Troubleshooting guide

Important points to note:
The GM-1 mapper is ONLY run on one node in the cluster. You should
choose one node in the cluster to be the mapper node, and any subsequent
invocations of the mapper should be done on this node only.
The GM-1 mapper must be run before any communication over Myrinet can
occur.
If a host is rebooted, you must reload the GM driver and rerun the GM-1
mapper.
If any topological change occurs in the cluster, the GM-1 mapper must be
rerun.
Never run the GM-1 mapper on multiple nodes at the same time, as serious
routing confusion will result.
The aforementioned mapping procedure uses the most common form of mapping: “Map
Once” Mapping. Depending upon your needs, there are three ways to run the GM
mapper:
Map Once Mapping
Static or “File” Mapping
High Availability (HA) Mapping
“Map Once” Mapping is by far the most common way of running the GM mapper. In
this method, the mapper is run on one host in the network (any of the hosts). It is rerun if
a host (re)boots or a hostname is changed or after a change of Myrinet topology
(swapping of ports on a switch). The command for this method of running the GM
mapper is:
cd <install_path>/sbin/
su root
./mapper ../etc/gm/map_once.args
“Static” Mapping is another way in which the GM mapper may be used. In this method,
an active mapper is run once when ALL of the hosts are up and running the GM driver.
This initial active mapper will generate a map file and a host file.
These files are then shared by NFS, or copied to all of the hosts in the
network.
An entry in the boot scripts will allow each host to read the map file and the
host file and update the routing table on its local Myrinet NIC(s).
The command for this method of running the GM-1 mapper is:
cd <install_path>/sbin/
su root
./mapper ../etc/gm/static.args
© 2007 Myricom, Inc. DRAFT
26