Skip to content

Conversation

@amorynan
Copy link
Contributor

@amorynan amorynan commented Mar 25, 2025

Fixed the issue of inserting into a struct type string literal with one more subfield causing BE coredump
some situation like this blow will make BE core

create table t(a int, b int, s struct<a:int>) PROPERTIES ("replication_allocation" = "tag.location.default: 1");
insert into t values(1,1,'{1,2}');

core info:

[WARNING!] /sys/kernel/mm/transparent_hugepage/enabled: [always] madvise never, Doris not recommend turning on THP, which may cause the BE process to use more memory and cannot be freed in time. Turn off THP: `echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled`
start BE in local mode
=================================================================
==2818976==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000f17a90 at pc 0x55eba7fdd69c bp 0x7f03243dbd30 sp 0x7f03243dbd28
READ of size 8 at 0x603000f17a90 thread T928 (brpc_light)
    #0 0x55eba7fdd69b in std::__shared_ptr<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2>::get() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:1291:16
    #1 0x55eba7fdd649 in std::__shared_ptr_access<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2, false, false>::_M_get() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:990:66
    #2 0x55eba7fda316 in std::__shared_ptr_access<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2, false, false>::operator->() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:984:9
    #3 0x55ebcfc8b19e in doris::vectorized::DataTypeStructSerDe::deserialize_one_cell_from_json(doris::vectorized::IColumn&, doris::Slice&, doris::vectorized::DataTypeSerDe::FormatOptions const&) const /mnt/disk1/wangqiannan/amory/doris/be/src/vec/data_types/serde/data_type_struct_serde.cpp:200:25
    #4 0x55ebdac49c8b in doris::vectorized::ConvertImplGenericFromString::execute(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long) /mnt/disk1/wangqiannan/amory/doris/be/src/vec/functions/function_cast.h:618:36
    #5 0x55ebda2234d0 in doris::Status std::__invoke_impl<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(std::__invoke_other, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:61:14
    #6 0x55ebda22323a in std::enable_if<is_invocable_r_v<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>, doris::Status>::type std::__invoke_r<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:114:9
    #7 0x55ebda222e71 in std::_Function_handler<doris::Status (doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long), doris::Status (*)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)>::_M_invoke(std::_Any_data const&, doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:291:9
    #8 0x55ebd9b3f1d2 in std::function<doris::Status (doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long)>::operator()(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long) const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:560:9
    #9 0x55ebda1ad7c7 in doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bool) const::'lambda'(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)::operator()(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long) const /mnt/disk1/wangqiannan/amory/doris/be/src/vec/functions/function_cast.h:2241:17
    #10 0x55ebda1acee2 in doris::Status std::__invoke_impl<doris::Status, doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bool) const::'lambda'(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)&, doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(std::__invoke_other, doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bo@@@

What problem does this PR solve?

Issue Number: close #xxx

Related PR: #xxx

Problem Summary:

Release note

None

Check List (For Author)

  • Test

    • Regression test
    • Unit Test
    • Manual test (add detailed scripts or steps below)
    • No need to test or manual test. Explain why:
      • This is a refactor/code format and no logic has been changed.
      • Previous test can cover this change.
      • No code files have been changed.
      • Other reason
  • Behavior changed:

    • No.
    • Yes.
  • Does this need documentation?

    • No.
    • Yes.

Check List (For Reviewer who merge this PR)

  • Confirm the release note
  • Confirm test cases
  • Confirm document
  • Add branch pick label

@Thearas
Copy link
Contributor

Thearas commented Mar 25, 2025

Thank you for your contribution to Apache Doris.
Don't know what should be done next? See How to process your PR.

Please clearly describe your PR:

  1. What problem was fixed (it's best to include specific error reporting information). How it was fixed.
  2. Which behaviors were modified. What was the previous behavior, what is it now, why was it modified, and what possible impacts might there be.
  3. What features were added. Why was this function added?
  4. Which code was refactored and why was this part of the code refactored?
  5. Which functions were optimized and what is the difference before and after the optimization?

