I wonder if that is a new problem… I was running a typical test with 50+ low vol and some high volume queries, and at some point xrootd on one worker died with:

0830 11:20:31.314 [0x7fc35b0fb700] DEBUG ScanSched (build/wsched/ChunkDisk.cc:234) - ChunkDisk registering for 2392 : SELECT COUNT(*) AS QS1_COUNT FROM LSST.Object_2392 AS QST_1_ WHERE y_instFlux>0.05 p=0x7fc334017ef8
0830 11:20:31.314 [0x7fc35b0fb700] INFO  Foreman (build/wcontrol/Foreman.cc:296) - Runner running Task: msg: session=327290 chunk=2392 db=LSST entry time=Sun Aug 30 11:18:48 2015
 frag: q=SELECT COUNT(*) AS QS1_COUNT FROM LSST.Object_2392 AS QST_1_ WHERE y_instFlux>0.05, sc= rt=r_3272901ce7680771ed0454755814f2988558df_2392_0 
0830 11:20:31.314 [0x7fc35b0fb700] INFO  Foreman (build/wdb/QueryAction.cc:177) - Exec in flight for Db = q_7482727be74daddaa3fdf1d59d93ba0e
0830 11:20:31.314 [0x7fc35b0fb700] WARN  Foreman (build/wdb/QueryAction.cc:109) - QueryAction overriding dbName with LSST
0830 11:20:31.315 [0x7fc35a3f5700] INFO  root (build/xrdsvc/ChannelStream.cc:122) - returning buffer (44, (last))
0830 11:20:31.316 [0x7fc35a3f5700] INFO  root (build/xrdsvc/SsiSession.cc:153) - RequestFinished type=isStream
0830 11:20:31.768 [0x7fc35b0fb700] INFO  root (build/wdb/QueryAction.cc:261) - &&& _fillRows size=5
terminate called after throwing an instance of 'lsst::qserv::sql::SqlErrorObject’


In:

#8  0x00007fc366b19235 in lsst::qserv::wdb::ChunkResourceMgr::Impl::release (this=0xeeacc0, i=...) at build/wdb/ChunkResource.cc:398
#9  0x00007fc366b17686 in lsst::qserv::wdb::ChunkResource::~ChunkResource (this=0x7fc35b0fab70, __in_chrg=<optimized out>)
    at build/wdb/ChunkResource.cc:131
#10 0x00007fc366b25efb in lsst::qserv::wdb::QueryAction::Impl::_dispatchChannel (this=0x7fc33c469f30) at build/wdb/QueryAction.cc:392
#11 0x00007fc366b24597 in lsst::qserv::wdb::QueryAction::Impl::act (this=0x7fc33c469f30) at build/wdb/QueryAction.cc:187
#12 0x00007fc366b27070 in lsst::qserv::wdb::QueryAction::operator() (this=0x7fc33c4394c8) at build/wdb/QueryAction.cc:450
#13 0x00007fc366b09f36 in lsst::qserv::wcontrol::ForemanImpl::Runner::operator() (this=0x7fc32403ce10) at build/wcontrol/Foreman.cc:302
#14 0x00007fc366b16ce0 in std::_Bind_simple<lsst::qserv::wcontrol::ForemanImpl::Runner ()>::_M_invoke<>(std::_Index_tuple<>) (this=0x7fc32403ce10)
    at /usr/include/c++/4.8.2/functional:1732
#15 0x00007fc366b16a7b in std::_Bind_simple<lsst::qserv::wcontrol::ForemanImpl::Runner ()>::operator()() (this=0x7fc32403ce10)
    at /usr/include/c++/4.8.2/functional:1720



Use REPLY-ALL to reply to list

To unsubscribe from the QSERV-L list, click the following link:
https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=QSERV-L&A=1