[fix](move-memtable) fix move memtable core when use multi table load #35458
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thank you for your contribution to Apache Doris. Since 2024-03-18, the Document has been moved to doris-website. |
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
|
PR approved by at least one committer and no changes requested. |
|
PR approved by anyone and no changes requested. |
TPC-H: Total hot run time: 42153 ms |
TPC-DS: Total hot run time: 168886 ms |
|
TeamCity be ut coverage result: |
ClickBench: Total hot run time: 30.6 s |
liaoxin01
previously approved these changes
May 27, 2024
gavinchou
approved these changes
May 27, 2024
|
clang-tidy review says "All clean, LGTM! 👍" |
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
TPC-H: Total hot run time: 40034 ms |
TPC-DS: Total hot run time: 169100 ms |
ClickBench: Total hot run time: 30.58 s |
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
TPC-H: Total hot run time: 42156 ms |
|
PR approved by at least one committer and no changes requested. |
liaoxin01
reviewed
Jun 3, 2024
|
run buildall |
|
clang-tidy review says "All clean, LGTM! 👍" |
|
TeamCity be ut coverage result: |
TPC-H: Total hot run time: 41673 ms |
TPC-DS: Total hot run time: 173022 ms |
ClickBench: Total hot run time: 30.77 s |
dataroaring
pushed a commit
that referenced
this pull request
Jun 7, 2024
…#35458) ## Proposed changes Move memtable core when use multi table load: ``` 0x51f000c73860 is located 3040 bytes inside of 3456-byte region [0x51f000c72c80,0x51f000c73a00) freed by thread T4867 (FragmentMgrThre) here: #0 0x558f6ad7f43d in operator delete(void*) (/mnt/hdd01/STRESS_ENV/be/lib/doris_be+0x22eec43d) (BuildId: b46f73d1f76dfcd6) #1 0x558f6e6cea2c in std::__new_allocator<doris::PTabletID>::deallocate(doris::PTabletID*, unsigned long) /mnt/disk2/xujianxu/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/13/../../../../include/c++/13/bits/new_allocator.h:168:2 #2 0x558f6e6ce9e7 in std::allocator<doris::PTabletID>::deallocate(doris::PTabletID*, unsigned long) /mnt/disk2/xujianxu/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/13/../../../../include/c++/13/bits/allocator.h:210:25 #3 0x558f6e6ce9e7 in std::allocator_traits<std::allocator<doris::PTabletID>>::deallocate(std::allocator<doris::PTabletID>&, doris::PTabletID*, unsigned long) /mnt/disk2/xujianxu/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/13/../../../../include/c++/13/bits/alloc_traits.h:516:13 #4 0x558f6e6ce9e7 in std::_Vector_base<doris::PTabletID, std::allocator<doris::PTabletID>>::_M_deallocate(doris::PTabletID*, unsigned long) /mnt/disk2/xujianxu/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/13/../../../../include/c++/13/bits/stl_vector.h:387:4 #5 0x558f6e6d0780 in void std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>::_M_range_insert<__gnu_cxx::__normal_iterator<doris::PTabletID const*, std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>>>(__gnu_cxx::__normal_iterator<doris::PTabletID*, std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>>, __gnu_cxx::__normal_iterator<doris::PTabletID const*, std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>>, __gnu_cxx::__normal_iterator<doris::PTabletID const*, std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>>, std::forward_iterator_tag) /mnt/disk2/xujianxu/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/13/../../../../include/c++/13/bits/vector.tcc:832:3 #6 0x558f6e6c54c5 in __gnu_cxx::__normal_iterator<doris::PTabletID*, std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>> std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>::insert<__gnu_cxx::__normal_iterator<doris::PTabletID const*, std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>>, void>(__gnu_cxx::__normal_iterator<doris::PTabletID const*, std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>>, __gnu_cxx::__normal_iterator<doris::PTabletID const*, std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>>, __gnu_cxx::__normal_iterator<doris::PTabletID const*, std::vector<doris::PTabletID, std::allocator<doris::PTabletID>>>) /mnt/disk2/xujianxu/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/13/../../../../include/c++/13/bits/stl_vector.h:1483:4 #7 0x558f9b4b214f in doris::LoadStreamMap::save_tablets_to_commit(long, std::vector<doris::PTabletID, std::allocator<doris::PTabletID>> const&) /mnt/disk2/xujianxu/doris/be/src/vec/sink/load_stream_map_pool.cpp:90:13 #8 0x558f9b7258dd in doris::vectorized::VTabletWriterV2::_calc_tablets_to_commit() /mnt/disk2/xujianxu/doris/be/src/vec/sink/writer/vtablet_writer_v2.cpp:650:27 #9 0x558f9b7229f1 in doris::vectorized::VTabletWriterV2::close(doris::Status) /mnt/disk2/xujianxu/doris/be/src/vec/sink/writer/vtablet_writer_v2.cpp:547:9 ``` Multiple sinks with different table loads use the load id, causing confusion in the use of shared data structures between sinks.
dataroaring
pushed a commit
that referenced
this pull request
Jul 25, 2024
We meet OOM when using single stream multi table  It exist memory leak, and heap profile like:  The stream load context will not release in some exception conditions as plan failed for high concurrency causing timeout when obtaining read lock. It is introduced by #35458 The solution effect is shown in the following figure, which can run stably with a small amount of memory 
dataroaring
pushed a commit
that referenced
this pull request
Jul 30, 2024
We meet OOM when using single stream multi table  It exist memory leak, and heap profile like:  The stream load context will not release in some exception conditions as plan failed for high concurrency causing timeout when obtaining read lock. It is introduced by #35458 The solution effect is shown in the following figure, which can run stably with a small amount of memory 
dataroaring
pushed a commit
that referenced
this pull request
Aug 4, 2024
…#38824) pick (#38255) We meet OOM when using single stream multi table  It exist memory leak, and heap profile like:  The stream load context will not release in some exception conditions as plan failed for high concurrency causing timeout when obtaining read lock. It is introduced by #35458 The solution effect is shown in the following figure, which can run stably with a small amount of memory 
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Proposed changes
Move memtable core when use multi table load:
Multiple sinks with different table loads use the load id, causing confusion in the use of shared data structures between sinks.
Further comments
If this is a relatively large or complex change, kick off the discussion at dev@doris.apache.org by explaining why you chose the solution you did and what alternatives you considered, etc...