Hello ,
I see different behavior between two different simple proxy machines that I am trying to debug.
from outside either cluster
xrd <proxy machine> dirlist /atlas gives different results -
These machines are running in different clusters. On one cluster
[benjamin@atl010 topd3pd-datamanagement]$ xrd atlas29.hep.anl.gov:1094
(C) 2004-2010 by the Xrootd group. Xrootd version: v3.0.5
Welcome to the xrootd command line interface.
Type 'help' for a list of available commands.
root://atlas29.hep.anl.gov:1094//> dirlist /atlas
drwx(051) 4096 2011-07-18 13:39:47 /atlas/ANLASC_TEST
-rw-(048) 277 2010-11-11 23:31:41 /atlas/I-love-computers.fail
drwx(051) 4096 2011-07-16 03:03:42 /atlas/UTA-T3-Test
drwx(051) 22 2010-11-03 17:09:34 /atlas/ddo
drwx(051) 4096 2011-09-14 03:54:50 /atlas/dq2
drwx(051) 22 2010-11-06 19:23:48 /atlas/group10
drwx(051) 4096 2011-05-11 00:49:38 /atlas/local
drwx(051) 16 2010-11-16 17:32:50 /atlas/mc09_7TeV
drwx(051) 4096 2011-09-13 15:24:00 /atlas/test
-rw-(048) 142 2010-11-10 03:44:21 /atlas/testfile.slac.fail
drwx(051) 35 2010-11-20 21:34:13 /atlas/user
-rw-(048) 0 2010-11-11 23:31:41 /atlas/DIR_LOCK
root://atlas29.hep.anl.gov:1094//> exit
Goodbye.
Yet on the other cluster
[benjamin@atl010 topd3pd-datamanagement]$ xrd titan12.physics.umass.edu:1095
(C) 2004-2010 by the Xrootd group. Xrootd version: v3.0.5
Welcome to the xrootd command line interface.
Type 'help' for a list of available commands.
root://titan12.physics.umass.edu:1095//> dirlist /atlas
root://titan12.physics.umass.edu:1095//> exit
Goodbye.
Here is the configuration files for each machine
-------------- atlas29.hep.anl.gov ------------------
all.adminpath /var/spool/xrootd/admin
all.export /atlas r/o
ofs.osslib /usr/lib64/libXrdPss.so
pss.origin headprv.hep.anl.gov:1094
# While we call this instance a "server" it is, in fact, a proxy server since we told the ofs
# to use libXrdPss.so as the storage handler (this is really the proxy service library). We
# do this so that we can directly subscribe to the meta-manager instead of doing so
# indirectly via a local manager. We don't need a local manager as there is a single
# proxy running in this cluster.
#
all.role server
all.manager glrd.usatlas.org:1095
xrd.port 1094 if exec xrootd
xrd.trace all -debug
cms.trace all -debug
xrd.allow host *
--------------------------- titan12.physics.umass.edu ---------------------------
all.adminpath /var/spool/xrootd/admin
all.export /atlas r/o
ofs.osslib /usr/lib64/libXrdPss.so
pss.origin 172.30.49.10:1094
# While we call this instance a "server" it is, in fact, a proxy server since we told the ofs
# to use libXrdPss.so as the storage handler (this is really the proxy service library). We
# do this so that we can directly subscribe to the meta-manager instead of doing so
# indirectly via a local manager. We don't need a local manager as there is a single
# proxy running in this cluster.
#
all.role server
all.manager glrd.usatlas.org:1095
xrd.port 1095 if exec xrootd
xrd.trace all -debug
cms.trace all -debug172.30.49.10
xrd.allow host *
----------------------------
Note it does not appear to be a network connection between titan12 and 172.30.49.10.
I can use the telnet command to connect to the xrootd and cmsd daemons running on 172.30.49.10.
Note the dirlist command against 172.30.49.10 from titan12 gives all of the directories that I
would expect.
Any idea what might be blocking all of this would be helpful.
Thanks,
Doug Benjamin
|