You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues-all@impala.apache.org by "sundyxiong (Jira)" <ji...@apache.org> on 2022/03/10 09:16:00 UTC
[jira] [Updated] (IMPALA-11174) Crash during PartitionedHashJoin
[ https://issues.apache.org/jira/browse/IMPALA-11174?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
sundyxiong updated IMPALA-11174:
--------------------------------
Description:
Impalad crashed while running PartitionedHashJoin. it cannot be reproduced stably.
We found that although each crash is in a fixed place, it is no problem to repeatedly execute sql each time.
We guess it is related to IMPALA-10342 and IMPALA-9993, but the problem is not solved after the merger
gdb stack:
{code:java}
#0 0x00007fa8643451d7 in raise () from /lib64/libc.so.6
#1 0x00007fa8643468c8 in abort () from /lib64/libc.so.6
#2 0x00007fa866ed9aa9 in os::abort(bool) () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
#3 0x00007fa86709d703 in VMError::report_and_die() () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
#4 0x00007fa866ee3a05 in JVM_handle_linux_signal () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
#5 0x00007fa866ed6cd8 in signalHandler(int, siginfo*, void*) () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
#6 <signal handler called>
#7 0x00007f9ff679a7a0 in ?? ()
#8 0x0000000001483aef in impala::PartitionedHashJoinNode::ProcessProbeBatch (this=this@entry=0x263340480,
out_batch=out_batch@entry=0x7f9f1cf33c60) at /data/impala-hn-gaotu/impala/be/src/exec/partitioned-hash-join-node.cc:495
#9 0x0000000001489c85 in impala::PartitionedHashJoinNode::GetNext (this=<optimized out>, state=0x269e8d400,
out_batch=<optimized out>, eos=0x7f9f1cf33c1f) at /data/impala-hn-gaotu/impala/be/src/exec/partitioned-hash-join-node.cc:574
#10 0x00000000014a7dfc in impala::SortNode::SortInput (this=this@entry=0x2c3fa380, state=state@entry=0x269e8d400)
at /data/impala-hn-gaotu/impala/be/src/exec/sort-node.cc:196
#11 0x00000000014a9d81 in impala::SortNode::Open (this=0x2c3fa380, state=0x269e8d400)
at /data/impala-hn-gaotu/impala/be/src/exec/sort-node.cc:111
#12 0x00000000014cdc20 in impala::AnalyticEvalNode::Open (this=0xa326400, state=0x269e8d400)
at /data/impala-hn-gaotu/impala/be/src/exec/analytic-eval-node.cc:205
#13 0x00000000014a6c3c in impala::SelectNode::Open (this=0x2c3fa1c0, state=0x269e8d400)
at /data/impala-hn-gaotu/impala/be/src/exec/select-node.cc:93 {code}
was:
Impalad crashed while running PartitionedHashJoin. it cannot be reproduced stably.
We found that although each crash is in a fixed place, it is no problem to repeatedly execute sql each time.
