added functionality to the select plugin so we didn't have to link to the block allocator anymore.  smap doesn't wo
rk right now.  Moe will fix.

ok, it looks like recussion works now, just a big of clean up now.

    job is in a pending state, then send the request directly to the slurmctld
    daemon and do not attempt to send the request to slurmd daemons, which are
    not running the job anyway.

real problems with some GTK themes and is really no longer necessary

This implements Moe's suggestion for NodeAddr/NodeHostname semantics,

   NodeName     "nid#####"    (this is what SLURM will refer to the node as)
   NodeHostName "c0-0c0s0n1"  (Cray's component ID, visible only with scontrol
		                                and sview's node display)
   NodeAddr     "###"         (hexadecimal X, Y and Z coordinates, visible only
		                                with scontrol and sview's node display)

For example,
palu> scontrol show node nid00189
NodeName=nid00189 Arch=XE CoresPerSocket=6
   CPUAlloc=0 CPUErr=0 CPUTot=24 Features=(null)
   Gres=(null)
   NodeAddr=01E NodeHostName=c1-0c0s1n1
   RealMemory=32000 Sockets=4
   ...

Please note:
~~~~~~~~~~~~
on XE systems each two nodes (0/1 and 2/3) on a node share the same network
interface and hence are located at identical Y coordinates in the torus. To
make tools such as smap work with these coordinates, we use "virtual" Y
coordinates, computed as

  y_coord = 4 * cage + cpu;

This scheme mirrors the one currently used to derive node coordinates on a
SeaStar/XT system.

09_Cray-hostlist.diff

This is a global compatibility test to ensure that any (remote) host trying to talk
to a cluster using select/cray meets the minimum requirements of supporting the
required Cray data structures and hooks.

As per previous patches, it may be possible to factor this out, but at this stage
is working code.

06_read_config--test-for-select-cray.diff

If this test is performed on a non-Cray system which tries to talk to 
a remote Cray system, it fails -- which it should not.

ela1:1 ~>echo $SLURM_CLUSTERS
palu
ela1:0 ~>squeue
squeue: fatal: Requested SelectType=select/cray in slurm.conf, but not running on a cray system.  If looking to emulate a Cray system use --enable-cray-emulation.

02_node_select_test.diff

This fixes a copy&paste bug where the wrong memory area was dereferenced,
found by these error messages in the logs:

 [2011-02-01T15:39:08] error: cray/get_select_jobinfo: jobinfo magic bad
 [2011-02-01T15:39:08] error: cray/get_select_jobinfo: jobinfo magic bad
 [2011-02-01T15:39:08] error: orphaned ALPS reservation 1022, trying to remove

While at it, added tests for the return values of these functions (resv_id
may be undefined if the return value is not SLURM_SUCCCESS).

01_Bug-Fix_pointer-dereference.diff

ok, it looks like we got it all!, at least all the nodes are accouted for.  I have to make sure all the wires are correct still though

Fix call to gtk_table_set_row_spacing() to not be called for 4-D in addition to not being called for 3-D

rather than using DIM_SIZE from the bluegene plugin, which is not portable

(if available) or local information otherwise

ok, if we would copy the list for each block only having the connections listed there before sending it out things will work fine.