[
https://issues.apache.org/jira/browse/IMPALA-11039?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17515407#comment-17515407
]
Andrew Sherman commented on IMPALA-11039:
-----------------------------------------
The code in the proposed fix is in the new code added in IMPALA-9873
> DCHECK_GE(num_buffered_values_, num_rows) fails in parquet-column-readers.cc
> ----------------------------------------------------------------------------
>
> Key: IMPALA-11039
> URL: https://issues.apache.org/jira/browse/IMPALA-11039
> Project: IMPALA
> Issue Type: Bug
> Reporter: Abhishek Rawat
> Assignee: Quanlong Huang
> Priority: Critical
>
> From the test logs, following test case seems to be failing:
> {code:java}
> query_test.test_parquet_stats.TestParquetStats.test_page_index[mt_dop: 1 |
> protocol: beeswax | exec_option: {'batch_size': 0, 'num_nodes': 0,
> 'disable_codegen_rows_threshold': 0, 'disable_codegen': False,
> 'abort_on_error': 1, 'exec_single_node_rows_threshold': 0} | table_format:
> parquet/none] (from pytest)
> ....
> -- 2021-11-28 16:19:15,196 INFO MainThread: Started query
> 724d7ada4453a955:cbd1617900000000
> SET
> client_identifier=query_test/test_parquet_stats.py::TestParquetStats::()::test_page_index[mt_dop:1|protocol:beeswax|exec_option:{'batch_size':0;'num_nodes':0;'disable_codegen_rows_threshold':0;'disable_codegen':False;'abort_on_error':1;'exec_single_node_rows_threshold':0}|;
> SET batch_size=32;
> SET num_nodes=0;
> SET disable_codegen_rows_threshold=0;
> SET disable_codegen=False;
> SET exec_single_node_rows_threshold=0;
> -- 2021-11-28 16:19:15,198 INFO MainThread: Loading query test file:
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/testdata/workloads/functional-query/queries/QueryTest/parquet-page-index-large.test
> -- executing against localhost:21000
> ...
> ...
> ...
> -- 2021-11-28 16:19:36,435 INFO MainThread: Started query
> cc42e37e061881ae:6128a31000000000
> </system-err><error message="test setup failure">conftest.py:376: in cleanup
> request.instance.execute_query_expect_success(request.instance.client,
> "use default")
> common/impala_test_suite.py:831: in wrapper
> return function(*args, **kwargs)
> common/impala_test_suite.py:839: in execute_query_expect_success
> result = cls.__execute_query(impalad_client, query, query_options, user)
> common/impala_test_suite.py:956: in __execute_query
> return impalad_client.execute(query, user=user)
> common/impala_connection.py:212: in execute
> return self.__beeswax_client.execute(sql_stmt, user=user)
> beeswax/impala_beeswax.py:189: in execute
> handle = self.__execute_query(query_string.strip(), user=user)
> beeswax/impala_beeswax.py:365: in __execute_query
> handle = self.execute_query_async(query_string, user=user)
> beeswax/impala_beeswax.py:359: in execute_query_async
> handle = self.__do_rpc(lambda: self.imp_service.query(query,))
> beeswax/impala_beeswax.py:518: in __do_rpc
> raise ImpalaBeeswaxException("Not connected", None)
> E ImpalaBeeswaxException: ImpalaBeeswaxException:
> E Not connected</error><system-err>SET
> client_identifier=query_test/test_parquet_stats.py::TestParquetStats::()::test_page_index[mt_dop:1|protocol:beeswax|exec_option:{'batch_size':0;'num_nodes':0;'disable_codegen_rows_threshold':0;'disable_codegen':False;'abort_on_error':1;'exec_single_node_rows_threshold':0}|;
> SET sync_ddl=False;
> -- executing against localhost:21000 {code}
> Impalad logs:
> {code:java}
> F1128 16:19:37.713317 18815 parquet-column-readers.cc:1286]
> cc42e37e061881ae:6128a31000000002] Check failed: num_buffered_values_ >=
> num_rows (18848 vs. 106048) {code}
>
> Related stack trace:
> {code:java}
