Open yibin87 opened 2 years ago
2023-06-06 10:44:23
{"log":"[BaseDaemon.cpp:569] [\"\
0xacf0e5d\\tfaultSignalHandler(int, siginfo_t*, void*) [tiflash+181341789]\
\\tlibs/libdaemon/src/BaseDaemon.cpp:220\
0x7f592cca8d90\\t<unknown symbol> [libc.so.6+347536]\
0xc9e85af\\texec_ctx_run(grpc_closure*) [tiflash+211715503]\
\\tcontrib/grpc/src/core/lib/iomgr/exec_ctx.cc:49\
0xc9e8461\\tgrpc_core::ExecCtx::Flush() [tiflash+211715169]\
\\tcontrib/grpc/src/core/lib/iomgr/exec_ctx.cc:164\
0xca1a0e2\\trun_some_timers() [tiflash+211919074]\
\\tcontrib/grpc/src/core/lib/iomgr/timer_manager.cc:134\
0xca19ea7\\ttimer_main_loop() [tiflash+211918503]\
\\tcontrib/grpc/src/core/lib/iomgr/timer_manager.cc:237\
0xca19e1f\\ttimer_thread(void*) [tiflash+211918367]\
\\tcontrib/grpc/src/core/lib/iomgr/timer_manager.cc:284\
0xcdf2106\\tgrpc_core::(anonymous namespace)::ThreadInternalsPosix::ThreadInternalsPosix(char const*, void (*)(void*), void*, bool*, grpc_core::Thread::Options const&)::'lambda'(void*)::operator()(void*) const [tiflash+215949574]\
\\tcontrib/grpc/src/core/lib/gprpp/thd_posix.cc:140\
0xcdf2015\\tgrpc_core::(anonymous namespace)::ThreadInternalsPosix::ThreadInternalsPosix(char const*, void (*)(void*), void*, bool*, grpc_core::Thread::Options const&)::'lambda'(void*)::__invoke(void*) [tiflash+215949333]\
\\tcontrib/grpc/src/core/lib/gprpp/thd_posix.cc:110\
0x7f592ccf3802\\tstart_thread [libc.so.6+653314]\"] [source=BaseDaemon] [thread_id=1039]","level":"ERROR","container":"data0","pod":"tc-tiflash-2","namespace":"endless-htap-pipeline-random-failpoint-tps-1804838-1-6"}
2023-06-06 10:44:23
{"level":"ERROR","container":"data0","pod":"tc-tiflash-2","log":"[BaseDaemon.cpp:569] [\"\
0xacf0e5d\\tfaultSignalHandler(int, siginfo_t*, void*) [tiflash+181341789]\
\\tlibs/libdaemon/src/BaseDaemon.cpp:220\
0x7f592cca8d90\\t<unknown symbol> [libc.so.6+347536]\
0xc9e85af\\texec_ctx_run(grpc_closure*) [tiflash+211715503]\
\\tcontrib/grpc/src/core/lib/iomgr/exec_ctx.cc:49\
0xc9e8461\\tgrpc_core::ExecCtx::Flush() [tiflash+211715169]\
\\tcontrib/grpc/src/core/lib/iomgr/exec_ctx.cc:164\
0xca1a0e2\\trun_some_timers() [tiflash+211919074]\
\\tcontrib/grpc/src/core/lib/iomgr/timer_manager.cc:134\
0xca19ea7\\ttimer_main_loop() [tiflash+211918503]\
\\tcontrib/grpc/src/core/lib/iomgr/timer_manager.cc:237\
0xca19e1f\\ttimer_thread(void*) [tiflash+211918367]\
\\tcontrib/grpc/src/core/lib/iomgr/timer_manager.cc:284\
0xcdf2106\\tgrpc_core::(anonymous namespace)::ThreadInternalsPosix::ThreadInternalsPosix(char const*, void (*)(void*), void*, bool*, grpc_core::Thread::Options const&)::'lambda'(void*)::operator()(void*) const [tiflash+215949574]\
\\tcontrib/grpc/src/core/lib/gprpp/thd_posix.cc:140\
0xcdf2015\\tgrpc_core::(anonymous namespace)::ThreadInternalsPosix::ThreadInternalsPosix(char const*, void (*)(void*), void*, bool*, grpc_core::Thread::Options const&)::'lambda'(void*)::__invoke(void*) [tiflash+215949333]\
\\tcontrib/grpc/src/core/lib/gprpp/thd_posix.cc:110\
0x7f592ccf3802\\tstart_thread [libc.so.6+653314]\"] [source=BaseDaemon] [thread_id=1039]","namespace":"endless-htap-pipeline-random-failpoint-tps-1804838-1-6"}
Also found in pipeline random failpoint, but with different logs.