@amorynan
Copy link
Contributor Author

run buildall

@doris-robot
Copy link

BE UT Coverage Report

Increment line coverage 100.00% (2/2) 🎉

Increment coverage report
Complete coverage report

Category Coverage
Function Coverage 50.89% (13619/26763)
Line Coverage 40.28% (118230/293550)
Region Coverage 38.95% (60054/154201)
Branch Coverage 33.86% (30209/89216)

4 \N \N {"f1":null, "f2":null, "f3":null, "f4":null} {"f1":"abc", "f2":"def", "f3":"hij"}

-- !select --
1 {"a":1} {"a":1, "b":"a"} {"a":1, "s":{"a":1}} {"a":1, "s":{"a":1, "b":"a"}} {"a":1, "s":{"b":1, "s":{"c":1}}} {"a":1, "b":{"c":1, "d":"a"}, "e":1}
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why not using beut to test this case?

@github-actions github-actions bot added the approved Indicates a PR has been approved by one committer. label Mar 26, 2025
@github-actions
Copy link
Contributor

PR approved by at least one committer and no changes requested.

@github-actions
Copy link
Contributor

PR approved by anyone and no changes requested.

Copy link
Member

@eldenmoon eldenmoon left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@eldenmoon eldenmoon merged commit edee8c1 into apache:master Mar 26, 2025
30 of 34 checks passed
github-actions bot pushed a commit that referenced this pull request Mar 26, 2025
…iteral with one more subfield causing BE coredump (#49485)

Fixed the issue of inserting into a struct type string literal with one
more subfield causing BE coredump
some situation like this blow will make BE core
```
create table t(a int, b int, s struct<a:int>) PROPERTIES ("replication_allocation" = "tag.location.default: 1");
insert into t values(1,1,'{1,2}');
```
core info:
```
[WARNING!] /sys/kernel/mm/transparent_hugepage/enabled: [always] madvise never, Doris not recommend turning on THP, which may cause the BE process to use more memory and cannot be freed in time. Turn off THP: `echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled`
start BE in local mode
=================================================================
==2818976==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000f17a90 at pc 0x55eba7fdd69c bp 0x7f03243dbd30 sp 0x7f03243dbd28
READ of size 8 at 0x603000f17a90 thread T928 (brpc_light)
    #0 0x55eba7fdd69b in std::__shared_ptr<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2>::get() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:1291:16
    #1 0x55eba7fdd649 in std::__shared_ptr_access<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2, false, false>::_M_get() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:990:66
    #2 0x55eba7fda316 in std::__shared_ptr_access<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2, false, false>::operator->() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:984:9
    #3 0x55ebcfc8b19e in doris::vectorized::DataTypeStructSerDe::deserialize_one_cell_from_json(doris::vectorized::IColumn&, doris::Slice&, doris::vectorized::DataTypeSerDe::FormatOptions const&) const /mnt/disk1/wangqiannan/amory/doris/be/src/vec/data_types/serde/data_type_struct_serde.cpp:200:25
    #4 0x55ebdac49c8b in doris::vectorized::ConvertImplGenericFromString::execute(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long) /mnt/disk1/wangqiannan/amory/doris/be/src/vec/functions/function_cast.h:618:36
    #5 0x55ebda2234d0 in doris::Status std::__invoke_impl<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(std::__invoke_other, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:61:14
    #6 0x55ebda22323a in std::enable_if<is_invocable_r_v<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>, doris::Status>::type std::__invoke_r<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:114:9
    #7 0x55ebda222e71 in std::_Function_handler<doris::Status (doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long), doris::Status (*)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)>::_M_invoke(std::_Any_data const&, doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:291:9
    #8 0x55ebd9b3f1d2 in std::function<doris::Status (doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long)>::operator()(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long) const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:560:9
    #9 0x55ebda1ad7c7 in doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bool) const::'lambda'(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)::operator()(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long) const /mnt/disk1/wangqiannan/amory/doris/be/src/vec/functions/function_cast.h:2241:17
    #10 0x55ebda1acee2 in doris::Status std::__invoke_impl<doris::Status, doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bool) const::'lambda'(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)&, doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(std::__invoke_other, doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bo@@@
```
github-actions bot pushed a commit that referenced this pull request Mar 26, 2025
…iteral with one more subfield causing BE coredump (#49485)

