Andy
I run 4 simultaneous large queries: 3 object scans and 1 source scan.
Xrootd silently died on 2 machines, no core file. Below I pasted the
tail of the log files. Please start thinking about it while I am trying
to isolate the issue. BTW, it happens towards the end of running.
Does these log file give you any clue whatsoever?
Jacek
ccqserv108
0808 00:22:33.824 [0x7fb739583700] WARN Foreman
(build/wdb/QueryAction.cc:109) - QueryAction overriding dbName with LSST
0808 00:22:33.824 [0x7fb74a00e700] INFO root
(build/xrdsvc/ChannelStream.cc:122) - returning buffer (256, (more))
0808 00:22:33.826 [0x7fb74a00e700] INFO root
(build/xrdsvc/ChannelStream.cc:122) - returning buffer (62, (last))
0808 00:22:33.826 [0x7fb74a00e700] INFO root
(build/xrdsvc/SsiSession.cc:153) - RequestFinished type=isStream
0808 00:22:34.468 [0x7fb739583700] INFO root
(build/wdb/QueryAction.cc:261) - &&& _fillRows size=8
0808 00:22:34.469 [0x7fb739583700] DEBUG root
(build/wdb/QueryAction.cc:288) - _transmit last=1
0808 00:22:34.469 [0x7fb739583700] DEBUG root
(build/wdb/QueryAction.cc:307) - _transmitHeader
0808 00:22:34.469 [0x7fb739583700] INFO root
(build/proto/ProtoHeaderWrap.cc:52) - msgBuf size=256 -> [[0]=40,
[1]=13, [2]=2, [3]=0, [4]=0, ..., [251]=48, [252]=48, [253]=48,
[254]=48, [255]=48]
0808 00:22:34.469 [0x7fb739583700] INFO root
(build/xrdsvc/SsiSession_ReplyChannel.cc:85) - sendStream, checking
stream 0 len=256 last=0
-----
ccqserv124
0808 00:22:25.329 [0x7f25a67bf700] DEBUG ScanSched
(build/wsched/ChunkDisk.cc:234) - ChunkDisk registering for 2044 :
SELECT MIN(ra) AS QS1_MIN,MAX(ra) AS QS2_MAX,MIN(decl) AS
QS3_MIN,MAX(decl) AS QS4_MAX FROM LSST.Object_2044 AS QST_1_
p=0x7f257003d0b8
0808 00:22:25.329 [0x7f25a67bf700] INFO Foreman
(build/wcontrol/Foreman.cc:296) - Runner running Task: msg: session=7
chunk=2044 db=LSST entry time=Fri Aug 7 23:52:06 2015
frag: q=SELECT MIN(ra) AS QS1_MIN,MAX(ra) AS QS2_MAX,MIN(decl) AS
QS3_MIN,MAX(decl) AS QS4_MAX FROM LSST.Object_2044 AS QST_1_, sc=
rt=r_7bff268d0e369dda8fa314132538a96ad_2044_0
0808 00:22:25.329 [0x7f25a67bf700] INFO Foreman
(build/wdb/QueryAction.cc:177) - Exec in flight for Db =
q_b762c96f418726ae3457c74c0350d0c4
0808 00:22:25.329 [0x7f25a67bf700] WARN Foreman
(build/wdb/QueryAction.cc:109) - QueryAction overriding dbName with LSST
0808 00:22:25.330 [0x7f25a50b6700] INFO root
(build/xrdsvc/ChannelStream.cc:122) - returning buffer (44, (last))
0808 00:22:25.330 [0x7f25a50b6700] INFO root
(build/xrdsvc/SsiSession.cc:153) - RequestFinished type=isStream
0808 00:22:26.218 [0x7f25a67bf700] INFO root
(build/wdb/QueryAction.cc:261) - &&& _fillRows size=81
0808 00:22:26.218 [0x7f25a67bf700] DEBUG root
(build/wdb/QueryAction.cc:288) - _transmit last=1
0808 00:22:26.218 [0x7f25a67bf700] DEBUG root
(build/wdb/QueryAction.cc:307) - _transmitHeader
0808 00:22:26.218 [0x7f25a67bf700] INFO root
(build/proto/ProtoHeaderWrap.cc:52) - msgBuf size=256 -> [[0]=40,
[1]=13, [2]=2, [3]=0, [4]=0, ..., [251]=48, [252]=48, [253]=48,
[254]=48, [255]=48]
0808 00:22:26.218 [0x7f25a67bf700] INFO root
(build/xrdsvc/SsiSession_ReplyChannel.cc:85) - sendStream, checking
stream 0 len=256 last=0
########################################################################
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
|