New grpc core stack:
[ERROR] [BaseDaemon.cpp:570] [\"\
0x61b6fe1\faultSignalHandler(int, siginfo_t*, void*) [tiflash+102461409]\
\libs/libdaemon/src/BaseDaemon.cpp:221\
0x7f16eee37630\<unknown symbol> [libpthread.so.0+63024]\
0x7f16ee16c387\gsignal [libc.so.6+222087]\
0x7f16ee16da78\__GI_abort [libc.so.6+227960]\
0x76cfbcf\call_start_batch(grpc_call*, grpc_op const*, unsigned long, void*, int) [tiflash+124582863]\
\contrib/grpc/src/core/lib/surface/call.cc:0\
0x76ce7ef\grpc_call_start_batch [tiflash+124577775]\
\contrib/grpc/src/core/lib/surface/call.cc:1761\
0x6d74dff\grpc::internal::CallOpSet<grpc::internal::CallOpSendInitialMetadata, grpc::internal::CallOpSendMessage, grpc::internal::CallOpServerSendStatus, grpc::internal::CallNoOp<4>, grpc::internal::CallNoOp<5>, grpc::internal::CallNoOp<6> >::ContinueFillOpsAfterInterception() [tiflash+114773503]\
\contrib/grpc/include/grpcpp/impl/codegen/call_op_set.h:971\
0x6d724b6\grpc::ServerAsyncWriter<mpp::MPPDataPacket>::Write(mpp::MPPDataPacket const&, void*) [tiflash+114762934]\
\contrib/grpc/include/grpcpp/impl/codegen/async_stream.h:876\
0x6d70ae4\DB::EstablishCallData::tryConnectTunnel() [tiflash+114756324]\
\dbms/src/Flash/EstablishCall.cpp:163\
0x17fef95\DB::(anonymous namespace)::handleRpcs(grpc::ServerCompletionQueue*, std::__1::shared_ptr<DB::Logger> const&) [tiflash+25161621]\
\dbms/src/Server/FlashGrpcServerHolder.cpp:55\
0x17feaed\void* std::__1::__thread_proxy<std::__1::tuple<std::__1::unique_ptr<std::__1::__thread_struct, std::__1::default_delete<std::__1::__thread_struct> >, std::__1::thread DB::ThreadFactory::newThread<DB::FlashGrpcServerHolder::FlashGrpcServerHolder(DB::Context&, Poco::Util::LayeredConfiguration&, DB::TiFlashSecurityConfig&, DB::TiFlashRaftConfig const&, std::__1::shared_ptr<DB::Logger> const&)::$_5>(bool, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> >, DB::FlashGrpcServerHolder::FlashGrpcServerHolder(DB::Context&, Poco::Util::LayeredConfiguration&, DB::TiFlashSecurityConfig&, DB::TiFlashRaftConfig const&, std::__1::shared_ptr<DB::Logger> const&)::$_5&&)::'lambda'(auto&&...)> >(void*) [tiflash+25160429]\
\/usr/local/bin/../include/c++/v1/thread:291\
New met grpc core crash:
[ERROR] [BaseDaemon.cpp:569] [\"
0x756bfb1\\tfaultSignalHandler(int, siginfo_t*, void*) [tiflash+123125681]
\\tlibs/libdaemon/src/BaseDaemon.cpp:220
0x7fa5e1522db0\\t<unknown symbol> [libc.so.6+347568]
0x7fa5e156f54c\\t__pthread_kill_implementation [libc.so.6+660812]
0x7fa5e1522d06\\t__GI_raise [libc.so.6+347398]
0x7fa5e14f67f3\\tabort [libc.so.6+165875]
0x8b37b6f\\tcall_start_batch(grpc_call*, grpc_op const*, unsigned long, void*, int) [tiflash+145980271]
\\tcontrib/grpc/src/core/lib/surface/call.cc:0
0x8b3678f\\tgrpc_call_start_batch [tiflash+145975183]
\\tcontrib/grpc/src/core/lib/surface/call.cc:1761
0x8124f0f\\tgrpc::internal::CallOpSet<grpc::internal::CallOpSendInitialMetadata, grpc::internal::CallOpSendMessage, grpc::internal::CallOpServerSendStatus, grpc::internal::CallNoOp<4>, grpc::internal::CallNoOp<5>, grpc::internal::CallNoOp<6> >::ContinueFillOpsAfterInterception() [tiflash+135417615]
\\tcontrib/grpc/include/grpcpp/impl/codegen/call_op_set.h:971
