(master) reading parquet file from url does not work

[alexey-milovidov]

Describe what's wrong

ip-172-31-13-60.eu-central-1.compute.internal :) SELECT count() FROM url('https://datasets.clickhouse.com/hits.parquet')

SELECT count()
FROM url('https://datasets.clickhouse.com/hits.parquet')

Query id: 5946ca89-f28e-4eac-a820-daf421de65f0


Thread 1 "clickhouse" received signal SIGSEGV, Segmentation fault.
std::__1::basic_streambuf<char, std::__1::char_traits<char> >::xsputn (this=0x7fffffff5650, __s=0x17d68000 <error: Cannot access memory at address 0x17d68000>, __n=140737338223488) at ../contrib/libcxx/include/streambuf:464
464     ../contrib/libcxx/include/streambuf: No such file or directory.
(gdb) bt
#0  std::__1::basic_streambuf<char, std::__1::char_traits<char> >::xsputn (this=0x7fffffff5650, __s=0x17d68000 <error: Cannot access memory at address 0x17d68000>, __n=140737338223488) at ../contrib/libcxx/include/streambuf:464
#1  0x000000000a6ea291 in std::__1::basic_streambuf<char, std::__1::char_traits<char> >::sputn (this=0x7fffffff5650, __s=0x17d473c8 <arrow::global_state+8> "XW\366\a", __n=140737338223488) at ../contrib/libcxx/include/streambuf:229
#2  std::__1::__pad_and_output<char, std::__1::char_traits<char> > (__s=..., __s@entry=..., __ob=<optimized out>, __ob@entry=0x17d473c8 <arrow::global_state+8> "XW\366\a", __op=0x17d473c8 <arrow::global_state+8> "XW\366\a", 
    __oe=__oe@entry=0x80000ee19f48 <error: Cannot access memory at address 0x80000ee19f48>, __iob=..., __fl=<optimized out>) at ../contrib/libcxx/include/locale:1407
#3  0x000000000a6ea0c1 in std::__1::__put_character_sequence<char, std::__1::char_traits<char> > (__os=..., __str=0x17d473c8 <arrow::global_state+8> "XW\366\a", __len=<optimized out>) at ../contrib/libcxx/include/ostream:729
#4  0x00000000152eb239 in std::__1::operator<< <char, std::__1::char_traits<char>, std::__1::allocator<char> > (__os=..., __str=...) at ../contrib/libcxx/include/ostream:1056
#5  Poco::Net::HTTPBasicCredentials::authenticate (this=0x7fffffff6238, request=...) at ../contrib/poco/Net/src/HTTPBasicCredentials.cpp:96
#6  0x00000000103a506b in DB::detail::ReadWriteBufferFromHTTPBase<std::__1::shared_ptr<DB::UpdatableSession> >::call (this=this@entry=0x7ffff7065100, uri_=..., response=..., method_=...) at ../src/IO/ReadWriteBufferFromHTTP.h:176
#7  0x00000000103a43ed in DB::detail::ReadWriteBufferFromHTTPBase<std::__1::shared_ptr<DB::UpdatableSession> >::initialize (this=this@entry=0x7ffff7065100) at ../src/IO/ReadWriteBufferFromHTTP.h:290
#8  0x00000000103a2945 in DB::detail::ReadWriteBufferFromHTTPBase<std::__1::shared_ptr<DB::UpdatableSession> >::nextImpl (this=0x7ffff7065100) at ../src/IO/ReadWriteBufferFromHTTP.h:397
#9  0x000000000a6fed29 in DB::ReadBuffer::next (this=0x7ffff7065100) at ../src/IO/ReadBuffer.h:62
#10 DB::ReadBuffer::eof (this=0x7ffff7065100) at ../src/IO/ReadBuffer.h:96
#11 DB::ReadBuffer::read (this=0x7ffff7065100, to=0x7ffff084b900 "", n=65536) at ../src/IO/ReadBuffer.h:173
#12 DB::ReadBuffer::readBig (this=0x7ffff7065100, to=0x7ffff084b900 "", n=65536) at ../src/IO/ReadBuffer.h:200
#13 0x00000000134032b1 in DB::RandomAccessFileFromSeekableReadBuffer::Read (this=<optimized out>, nbytes=140737229052340, out=0x0) at ../src/Processors/Formats/Impl/ArrowBufferedStreams.cpp:85
#14 0x000000001340338b in DB::RandomAccessFileFromSeekableReadBuffer::Read (this=0x7ffff701dd08, nbytes=65536) at ../src/Processors/Formats/Impl/ArrowBufferedStreams.cpp:91
#15 0x0000000015d16dfe in arrow::io::RandomAccessFile::ReadAt(long, long) ()
#16 0x0000000015a17292 in parquet::SerializedFile::ParseMetaData() ()
#17 0x0000000015a14820 in parquet::ParquetFileReader::Contents::Open(std::__1::shared_ptr<arrow::io::RandomAccessFile>, parquet::ReaderProperties const&, std::__1::shared_ptr<parquet::FileMetaData>) ()
#18 0x0000000015a14e93 in parquet::ParquetFileReader::Open(std::__1::shared_ptr<arrow::io::RandomAccessFile>, parquet::ReaderProperties const&, std::__1::shared_ptr<parquet::FileMetaData>) ()
