[
https://issues.apache.org/jira/browse/IMPALA-13040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17841259#comment-17841259
]
Riza Suminto commented on IMPALA-13040:
---------------------------------------
I think it is possible, because there is no readiness coordination in
distributed runtime filter aggregation.
What do you think about adding some boolean flag in QueryState::QueryState
constructor and spin loop waiting it to be set?
> SIGSEGV in QueryState::UpdateFilterFromRemote
> ----------------------------------------------
>
> Key: IMPALA-13040
> URL: https://issues.apache.org/jira/browse/IMPALA-13040
> Project: IMPALA
> Issue Type: Bug
> Components: Backend
> Reporter: Csaba Ringhofer
> Priority: Critical
>
> {code}
> Crash reason: SIGSEGV /SEGV_MAPERR
> Crash address: 0x48
> Process uptime: not available
> Thread 114 (crashed)
> 0 libpthread.so.0 + 0x9d00
> rax = 0x000000019e57ad00 rdx = 0x000000002a656720
> rcx = 0x00000000059a9860 rbx = 0x0000000000000000
> rsi = 0x000000019e57ad00 rdi = 0x0000000000000038
> rbp = 0x00007f6233d544e0 rsp = 0x00007f6233d544a8
> r8 = 0x0000000006a53540 r9 = 0x0000000000000039
> r10 = 0x0000000000000000 r11 = 0x000000000000000a
> r12 = 0x000000019e57ad00 r13 = 0x00007f62a2f997d0
> r14 = 0x00007f6233d544f8 r15 = 0x000000001632c0f0
> rip = 0x00007f62a2f96d00
> Found by: given as instruction pointer in context
> 1
> impalad!impala::QueryState::UpdateFilterFromRemote(impala::UpdateFilterParamsPB
> const&, kudu::rpc::RpcContext*) [query-state.cc : 1033 + 0x5]
> rbp = 0x00007f6233d54520 rsp = 0x00007f6233d544f0
> rip = 0x00000000015c0837
> Found by: previous frame's frame pointer
> 2
> impalad!impala::DataStreamService::UpdateFilterFromRemote(impala::UpdateFilterParamsPB
> const*, impala::UpdateFilterResultPB*, kudu::rpc::RpcContext*)
> [data-stream-service.cc : 134 + 0xb]
> rbp = 0x00007f6233d54640 rsp = 0x00007f6233d54530
> rip = 0x00000000017c05de
> Found by: previous frame's frame pointer
> {code}
> The line that crashes is
> https://github.com/apache/impala/blob/b39cd79ae84c415e0aebec2c2b4d7690d2a0cc7a/be/src/runtime/query-state.cc#L1033
> My guess is that inside the actual segfault is within WaitForPrepare() but it
> was inlined. Not sure if a remote filter can arrive even before
> QueryState::Init is finished - that would explain the issue, as
> instances_prepared_barrier_ is not yet created at that point.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