0x8123656\\tgrpc::ServerAsyncWriter<mpp::MPPDataPacket>::Write(mpp::MPPDataPacket const&, void*) [tiflash+135411286]
\\tcontrib/grpc/include/grpcpp/impl/codegen/async_stream.h:876
0x81211ae\\tDB::EstablishCallData::tryConnectTunnel() [tiflash+135401902]
\\tdbms/src/Flash/EstablishCall.cpp:166
0x1e91395\\tDB::(anonymous namespace)::handleRpcs(grpc::ServerCompletionQueue*, std::__1::shared_ptr<DB::Logger> const&) [tiflash+32052117]
\\tdbms/src/Server/FlashGrpcServerHolder.cpp:63
0x1e90eed\\tvoid* std::__1::__thread_proxy<std::__1::tuple<std::__1::unique_ptr<std::__1::__thread_struct, std::__1::default_delete<std::__1::__thread_struct> >, std::__1::thread DB::ThreadFactory::newThread<DB::FlashGrpcServerHolder::FlashGrpcServerHolder(DB::Context&, Poco::Util::LayeredConfiguration&, DB::TiFlashRaftConfig const&, std::__1::shared_ptr<DB::Logger> const&)::$_5>(bool, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> >, DB::FlashGrpcServerHolder::FlashGrpcServerHolder(DB::Context&, Poco::Util::LayeredConfiguration&, DB::TiFlashRaftConfig const&, std::__1::shared_ptr<DB::Logger> const&)::$_5&&)::'lambda'(auto&&...)> >(void*) [tiflash+32050925]
\\t/usr/local/bin/../include/c++/v1/thread:291
0x7fa5e156d802\\tstart_thread [libc.so.6+653314]\"] [source=BaseDaemon] [thread_id=896]
[ERROR] [BaseDaemon.cpp:569] [\"
0x756bfb1\\tfaultSignalHandler(int, siginfo_t*, void*) [tiflash+123125681]
\\tlibs/libdaemon/src/BaseDaemon.cpp:220
0x7fa5e1522db0\\t<unknown symbol> [libc.so.6+347568]
0x7fa5e156f54c\\t__pthread_kill_implementation [libc.so.6+660812]
0x7fa5e1522d06\\t__GI_raise [libc.so.6+347398]
0x7fa5e14f67f3\\tabort [libc.so.6+165875]
0x8b37b6f\\tcall_start_batch(grpc_call*, grpc_op const*, unsigned long, void*, int) [tiflash+145980271]
\\tcontrib/grpc/src/core/lib/surface/call.cc:0
0x8b3678f\\tgrpc_call_start_batch [tiflash+145975183]
\\tcontrib/grpc/src/core/lib/surface/call.cc:1761
0x8124f0f\\tgrpc::internal::CallOpSet<grpc::internal::CallOpSendInitialMetadata, grpc::internal::CallOpSendMessage, grpc::internal::CallOpServerSendStatus, grpc::internal::CallNoOp<4>, grpc::internal::CallNoOp<5>, grpc::internal::CallNoOp<6> >::ContinueFillOpsAfterInterception() [tiflash+135417615]
\\tcontrib/grpc/include/grpcpp/impl/codegen/call_op_set.h:971
0x8123656\\tgrpc::ServerAsyncWriter<mpp::MPPDataPacket>::Write(mpp::MPPDataPacket const&, void*) [tiflash+135411286]
\\tcontrib/grpc/include/grpcpp/impl/codegen/async_stream.h:876
0x81211ae\\tDB::EstablishCallData::tryConnectTunnel() [tiflash+135401902]
\\tdbms/src/Flash/EstablishCall.cpp:166
0x1e91395\\tDB::(anonymous namespace)::handleRpcs(grpc::ServerCompletionQueue*, std::__1::shared_ptr<DB::Logger> const&) [tiflash+32052117]
\\tdbms/src/Server/FlashGrpcServerHolder.cpp:63
0x1e90eed\\tvoid* std::__1::__thread_proxy<std::__1::tuple<std::__1::unique_ptr<std::__1::__thread_struct, std::__1::default_delete<std::__1::__thread_struct> >, std::__1::thread DB::ThreadFactory::newThread<DB::FlashGrpcServerHolder::FlashGrpcServerHolder(DB::Context&, Poco::Util::LayeredConfiguration&, DB::TiFlashRaftConfig const&, std::__1::shared_ptr<DB::Logger> const&)::$_5>(bool, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> >, DB::FlashGrpcServerHolder::FlashGrpcServerHolder(DB::Context&, Poco::Util::LayeredConfiguration&, DB::TiFlashRaftConfig const&, std::__1::shared_ptr<DB::Logger> const&)::$_5&&)::'lambda'(auto&&...)> >(void*) [tiflash+32050925]
