[jira] [Comment Edited] (ARROW-11075) [Python] Getting reference not found with OCR enabled pyarrow
[
https://issues.apache.org/jira/browse/ARROW-11075?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17271070#comment-17271070
]
Kandarpa edited comment on ARROW-11075 at 1/25/21, 5:20 AM:
Hello [~uwe], [~wesm], thanks for looking into this issue.
Ran cmake as following :Ran cmake as following :
{code:java}
#cmake -DCMAKE_INSTALL_PREFIX=$ARROW_HOME
-DCMAKE_INSTALL_LIBDIR=lib
-DARROW_WITH_BZ2=ON
-DARROW_WITH_ZLIB=ON
-DARROW_WITH_ZSTD=ON
-DARROW_WITH_LZ4=ON
-DARROW_WITH_SNAPPY=ON
-DARROW_WITH_BROTLI=ON
-DARROW_PARQUET=ON
-DARROW_PYTHON=ON
-DARROW_BUILD_TESTS=ON
-DARROW_CUDA=ON
-DCUDA_CUDA_LIBRARY=/usr/local/cuda/lib64/stubs/libcuda.so
-DARROW_ORC=ON
-DARROW_JEMALLOC=ON
-DARROW_DATASET=ON
..
#make -j
{code}
nm -D ./release/libarrow.so | c++filt | grep orc
00bf21d0 u guard variable for
arrow::adapters::orc::ArrowInputFile::getName[abi:cxx11]() const::filename
U orc::ParseError::ParseError(char const*)
U orc::ParseError::ParseError(std::__cxx11::basic_string, std::allocator > const&)
U orc::ParseError::~ParseError()
U orc::InputStream::~InputStream()
U orc::createReader(std::unique_ptr >, orc::ReaderOptions const&)
U orc::ReaderOptions::ReaderOptions()
U orc::ReaderOptions::~ReaderOptions()
U orc::RowReaderOptions::includeTypes(std::__cxx11::list > const&)
U orc::RowReaderOptions::range(unsigned long, unsigned long)
U orc::RowReaderOptions::RowReaderOptions(orc::RowReaderOptions const&)
U orc::RowReaderOptions::RowReaderOptions()
U orc::RowReaderOptions::~RowReaderOptions()
00474110 T
arrow::io::internal::LibHdfsShim::BuilderSetForceNewInstance(hdfsBuilder*)
009cfda0 T arrow::adapters::orc::AppendBatch(orc::Type const*,
orc::ColumnVectorBatch*, long, long, arrow::ArrayBuilder*)
009cb720 T arrow::adapters::orc::GetArrowType(orc::Type const*,
std::shared_ptr*)
009c2ad0 T
arrow::adapters::orc::ORCFileReader::ReadSchema(std::shared_ptr*)
009c4140 T arrow::adapters::orc::ORCFileReader::ReadStripe(long,
std::shared_ptr*)
009c4690 T arrow::adapters::orc::ORCFileReader::ReadStripe(long,
std::vector > const&,
std::shared_ptr*)
009c2a80 T arrow::adapters::orc::ORCFileReader::NumberOfRows()
009c2a50 T arrow::adapters::orc::ORCFileReader::NumberOfStripes()
009c4e50 T arrow::adapters::orc::ORCFileReader::NextStripeReader(long,
std::shared_ptr*)
009c4f60 T arrow::adapters::orc::ORCFileReader::NextStripeReader(long,
std::vector > const&,
std::shared_ptr*)
009c2ba0 T
arrow::adapters::orc::ORCFileReader::Open(std::shared_ptr
const&, arrow::MemoryPool*,
std::unique_ptr >*)
{color:#0747a6}*009c32a0 T
arrow::adapters::orc::ORCFileReader::Read(std::shared_ptr*)*{color}
{color:#0747a6}*009c3630 T
arrow::adapters::orc::ORCFileReader::Read(std::shared_ptr
const&, std::shared_ptr*)*{color}
{color:#0747a6}*009c3d80 T
arrow::adapters::orc::ORCFileReader::Read(std::shared_ptr
const&, std::vector > const&,
std::shared_ptr*)*{color}
009c3760 T arrow::adapters::orc::ORCFileReader::Read(std::vector > const&, std::shared_ptr*)
009c2810 T arrow::adapters::orc::ORCFileReader::Seek(long)
009c2600 T arrow::adapters::orc::ORCFileReader::ORCFileReader()
009c2600 T arrow::adapters::orc::ORCFileReader::ORCFileReader()
009c2770 T arrow::adapters::orc::ORCFileReader::~ORCFileReader()
