AuthorDate: Wed Jul 26 08:57:31 2023 +0800
[Fix](mutli-catalog) Fix orc reader crashed when hdfs reading error by
catching exception. (#22193)
orc reader crashed when hdfs reading error.
0# doris::signal::(anonymous namespace)::FailureSignalHandler(int,
siginfo_t*, void*) at
/home/zcp/repo_center/zcp_repo/be/src/common/signal_handler.h:413
1# 0x00007F6F8B3C00C0 in /lib/x86_64-linux-gnu/libc.so.6
2# raise in /lib/x86_64-linux-gnu/libc.so.6
3# abort in /lib/x86_64-linux-gnu/libc.so.6
4# _gnu_cxx::_verbose_terminate_handler() [clone .cold] at
../../../../libstdc+-v3/libsupc+/vterminate.cc:75
5# _cxxabiv1::_terminate(void ()) at
../../../../libstdc+-v3/libsupc+/eh_terminate.cc:48
6# 0x0000555CBC4718C1 in /mnt/hdd01/STRESS_ENV/be/lib/doris_be
7# 0x0000555CBC471A14 in /mnt/hdd01/STRESS_ENV/be/lib/doris_be
8# doris::vectorized::ORCFileInputStream::read(void*, unsigned long,
unsigned long) at
/home/zcp/repo_center/zcp_repo/be/src/vec/exec/format/orc/vorc_reader.cpp:121
9# orc::SeekableFileInputStream::Next(void const*, int) in
/mnt/hdd01/STRESS_ENV/be/lib/doris_be
10# orc::DecompressionStream::readHeader() in
/mnt/hdd01/STRESS_ENV/be/lib/doris_be
11# orc::DecompressionStream::Next(void const*, int) in
/mnt/hdd01/STRESS_ENV/be/lib/doris_be
12# void orc::RleDecoderV2::next<long>(long*, unsigned long, char const*)
in /mnt/hdd01/STRESS_ENV/be/lib/doris_be
13# orc::StringDictionaryColumnReader::loadDictionary() in
/mnt/hdd01/STRESS_ENV/be/lib/doris_be
14# orc::StructColumnReader::loadStringDicts(std::unordered_map<unsigned
long, std::_cxx11::basic_string<char, std::char_traits<char>,
std::allocator<char> >, std::hash<unsigned long>, std::equal_to<unsigned long>,
std::allocator<std::pair<unsigned long const, std::cxx11::basic_string<char,
std::char_traits<char>, std::allocator<char> > > > > const&,
std::unordered_map<std::cxx11::basic_string<char, std::char_traits<char>,
std::allocator<char> >, orc::StringDictionary*, std::hash<std: [...]
15# orc::RowReaderImpl::startNextStripe(orc::ReadPhase const&) in
/mnt/hdd01/STRESS_ENV/be/lib/doris_be
16# orc::RowReaderImpl::nextBatch(orc::ColumnVectorBatch&, void*) in
/mnt/hdd01/STRESS_ENV/be/lib/doris_be
17# doris::vectorized::OrcReader::get_next_block(doris::vectorized::Block*,
unsigned long*, bool*) at
/home/zcp/repo_center/zcp_repo/be/src/vec/exec/format/orc/vorc_reader.cpp:1420
18# doris::vectorized::VFileScanner::_get_block_impl(doris::RuntimeState*,
doris::vectorized::Block*, bool*) at
/home/zcp/repo_center/zcp_repo/be/src/vec/exec/scan/vfile_scanner.cpp:250
19# doris::vectorized::VScanner::get_block(doris::RuntimeState*,
doris::vectorized::Block*, bool*) in /mnt/hdd01/STRESS_ENV/be/lib/doris_be
20#
doris::vectorized::ScannerScheduler::_scanner_scan(doris::vectorized::ScannerScheduler*,
doris::vectorized::ScannerContext*,
std::shared_ptr<doris::vectorized::VScanner>) at
/home/zcp/repo_center/zcp_repo/be/src/vec/exec/scan/scanner_scheduler.cpp:335
21# std::_Function_handler<void (),
doris::vectorized::ScannerScheduler::_schedule_scanners(doris::vectorized::ScannerContext*)::$_1::operator()()
const::
---
be/src/vec/exec/format/orc/vorc_reader.cpp | 50 ++++++++++++++++++------------