\\t/usr/local/bin/../include/c++/v1/thread:291
0x7fa5e156d802\\tstart_thread [libc.so.6+653314]\"] [source=BaseDaemon] [thread_id=896]
another
[2024/09/02 02:52:56.091 +00:00] [ERROR] [BaseDaemon.cpp:376] [########################################] [source=BaseDaemon] [thread_id=917]
[2024/09/02 02:52:56.092 +00:00] [ERROR] [BaseDaemon.cpp:377] ["(from thread 829) Received signal Aborted(6)."] [source=BaseDaemon] [thread_id=917]
[2024/09/02 02:52:56.112 +00:00] [ERROR] [BaseDaemon.cpp:569] ["\n 0x756bfb1\tfaultSignalHandler(int, siginfo_t*, void*) [tiflash+123125681]\n \tlibs/libdaemon/src/BaseDaemon.cpp:220\n 0x7f7952618db0\t<unknown symbol> [libc.so.6+347568]\n 0x7f795266554c\t__pthread_kill_implementation [libc.so.6+660812]\n 0x7f7952618d06\t__GI_raise [libc.so.6+347398]\n 0x7f79525ec7f3\tabort [libc.so.6+165875]\n 0x8b37b6f\tcall_start_batch(grpc_call*, grpc_op const*, unsigned long, void*, int) [tiflash+145980271]\n \tcontrib/grpc/src/core/lib/surface/[call.cc:0](http://call.cc:0/)\n 0x8b3678f\tgrpc_call_start_batch [tiflash+145975183]\n \tcontrib/grpc/src/core/lib/surface/[call.cc:1761](http://call.cc:1761/)\n 0x8124f0f\tgrpc::internal::CallOpSet<grpc::internal::CallOpSendInitialMetadata, grpc::internal::CallOpSendMessage, grpc::internal::CallOpServerSendStatus, grpc::internal::CallNoOp<4>, grpc::internal::CallNoOp<5>, grpc::internal::CallNoOp<6> >::ContinueFillOpsAfterInterception() [tiflash+135417615]\n \tcontrib/grpc/include/grpcpp/impl/codegen/call_op_set.h:971\n 0x8123656\tgrpc::ServerAsyncWriter<mpp::MPPDataPacket>::Write(mpp::MPPDataPacket const&, void*) [tiflash+135411286]\n \tcontrib/grpc/include/grpcpp/impl/codegen/async_stream.h:876\n 0x81211ae\tDB::EstablishCallData::tryConnectTunnel() [tiflash+135401902]\n \tdbms/src/Flash/EstablishCall.cpp:166\n 0x1e91395\tDB::(anonymous namespace)::handleRpcs(grpc::ServerCompletionQueue*, std::__1::shared_ptr<DB::Logger> const&) [tiflash+32052117]\n \tdbms/src/Server/FlashGrpcServerHolder.cpp:63\n 0x1e90eed\tvoid* std::__1::__thread_proxy<std::__1::tuple<std::__1::unique_ptr<std::__1::__thread_struct, std::__1::default_delete<std::__1::__thread_struct> >, std::__1::thread DB::ThreadFactory::newThread<DB::FlashGrpcServerHolder::FlashGrpcServerHolder(DB::Context&, Poco::Util::LayeredConfiguration&, DB::TiFlashRaftConfig const&, std::__1::shared_ptr<DB::Logger> const&)::$_5>(bool, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> >, DB::FlashGrpcServerHolder::FlashGrpcServerHolder(DB::Context&, Poco::Util::LayeredConfiguration&, DB::TiFlashRaftConfig const&, std::__1::shared_ptr<DB::Logger> const&)::$_5&&)::'lambda'(auto&&...)> >(void*) [tiflash+32050925]\n \t/usr/local/bin/../include/c++/v1/thread:291\n 0x7f7952663802\tstart_thread [libc.so.6+653314]"] [source=BaseDaemon] [thread_id=917]
Run tiflash random failpoints test, enable "random_join_build_failpoint", tifalsh crashed with little possiblity: