We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
CREATE TABLE t_test_vector_table ( id bigint(20) NOT NULL COMMENT "", vector ARRAY<FLOAT> NOT NULL COMMENT "", INDEX index_vector (vector) USING VECTOR ( "index_type" = "hnsw", "dim"="4", "metric_type" = "l2_distance", "is_vector_normed" = "false", "M" = "1", -- If set to 2, then we will not encounter this issue. "efconstruction" = "2" ) ) ENGINE=OLAP DUPLICATE KEY(id) DISTRIBUTED BY HASH(id) BUCKETS 1 PROPERTIES ( "replication_num" = "1" ); insert into t_test_vector_table values (1, [1.0, 2.0, 3.0, 4.0]), (2, [1.1, 2.1, 3.1, 4.1]), (3, [1.2, 2.2, 3.2, 4.2]), (4, [10.0, 10.0, 10.0, 10.0]), (5, [10.1, 10.1, 10.1, 10.1]), (6, [10.2, 10.2, 10.2, 10.2]), (7, [5.0, 5.0, 5.0, 5.0]), (8, [5.1, 5.1, 5.1, 5.1]), (9, [0.5, 0.5, 0.5, 0.5]), (10, [0.6, 0.6, 0.6, 0.6]) ;
The process of BE is killed by the system due to OOM, and tenann allocates large memory lots of times as follows.
W20250114 13:47:51.076904 140145512130304 mem_hook.cpp:103] large memory alloc, query_id:00000000-0000-0000-0000-000000000000 instance: 00000000-0000-0000-0000-000000000000 acquire:68719476736 bytes, stack: @ 0x3dfb311 starrocks::get_stack_trace[abi:cxx11]() @ 0x3d56164 malloc @ 0xea90368 operator new(unsigned long) @ 0xd6c866d faiss::(anonymous namespace)::hnsw_add_vertices(faiss::IndexHNSW&, unsigned long, unsigned long, float const*, bool, bool) @ 0xd5d463d tenann::FaissIndexBuilder::AddImpl(std::vector<tenann::SeqView, std::allocator<tenann::SeqView> > const&, long const*, unsigned char const*) @ 0xd5d3e63 tenann::FaissIndexBuilder::Add(std::vector<tenann::SeqView, std::allocator<tenann::SeqView> > const&, long const*, unsigned char const*, bool) @ 0x793698a starrocks::TenAnnIndexBuilderProxy::add(starrocks::Column const&) @ 0x792f83a starrocks::VectorIndexWriter::_append_data(starrocks::Column const&, unsigned long) @ 0x79309f1 starrocks::VectorIndexWriter::append(starrocks::Column const&) @ 0x78ef2a8 starrocks::ArrayColumnWriter::append(starrocks::Column const&) @ 0x6f2dce9 starrocks::SegmentWriter::append_chunk(starrocks::Chunk const&) @ 0x79590c8 starrocks::HorizontalRowsetWriter::_flush_chunk(starrocks::Chunk const&, starrocks::SegmentPB*) @ 0x79592a8 starrocks::HorizontalRowsetWriter::flush_chunk(starrocks::Chunk const&, starrocks::SegmentPB*) @ 0x6fe9d9a starrocks::MemTableRowsetWriterSink::flush_chunk(starrocks::Chunk const&, starrocks::SegmentPB*, bool) @ 0x70337d8 starrocks::MemTable::flush(starrocks::SegmentPB*, bool) @ 0x6d5d63a starrocks::FlushToken::_flush_memtable(starrocks::MemTable*, starrocks::SegmentPB*, bool) @ 0x6d5ebdf starrocks::MemtableFlushTask::run() @ 0x3e22448 starrocks::ThreadPool::dispatch_thread() @ 0x3e18780 starrocks::Thread::supervise_thread(void*) @ 0x7f7649895ea5 start_thread @ 0x7f76474c6b0d __clone
main e446727
The text was updated successfully, but these errors were encountered:
Successfully merging a pull request may close this issue.
Steps to reproduce the behavior (Required)
Real behavior (Required)
The process of BE is killed by the system due to OOM, and tenann allocates large memory lots of times as follows.
StarRocks version (Required)
main e446727
The text was updated successfully, but these errors were encountered: