[ 
https://issues.apache.org/jira/browse/IMPALA-6587?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Tim Armstrong resolved IMPALA-6587.
-----------------------------------
       Resolution: Fixed
    Fix Version/s: Impala 3.1.0
                   Impala 2.13.0

> Crash in DiskMgr::AllocateBuffersForRange
> -----------------------------------------
>
>                 Key: IMPALA-6587
>                 URL: https://issues.apache.org/jira/browse/IMPALA-6587
>             Project: IMPALA
>          Issue Type: Sub-task
>          Components: Backend
>    Affects Versions: Impala 2.12.0
>            Reporter: Tim Armstrong
>            Assignee: Tim Armstrong
>            Priority: Major
>              Labels: broken-build, crash
>             Fix For: Impala 2.13.0, Impala 3.1.0
>
>
> {noformat}
> F0224 17:43:08.522589 13124 reservation-tracker.cc:376] Check failed: bytes 
> <= unused_reservation() (8192 vs. 0) 
> {noformat}
> {noformat}
> #0  0x0000003cb32328e5 in raise () from /lib64/libc.so.6
> #1  0x0000003cb32340c5 in abort () from /lib64/libc.so.6
> #2  0x0000000003c5a244 in google::DumpStackTraceAndExit() ()
> #3  0x0000000003c50cbd in google::LogMessage::Fail() ()
> #4  0x0000000003c52562 in google::LogMessage::SendToLog() ()
> #5  0x0000000003c50697 in google::LogMessage::Flush() ()
> #6  0x0000000003c53c5e in google::LogMessageFatal::~LogMessageFatal() ()
> #7  0x0000000001b7a813 in impala::ReservationTracker::AllocateFromLocked 
> (this=0x1a75d2a98, bytes=8192) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/repos/Impala/be/src/runtime/bufferpool/reservation-tracker.cc:376
> #8  0x0000000001b7a5ed in impala::ReservationTracker::AllocateFrom 
> (this=0x1a75d2a98, bytes=8192) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/repos/Impala/be/src/runtime/bufferpool/reservation-tracker.cc:370
> #9  0x0000000001b72127 in impala::BufferPool::Client::PrepareToAllocateBuffer 
> (this=0x1a75d2a80, len=8192, reserved=true, success=0x0) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/repos/Impala/be/src/runtime/bufferpool/buffer-pool.cc:567
> #10 0x0000000001b6ea13 in impala::BufferPool::AllocateBuffer (this=0xa6af380, 
> client=0x14121248, len=8192, handle=0x7fede6224260) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/repos/Impala/be/src/runtime/bufferpool/buffer-pool.cc:229
> #11 0x0000000002b894f0 in impala::io::DiskIoMgr::AllocateBuffersForRange 
> (this=0xb06fd40, reader=0x1ecf10300, bp_client=0x14121248, range=0x14711180, 
> max_bytes=8192) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/repos/Impala/be/src/runtime/io/disk-io-mgr.cc:470
> #12 0x0000000001bef7ff in impala::HdfsScanNode::ScannerThread 
> (this=0x14121100, scanner_thread_reservation=8192) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/repos/Impala/be/src/exec/hdfs-scan-node.cc:393
> #13 0x0000000001beec52 in impala::HdfsScanNode::<lambda()>::operator()(void) 
> const (__closure=0x7fede6224bc8) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/repos/Impala/be/src/exec/hdfs-scan-node.cc:303
> #14 0x0000000001bf0d75 in 
> boost::detail::function::void_function_obj_invoker0<impala::HdfsScanNode::ThreadTokenAvailableCb(impala::ThreadResourceMgr::ResourcePool*)::<lambda()>,
>  void>::invoke(boost::detail::function::function_buffer &) 
> (function_obj_ptr=...) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/Impala-Toolchain/boost-1.57.0-p3/include/boost/function/function_template.hpp:153
> #15 0x000000000183e44a in boost::function0<void>::operator() 
> (this=0x7fede6224bc0) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/Impala-Toolchain/boost-1.57.0-p3/include/boost/function/function_template.hpp:767
