Antoine Pitrou created ARROW-7884:
-------------------------------------
Summary: [C++][Python] Crash in pq.read_table()
Key: ARROW-7884
URL: https://issues.apache.org/jira/browse/ARROW-7884
Project: Apache Arrow
Issue Type: Bug
Components: C++, Python
Reporter: Antoine Pitrou
The following crashes:
{code:python}
>>> import pyarrow.parquet as pq
>>>
>>>
>>> tab =
>>> pq.read_table("../cpp/submodules/parquet-testing/data/nation.dict-malformed.parquet")
{code}
Here is the backtrace:
{code}
#0 __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:51
#1 0x00007ffff7805801 in __GI_abort () at abort.c:79
#2 0x00007fffb8a18e42 in arrow::util::CerrLog::~CerrLog (this=0x7fff84001690,
__in_chrg=<optimized out>) at ../src/arrow/util/logging.cc:50
#3 0x00007fffb8a18e5e in arrow::util::CerrLog::~CerrLog (this=0x7fff84001690,
__in_chrg=<optimized out>) at ../src/arrow/util/logging.cc:52
#4 0x00007fffb8a18c9f in arrow::util::ArrowLog::~ArrowLog
(this=0x7fffaeffbf60, __in_chrg=<optimized out>) at
../src/arrow/util/logging.cc:228
#5 0x00007fffb89e1607 in
arrow::io::internal::SharedExclusiveChecker::LockExclusive
(this=0x555555db1338) at ../src/arrow/io/interfaces.cc:287
#6 0x00007fffb89b0b10 in
arrow::io::internal::ExclusiveLockGuard<arrow::io::internal::SharedExclusiveChecker>::ExclusiveLockGuard
(this=0x7fffaeffbff8,
lock=0x555555db1338) at ../src/arrow/io/concurrency.h:47
#7 0x00007fffb89ad20f in
arrow::io::internal::SharedExclusiveChecker::exclusive_guard
(this=0x555555db1338) at ../src/arrow/io/concurrency.h:74
#8 0x00007fffb89cb74b in
arrow::io::internal::RandomAccessFileConcurrencyWrapper<arrow::io::ReadableFile>::GetSize
(this=0x555555db1320)
at ../src/arrow/io/concurrency.h:200
#9 0x00007fffb4ca61f3 in parquet::SerializedRowGroup::GetColumnPageReader
(this=0x7fff840013e0, i=2) at ../src/parquet/file_reader.cc:117
#10 0x00007fffb4ca2b0e in parquet::RowGroupReader::GetColumnPageReader
(this=0x7fff840014b0, i=2) at ../src/parquet/file_reader.cc:75
#11 0x00007fffb4b03296 in parquet::arrow::FileColumnIterator::NextChunk
(this=0x7fff84000c10) at ../src/parquet/arrow/reader_internal.h:81
#12 0x00007fffb4b06ccc in parquet::arrow::LeafReader::NextRowGroup
(this=0x7fff84000ef0) at ../src/parquet/arrow/reader.cc:452
#13 0x00007fffb4b0677e in parquet::arrow::LeafReader::LeafReader
(this=0x7fff84000ef0, ctx=std::shared_ptr<parquet::arrow::ReaderContext>
(empty) = {...},
field=std::shared_ptr<arrow::Field> (empty) = {...},
input=std::unique_ptr<parquet::arrow::FileColumnIterator> = {...}) at
../src/parquet/arrow/reader.cc:407
#14 0x00007fffb4afbdac in parquet::arrow::GetReader (field=...,
ctx=std::shared_ptr<parquet::arrow::ReaderContext> (use count 2, weak count 0)
= {...},
out=0x7fffaeffc580) at ../src/parquet/arrow/reader.cc:709
#15 0x00007fffb4b0425a in parquet::arrow::FileReaderImpl::GetFieldReader
(this=0x555555dbf480, i=2,
included_leaves=std::shared_ptr<std::unordered_set<int, std::hash<int>,
std::equal_to<int>, std::allocator<int> >> (use count 5, weak count 0) = {...},
row_groups=std::vector of length 1, capacity 1 = {...}, out=0x7fffaeffc580)
at ../src/parquet/arrow/reader.cc:173
#16 0x00007fffb4b04451 in parquet::arrow::FileReaderImpl::ReadSchemaField
(this=0x555555dbf480, i=2,
included_leaves=std::shared_ptr<std::unordered_set<int, std::hash<int>,
std::equal_to<int>, std::allocator<int> >> (use count 5, weak count 0) = {...},
row_groups=std::vector of length 1, capacity 1 = {...},
out_field=0x555555dce870, out=0x555555dce790) at
../src/parquet/arrow/reader.cc:186
#17 0x00007fffb4afcf7f in