> #2 0x00000000056d9124 in google::DumpStackTraceAndExit() ()
> #3 0x00000000056ce55d in google::LogMessage::Fail() ()
> #4 0x00000000056cfe0d in google::LogMessage::SendToLog() ()
> #5 0x00000000056cdebb in google::LogMessage::Flush() ()
> #6 0x00000000056d1a79 in google::LogMessageFatal::~LogMessageFatal() ()
> #7 0x00000000031eedcd in
> impala::BaseScalarColumnReader::SkipTopLevelRows<false> (this=0x1bb14400,
> num_rows=106048, remaining=0x7f3e8a32a318) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/exec/parquet/parquet-column-readers.cc:1286
> #8 0x00000000031ed11c in
> impala::BaseScalarColumnReader::SkipRowsInternal<false> (this=0x1bb14400,
> num_rows=18848, skip_row_id=959199) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/exec/parquet/parquet-column-readers.cc:1548
> #9 0x00000000031ea414 in impala::BaseScalarColumnReader::SkipRows
> (this=0x1bb14400, num_rows=18848, skip_row_id=959199) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/exec/parquet/parquet-column-readers.h:527
> #10 0x0000000003160f68 in impala::HdfsParquetScanner::SkipRowsForColumns
> (this=0x181cfc00, column_readers=..., num_rows_to_skip=0x7f3e8a32a5c8,
> skip_to_row=0x7f3e8a32a5c0) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/exec/parquet/hdfs-parquet-scanner.cc:2341
> #11 0x000000000316d8cb in impala::HdfsParquetScanner::AssembleRows<true>
> (this=0x181cfc00, row_batch=0x188b0270, skip_row_group=0x181cfdd0) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/exec/parquet/hdfs-parquet-scanner.cc:2320
> #12 0x0000000003152bf9 in impala::HdfsParquetScanner::GetNextInternal
> (this=0x181cfc00, row_batch=0x188b0270) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/exec/parquet/hdfs-parquet-scanner.cc:537
> #13 0x0000000003150b7e in impala::HdfsParquetScanner::ProcessSplit
> (this=0x181cfc00) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/exec/parquet/hdfs-parquet-scanner.cc:427
> #14 0x0000000002d1d099 in impala::HdfsScanNode::ProcessSplit
> (this=0x139e7000, filter_ctxs=..., expr_results_pool=0x7f3e8a32b400,
> scan_range=0x1a990000, scanner_thread_reservation=0x7f3e8a32b328) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/exec/hdfs-scan-node.cc:500
> #15 0x0000000002d1c41a in impala::HdfsScanNode::ScannerThread
> (this=0x139e7000, first_thread=true, scanner_thread_reservation=41943040) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/exec/hdfs-scan-node.cc:418
> #16 0x0000000002d1b782 in impala::HdfsScanNode::<lambda()>::operator()(void)
> const (__closure=0x7f3e8a32bb28) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/exec/hdfs-scan-node.cc:339
> #17 0x0000000002d1e3a4 in
> boost::detail::function::void_function_obj_invoker0<impala::HdfsScanNode::ThreadTokenAvailableCb(impala::ThreadResourcePool*)::<lambda()>,
> void>::invoke(boost::detail::function::function_buffer &)
> (function_obj_ptr=...) at
> /data/jenkins/workspace/impala-asf-master-core-s3/Impala-Toolchain/toolchain-packages-gcc7.5.0/boost-1.74.0-p1/include/boost/function/function_template.hpp:158
> #18 0x00000000022ab70e in boost::function0<void>::operator()
> (this=0x7f3e8a32bb20) at
> /data/jenkins/workspace/impala-asf-master-core-s3/Impala-Toolchain/toolchain-packages-gcc7.5.0/boost-1.74.0-p1/include/boost/function/function_template.hpp:763
> #19 0x0000000002a77241 in
> impala::Thread::SuperviseThread(std::__cxx11::basic_string<char,
> std::char_traits<char>, std::allocator<char> > const&,
> std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>
> > const&, boost::function<void ()>, impala::ThreadDebugInfo const*,
> impala::Promise<long, (impala::PromiseMode)0>*) (name=..., category=...,
> functor=..., parent_thread_info=0x7f3e800f87c0,