Fixed the issue of inserting into a struct type string literal with one
more subfield causing BE coredump
some situation like this blow will make BE core
```
create table t(a int, b int, s struct<a:int>) PROPERTIES ("replication_allocation" = "tag.location.default: 1");
insert into t values(1,1,'{1,2}');
```
core info:
```
[WARNING!] /sys/kernel/mm/transparent_hugepage/enabled: [always] madvise never, Doris not recommend turning on THP, which may cause the BE process to use more memory and cannot be freed in time. Turn off THP: `echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled`
start BE in local mode
=================================================================
==2818976==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000f17a90 at pc 0x55eba7fdd69c bp 0x7f03243dbd30 sp 0x7f03243dbd28
READ of size 8 at 0x603000f17a90 thread T928 (brpc_light)
    #0 0x55eba7fdd69b in std::__shared_ptr<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2>::get() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:1291:16
    #1 0x55eba7fdd649 in std::__shared_ptr_access<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2, false, false>::_M_get() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:990:66
    #2 0x55eba7fda316 in std::__shared_ptr_access<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2, false, false>::operator->() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:984:9
    #3 0x55ebcfc8b19e in doris::vectorized::DataTypeStructSerDe::deserialize_one_cell_from_json(doris::vectorized::IColumn&, doris::Slice&, doris::vectorized::DataTypeSerDe::FormatOptions const&) const /mnt/disk1/wangqiannan/amory/doris/be/src/vec/data_types/serde/data_type_struct_serde.cpp:200:25
    #4 0x55ebdac49c8b in doris::vectorized::ConvertImplGenericFromString::execute(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long) /mnt/disk1/wangqiannan/amory/doris/be/src/vec/functions/function_cast.h:618:36
    #5 0x55ebda2234d0 in doris::Status std::__invoke_impl<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(std::__invoke_other, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:61:14
    #6 0x55ebda22323a in std::enable_if<is_invocable_r_v<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>, doris::Status>::type std::__invoke_r<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:114:9
    #7 0x55ebda222e71 in std::_Function_handler<doris::Status (doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long), doris::Status (*)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)>::_M_invoke(std::_Any_data const&, doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:291:9
    #8 0x55ebd9b3f1d2 in std::function<doris::Status (doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long)>::operator()(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long) const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:560:9
    #9 0x55ebda1ad7c7 in doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bool) const::'lambda'(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)::operator()(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long) const /mnt/disk1/wangqiannan/amory/doris/be/src/vec/functions/function_cast.h:2241:17
    #10 0x55ebda1acee2 in doris::Status std::__invoke_impl<doris::Status, doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bool) const::'lambda'(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)&, doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(std::__invoke_other, doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bo@@@
```
dataroaring pushed a commit that referenced this pull request Mar 27, 2025
…ype string literal with one more subfield causing BE coredump #49485 (#49552)

Cherry-picked from #49485

Co-authored-by: amory <wangqiannan@selectdb.com>
yiguolei pushed a commit that referenced this pull request Mar 29, 2025
…iteral with one more subfield causing BE coredump (#49485)

Fixed the issue of inserting into a struct type string literal with one
more subfield causing BE coredump
some situation like this blow will make BE core
```
create table t(a int, b int, s struct<a:int>) PROPERTIES ("replication_allocation" = "tag.location.default: 1");
insert into t values(1,1,'{1,2}');
```
core info:
```
[WARNING!] /sys/kernel/mm/transparent_hugepage/enabled: [always] madvise never, Doris not recommend turning on THP, which may cause the BE process to use more memory and cannot be freed in time. Turn off THP: `echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled`
start BE in local mode
=================================================================
==2818976==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000f17a90 at pc 0x55eba7fdd69c bp 0x7f03243dbd30 sp 0x7f03243dbd28
READ of size 8 at 0x603000f17a90 thread T928 (brpc_light)
    #0 0x55eba7fdd69b in std::__shared_ptr<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2>::get() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:1291:16
    #1 0x55eba7fdd649 in std::__shared_ptr_access<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2, false, false>::_M_get() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:990:66
    #2 0x55eba7fda316 in std::__shared_ptr_access<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2, false, false>::operator->() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:984:9
    #3 0x55ebcfc8b19e in doris::vectorized::DataTypeStructSerDe::deserialize_one_cell_from_json(doris::vectorized::IColumn&, doris::Slice&, doris::vectorized::DataTypeSerDe::FormatOptions const&) const /mnt/disk1/wangqiannan/amory/doris/be/src/vec/data_types/serde/data_type_struct_serde.cpp:200:25
    #4 0x55ebdac49c8b in doris::vectorized::ConvertImplGenericFromString::execute(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long) /mnt/disk1/wangqiannan/amory/doris/be/src/vec/functions/function_cast.h:618:36
    #5 0x55ebda2234d0 in doris::Status std::__invoke_impl<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(std::__invoke_other, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:61:14
    #6 0x55ebda22323a in std::enable_if<is_invocable_r_v<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>, doris::Status>::type std::__invoke_r<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:114:9
    #7 0x55ebda222e71 in std::_Function_handler<doris::Status (doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long), doris::Status (*)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)>::_M_invoke(std::_Any_data const&, doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:291:9
    #8 0x55ebd9b3f1d2 in std::function<doris::Status (doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long)>::operator()(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long) const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:560:9
    #9 0x55ebda1ad7c7 in doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bool) const::'lambda'(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)::operator()(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long) const /mnt/disk1/wangqiannan/amory/doris/be/src/vec/functions/function_cast.h:2241:17
    #10 0x55ebda1acee2 in doris::Status std::__invoke_impl<doris::Status, doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bool) const::'lambda'(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)&, doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(std::__invoke_other, doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bo@@@
```
koarz pushed a commit to koarz/doris that referenced this pull request Jun 4, 2025
…iteral with one more subfield causing BE coredump (apache#49485)

