You are viewing a plain text version of this content. The canonical link for it is here.
Posted to jira@arrow.apache.org by "zzh (Jira)" <ji...@apache.org> on 2022/03/10 01:33:00 UTC
[jira] [Updated] (ARROW-15881) [c++] When link to libavrocpp.so, call parquet::arrow::WriteTable in a child thread get segmentation fault
[ https://issues.apache.org/jira/browse/ARROW-15881?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
zzh updated ARROW-15881:
------------------------
Description:
When I try to use Arrow to write parquet files, I encounter a error. The parquet::arrow::WriteTable out child thread can call successful, but parquet::arrow::WriteTable in child thread while cause Segmentation fault.
In my CMakeList.txt,I link libavrocpp.so because I want to use avro in project after finish this test. And I find that if I remove the link of libavrocpp.so, code while run successful.
The code like this:
{code:cpp}
arrow::Int64Builder test_a;
for (int i = 0; i < 1e7; ++i) {
PARQUET_THROW_NOT_OK(test_a.Append(i));
}
auto sc = arrow::schema({arrow::field("A", arrow::int64())});
auto table = arrow::Table::Make(sc,{test_a.Finish().ValueOrDie()});
const string &fileid = sole::uuid4().str();
string filename = "test.parq";
try {
std::shared_ptr<arrow::io::FileOutputStream> outfile;
PARQUET_ASSIGN_OR_THROW(
outfile,arrow::io::FileOutputStream::Open(filename)
);
PARQUET_THROW_NOT_OK(
parquet::arrow::WriteTable(*table, arrow::default_memory_pool(), outfile, table->num_rows())
);
} catch (exception &ex) {
cout << ex.what() << endl;
}
shared_ptr<std::thread> thread = make_shared<std::thread>([=]() {
arrow::Int64Builder test_a;
for (int i = 0; i < 1e7; ++i) {
PARQUET_THROW_NOT_OK(test_a.Append(i));
}
auto sc = arrow::schema({arrow::field("A", arrow::int64())});
auto table = arrow::Table::Make(sc,{test_a.Finish().ValueOrDie()});
const string &fileid = sole::uuid4().str();
string filename = "test.parq";
try {
std::shared_ptr<arrow::io::FileOutputStream> outfile;
PARQUET_ASSIGN_OR_THROW(
outfile,arrow::io::FileOutputStream::Open(filename)
);
PARQUET_THROW_NOT_OK(
parquet::arrow::WriteTable(*table, arrow::default_memory_pool(), outfile, table->num_rows())
);
} catch (exception &ex) {
cout << ex.what() << endl;
}
};{code}
The stack message is in the picture in attachment.
was:
When I try to use Arrow to write parquet files, I encounter a error. The parquet::arrow::WriteTable out child thread can call successful, but parquet::arrow::WriteTable in child thread while cause Segmentation fault.
The code like this:
{code:cpp}
arrow::Int64Builder test_a;
for (int i = 0; i < 1e7; ++i) {
PARQUET_THROW_NOT_OK(test_a.Append(i));
}
auto sc = arrow::schema({arrow::field("A", arrow::int64())});
auto table = arrow::Table::Make(sc,{test_a.Finish().ValueOrDie()});
const string &fileid = sole::uuid4().str();
string filename = "test.parq";
try {
std::shared_ptr<arrow::io::FileOutputStream> outfile;
PARQUET_ASSIGN_OR_THROW(
outfile,arrow::io::FileOutputStream::Open(filename)
);
PARQUET_THROW_NOT_OK(
parquet::arrow::WriteTable(*table, arrow::default_memory_pool(), outfile, table->num_rows())
);
} catch (exception &ex) {
cout << ex.what() << endl;
}
shared_ptr<std::thread> thread = make_shared<std::thread>([=]() {
arrow::Int64Builder test_a;
for (int i = 0; i < 1e7; ++i) {
PARQUET_THROW_NOT_OK(test_a.Append(i));
}
auto sc = arrow::schema({arrow::field("A", arrow::int64())});
auto table = arrow::Table::Make(sc,{test_a.Finish().ValueOrDie()});
const string &fileid = sole::uuid4().str();
string filename = "test.parq";
try {
std::shared_ptr<arrow::io::FileOutputStream> outfile;
PARQUET_ASSIGN_OR_THROW(
outfile,arrow::io::FileOutputStream::Open(filename)
);
PARQUET_THROW_NOT_OK(
parquet::arrow::WriteTable(*table, arrow::default_memory_pool(), outfile, table->num_rows())
);
} catch (exception &ex) {
cout << ex.what() << endl;
}
};{code}
The stack message is in the picture in attachment.