parquet::arrow::FileReaderImpl::<lambda(int)>::operator()(int) const
(__closure=0x555555dd4e08, i=2) at ../src/parquet/arrow/reader.cc:810
#18 0x00007fffb4b01151 in std::__invoke_impl<arrow::Status,
parquet::arrow::FileReaderImpl::ReadRowGroups(const std::vector<int>&, const
std::vector<int>&, std::shared_ptr<arrow::Table>*)::<lambda(int)>&,
int&>(std::__invoke_other, parquet::arrow::FileReaderImpl::<lambda(int)> &, int
&) (__f=..., __args#0=@0x555555dd4e38: 2)
at /usr/include/c++/7/bits/invoke.h:60
#19 0x00007fffb4b010dc in
std::__invoke<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>&,
int&>(parquet::arrow::FileReaderImpl::<lambda(int)> &, int &) (__fn=...,
__args#0=@0x555555dd4e38: 2) at /usr/include/c++/7/bits/invoke.h:96
#20 0x00007fffb4b00fe1 in
std::_Bind<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>(int)>::__call<arrow::Status,
0>(std::tuple<> &&, std::_Index_tuple<0>) (this=0x555555dd4e08, __args=...) at
/usr/include/c++/7/functional:469
#21 0x00007fffb4b00b0d in
std::_Bind<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>(int)>::operator()<>(void)
(this=0x555555dd4e08) at /usr/include/c++/7/functional:551
#22 0x00007fffb4b00742 in std::__invoke_impl<arrow::Status,
std::_Bind<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>(int)>&>(std::__invoke_other,
std::_Bind<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>(int)> &) (__f=...) at
/usr/include/c++/7/bits/invoke.h:60
#23 0x00007fffb4b004c5 in
std::__invoke<std::_Bind<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>(int)>&>(std::_Bind<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>(int)> &) (__fn=...) at
/usr/include/c++/7/bits/invoke.h:96
#24 0x00007fffb4b001bb in
std::__future_base::_Task_state<std::_Bind<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>(int)>, std::allocator<int>,
arrow::Status()>::<lambda()>::operator()(void) const (__closure=0x7fffaeffcc28)
at /usr/include/c++/7/future:1421
#25 0x00007fffb4b00bf9 in
std::__future_base::_Task_setter<std::unique_ptr<std::__future_base::_Result<arrow::Status>,
std::__future_base::_Result_base::_Deleter>,
std::__future_base::_Task_state<_Fn, _Alloc, _Res(_Args ...)>::_M_run(_Args&&
...) [with _Fn = std::_Bind<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>(int)>; _Alloc =
std::allocator<int>; _Res = arrow::Status; _Args = {}]::<lambda()>,
arrow::Status>::operator()(void) const (this=0x7fffaeffcc30) at
/usr/include/c++/7/future:1339
#26 0x00007fffb4b0080a in
std::_Function_handler<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter>(),
std::__future_base::_Task_setter<std::unique_ptr<std::__future_base::_Result<arrow::Status>,
std::__future_base::_Result_base::_Deleter>,
std::__future_base::_Task_state<_Fn, _Alloc, _Res(_Args ...)>::_M_run(_Args&&
...) [with _Fn = std::_Bind<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>(int)>; _Alloc =
std::allocator<int>; _Res = arrow::Status; _Args = {}]::<lambda()>,
arrow::Status> >::_M_invoke(const std::_Any_data &) (
__functor=...) at /usr/include/c++/7/bits/std_function.h:302
#27 0x00007fffb4b0861e in
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>::operator()() const (
this=0x7fffaeffcc30) at /usr/include/c++/7/bits/std_function.h:706
#28 0x00007fffb4b028e6 in
std::__future_base::_State_baseV2::_M_do_set(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*) (this=0x555555dd4de0,
__f=0x7fffaeffcc30, __did_set=0x7fffaeffcb9f) at /usr/include/c++/7/future:561
#29 0x00007fffb4b126c5 in std::__invoke_impl<void, void
(std::__future_base::_State_baseV2::*)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*,
