This is an automated email from the ASF dual-hosted git repository.

yiguolei pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git


The following commit(s) were added to refs/heads/master by this push:
     new 0d43a1aed18 [fix](brpc) coredump caused by brpc checking (#44047)
0d43a1aed18 is described below

commit 0d43a1aed183da05f5d7dcf66157ca8351fe5b38
Author: Jerry Hu <[email protected]>
AuthorDate: Sun Nov 17 15:57:56 2024 +0800

    [fix](brpc) coredump caused by brpc checking (#44047)
    
    ### What problem does this PR solve?
    
    ```
    /root/doris/be/src/runtime/fragment_mgr.cpp:1064:20: runtime error: member 
call on null pointer of type 'doris::PBackendService_Stub'
    #0 0x55bd899c9aaa in 
doris::FragmentMgr::_check_brpc_available(std::shared_ptr<doris::PBackendService_Stub>
 const&, doris::FragmentMgr::BrpcItem const&) 
/root/doris/be/src/runtime/fragment_mgr.cpp:1064:20
    #1 0x55bd899c521f in doris::FragmentMgr::cancel_worker() 
/root/doris/be/src/runtime/fragment_mgr.cpp:1021:13
    #2 0x55bd8a4c97ae in std::function<void ()>::operator()() const 
/var/local/ldb-toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:560:9
    #3 0x55bd8a4c97ae in doris::Thread::supervise_thread(void*) 
/root/doris/be/src/util/thread.cpp:498:5
    #4 0x7f7601092608 in start_thread 
/build/glibc-SzIz7B/glibc-2.31/nptl/pthread_create.c:477:8
    #5 0x7f760133f132 in __clone 
/build/glibc-SzIz7B/glibc-2.31/misc/../sysdeps/unix/sysv/linux/x86_64/clone.S:95
    
    SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior 
/root/doris/be/src/runtime/fragment_mgr.cpp:1064:20 in
    *** Query id: 0-0 ***
    *** is nereids: 0 ***
    *** tablet id: 0 ***
    *** Aborted at 1731663847 (unix time) try "date -d @1731663847" if you are 
using GNU date ***
    *** Current BE git commitID: b663df0e50 ***
    *** SIGSEGV address not mapped to object (@0x0) received by PID 17169 (TID 
17463 OR 0x7f746d21a700) from PID 0; stack trace: ***
    0# doris::signal::(anonymous namespace)::FailureSignalHandler(int, 
siginfo_t*, void*) at /root/doris/be/src/common/signal_handler.h:421
    1# PosixSignals::chained_handler(int, siginfo_t*, void*) [clone .part.0] in 
/usr/lib/jvm/java-17-openjdk-amd64/lib/server/libjvm.so
    2# JVM_handle_linux_signal in 
/usr/lib/jvm/java-17-openjdk-amd64/lib/server/libjvm.so
    3# 0x00007F7601263090 in /lib/x86_64-linux-gnu/libc.so.6
    4# 
doris::FragmentMgr::_check_brpc_available(std::shared_ptr<doris::PBackendService_Stub>
 const&, doris::FragmentMgr::BrpcItem const&) in 
/mnt/ssd01/pipline/OpenSourceDoris/clusterEnv/P0/Cluster0/be/lib/doris_be
    5# doris::FragmentMgr::cancel_worker() at 
/root/doris/be/src/runtime/fragment_mgr.cpp:1022
    6# doris::Thread::supervise_thread(void*) at 
/root/doris/be/src/util/thread.cpp:499
    7# start_thread at /build/glibc-SzIz7B/glibc-2.31/nptl/pthread_create.c:478
    8# __clone at ../sysdeps/unix/sysv/linux/x86_64/clone.S:97
    ```
---
 be/src/runtime/fragment_mgr.cpp         | 10 ++++++++--
 be/src/vec/sink/vdata_stream_sender.cpp | 12 +++++-------
 2 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/be/src/runtime/fragment_mgr.cpp b/be/src/runtime/fragment_mgr.cpp
index 95e5f8e2ce1..2896190f606 100644
--- a/be/src/runtime/fragment_mgr.cpp
+++ b/be/src/runtime/fragment_mgr.cpp
@@ -1017,8 +1017,14 @@ void FragmentMgr::cancel_worker() {
             }
         }
 
-        for (auto it : brpc_stub_with_queries) {
-            _check_brpc_available(it.first, it.second);
+        if (config::enable_brpc_connection_check) {
+            for (auto it : brpc_stub_with_queries) {
+                if (!it.first) {
+                    LOG(WARNING) << "brpc stub is nullptr, skip it.";
+                    continue;
+                }
+                _check_brpc_available(it.first, it.second);
+            }
         }
 
         if (!queries_lost_coordinator.empty()) {
diff --git a/be/src/vec/sink/vdata_stream_sender.cpp 
b/be/src/vec/sink/vdata_stream_sender.cpp
index 5fb1bd327ae..66aacc59f6c 100644
--- a/be/src/vec/sink/vdata_stream_sender.cpp
+++ b/be/src/vec/sink/vdata_stream_sender.cpp
@@ -70,19 +70,13 @@ Status Channel::init(RuntimeState* state) {
         return Status::OK();
     }
 
+    auto network_address = _brpc_dest_addr;
     if (_brpc_dest_addr.hostname == BackendOptions::get_localhost()) {
         _brpc_stub = 
state->exec_env()->brpc_internal_client_cache()->get_client(
                 "127.0.0.1", _brpc_dest_addr.port);
-        auto network_address = _brpc_dest_addr;
         network_address.hostname = "127.0.0.1";
-        if (config::enable_brpc_connection_check) {
-            state->get_query_ctx()->add_using_brpc_stub(network_address, 
_brpc_stub);
-        }
     } else {
         _brpc_stub = 
state->exec_env()->brpc_internal_client_cache()->get_client(_brpc_dest_addr);
-        if (config::enable_brpc_connection_check) {
-            state->get_query_ctx()->add_using_brpc_stub(_brpc_dest_addr, 
_brpc_stub);
-        }
     }
 
     if (!_brpc_stub) {
@@ -91,6 +85,10 @@ Status Channel::init(RuntimeState* state) {
         LOG(WARNING) << msg;
         return Status::InternalError(msg);
     }
+
+    if (config::enable_brpc_connection_check) {
+        state->get_query_ctx()->add_using_brpc_stub(_brpc_dest_addr, 
_brpc_stub);
+    }
     return Status::OK();
 }
 


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to