#19 0x000000001593c0b7 in parquet::arrow::FileReaderBuilder::Open(std::__1::shared_ptr<arrow::io::RandomAccessFile>, parquet::ReaderProperties const&, std::__1::shared_ptr<parquet::FileMetaData>) ()
#20 0x000000001593c43d in parquet::arrow::OpenFile(std::__1::shared_ptr<arrow::io::RandomAccessFile>, arrow::MemoryPool*, std::__1::unique_ptr<parquet::arrow::FileReader, std::__1::default_delete<parquet::arrow::FileReader> >*) ()
#21 0x00000000134941d6 in DB::getFileReaderAndSchema (in=..., file_reader=..., schema=..., format_settings=..., is_stopped=...) at ../src/Processors/Formats/Impl/ParquetBlockInputFormat.cpp:121
#22 0x0000000013494642 in DB::ParquetSchemaReader::readSchema (this=<optimized out>) at ../src/Processors/Formats/Impl/ParquetBlockInputFormat.cpp:168
#23 0x00000000133c206d in DB::readSchemaFromFormat(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > const&, std::__1::optional<DB::FormatSettings> const&, std::__1::function<std::__1::unique_ptr<DB::ReadBuffer, std::__1::default_delete<DB::ReadBuffer> > ()>, std::__1::shared_ptr<DB::Context const>, std::__1::unique_ptr<DB::ReadBuffer, std::__1::default_delete<DB::ReadBuffer> >&) (format_name=..., format_settings=..., read_buffer_creator=..., context=..., buf_out=...) at ../src/Formats/ReadSchemaUtils.cpp:49
#24 0x00000000133c2e08 in DB::readSchemaFromFormat(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > const&, std::__1::optional<DB::FormatSettings> const&, std::__1::function<std::__1::unique_ptr<DB::ReadBuffer, std::__1::default_delete<DB::ReadBuffer> > ()>, std::__1::shared_ptr<DB::Context const>) (format_name=..., format_settings=..., read_buffer_creator=..., context=...) at ../src/Formats/ReadSchemaUtils.cpp:65
#25 0x0000000012f45d3d in DB::IStorageURLBase::getTableStructureFromData (format=..., uri=..., compression_method=..., headers=..., format_settings=..., context=...) at ../src/Storages/StorageURL.cpp:104
#26 0x0000000012f458a0 in DB::IStorageURLBase::IStorageURLBase (this=this@entry=0x7ffff711e800, uri_=..., context_=..., table_id_=..., format_name_=..., format_settings_=..., columns_=..., constraints_=..., comment=..., compression_method_=..., headers_=..., http_method_=..., 
    partition_by_=...) at ../src/Storages/StorageURL.cpp:67
#27 0x0000000012f49524 in DB::StorageURL::StorageURL (this=0x7ffff711e800, uri_=..., table_id_=..., format_name_=..., format_settings_=..., columns_=..., constraints_=..., comment=..., context_=..., compression_method_=..., headers_=..., http_method_=..., partition_by_=...)
    at ../src/Storages/StorageURL.cpp:534
#28 0x0000000011d5366f in shared_ptr_helper<DB::StorageURL>::create<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > const&, DB::StorageID, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > const&, std::__1::nullopt_t const&, DB::ColumnsDescription const&, DB::ConstraintsDescription, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> >, std::__1::shared_ptr<DB::Context const>&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > const&, std::__1::vector<std::__1::tuple<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> >, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > >, std::__1::allocator<std::__1::tuple<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> >, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > > > >, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > const&> (args=..., 
    args=..., args=..., args=..., args=..., args=..., args=..., args=..., args=..., args=..., args=...) at ../base/base/../base/shared_ptr_helper.h:17
#29 0x0000000011d52de3 in DB::TableFunctionURL::getStorage (this=this@entry=0x7ffff0800518, source=..., format_=..., columns=..., global_context=..., table_name=..., compression_method_=...) at ../src/TableFunctions/TableFunctionURL.cpp:69
#30 0x0000000011d52210 in DB::ITableFunctionFileLike::executeImpl (this=0x7ffff0800518, context=..., table_name=...) at ../src/TableFunctions/ITableFunctionFileLike.cpp:98
#31 0x00000000122fa958 in DB::ITableFunction::execute (this=0x7ffff0800518, ast_function=..., context=..., table_name=..., cached_columns=..., use_global_context=<optimized out>) at ../src/TableFunctions/ITableFunction.cpp:26