009c2770 T arrow::adapters::orc::ORCFileReader::~ORCFileReader()
009d0fc0 T arrow::adapters::orc::AppendMapBatch(orc::Type const*,
orc::ColumnVectorBatch*, long, long, arrow::ArrayBuilder*)
009ca990 T
arrow::adapters::orc::AppendBoolBatch(orc::ColumnVectorBatch*, long, long,
arrow::ArrayBuilder*)
009d0770 T arrow::adapters::orc::AppendListBatch(orc::Type const*,
orc::ColumnVectorBatch*, long, long, arrow::ArrayBuilder*)
009d1610 W arrow::Status
arrow::adapters::orc::AppendBinaryBatch(orc::ColumnVectorBatch*,
long, long, arrow::ArrayBuilder*)
009d1df0 W arrow::Status
arrow::adapters::orc::AppendBinaryBatch(orc::ColumnVectorBatch*,
long, long, arrow::ArrayBuilder*)
009d0490 T arrow::adapters::orc::AppendStructBatch(orc::Type const*,
orc::ColumnVectorBatch*, long, long, arrow::ArrayBuilder*)
009cfa60 T arrow::adapters::orc::AppendDecimalBatch(orc::Type const*,
orc::ColumnVectorBatch*, long, long, arrow::ArrayBuilder*)
009cb160 T
arrow::adapters::orc::AppendTimestampBatch(orc::ColumnVectorBatch*, long, long,
arrow::ArrayBuilder*)
009cf7d0 T
arrow::adapters::orc::AppendFixedBinaryBatch(orc::ColumnVectorBatch*, long,
long, arrow::ArrayBuilder*)
009d46c0 W arrow::Status
arrow::adapters::orc::AppendNumericBatchCast,
int, orc::LongVe
[jira] [Comment Edited] (ARROW-11075) [Python] Getting reference not found with OCR enabled pyarrow
[
https://issues.apache.org/jira/browse/ARROW-11075?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17271070#comment-17271070
]
Kandarpa edited comment on ARROW-11075 at 1/25/21, 5:19 AM:
Hello [~uwe], [~wesm], thanks for looking into this issue.
Ran cmake as following :Ran cmake as following :
{code:java}
#cmake -DCMAKE_INSTALL_PREFIX=$ARROW_HOME
-DCMAKE_INSTALL_LIBDIR=lib
-DARROW_WITH_BZ2=ON
-DARROW_WITH_ZLIB=ON
-DARROW_WITH_ZSTD=ON
-DARROW_WITH_LZ4=ON
-DARROW_WITH_SNAPPY=ON
-DARROW_WITH_BROTLI=ON
-DARROW_PARQUET=ON
-DARROW_PYTHON=ON
-DARROW_BUILD_TESTS=ON
-DARROW_CUDA=ON
-DCUDA_CUDA_LIBRARY=/usr/local/cuda/lib64/stubs/libcuda.so
-DARROW_ORC=ON
-DARROW_JEMALLOC=ON
-DARROW_DATASET=ON
..
#make -j
{code}
# nm -D ./release/libarrow.so | c++filt | grep orc
00bf21d0 u guard variable for
arrow::adapters::orc::ArrowInputFile::getName[abi:cxx11]() const::filename
U orc::ParseError::ParseError(char const*)
U orc::ParseError::ParseError(std::__cxx11::basic_string, std::allocator > const&)
U orc::ParseError::~ParseError()
U orc::InputStream::~InputStream()
U orc::createReader(std::unique_ptr >, orc::ReaderOptions const&)
U orc::ReaderOptions::ReaderOptions()
U orc::ReaderOptions::~ReaderOptions()
U orc::RowReaderOptions::includeTypes(std::__cxx11::list > const&)
U orc::RowReaderOptions::range(unsigned long, unsigned long)
U orc::RowReaderOptions::RowReaderOptions(orc::RowReaderOptions const&)
U orc::RowReaderOptions::RowReaderOptions()
U orc::RowReaderOptions::~RowReaderOptions()
00474110 T
arrow::io::internal::LibHdfsShim::BuilderSetForceNewInstance(hdfsBuilder*)
009cfda0 T arrow::adapters::orc::AppendBatch(orc::Type const*,
orc::ColumnVectorBatch*, long, long, arrow::ArrayBuilder*)
009cb720 T arrow::adapters::orc::GetArrowType(orc::Type const*,
std::shared_ptr*)
009c2ad0 T
arrow::adapters::orc::ORCFileReader::ReadSchema(std::shared_ptr*)
009c4140 T arrow::adapters::orc::ORCFileReader::ReadStripe(long,
std::shared_ptr*)
009c4690 T arrow::adapters::orc::ORCFileReader::ReadStripe(long,
