Hi,
I have a fresh gexec implementation with libe-0.3.1, authd-0.2.3, and
gexec-0.3.7 built and installed from scratch installed on Fedora 10
x86_64 2.6.27.5-117.fc10.x86_64. Unfortunately, It does not
appear to be functioning properly.
Following the documentation, I have performed the following for a beowulf
cluster with a master + 8 compute nodes:
export GEXEC_SVRS="grendel-01 grendel-02 grendel-03 grendel-04 grendel-05
grendel-06 grendel-07 grendel-08"
[r...@grendel ~]# gexec -v -n 0 /bin/hostname
Could not connect to grendel-01.bpcservers.invalid (10.0.4.1)
Could not connect to grendel-02.bpcservers.invalid (10.0.4.2)
I can see the connection clearly when using tcpdump on node 1
(grendel-01).
strace on GEXEC shows that the tcp connections are up:
connect(3, {sa_family=AF_INET, sin_port=htons(2875),
sin_addr=inet_addr("10.0.4.1")}, 16) = 0
and I can telnet to port 2875 on node 1 and make a successful tcp
connection to be sure.
I don't see any logging (or know what facility it would be).
Any helpful advice would be most appreciated.
X.
------------------------------------------------------------------------------
Enter the BlackBerry Developer Challenge
This is your chance to win up to $100,000 in prizes! For a limited time,
vendors submitting new applications to BlackBerry App World(TM) will have
the opportunity to enter the BlackBerry Developer Challenge. See full prize
details at: http://p.sf.net/sfu/Challenge
_______________________________________________
Ganglia-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/ganglia-general