> #16 0x0000000001b484cf in impala::Thread::SuperviseThread (name=..., 
> category=..., functor=..., parent_thread_info=0x7fede6c25870, 
> thread_started=0x7fede6c24160) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/repos/Impala/be/src/util/thread.cc:356
> #17 0x0000000001b509a5 in 
> boost::_bi::list5<boost::_bi::value<std::basic_string<char, 
> std::char_traits<char>, std::allocator<char> > >, 
> boost::_bi::value<std::basic_string<char, std::char_traits<char>, 
> std::allocator<char> > >, boost::_bi::value<boost::function<void()> >, 
> boost::_bi::value<impala::ThreadDebugInfo*>, 
> boost::_bi::value<impala::Promise<long int>*> >::operator()<void (*)(const 
> std::basic_string<char>&, const std::basic_string<char>&, 
> boost::function<void()>, const impala::ThreadDebugInfo*, impala::Promise<long 
> int>*), boost::_bi::list0>(boost::_bi::type<void>, void (*&)(const 
> std::basic_string<char, std::char_traits<char>, std::allocator<char> > &, 
> const std::basic_string<char, std::char_traits<char>, std::allocator<char> > 
> &, boost::function<void()>, const impala::ThreadDebugInfo *, 
> impala::Promise<long> *), boost::_bi::list0 &, int) (this=0x1c9dd2fc0, 
> f=@0x1c9dd2fb8, a=...) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/Impala-Toolchain/boost-1.57.0-p3/include/boost/bind/bind.hpp:525
> #18 0x0000000001b508c9 in boost::_bi::bind_t<void, void (*)(const 
> std::basic_string<char, std::char_traits<char>, std::allocator<char> >&, 
> const std::basic_string<char, std::char_traits<char>, std::allocator<char> 
> >&, boost::function<void()>, const impala::ThreadDebugInfo*, 
> impala::Promise<long int>*), 
> boost::_bi::list5<boost::_bi::value<std::basic_string<char, 
> std::char_traits<char>, std::allocator<char> > >, 
> boost::_bi::value<std::basic_string<char, std::char_traits<char>, 
> std::allocator<char> > >, boost::_bi::value<boost::function<void()> >, 
> boost::_bi::value<impala::ThreadDebugInfo*>, 
> boost::_bi::value<impala::Promise<long int>*> > >::operator()(void) 
> (this=0x1c9dd2fb8) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/Impala-Toolchain/boost-1.57.0-p3/include/boost/bind/bind_template.hpp:20
> #19 0x0000000001b5088c in boost::detail::thread_data<boost::_bi::bind_t<void, 
> void (*)(const std::basic_string<char, std::char_traits<char>, 
> std::allocator<char> >&, const std::basic_string<char, 
> std::char_traits<char>, std::allocator<char> >&, boost::function<void()>, 
> const impala::ThreadDebugInfo*, impala::Promise<long int>*), 
> boost::_bi::list5<boost::_bi::value<std::basic_string<char, 
> std::char_traits<char>, std::allocator<char> > >, 
> boost::_bi::value<std::basic_string<char, std::char_traits<char>, 
> std::allocator<char> > >, boost::_bi::value<boost::function<void()> >, 
> boost::_bi::value<impala::ThreadDebugInfo*>, 
> boost::_bi::value<impala::Promise<long int>*> > > >::run(void) 
> (this=0x1c9dd2e00) at 
> /data/jenkins/workspace/impala-asf-master-exhaustive-integration/Impala-Toolchain/boost-1.57.0-p3/include/boost/thread/detail/thread.hpp:116
> #20 0x0000000002dda25a in thread_proxy ()
> #21 0x0000003cb3607851 in start_thread () from /lib64/libpthread.so.0
> #22 0x0000003cb32e894d in clone () from /lib64/libc.so.6
> {noformat}
> These tests were running:
> {noformat}
> 17:47:19 [gw1] ERROR 
> query_test/test_scanners.py::TestParquet::test_def_levels[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': 
> '-1:OPEN:[email protected]', 
> 'exec_single_node_rows_threshold': 0} | table_format: parquet/none] 
> 17:47:19 [gw2] FAILED 
> query_test/test_queries.py::TestHdfsQueries::test_top_n[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': False, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: seq/none] 