bool*>(std::__invoke_memfun_deref, void
(std::__future_base::_State_baseV2::*&&)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*&&,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*&&, bool*&&) (__f=
@0x7fffaeffcbe0: (void
(std::__future_base::_State_baseV2::*)(std::__future_base::_State_baseV2 *
const, std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter>()> *, bool *)) 0x7fffb4b028b0
<std::__future_base::_State_baseV2::_M_do_set(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*)>,
__t=@0x7fffaeffcbb0: 0x555555dd4de0, __args#0=@0x7fffaeffcbb8: 0x7fffaeffcc30,
---Type <return> to continue, or q <return> to quit---
__args#1=@0x7fffaeffcbc0: 0x7fffaeffcb9f) at
/usr/include/c++/7/bits/invoke.h:73
#30 0x00007fffb4b0c9f2 in std::__invoke<void
(std::__future_base::_State_baseV2::*)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*>(void
(std::__future_base::_State_baseV2::*&&)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*&&,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*&&, bool*&&) (__fn=
@0x7fffaeffcbe0: (void
(std::__future_base::_State_baseV2::*)(std::__future_base::_State_baseV2 *
const, std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter>()> *, bool *)) 0x7fffb4b028b0
<std::__future_base::_State_baseV2::_M_do_set(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*)>,
__args#0=@0x7fffaeffcbb0: 0x555555dd4de0, __args#1=@0x7fffaeffcbb8:
0x7fffaeffcc30,
__args#2=@0x7fffaeffcbc0: 0x7fffaeffcb9f) at
/usr/include/c++/7/bits/invoke.h:95
#31 0x00007fffb4b0819e in void std::call_once<void
(std::__future_base::_State_baseV2::*)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*>(std::once_flag&, void
(std::__future_base::_State_baseV2::*&&)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*&&,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*&&,
bool*&&)::{lambda()#1}::operator()() const (__closure=0x7fffaeffcb20) at
/usr/include/c++/7/mutex:672
#32 0x00007fffb4b08209 in void std::call_once<void
(std::__future_base::_State_baseV2::*)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*>(std::once_flag&, void
(std::__future_base::_State_baseV2::*&&)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*&&,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*&&,
bool*&&)::{lambda()#2}::operator()() const (__closure=0x0) at
/usr/include/c++/7/mutex:677
#33 0x00007fffb4b0821a in void std::call_once<void
(std::__future_base::_State_baseV2::*)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*>(std::once_flag&, void
(std::__future_base::_State_baseV2::*&&)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*&&,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*&&,
bool*&&)::{lambda()#2}::_FUN() () at /usr/include/c++/7/mutex:677
#34 0x00007ffff7bc5827 in __pthread_once_slow (once_control=0x555555dd4df8,
init_routine=0x7fffb6d52782 <std::__once_proxy()>) at pthread_once.c:116
#35 0x00007fffb4afa2fa in __gthread_once (__once=0x555555dd4df8,
__func=0x7fffb6d52782 <std::__once_proxy()>)
at /usr/include/x86_64-linux-gnu/c++/7/bits/gthr-default.h:699
#36 0x00007fffb4b082d3 in std::call_once<void
(std::__future_base::_State_baseV2::*)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*>(std::once_flag&, void
(std::__future_base::_State_baseV2::*&&)(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*),
std::__future_base::_State_baseV2*&&,
std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*&&, bool*&&) (__once=..., __f=
@0x7fffaeffcbe0: (void
(std::__future_base::_State_baseV2::*)(std::__future_base::_State_baseV2 *