std::vector > const&,
std::shared_ptr*)
009c2a80 T arrow::adapters::orc::ORCFileReader::NumberOfRows()
009c2a50 T arrow::adapters::orc::ORCFileReader::NumberOfStripes()
009c4e50 T arrow::adapters::orc::ORCFileReader::NextStripeReader(long,
std::shared_ptr*)
009c4f60 T arrow::adapters::orc::ORCFileReader::NextStripeReader(long,
std::vector > const&,
std::shared_ptr*)
009c2ba0 T
arrow::adapters::orc::ORCFileReader::Open(std::shared_ptr
const&, arrow::MemoryPool*,
std::unique_ptr >*)
{color:#0747a6}*009c32a0 T
arrow::adapters::orc::ORCFileReader::Read(std::shared_ptr*)*{color}
{color:#0747a6}*009c3630 T
arrow::adapters::orc::ORCFileReader::Read(std::shared_ptr
const&, std::shared_ptr*)*{color}
{color:#0747a6}*009c3d80 T
arrow::adapters::orc::ORCFileReader::Read(std::shared_ptr
const&, std::vector > const&,
std::shared_ptr*)*{color}
009c3760 T arrow::adapters::orc::ORCFileReader::Read(std::vector > const&, std::shared_ptr*)
009c2810 T arrow::adapters::orc::ORCFileReader::Seek(long)
009c2600 T arrow::adapters::orc::ORCFileReader::ORCFileReader()
009c2600 T arrow::adapters::orc::ORCFileReader::ORCFileReader()
009c2770 T arrow::adapters::orc::ORCFileReader::~ORCFileReader()
009c2770 T arrow::adapters::orc::ORCFileReader::~ORCFileReader()
009d0fc0 T arrow::adapters::orc::AppendMapBatch(orc::Type const*,
orc::ColumnVectorBatch*, long, long, arrow::ArrayBuilder*)
009ca990 T
arrow::adapters::orc::AppendBoolBatch(orc::ColumnVectorBatch*, long, long,
arrow::ArrayBuilder*)
009d0770 T arrow::adapters::orc::AppendListBatch(orc::Type const*,
orc::ColumnVectorBatch*, long, long, arrow::ArrayBuilder*)
009d1610 W arrow::Status
arrow::adapters::orc::AppendBinaryBatch(orc::ColumnVectorBatch*,
long, long, arrow::ArrayBuilder*)
009d1df0 W arrow::Status
arrow::adapters::orc::AppendBinaryBatch(orc::ColumnVectorBatch*,
long, long, arrow::ArrayBuilder*)
009d0490 T arrow::adapters::orc::AppendStructBatch(orc::Type const*,
orc::ColumnVectorBatch*, long, long, arrow::ArrayBuilder*)
009cfa60 T arrow::adapters::orc::AppendDecimalBatch(orc::Type const*,
orc::ColumnVectorBatch*, long, long, arrow::ArrayBuilder*)
009cb160 T
arrow::adapters::orc::AppendTimestampBatch(orc::ColumnVectorBatch*, long, long,
arrow::ArrayBuilder*)
009cf7d0 T
arrow::adapters::orc::AppendFixedBinaryBatch(orc::ColumnVectorBatch*, long,
long, arrow::ArrayBuilder*)
009d46c0 W arrow::Status
arrow::adapters::orc::AppendNumericBatchCast,
int, orc::L
[jira] [Comment Edited] (ARROW-11075) [Python] Getting reference not found with OCR enabled pyarrow
[
https://issues.apache.org/jira/browse/ARROW-11075?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17262386#comment-17262386
]
Kandarpa edited comment on ARROW-11075 at 1/11/21, 4:31 AM:
Hello [~uwe]
Please find following:
|Conda list|[^conda_list.txt]|
|Arrow cpp build logs
This includes cmake, make, make install|[^arrow_cpp_build.log]|
|Arrow python build logs|[^arrow_python_build.log]|
Please let me know if you need any further information.
Regards,
Kandarpa
was (Author: kandarpamalipeddi):
Hello [~uwe]
Please find following:
|Conda list|[^conda_list.txt]|
|Arrow cpp build logs
This includes cmake, make, make install|[^arrow_cpp_build.log]|
|Arrow python build logs|[^arrow_python_build.log]|
Please let me know if you need any further information.