> 17:47:19 query_test/test_queries.py::TestHdfsQueries::test_top_n[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: seq/none] 
> 17:47:19 [gw0] FAILED 
> query_test/test_scanners.py::TestScanRangeLengths::test_scan_ranges[max_scan_range_length:
>  1 | exec_option: {'batch_size': 0, 'num_nodes': 0, 
> 'disable_codegen_rows_threshold': 0, 'disable_codegen': False, 
> 'abort_on_error': 1, 'debug_action': None, 'exec_single_node_rows_threshold': 
> 0} | table_format: text/lzo/block] 
> 17:47:19 
> query_test/test_scanners.py::TestScanRangeLengths::test_scan_ranges[max_scan_range_length:
>  2 | exec_option: {'batch_size': 0, 'num_nodes': 0, 
> 'disable_codegen_rows_threshold': 0, 'disable_codegen': False, 
> 'abort_on_error': 1, 'debug_action': None, 'exec_single_node_rows_threshold': 
> 0} | table_format: rc/snap/block] 
> 17:47:19 [gw2] FAILED 
> query_test/test_queries.py::TestHdfsQueries::test_top_n[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: seq/none] 
> 17:47:19 query_test/test_queries.py::TestHdfsQueries::test_top_n[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: seq/def/block] 
> 17:47:19 [gw1] ERROR 
> query_test/test_scanners.py::TestParquet::test_def_levels[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': 
> '-1:OPEN:[email protected]', 
> 'exec_single_node_rows_threshold': 0} | table_format: parquet/none] 
> 17:47:19 
> query_test/test_scanners.py::TestParquet::test_def_levels[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': False, 'abort_on_error': 1, 'debug_action': 
> '-1:OPEN:[email protected]', 
> 'exec_single_node_rows_threshold': 0} | table_format: parquet/none] 
> 17:47:19 [gw0] FAILED 
> query_test/test_scanners.py::TestScanRangeLengths::test_scan_ranges[max_scan_range_length:
>  2 | exec_option: {'batch_size': 0, 'num_nodes': 0, 
> 'disable_codegen_rows_threshold': 0, 'disable_codegen': False, 
> 'abort_on_error': 1, 'debug_action': None, 'exec_single_node_rows_threshold': 
> 0} | table_format: rc/snap/block] 
> 17:47:19 
> query_test/test_scanners.py::TestScanRangeLengths::test_scan_ranges[max_scan_range_length:
>  5 | exec_option: {'batch_size': 0, 'num_nodes': 0, 
> 'disable_codegen_rows_threshold': 0, 'disable_codegen': False, 
> 'abort_on_error': 1, 'debug_action': None, 'exec_single_node_rows_threshold': 
> 0} | table_format: rc/snap/block] 
> 17:47:19 [gw2] FAILED 
> query_test/test_queries.py::TestHdfsQueries::test_top_n[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: seq/def/block] 
> 17:47:19 query_test/test_queries.py::TestHdfsQueries::test_top_n[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': False, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: seq/def/block] 
> 17:47:19 [gw1] ERROR 
> query_test/test_scanners.py::TestParquet::test_def_levels[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': False, 'abort_on_error': 1, 'debug_action': 
> '-1:OPEN:[email protected]', 
> 'exec_single_node_rows_threshold': 0} | table_format: parquet/none] 
> 17:47:22 [gw0] FAILED 
> query_test/test_scanners.py::TestScanRangeLengths::test_scan_ranges[max_scan_range_length:
>  5 | exec_option: {'batch_size': 0, 'num_nodes': 0, 
> 'disable_codegen_rows_threshold': 0, 'disable_codegen': False, 
> 'abort_on_error': 1, 'debug_action': None, 'exec_single_node_rows_threshold': 
> 0} | table_format: rc/snap/block] -- closing connection to: localhost:21000
> 17:47:24 
> 17:47:24 
> {noformat}
> Tests that were running in a second occurence:
> {noformat}
> 12:33:14 [gw0] PASSED 
> query_test/test_scanners.py::TestParquet::test_huge_num_rows[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': False, 'abort_on_error': 1, 'debug_action': 