Fixed the issue of inserting into a struct type string literal with one
more subfield causing BE coredump
some situation like this blow will make BE core
```
create table t(a int, b int, s struct<a:int>) PROPERTIES ("replication_allocation" = "tag.location.default: 1");
insert into t values(1,1,'{1,2}');
```
core info:
```
[WARNING!] /sys/kernel/mm/transparent_hugepage/enabled: [always] madvise never, Doris not recommend turning on THP, which may cause the BE process to use more memory and cannot be freed in time. Turn off THP: `echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled`
start BE in local mode
=================================================================
==2818976==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000f17a90 at pc 0x55eba7fdd69c bp 0x7f03243dbd30 sp 0x7f03243dbd28
READ of size 8 at 0x603000f17a90 thread T928 (brpc_light)
    #0 0x55eba7fdd69b in std::__shared_ptr<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2>::get() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:1291:16
    apache#1 0x55eba7fdd649 in std::__shared_ptr_access<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2, false, false>::_M_get() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:990:66
    apache#2 0x55eba7fda316 in std::__shared_ptr_access<doris::vectorized::DataTypeSerDe, (__gnu_cxx::_Lock_policy)2, false, false>::operator->() const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:984:9
    apache#3 0x55ebcfc8b19e in doris::vectorized::DataTypeStructSerDe::deserialize_one_cell_from_json(doris::vectorized::IColumn&, doris::Slice&, doris::vectorized::DataTypeSerDe::FormatOptions const&) const /mnt/disk1/wangqiannan/amory/doris/be/src/vec/data_types/serde/data_type_struct_serde.cpp:200:25
    apache#4 0x55ebdac49c8b in doris::vectorized::ConvertImplGenericFromString::execute(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long) /mnt/disk1/wangqiannan/amory/doris/be/src/vec/functions/function_cast.h:618:36
    apache#5 0x55ebda2234d0 in doris::Status std::__invoke_impl<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(std::__invoke_other, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:61:14
    apache#6 0x55ebda22323a in std::enable_if<is_invocable_r_v<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>, doris::Status>::type std::__invoke_r<doris::Status, doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(doris::Status (*&)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long), doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:114:9
    apache#7 0x55ebda222e71 in std::_Function_handler<doris::Status (doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long), doris::Status (*)(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)>::_M_invoke(std::_Any_data const&, doris::FunctionContext*&&, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long&&, unsigned long&&) /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:291:9
    apache#8 0x55ebd9b3f1d2 in std::function<doris::Status (doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long)>::operator()(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long) const /mnt/disk1/wangqiannan/tool/ldb_toolchain_16/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:560:9
    apache#9 0x55ebda1ad7c7 in doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bool) const::'lambda'(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)::operator()(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long) const /mnt/disk1/wangqiannan/amory/doris/be/src/vec/functions/function_cast.h:2241:17
    apache#10 0x55ebda1acee2 in doris::Status std::__invoke_impl<doris::Status, doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bool) const::'lambda'(doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned int, unsigned long)&, doris::FunctionContext*, doris::vectorized::Block&, std::vector<unsigned int, std::allocator<unsigned int>> const&, unsigned long, unsigned long>(std::__invoke_other, doris::vectorized::FunctionCast::prepare_remove_nullable(doris::FunctionContext*, std::shared_ptr<doris::vectorized::IDataType const> const&, std::shared_ptr<doris::vectorized::IDataType const> const&, bo@@@
```
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

approved Indicates a PR has been approved by one committer. dev/2.1.x dev/3.0.5-merged p0_c reviewed

Projects

None yet

Development

Successfully merging this pull request may close these issues.

6 participants