Regards,
Kandarpa
> [Python] Getting reference not found with OCR enabled pyarrow
> -
>
> Key: ARROW-11075
> URL: https://issues.apache.org/jira/browse/ARROW-11075
> Project: Apache Arrow
> Issue Type: Bug
> Components: Python
>Affects Versions: 1.0.1
> Environment: PPC64LE
>Reporter: Kandarpa
>Priority: Major
> Attachments: arrow_cpp_build.log, arrow_python_build.log,
> conda_list.txt
>
>
> Generated the pyarrow with OCR enabled on Power using following steps:
> {code:java}
> export ARROW_HOME=$CONDA_PREFIX
> mkdir cpp/build
> cd cpp/build
> cmake -DCMAKE_INSTALL_PREFIX=$ARROW_HOME \
> -DCMAKE_INSTALL_LIBDIR=lib \
> -DARROW_WITH_BZ2=ON \
> -DARROW_WITH_ZLIB=ON \
> -DARROW_WITH_ZSTD=ON \
> -DARROW_WITH_LZ4=ON \
> -DARROW_WITH_SNAPPY=ON \
> -DARROW_WITH_BROTLI=ON \
> -DARROW_PARQUET=ON \
> -DARROW_PYTHON=ON \
> -DARROW_BUILD_TESTS=ON \
> -DARROW_CUDA=ON \
> -DCUDA_CUDA_LIBRARY=/usr/local/cuda/lib64/stubs/libcuda.so \
> -DARROW_ORC=ON \
> ..
> make -j
> make install
> cd ../../python
> python setup.py build_ext --bundle-arrow-cpp --with-orc --with-cuda
> --with-parquet bdist_wheel
> {code}
>
>
> With the generated whl package installed, ran CUDF tests and observed
> following error:
> *_ERROR cudf - ImportError:
> /conda/envs/rmm/lib/python3.7/site-packages/pyarrow/_orc.cpython-37m-powerpc64le-linux-gnu.so:
> undefined symbol: _ZN5arrow8adapters3orc13OR..._*
> Please find the whole error log below:
>
> ERRORS
>
> ERROR
> collecting test session
> _
> /conda/envs/rmm/lib/python3.7/importlib/__init__.py:127: in import_module
> return _bootstrap._gcd_import(name[level:], package, level)
> :1006: in _gcd_import
> ???
> :983: in _find_and_load
> ???
> :953: in _find_and_load_unlocked
> ???
> :219: in _call_with_frames_removed
> ???
> :1006: in _gcd_import
> ???
> :983: in _find_and_load
> ???
> :953: in _find_and_load_unlocked
> ???
> :219: in _call_with_frames_removed
> ???
> :1006: in _gcd_import
> ???
> :983: in _find_and_load
> ???
> :967: in _find_and_load_unlocked
> ???
> :677: in _load_unlocked
> ???
> :728: in exec_module
> ???
> :219: in _call_with_frames_removed
> ???
> cudf/cudf/__init__.py:60: in
> from cudf.io import (
> cudf/cudf/io/__init__.py:8: in
> from cudf.io.orc import read_orc, read_orc_metadata, to_orc
> cudf/cudf/io/orc.py:6: in
> from pyarrow import orc as orc
> /conda/envs/rmm/lib/python3.7/site-packages/pyarrow/orc.py:24: in
> import pyarrow._orc as _orc
> {color:#de350b}E ImportError:
> /conda/envs/rmm/lib/python3.7/site-packages/pyarrow/_orc.cpython-37m-powerpc64le-linux-gnu.so:
> undefined symbol:
> _ZN5arrow8adapters3orc13ORCFileReader4ReadEPSt10shared_ptrINS_5TableEE{color}
> ===
> short test summary info
>
> *_ERROR cudf - ImportError:
> /conda/envs/rmm/lib/python3.7/site-packages/pyarrow/_orc.cpython-37m-powerpc64le-linux-gnu.so:
> undefined symbol: _ZN5arrow8adapters3orc13OR..._*
>
> Interrupted: 1 error during collection
>
> ===
> 1 error in 1.54s
> ===
> Fatal Python error: Segmentation fault
--
This messag
[jira] [Comment Edited] (ARROW-11075) [Python] Getting reference not found with OCR enabled pyarrow
[
https://issues.apache.org/jira/browse/ARROW-11075?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17262386#comment-17262386
]
Kandarpa edited comment on ARROW-11075 at 1/11/21, 4:30 AM:
Hello [~uwe]
Please find following:
|Conda list|[^conda_list.txt]|
|Arrow cpp build logs
This includes cmake, make, make install|[^arrow_cpp_build.log]|
|Arrow python build logs|[^arrow_python_build.log]|
Please let me know if you need any further information.