const, std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter>()> *, bool *)) 0x7fffb4b028b0
<std::__future_base::_State_baseV2::_M_do_set(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>*, bool*)>,
__args#0=@0x7fffaeffcbb0: 0x555555dd4de0, __args#1=@0x7fffaeffcbb8:
0x7fffaeffcc30,
__args#2=@0x7fffaeffcbc0: 0x7fffaeffcb9f) at /usr/include/c++/7/mutex:684
#37 0x00007fffb4b02488 in
std::__future_base::_State_baseV2::_M_set_result(std::function<std::unique_ptr<std::__future_base::_Result_base,
std::__future_base::_Result_base::_Deleter> ()>, bool) (this=0x555555dd4de0,
__res=..., __ignore_failure=false) at /usr/include/c++/7/future:401
#38 0x00007fffb4b00241 in
std::__future_base::_Task_state<std::_Bind<parquet::arrow::FileReaderImpl::ReadRowGroups(const
std::vector<int>&, const std::vector<int>&,
std::shared_ptr<arrow::Table>*)::<lambda(int)>(int)>, std::allocator<int>,
arrow::Status()>::_M_run(void) (this=0x555555dd4de0) at
/usr/include/c++/7/future:1423
#39 0x00007fffb708834d in std::packaged_task<arrow::Status ()>::operator()()
(this=0x555555dd4e90) at /usr/include/c++/7/future:1556
#40 0x00007fffb7080078 in
arrow::internal::detail::packaged_task_wrapper<arrow::Status>::operator()
(this=0x555555dd4eb0) at ../src/arrow/util/thread_pool.h:70
#41 0x00007fffb4b15d78 in std::_Function_handler<void (),
arrow::internal::detail::packaged_task_wrapper<arrow::Status>
>::_M_invoke(std::_Any_data const&) (
__functor=...) at /usr/include/c++/7/bits/std_function.h:316
#42 0x00007fffb8a2c73e in std::function<void ()>::operator()() const
(this=0x7fffaeffcd50) at /usr/include/c++/7/bits/std_function.h:706
#43 0x00007fffb8a2a644 in arrow::internal::WorkerLoop
(state=std::shared_ptr<arrow::internal::ThreadPool::State> (use count 49, weak
count 0) = {...}, it={
_M_id = {
_M_thread = 140736129390336
}
}) at ../src/arrow/util/thread_pool.cc:88
#44 0x00007fffb8a2b032 in
arrow::internal::ThreadPool::<lambda()>::operator()(void) const
(__closure=0x555555dd2578) at ../src/arrow/util/thread_pool.cc:225
#45 0x00007fffb8a2bc93 in std::__invoke_impl<void,
arrow::internal::ThreadPool::LaunchWorkersUnlocked(int)::<lambda()>
>(std::__invoke_other, arrow::internal::ThreadPool::<lambda()> &&) (__f=...) at
/usr/include/c++/7/bits/invoke.h:60
#46 0x00007fffb8a2b9d4 in
std::__invoke<arrow::internal::ThreadPool::LaunchWorkersUnlocked(int)::<lambda()>
>(arrow::internal::ThreadPool::<lambda()> &&) (__fn=...)
at /usr/include/c++/7/bits/invoke.h:95
#47 0x00007fffb8a2bec6 in
std::thread::_Invoker<std::tuple<arrow::internal::ThreadPool::LaunchWorkersUnlocked(int)::<lambda()>
> >::_M_invoke<0>(std::_Index_tuple<0>)
(this=0x555555dd2578) at /usr/include/c++/7/thread:234
#48 0x00007fffb8a2be82 in
std::thread::_Invoker<std::tuple<arrow::internal::ThreadPool::LaunchWorkersUnlocked(int)::<lambda()>
> >::operator()(void) (
this=0x555555dd2578) at /usr/include/c++/7/thread:243
#49 0x00007fffb8a2be52 in
std::thread::_State_impl<std::thread::_Invoker<std::tuple<arrow::internal::ThreadPool::LaunchWorkersUnlocked(int)::<lambda()>
> > >::_M_run(void) (this=0x555555dd2570) at /usr/include/c++/7/thread:186
#50 0x00007fffb6d53163 in std::execute_native_thread_routine
(__p=0x555555dd2570)
at
/home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80
#51 0x00007ffff7bbd6db in start_thread (arg=0x7fffaeffd700) at
pthread_create.c:463
---Type <return> to continue, or q <return> to quit---
#52 0x00007ffff78e688f in clone () at
../sysdeps/unix/sysv/linux/x86_64/clone.S:95
{code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)