#32 0x000000001240b1ab in DB::Context::executeTableFunction (this=<optimized out>, table_expression=...) at ../src/Interpreters/Context.cpp:1039
#33 0x00000000129ce8f8 in DB::JoinedTables::getLeftTableStorage (this=<optimized out>) at ../src/Interpreters/JoinedTables.cpp:195
#34 0x00000000127b5190 in DB::InterpreterSelectQuery::InterpreterSelectQuery (this=0x7ffff080b000, query_ptr_=..., context_=..., input_pipe_=..., storage_=..., options_=..., required_result_column_names=..., metadata_snapshot_=..., prepared_sets_=...)
    at ../src/Interpreters/InterpreterSelectQuery.cpp:316
#35 0x00000000127b4714 in DB::InterpreterSelectQuery::InterpreterSelectQuery (this=0x0, query_ptr_=..., context_=..., options_=..., required_result_column_names_=...) at ../src/Interpreters/InterpreterSelectQuery.cpp:158
#36 0x00000000129aca1f in std::__1::make_unique<DB::InterpreterSelectQuery, std::__1::shared_ptr<DB::IAST> const&, std::__1::shared_ptr<DB::Context>&, DB::SelectQueryOptions&, std::__1::vector<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> >, std::__1::allocator<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > > > const&> (__args=..., __args=..., __args=..., __args=...) at ../contrib/libcxx/include/memory:2068
#37 DB::InterpreterSelectWithUnionQuery::buildCurrentChildInterpreter (this=this@entry=0x7ffff6c3f8e0, ast_ptr_=..., current_required_result_column_names=...) at ../src/Interpreters/InterpreterSelectWithUnionQuery.cpp:218
#38 0x00000000129ab684 in DB::InterpreterSelectWithUnionQuery::InterpreterSelectWithUnionQuery (this=<optimized out>, query_ptr_=..., context_=..., options_=..., required_result_column_names=...) at ../src/Interpreters/InterpreterSelectWithUnionQuery.cpp:140
#39 0x0000000012766514 in std::__1::make_unique<DB::InterpreterSelectWithUnionQuery, std::__1::shared_ptr<DB::IAST>&, std::__1::shared_ptr<DB::Context>&, DB::SelectQueryOptions const&> (__args=..., __args=..., __args=...) at ../contrib/libcxx/include/memory:2068
#40 0x0000000012765838 in DB::InterpreterFactory::get (query=..., context=..., options=...) at ../src/Interpreters/InterpreterFactory.cpp:120
#41 0x0000000012b62640 in DB::executeQueryImpl (begin=begin@entry=0x7ffff6c3b0b0 "SELECT count() FROM url('https://datasets.clickhouse.com/hits.parquet')", end=<optimized out>, context=..., internal=false, stage=DB::QueryProcessingStage::Complete, istr=0x0)
    at ../src/Interpreters/executeQuery.cpp:632
#42 0x0000000012b60f0d in DB::executeQuery (query=..., context=..., internal=false, stage=DB::QueryProcessingStage::Complete) at ../src/Interpreters/executeQuery.cpp:985
#43 0x0000000013316f2c in DB::LocalConnection::sendQuery (this=this@entry=0x7ffff7040a00, query=..., query_id=..., stage=2) at ../src/Client/LocalConnection.cpp:94
#44 0x00000000132d7964 in DB::ClientBase::processOrdinaryQuery (this=this@entry=0x7fffffffc4c0, query_to_execute=..., parsed_query=...) at ../src/Client/ClientBase.cpp:645
#45 0x00000000132d6f61 in DB::ClientBase::processParsedSingleQuery (this=this@entry=0x7fffffffc4c0, full_query=..., query_to_execute=..., parsed_query=..., echo_query_=..., report_error=<optimized out>) at ../src/Client/ClientBase.cpp:1315
#46 0x00000000132d6805 in DB::ClientBase::processTextAsSingleQuery (this=this@entry=0x7fffffffc4c0, full_query=...) at ../src/Client/ClientBase.cpp:610
#47 0x00000000132ddcff in DB::ClientBase::processQueryText (this=this@entry=0x7fffffffc4c0, text=...) at ../src/Client/ClientBase.cpp:1467
#48 0x00000000132df0fc in DB::ClientBase::runInteractive (this=<optimized out>) at ../src/Client/ClientBase.cpp:1602
#49 0x000000000a7a8c50 in DB::LocalServer::main (this=0x7fffffffc4c0) at ../programs/local/LocalServer.cpp:479
#50 0x0000000015327aa6 in Poco::Util::Application::run (this=0x7fffffffc4c0) at ../contrib/poco/Util/src/Application.cpp:334
#51 0x000000000a7aea60 in mainEntryClickHouseLocal (argc=1, argv=0x7ffff7001170) at ../programs/local/LocalServer.cpp:812
#52 0x000000000a6e9ae1 in main (argc_=<optimized out>, argv_=<optimized out>) at ../programs/main.cpp:378