> thread_started=0x7f3e800f75c0) at
> /data/jenkins/workspace/impala-asf-master-core-s3/repos/Impala/be/src/util/thread.cc:360
> #20 0x0000000002a7fb91 in
> boost::_bi::list5<boost::_bi::value<std::__cxx11::basic_string<char,
> std::char_traits<char>, std::allocator<char> > >,
> boost::_bi::value<std::__cxx11::basic_string<char, std::char_traits<char>,
> std::allocator<char> > >, boost::_bi::value<boost::function<void ()> >,
> boost::_bi::value<impala::ThreadDebugInfo*>,
> boost::_bi::value<impala::Promise<long, (impala::PromiseMode)0>*>
> >::operator()<void (*)(std::__cxx11::basic_string<char,
> std::char_traits<char>, std::allocator<char> > const&,
> std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>
> > const&, boost::function<void ()>, impala::ThreadDebugInfo const*,
> impala::Promise<long, (impala::PromiseMode)0>*),
> boost::_bi::list0>(boost::_bi::type<void>, void
> (*&)(std::__cxx11::basic_string<char, std::char_traits<char>,
> std::allocator<char> > const&, std::__cxx11::basic_string<char,
> std::char_traits<char>, std::allocator<char> > const&, boost::function<void
> ()>, impala::ThreadDebugInfo const*, impala::Promise<long,
> (impala::PromiseMode)0>*), boost::_bi::list0&, int) (this=0x160d4840,
> f=@0x160d4838: 0x2a76efe
> <impala::Thread::SuperviseThread(std::__cxx11::basic_string<char,
> std::char_traits<char>, std::allocator<char> > const&,
> std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>
> > const&, boost::function<void ()>, impala::ThreadDebugInfo const*,
> impala::Promise<long, (impala::PromiseMode)0>*)>, a=...) at
> /data/jenkins/workspace/impala-asf-master-core-s3/Impala-Toolchain/toolchain-packages-gcc7.5.0/boost-1.74.0-p1/include/boost/bind/bind.hpp:531
> #21 0x0000000002a7fab5 in boost::_bi::bind_t<void, void
> (*)(std::__cxx11::basic_string<char, std::char_traits<char>,
> std::allocator<char> > const&, std::__cxx11::basic_string<char,
> std::char_traits<char>, std::allocator<char> > const&, boost::function<void
> ()>, impala::ThreadDebugInfo const*, impala::Promise<long,
> (impala::PromiseMode)0>*),
> boost::_bi::list5<boost::_bi::value<std::__cxx11::basic_string<char,
> std::char_traits<char>, std::allocator<char> > >,
> boost::_bi::value<std::__cxx11::basic_string<char, std::char_traits<char>,
> std::allocator<char> > >, boost::_bi::value<boost::function<void ()> >,
> boost::_bi::value<impala::ThreadDebugInfo*>,
> boost::_bi::value<impala::Promise<long, (impala::PromiseMode)0>*> >
> >::operator()() (this=0x160d4838) at
> /data/jenkins/workspace/impala-asf-master-core-s3/Impala-Toolchain/toolchain-packages-gcc7.5.0/boost-1.74.0-p1/include/boost/bind/bind.hpp:1294
> #22 0x0000000002a7fa76 in boost::detail::thread_data<boost::_bi::bind_t<void,
> void (*)(std::__cxx11::basic_string<char, std::char_traits<char>,
> std::allocator<char> > const&, std::__cxx11::basic_string<char,
> std::char_traits<char>, std::allocator<char> > const&, boost::function<void
> ()>, impala::ThreadDebugInfo const*, impala::Promise<long,
> (impala::PromiseMode)0>*),
> boost::_bi::list5<boost::_bi::value<std::__cxx11::basic_string<char,
> std::char_traits<char>, std::allocator<char> > >,
> boost::_bi::value<std::__cxx11::basic_string<char, std::char_traits<char>,
> std::allocator<char> > >, boost::_bi::value<boost::function<void ()> >,
> boost::_bi::value<impala::ThreadDebugInfo*>,
> boost::_bi::value<impala::Promise<long, (impala::PromiseMode)0>*> > >
> >::run() (this=0x160d4700) at
> /data/jenkins/workspace/impala-asf-master-core-s3/Impala-Toolchain/toolchain-packages-gcc7.5.0/boost-1.74.0-p1/include/boost/thread/detail/thread.hpp:120
> {code}
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]