We guess it is related to IMPALA-10342 and IMPALA-9993, but the problem is not solved after the merger
gdb stack:
{code:java}
#0 0x00007fa8643451d7 in raise () from /lib64/libc.so.6
#1 0x00007fa8643468c8 in abort () from /lib64/libc.so.6
#2 0x00007fa866ed9aa9 in os::abort(bool) () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
#3 0x00007fa86709d703 in VMError::report_and_die() () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
#4 0x00007fa866ee3a05 in JVM_handle_linux_signal () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
#5 0x00007fa866ed6cd8 in signalHandler(int, siginfo*, void*) () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
#6 <signal handler called>
#7 0x00007f9ff679a7a0 in ?? ()
#8 0x0000000001483aef in impala::PartitionedHashJoinNode::ProcessProbeBatch (this=this@entry=0x263340480,
out_batch=out_batch@entry=0x7f9f1cf33c60) at /data/impala-hn-gaotu/impala/be/src/exec/partitioned-hash-join-node.cc:495
#9 0x0000000001489c85 in impala::PartitionedHashJoinNode::GetNext (this=<optimized out>, state=0x269e8d400,
out_batch=<optimized out>, eos=0x7f9f1cf33c1f) at /data/impala-hn-gaotu/impala/be/src/exec/partitioned-hash-join-node.cc:574
#10 0x00000000014a7dfc in impala::SortNode::SortInput (this=this@entry=0x2c3fa380, state=state@entry=0x269e8d400)
at /data/impala-hn-gaotu/impala/be/src/exec/sort-node.cc:196
#11 0x00000000014a9d81 in impala::SortNode::Open (this=0x2c3fa380, state=0x269e8d400)
at /data/impala-hn-gaotu/impala/be/src/exec/sort-node.cc:111
#12 0x00000000014cdc20 in impala::AnalyticEvalNode::Open (this=0xa326400, state=0x269e8d400)
at /data/impala-hn-gaotu/impala/be/src/exec/analytic-eval-node.cc:205
#13 0x00000000014a6c3c in impala::SelectNode::Open (this=0x2c3fa1c0, state=0x269e8d400)
at /data/impala-hn-gaotu/impala/be/src/exec/select-node.cc:93 {code}
> Crash during PartitionedHashJoin
> --------------------------------
>
> Key: IMPALA-11174
> URL: https://issues.apache.org/jira/browse/IMPALA-11174
> Project: IMPALA
> Issue Type: Bug
> Components: Backend
> Affects Versions: Impala 3.4.0
> Reporter: sundyxiong
> Priority: Blocker
>
> Impalad crashed while running PartitionedHashJoin. it cannot be reproduced stably.
> We found that although each crash is in a fixed place, it is no problem to repeatedly execute sql each time.
> We guess it is related to IMPALA-10342 and IMPALA-9993, but the problem is not solved after the merger
> gdb stack:
> {code:java}
> #0 0x00007fa8643451d7 in raise () from /lib64/libc.so.6
> #1 0x00007fa8643468c8 in abort () from /lib64/libc.so.6
> #2 0x00007fa866ed9aa9 in os::abort(bool) () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
> #3 0x00007fa86709d703 in VMError::report_and_die() () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
> #4 0x00007fa866ee3a05 in JVM_handle_linux_signal () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
> #5 0x00007fa866ed6cd8 in signalHandler(int, siginfo*, void*) () from /usr/local/jdk/jre/lib/amd64/server/libjvm.so
> #6 <signal handler called>
> #7 0x00007f9ff679a7a0 in ?? ()
> #8 0x0000000001483aef in impala::PartitionedHashJoinNode::ProcessProbeBatch (this=this@entry=0x263340480,
> out_batch=out_batch@entry=0x7f9f1cf33c60) at /data/impala-hn-gaotu/impala/be/src/exec/partitioned-hash-join-node.cc:495
> #9 0x0000000001489c85 in impala::PartitionedHashJoinNode::GetNext (this=<optimized out>, state=0x269e8d400,
> out_batch=<optimized out>, eos=0x7f9f1cf33c1f) at /data/impala-hn-gaotu/impala/be/src/exec/partitioned-hash-join-node.cc:574
> #10 0x00000000014a7dfc in impala::SortNode::SortInput (this=this@entry=0x2c3fa380, state=state@entry=0x269e8d400)
> at /data/impala-hn-gaotu/impala/be/src/exec/sort-node.cc:196
> #11 0x00000000014a9d81 in impala::SortNode::Open (this=0x2c3fa380, state=0x269e8d400)
> at /data/impala-hn-gaotu/impala/be/src/exec/sort-node.cc:111
> #12 0x00000000014cdc20 in impala::AnalyticEvalNode::Open (this=0xa326400, state=0x269e8d400)
> at /data/impala-hn-gaotu/impala/be/src/exec/analytic-eval-node.cc:205
> #13 0x00000000014a6c3c in impala::SelectNode::Open (this=0x2c3fa1c0, state=0x269e8d400)
> at /data/impala-hn-gaotu/impala/be/src/exec/select-node.cc:93 {code}
>
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-all-unsubscribe@impala.apache.org
For additional commands, e-mail: issues-all-help@impala.apache.org