impala-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Alex Behm <alex.b...@cloudera.com>
Subject Re: crash in PHJ on master
Date Mon, 24 Oct 2016 15:48:06 GMT
Maybe you are using an "unusual" log level?

On Mon, Oct 24, 2016 at 8:35 AM, Marcel Kornacker <marcel@cloudera.com>
wrote:

> I'm seeing a crash in PartitionedHashJoinNode, is anyone experiencing the
> same or know what's going on?
>
> Here is the stack:
> C  [libExec.so+0x53706c]  std::unique_ptr<impala::BufferedTupleStream,
> std::default_delete<impala::BufferedTupleStream> >::get() const+0x18
> C  [libExec.so+0x54d6bc]
>  impala::PartitionedHashJoinNode::NodeDebugString() const+0x296
> C  [libExec.so+0x54d0bd]
>  impala::PartitionedHashJoinNode::UpdateState(impala::
> PartitionedHashJoinNode::HashJoinState)+0x37f
> C  [libExec.so+0x53eeb5]
>  impala::PartitionedHashJoinNode::Open(impala::RuntimeState*)+0x793
> C  [libExec.so+0x512fde]
>  impala::PartitionedAggregationNode::Open(impala::RuntimeState*)+0x4b4
> C  [libRuntime.so+0x53ff0e]
>  impala::PlanFragmentExecutor::OpenInternal()+0x3ae
> C  [libRuntime.so+0x53fa33]  impala::PlanFragmentExecutor::Open()+0x229
> C  [libService.so+0x30e7a8]
>  impala::FragmentMgr::FragmentExecState::Exec()+0x66
> C  [libService.so+0x31c0c8]
>  impala::FragmentMgr::FragmentThread(impala::TUniqueId)+0x78
> C  [libService.so+0x33863e]  boost::_mfi::mf1<void, impala::FragmentMgr,
> impala::TUniqueId>::operator()(impala::FragmentMgr*, impala::TUniqueId)
> const+0x84
> C  [libService.so+0x336c6b]  void
> boost::_bi::list2<boost::_bi::value<impala::FragmentMgr*>,
> boost::_bi::value<impala::TUniqueId> >::operator()<boost::_mfi::mf1<void,
> impala::FragmentMgr, impala::TUniqueId>,
> boost::_bi::list0>(boost::_bi::type<void>, boost::_mfi::mf1<void,
> impala::FragmentMgr, impala::TUniqueId>&, boost::_bi::list0&, int)+0x7d
> C  [libService.so+0x335557]  boost::_bi::bind_t<void,
> boost::_mfi::mf1<void, impala::FragmentMgr, impala::TUniqueId>,
> boost::_bi::list2<boost::_bi::value<impala::FragmentMgr*>,
> boost::_bi::value<impala::TUniqueId> > >::operator()()+0x3b
> C  [libService.so+0x33288c]
>  boost::detail::function::void_function_obj_invoker0<boost::_
> bi::bind_t<void,
> boost::_mfi::mf1<void, impala::FragmentMgr, impala::TUniqueId>,
> boost::_bi::list2<boost::_bi::value<impala::FragmentMgr*>,
> boost::_bi::value<impala::TUniqueId> > >,
> void>::invoke(boost::detail::function::function_buffer&)+0x23
> C  [libUtil.so+0x2e75f0]  boost::function0<void>::operator()() const+0x52
> C  [libUtil.so+0x2e6b97]  impala::Thread::SuperviseThread(std::string
> const&, std::string const&, boost::function<void ()()>,
> impala::Promise<long>*)+0x2c5
> C  [libUtil.so+0x2ee48e]  void
> boost::_bi::list4<boost::_bi::value<std::string>,
> boost::_bi::value<std::string>, boost::_bi::value<boost::function<void
> ()()> >, boost::_bi::value<impala::Promise<long>*> >::operator()<void
> (*)(std::string const&, std::string const&, boost::function<void ()()>,
> impala::Promise<long>*), boost::_bi::list0>(boost::_bi::type<void>, void
> (*&)(std::string const&, std::string const&, boost::function<void ()()>,
> impala::Promise<long>*), boost::_bi::list0&, int)+0xb2
> C  [libUtil.so+0x2ee3d1]  boost::_bi::bind_t<void, void (*)(std::string
> const&, std::string const&, boost::function<void ()()>,
> impala::Promise<long>*), boost::_bi::list4<boost::_bi::value<std::string>,
> boost::_bi::value<std::string>, boost::_bi::value<boost::function<void
> ()()> >, boost::_bi::value<impala::Promise<long>*> > >::operator()()+0x3b
> C  [libUtil.so+0x2ee32c]
>  boost::detail::thread_data<boost::_bi::bind_t<void, void (*)(std::string
> const&, std::string const&, boost::function<void ()()>,
> impala::Promise<long>*), boost::_bi::list4<boost::_bi::value<std::string>,
> boost::_bi::value<std::string>, boost::_bi::value<boost::function<void
> ()()> >, boost::_bi::value<impala::Promise<long>*> > > >::run()+0x1e
>
> I'm at git hash ff6b450  (IMPALA-4285/IMPALA-4286: Fixes for Parquet
> scanner with MT_DOP > 0), ie, the latest on master.
>

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message