1 file changed, 30 insertions(+), 20 deletions(-)
diff --git a/be/src/vec/exec/format/orc/vorc_reader.cpp
b/be/src/vec/exec/format/orc/vorc_reader.cpp
index e81f42a98e..77fd37e913 100644
--- a/be/src/vec/exec/format/orc/vorc_reader.cpp
+++ b/be/src/vec/exec/format/orc/vorc_reader.cpp
@@ -755,14 +755,14 @@ Status OrcReader::set_fill_columns(
_fill_all_columns = true;
// create orc row reader
- _row_reader_options.range(_range_start_offset, _range_size);
- _row_reader_options.setTimezoneName(_ctz == "CST" ? "Asia/Shanghai" :
_ctz);
- _row_reader_options.include(_read_cols);
- if (_lazy_read_ctx.can_lazy_read) {
- _row_reader_options.filter(_lazy_read_ctx.predicate_orc_columns);
- _orc_filter = std::unique_ptr<ORCFilterImpl>(new ORCFilterImpl(this));
- }
try {
+ _row_reader_options.range(_range_start_offset, _range_size);
+ _row_reader_options.setTimezoneName(_ctz == "CST" ? "Asia/Shanghai" :
_ctz);
+ _row_reader_options.include(_read_cols);
+ if (_lazy_read_ctx.can_lazy_read) {
+ _row_reader_options.filter(_lazy_read_ctx.predicate_orc_columns);
+ _orc_filter = std::unique_ptr<ORCFilterImpl>(new
ORCFilterImpl(this));
+ }
_row_reader_options.setEnableLazyDecoding(true);
if (!_lazy_read_ctx.conjuncts.empty()) {
_string_dict_filter = std::make_unique<StringDictFilterImpl>(this);
@@ -770,12 +770,12 @@ Status OrcReader::set_fill_columns(
_row_reader = _reader->createRowReader(_row_reader_options,
_orc_filter.get(),
_string_dict_filter.get());
_batch = _row_reader->createRowBatch(_batch_size);
+ auto& selected_type = _row_reader->getSelectedType();
+ int idx = 0;
+ _init_select_types(selected_type, idx);
} catch (std::exception& e) {
return Status::InternalError("Failed to create orc row reader. reason
= {}", e.what());
}
- auto& selected_type = _row_reader->getSelectedType();
- int idx = 0;
- _init_select_types(selected_type, idx);
if (!_slot_id_to_filter_conjuncts) {
return Status::OK();
@@ -1383,11 +1383,16 @@ Status OrcReader::get_next_block(Block* block, size_t*
read_rows, bool* eof) {
SCOPED_RAW_TIMER(&_statistics.get_batch_time);
// reset decimal_scale_params_index;
_decimal_scale_params_index = 0;
- rr = _row_reader->nextBatch(*_batch, block);
- if (rr == 0) {
- *eof = true;
- *read_rows = 0;
- return Status::OK();
+ try {
+ rr = _row_reader->nextBatch(*_batch, block);
+ if (rr == 0) {
+ *eof = true;
+ *read_rows = 0;
+ return Status::OK();
+ }
+ } catch (std::exception& e) {
+ return Status::InternalError("Orc row reader nextBatch failed.
reason = {}",
+ e.what());
}
}
@@ -1434,11 +1439,16 @@ Status OrcReader::get_next_block(Block* block, size_t*
read_rows, bool* eof) {
SCOPED_RAW_TIMER(&_statistics.get_batch_time);
// reset decimal_scale_params_index;
_decimal_scale_params_index = 0;
- rr = _row_reader->nextBatch(*_batch, block);
- if (rr == 0) {
- *eof = true;
- *read_rows = 0;
- return Status::OK();
+ try {
+ rr = _row_reader->nextBatch(*_batch, block);
+ if (rr == 0) {
+ *eof = true;
+ *read_rows = 0;
+ return Status::OK();
+ }
+ } catch (std::exception& e) {
+ return Status::InternalError("Orc row reader nextBatch failed.
reason = {}",
+ e.what());
}
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
