Print

Print


We have seen xrdcp processes which are hanging for a long time. For example:

root      9775  0.0  0.0 103308   864 pts/0    S+   19:08   0:00 grep xrdcp
stage    31823  0.0  0.0 427516 61896 ?        Sl   Jul19   2:09 xrdcp -N root://p05798818s26894.cern.ch:[log in to unmask]?castor.accessop=0&castor.txtype=d2duser&castor.exptime=1437339330&castor.pfn2=0:15511:1a5a38c6-84a5-7fee-e053-a908100acf8f&[log in to unmask]&castor.signature=I+7E0Q5KcvQn8wYXWy070SCq3IAPZOeuBzUHgwN8wz738q52vGJy5D9TbMDUeYnHrg/T3ErFi6F6ZEKuvdv3OA== root://localhost:[log in to unmask]?castor.accessop=0&castor.txtype=d2duser&castor.exptime=1437339330&castor.pfn2=0:15511:1a5a38c6-84a5-7fee-e053-a908100acf8f&<
 /span>ca
 [log in to unmask]&castor.signature=NVQ6OqRWr1gz1sN/vscKqSLsRkSyi9lDjVofTU3haepuGNdG+WFokT1Tth4exwPiyZfzyOLltyI3mdn+ZKu7og==

Looking at the state of the threads:

(gdb) info threads 
* 1 Thread 31828  0x00000038bf80efe0 in nanosleep () from /lib64/libpthread.so.0
(gdb) bt
#0  0x00000038bf80efe0 in nanosleep () from /lib64/libpthread.so.0
#1  0x00000038bf80917b in __pthread_mutex_lock_full () from /lib64/libpthread.so.0
#2  0x000000310526bb73 in Lock (this=0x249c010, status=0x7feec40008c0, openInfo=0x0, hostList=0x7feed4000c60) at /usr/src/debug/xrootd/xrootd/src/XrdSys/XrdSysPthread.hh:149
#3  XrdSysMutexHelper (this=0x249c010, status=0x7feec40008c0, openInfo=0x0, hostList=0x7feed4000c60) at /usr/src/debug/xrootd/xrootd/src/XrdSys/XrdSysPthread.hh:208
#4  XrdCl::FileStateHandler::OnOpen (this=0x249c010, status=0x7feec40008c0, openInfo=0x0, hostList=0x7feed4000c60) at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClFileStateHandler.cc:889
#5  0x000000310526c641 in (anonymous namespace)::OpenHandler::HandleResponseWithHosts (this=0x7feed4002f90, status=0x7feec40008c0, response=0x0, hostList=0x7feed4000c60)
    at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClFileStateHandler.cc:83
#6  0x0000003105259891 in XrdCl::XRootDMsgHandler::HandleResponse (this=0x7feed40035f0) at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClXRootDMsgHandler.cc:1064
#7  0x000000310525a0d3 in XrdCl::XRootDMsgHandler::HandleError (this=0x7feed40035f0, status=..., msg=<value optimized out>) at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClXRootDMsgHandler.cc:1795
#8  0x000000310525ae3d in XrdCl::XRootDMsgHandler::Process (this=0x7feed40035f0, msg=<value optimized out>) at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClXRootDMsgHandler.cc:342
#9  0x0000003105244bde in XrdCl::Stream::HandleIncMsgJob::Run (this=0x7feed4002a10, arg=<value optimized out>) at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClStream.hh:279
#10 0x00000031052889cd in XrdCl::JobManager::RunJobs (this=0x2496e40) at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClJobManager.cc:148
#11 0x0000003105288a49 in RunRunnerThread (arg=<value optimized out>) at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClJobManager.cc:33
#12 0x00000038bf8079d1 in start_thread () from /lib64/libpthread.so.0
#13 0x00000038bf4e88fd in sysctl () from /lib64/libc.so.6
#14 0x0000000000000000 in ?? ()

(gdb) bt
#0  0x00000038bf80822d in pthread_join () from /lib64/libpthread.so.0
#1  0x0000003105288784 in XrdCl::JobManager::StopWorkers (this=0x2496e40, n=2) at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClJobManager.cc:127
#2  0x0000003105288be6 in XrdCl::JobManager::Stop (this=0x2496e40) at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClJobManager.cc:103
#3  0x000000310523e161 in XrdCl::PostMaster::Stop (this=0x2496260) at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClPostMaster.cc:140
#4  0x0000003105230cca in XrdCl::DefaultEnv::Finalize () at /usr/src/debug/xrootd/xrootd/src/XrdCl/XrdClDefaultEnv.cc:590
#5  0x00000038bf435ebd in __cxa_finalize () from /lib64/libc.so.6
#6  0x0000003105224db6 in __do_global_dtors_aux () from /usr/lib64/libXrdCl.so.2
#7  0x0000000000000000 in ?? ()

These are the only threads for which I could get useful info. These processes usually have the xrdcp binary removed i.e.

# ls -lrt /proc/31823/
total 0
lrwxrwxrwx. 1 stage st 0 Sep 28 13:40 exe -> /usr/bin/xrdcp (deleted)


Reply to this email directly or view it on GitHub.



Use REPLY-ALL to reply to list

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