[Crash] 升级2.5.16之后集群be节点频繁crash

2.5.16版本

2.5.16 RELEASE (build 8ddf3c7)
query_id:00000000-0000-0000-0000-000000000000, fragment_instance:59c63633-90d5-11ee-a84e-00163e045696
tracker:process consumption: 44496321944
tracker:query_pool consumption: 4587183946
tracker:load consumption: 377900656
tracker:metadata consumption: 626396590
tracker:tablet_metadata consumption: 100627452
tracker:rowset_metadata consumption: 65630003
tracker:segment_metadata consumption: 42298028
tracker:column_metadata consumption: 417841107
tracker:tablet_schema consumption: 20088252
tracker:segment_zonemap consumption: 26040375
tracker:short_key_index consumption: 11664517
tracker:column_zonemap_index consumption: 72883243
tracker:ordinal_index consumption: 176219216
tracker:bitmap_index consumption: 540000
tracker:bloom_filter_index consumption: 1496472
tracker:compaction consumption: 44178016
tracker:schema_change consumption: 0
tracker:column_pool consumption: 2602223738
tracker:page_cache consumption: 26617164144
tracker:update consumption: 5914720013
tracker:chunk_allocator consumption: 1833230464
tracker:clone consumption: 0
tracker:consistency consumption: 0
*** Aborted at 1701495650 (unix time) try “date -d @1701495650” if you are using GNU date ***
PC: @ 0x4ac14d6 starrocks::DataStreamRecvr::PipelineSenderQueue::add_chunks<>()
*** SIGSEGV (@0x2fe5a9) received by PID 2225 (TID 0x7efc0e7f7700) from PID 3138985; stack trace: ***
@ 0x5bfc982 google::(anonymous namespace)::FailureSignalHandler()
@ 0x7efe7eb93630 (unknown)
@ 0x4ac14d6 starrocks::DataStreamRecvr::PipelineSenderQueue::add_chunks<>()
@ 0x4ab95a2 starrocks::DataStreamRecvr::PipelineSenderQueue::add_chunks()
@ 0x4a2f6db starrocks::DataStreamRecvr::add_chunks()
@ 0x49cf026 starrocks::DataStreamMgr::transmit_chunk()
@ 0x54639f8 starrocks::PInternalServiceImplBase<>::transmit_chunk()
@ 0x5e33d4d brpc::policy::ProcessRpcRequest()
@ 0x5f144f7 brpc::ProcessInputMessage()
@ 0x5f153cb brpc::InputMessenger::OnNewMessages()
@ 0x5dba68e brpc::Socket::ProcessEvent()
@ 0x5d5e68f bthread::TaskGroup::task_runner()
@ 0x5ea2bf1 bthread_make_fcontext
start time: Sat Dec 2 13:40:58 CST 2023

降级到2.5.14版本还是crash
2.5.14 RELEASE (build e4ca4dd)
query_id:00000000-0000-0000-0000-000000000000, fragment_instance:a5be0512-90dd-11ee-a0ce-00163e046b57
tracker:process consumption: 41955760886
tracker:query_pool consumption: 215903703
tracker:load consumption: 22794464
tracker:metadata consumption: 397795708
tracker:tablet_metadata consumption: 134245983
tracker:rowset_metadata consumption: 82532715
tracker:segment_metadata consumption: 18357255
tracker:column_metadata consumption: 162659755
tracker:tablet_schema consumption: 23843103
tracker:segment_zonemap consumption: 10458927
tracker:short_key_index consumption: 6382460
tracker:column_zonemap_index consumption: 35210915
tracker:ordinal_index consumption: 70482728
tracker:bitmap_index consumption: 374400
tracker:bloom_filter_index consumption: 621648
tracker:compaction consumption: 31704088
tracker:schema_change consumption: 0
tracker:column_pool consumption: 2482945061
tracker:page_cache consumption: 26408126672
tracker:update consumption: 7998604399
tracker:chunk_allocator consumption: 1549271120
tracker:clone consumption: 0
tracker:consistency consumption: 0
*** Aborted at 1701499215 (unix time) try “date -d @1701499215” if you are using GNU date ***
PC: @ 0x4a32ecc starrocks::DataStreamRecvr::add_chunks()
*** SIGSEGV (@0x0) received by PID 20303 (TID 0x7fb407665700) from PID 0; stack trace: ***
@ 0x5c034e2 google::(anonymous namespace)::FailureSignalHandler()
@ 0x7fb666324630 (unknown)
@ 0x4a32ecc starrocks::DataStreamRecvr::add_chunks()
@ 0x49d2726 starrocks::DataStreamMgr::transmit_chunk()
@ 0x546a4e8 starrocks::PInternalServiceImplBase<>::transmit_chunk()
@ 0x5e3a8ad brpc::policy::ProcessRpcRequest()
@ 0x5f1b057 brpc::ProcessInputMessage()
@ 0x5f1bf2b brpc::InputMessenger::OnNewMessages()
@ 0x5dc11ee brpc::Socket::ProcessEvent()
@ 0x5d651ef bthread::TaskGroup::task_runner()
@ 0x5ea9751 bthread_make_fcontext
start time: Sat Dec 2 14:40:20 CST 2023

date -d @1701499215
输入这个命令, 看看呢

加个微信具体定位下问题?

@U_1664268205912_3017
用微信沟通吧,请您提供一下be.out中的错误栈.

您好,有同事在帮忙看了