> '-1:OPEN:[email protected]', 
> 'exec_single_node_rows_threshold': 0} | table_format: parquet/none] 
> 12:39:18 
> query_test/test_scanners.py::TestParquet::test_multi_compression_types[exec_option:
>  {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: parquet/none] 
> 12:39:18 [gw1] FAILED 
> query_test/test_scanners.py::TestScanRangeLengths::test_scan_ranges[max_scan_range_length:
>  1 | exec_option: {'batch_size': 0, 'num_nodes': 0, 
> 'disable_codegen_rows_threshold': 0, 'disable_codegen': False, 
> 'abort_on_error': 1, 'debug_action': None, 'exec_single_node_rows_threshold': 
> 0} | table_format: text/lzo/block] 
> 12:39:18 
> query_test/test_scanners.py::TestScanRangeLengths::test_scan_ranges[max_scan_range_length:
>  2 | exec_option: {'batch_size': 0, 'num_nodes': 0, 
> 'disable_codegen_rows_threshold': 0, 'disable_codegen': False, 
> 'abort_on_error': 1, 'debug_action': None, 'exec_single_node_rows_threshold': 
> 0} | table_format: rc/snap/block] 
> 12:39:18 [gw2] FAILED 
> query_test/test_queries.py::TestHdfsQueries::test_analytic_fns[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: rc/none] 
> 12:39:18 [gw3] FAILED 
> query_test/test_queries.py::TestQueries::test_analytic_fns[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: rc/snap/block] 
> 12:39:18 
> query_test/test_queries.py::TestHdfsQueries::test_analytic_fns[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': False, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: rc/none] 
> 12:39:18 
> query_test/test_queries.py::TestQueries::test_analytic_fns[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': False, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: rc/snap/block] 
> 12:39:18 [gw2] FAILED 
> query_test/test_queries.py::TestHdfsQueries::test_analytic_fns[exec_option: 
> {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': False, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: rc/none] 
> 12:39:18 
> query_test/test_queries.py::TestHdfsQueries::test_analytic_fns[exec_option: 
> {'disable_codegen_rows_threshold': 0, 'disable_codegen': True, 
> 'abort_on_error': 1, 'debug_action': None, 'exec_single_node_rows_threshold': 
> 100, 'batch_size': 0, 'num_nodes': 0} | table_format: rc/none] 
> 12:39:18 [gw0] ERROR 
> query_test/test_scanners.py::TestParquet::test_multi_compression_types[exec_option:
>  {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: parquet/none] 
> 12:39:18 [gw2] FAILED 
> query_test/test_queries.py::TestHdfsQueries::test_analytic_fns[exec_option: 
> {'disable_codegen_rows_threshold': 0, 'disable_codegen': True, 
> 'abort_on_error': 1, 'debug_action': None, 'exec_single_node_rows_threshold': 
> 100, 'batch_size': 0, 'num_nodes': 0} | table_format: rc/none] 
> 12:39:19 
> query_test/test_queries.py::TestHdfsQueries::test_analytic_fns[exec_option: 
> {'disable_codegen_rows_threshold': 0, 'disable_codegen': False, 
> 'abort_on_error': 1, 'debug_action': None, 'exec_single_node_rows_threshold': 
> 100, 'batch_size': 0, 'num_nodes': 0} | table_format: rc/none] 
> 12:39:19 [gw0] ERROR 
> query_test/test_scanners.py::TestParquet::test_multi_compression_types[exec_option:
>  {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': True, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: parquet/none] 
> 12:39:19 
> query_test/test_scanners.py::TestParquet::test_multi_compression_types[exec_option:
>  {'batch_size': 0, 'num_nodes': 0, 'disable_codegen_rows_threshold': 0, 
> 'disable_codegen': False, 'abort_on_error': 1, 'debug_action': None, 
> 'exec_single_node_rows_threshold': 0} | table_format: parquet/none] 
> {noformat}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

Reply via email to