Regards,
Kandarpa
was (Author: kandarpamalipeddi):
Hello [~uwe]
Please find following:
|Conda list|[^conda_list.txt]|
|Arrow cpp build logs
This includes cmake, make, make install|[^arrow_cpp_build.log]|
|Arrow python build logs|[^arrow_python_build.log]|
Please let me know if you need any further information.
Regards,
Kandarpa
> [Python] Getting reference not found with OCR enabled pyarrow
> -
>
> Key: ARROW-11075
> URL: https://issues.apache.org/jira/browse/ARROW-11075
> Project: Apache Arrow
> Issue Type: Bug
> Components: Python
>Affects Versions: 1.0.1
> Environment: PPC64LE
>Reporter: Kandarpa
>Priority: Major
> Attachments: arrow_cpp_build.log, arrow_python_build.log,
> conda_list.txt
>
>
> Generated the pyarrow with OCR enabled on Power using following steps:
> {code:java}
> export ARROW_HOME=$CONDA_PREFIX
> mkdir cpp/build
> cd cpp/build
> cmake -DCMAKE_INSTALL_PREFIX=$ARROW_HOME \
> -DCMAKE_INSTALL_LIBDIR=lib \
> -DARROW_WITH_BZ2=ON \
> -DARROW_WITH_ZLIB=ON \
> -DARROW_WITH_ZSTD=ON \
> -DARROW_WITH_LZ4=ON \
> -DARROW_WITH_SNAPPY=ON \
> -DARROW_WITH_BROTLI=ON \
> -DARROW_PARQUET=ON \
> -DARROW_PYTHON=ON \
> -DARROW_BUILD_TESTS=ON \
> -DARROW_CUDA=ON \
> -DCUDA_CUDA_LIBRARY=/usr/local/cuda/lib64/stubs/libcuda.so \
> -DARROW_ORC=ON \
> ..
> make -j
> make install
> cd ../../python
> python setup.py build_ext --bundle-arrow-cpp --with-orc --with-cuda
> --with-parquet bdist_wheel
> {code}
>
>
> With the generated whl package installed, ran CUDF tests and observed
> following error:
> *_ERROR cudf - ImportError:
> /conda/envs/rmm/lib/python3.7/site-packages/pyarrow/_orc.cpython-37m-powerpc64le-linux-gnu.so:
> undefined symbol: _ZN5arrow8adapters3orc13OR..._*
> Please find the whole error log below:
>
> ERRORS
>
> ERROR
> collecting test session
> _
> /conda/envs/rmm/lib/python3.7/importlib/__init__.py:127: in import_module
> return _bootstrap._gcd_import(name[level:], package, level)
> :1006: in _gcd_import
> ???
> :983: in _find_and_load
> ???
> :953: in _find_and_load_unlocked
> ???
> :219: in _call_with_frames_removed
> ???
> :1006: in _gcd_import
> ???
> :983: in _find_and_load
> ???
> :953: in _find_and_load_unlocked
> ???
> :219: in _call_with_frames_removed
> ???
> :1006: in _gcd_import
> ???
> :983: in _find_and_load
> ???
> :967: in _find_and_load_unlocked
> ???
> :677: in _load_unlocked
> ???
> :728: in exec_module
> ???
> :219: in _call_with_frames_removed
> ???
> cudf/cudf/__init__.py:60: in
> from cudf.io import (
> cudf/cudf/io/__init__.py:8: in
> from cudf.io.orc import read_orc, read_orc_metadata, to_orc
> cudf/cudf/io/orc.py:6: in
> from pyarrow import orc as orc
> /conda/envs/rmm/lib/python3.7/site-packages/pyarrow/orc.py:24: in
> import pyarrow._orc as _orc
> {color:#de350b}E ImportError:
> /conda/envs/rmm/lib/python3.7/site-packages/pyarrow/_orc.cpython-37m-powerpc64le-linux-gnu.so:
> undefined symbol:
> _ZN5arrow8adapters3orc13ORCFileReader4ReadEPSt10shared_ptrINS_5TableEE{color}
> ===
> short test summary info
>
> *_ERROR cudf - ImportError:
> /conda/envs/rmm/lib/python3.7/site-packages/pyarrow/_orc.cpython-37m-powerpc64le-linux-gnu.so:
> undefined symbol: _ZN5arrow8adapters3orc13OR..._*
>
> Interrupted: 1 error during collection
>
> ===
> 1 error in 1.54s
> ===
> Fatal Python error: Segmentation fault
--
This mess