Summary: [c++] When link to libavrocpp.so, call parquet::arrow::WriteTable in a child thread get segmentation fault (was: [c++] call parquet::arrow::WriteTable in a child thread get segmentation fault)
> [c++] When link to libavrocpp.so, call parquet::arrow::WriteTable in a child thread get segmentation fault
> ----------------------------------------------------------------------------------------------------------
>
> Key: ARROW-15881
> URL: https://issues.apache.org/jira/browse/ARROW-15881
> Project: Apache Arrow
> Issue Type: Bug
> Components: C++
> Affects Versions: 7.0.0
> Environment: CentOS7,gcc7.0+,C++17
> Reporter: zzh
> Priority: Major
> Labels: newbie
> Attachments: message.png
>
>
> When I try to use Arrow to write parquet files, I encounter a error. The parquet::arrow::WriteTable out child thread can call successful, but parquet::arrow::WriteTable in child thread while cause Segmentation fault.
> In my CMakeList.txt,I link libavrocpp.so because I want to use avro in project after finish this test. And I find that if I remove the link of libavrocpp.so, code while run successful.
> The code like this:
> {code:cpp}
> arrow::Int64Builder test_a;
> for (int i = 0; i < 1e7; ++i) {
> PARQUET_THROW_NOT_OK(test_a.Append(i));
> }
> auto sc = arrow::schema({arrow::field("A", arrow::int64())});
> auto table = arrow::Table::Make(sc,{test_a.Finish().ValueOrDie()});
> const string &fileid = sole::uuid4().str();
> string filename = "test.parq";
> try {
> std::shared_ptr<arrow::io::FileOutputStream> outfile;
> PARQUET_ASSIGN_OR_THROW(
> outfile,arrow::io::FileOutputStream::Open(filename)
> );
> PARQUET_THROW_NOT_OK(
> parquet::arrow::WriteTable(*table, arrow::default_memory_pool(), outfile, table->num_rows())
> );
> } catch (exception &ex) {
> cout << ex.what() << endl;
> }
> shared_ptr<std::thread> thread = make_shared<std::thread>([=]() {
> arrow::Int64Builder test_a;
> for (int i = 0; i < 1e7; ++i) {
> PARQUET_THROW_NOT_OK(test_a.Append(i));
> }
> auto sc = arrow::schema({arrow::field("A", arrow::int64())});
> auto table = arrow::Table::Make(sc,{test_a.Finish().ValueOrDie()});
> const string &fileid = sole::uuid4().str();
> string filename = "test.parq";
> try {
> std::shared_ptr<arrow::io::FileOutputStream> outfile;
> PARQUET_ASSIGN_OR_THROW(
> outfile,arrow::io::FileOutputStream::Open(filename)
> );
> PARQUET_THROW_NOT_OK(
> parquet::arrow::WriteTable(*table, arrow::default_memory_pool(), outfile, table->num_rows())
> );
> } catch (exception &ex) {
> cout << ex.what() << endl;
> }
> };{code}
>
> The stack message is in the picture in attachment.
>
--
This message was sent by Atlassian Jira
(v8.20.1#820001)