Well, here it is:  The checkin implementing robust recovery/retry and
asynchronous safe termination in plab allocation/deallocation/setup.

Here are some of the more prominent changes/additions:

* Bounded plab agent communication
  Scripts should never hang waiting for plab xmlrpc commands to complete;
  they have their own internal timeouts.  Node.create() in libplab is an
  exception, but is always run under a timeout constraint in vnode_setup
  and can be changed easily if the need arises.

* Wrote functions in libplab to do the retry/recovery/timeout of remote
  command exection.

* Wrapped critical sections with a signal watcher.

* Added code to handle various error conditions properly

* Added a libtestbed function, TBForkCmd, which runs a given program in
  a child process, and can optionally catch incoming SIGTERMs and terminate
  the child (then exit itself).

* Fixed up vnode_setup to batch the 'plabnode free' operation along with
  a few other cleanups.  This should alleviate Jay's concern about how
  long it used to take to teardown a plab expt.

* Whacked plabmonitord into better shape; fixed a couple bugs, taught it how
  to daemonize, and implemented a priority list for testing broken plab nodes.
  This list causes new (as yet unseen) nodes to be tried first over ones that
  have been tested already.

a full-out explanation of the new way we add nodes to the testbed,
the new (well, not that new anymore) newnode MFS, web page, etc.

into a new file.

Remove reference to cvsup, since we're moving away from it.

Remove reference to dhcpd, since a better explanation is now in
setup-nodes.txt .

Fix up text about named.

change awkward "uncompress" to "decompress"

This will happen for plab nodes because of the way that we can get the
data. Not ideal, but not sure what to do about it.

what window is what.

pop up a save dialog box, no matter what the user's settings for the
mime type are.

information. Rather than pass it all in, which was getting very
cumbersome, and inconsistent between Cisco and Intel switches, the
modules query the database themselves (via a new function in
snmpit_lib.pm).

Also in this commit are two new options for switch stacks - the
ability to specify minimum and maximum VLAN number to use.

Fix a bug with limited trivial link bandwidth. It used to be the case
that we penalized solutions that over-used the trivial bandwidth based
on the number of links that were over it. Turns out this was a
problem, if you had links of differing bandwidths, and were near the
limit. Certain orderings were possible where you would remove two
trivial links in a different order than you added them, which might
result in more (or fewer) violations being scored then when you did
them originally. The fix for this is to penalize these based on
bandwidth, which is what assign now does.

Added a '-g' flag, which does greedy link selection - assign normally
does random link selection until the very end, when it does one pass
with greedy selection. This flag makes it do this all the time. This
is useful for debugging, because it cuts out a call to random(). Turns
out, it doesn't seem to make assign much slower. I might consider
making it the default.

Better output when the selftest (-T) fails.

uid.  A better way to deal with this would probably be a general check
for the existence of an account prior to creation.  If its there, then
delete it first.

specific notes. Also convert examples to use physical nodes in
tb-fix-node, and fix the types using in tb-set-hardware statements.

* Remove all of the code that dealt with allocating unconnected nodes.
  It used to be assign_wrapper passed all widearea node allocation
  decisions to wanassign, those in links and those that were
  unconnected. assign_wrapper now handles all unconnected nodes since
  assign is much better with features/desires and node type stuff.

* Do not modify any database state in wanassign; It used to do the
  actual nalloc calls, but now it just returns the mapping to
  assign_wrapper so that we can more easily track "recoverability" and
  because there is existing code in assign_wrapper to allocate vnodes
  on the selected pnodes. No point in duplication.

* Switch from mapping to vnodes, to mapping to pnodes. We made this
  change for other virtual nodes; instead of "fixing" to a vnode on a
  pnode, fix to the pnode. The resulting mappings are also given as
  pnodes, and assign_wrapper does the allocation on those selected
  nodes.

Now all we need is uptodate widearea data!

previous revision.

Bump maxrun for plab experiments from 1 to 2 (special case predated my
changes).

   data block" field was non-zero.  This happened with the Intel-provided
   Dell boxen and their initial Linux disk.

2. Added some more sanity checks in the Linux code.

3. Fixed a bug I just introduced where slice mode would fail on a disk
   with an extended partition.

Blew it up with the current set of 145 remote nodes. I increased the
limits and added checks so that it does not return bogus output.
Needs a pass to turn them into dynamically sized arrays, at some
point.

other than the first object name.

1) IP address based routes can now be added
   - The IP address is set on a link object
   - An "$ns rlink" is used to instantiate links
     that get cut and cross physical partitions
   - Traffic agents that are across physical
     partitions (i.e. different instances of nse)
     are connected by a new "$ns ip-connect"
     mechanism
   - A new Node instproc "add-route-to-ip" adds
     IP address based routes.
   - Changed ns multicast addressing to use 3 bits
     instead of the default 1
   - Currently, the classifier does a lookup on a
     complete 32 bit IP and if a target to route to
     is not found, uses a 24 bit IP mask. It does not
     try to match IP prefixes of all lengths. I'll add
     that later if necessary
2) NS packets that cross partitions are encapsulated in
   IPPROTO_ENCAP IP packets.
3) RAW IP sockets used to inject packets into the network
   now use a rtabid paramater so that packets can be
   routed according to different routing tables

Tested with 2 test cases, one with UDP/CBR traffic
and another with default NS TCP/FTP traffic. Setup was done
manually. As I do testbed integration, there may be more changes.
Here's the test setup:

   2.2    2.3   1.2      1.3   3.2      3.3
n0 --------- n1 ----------- n2 ------------ n3

n0,n1 are on one physical node and n2,n3 are on another. The n1-n2 link
is cut.

A TCP example:

---------------------physnode0---------------------
set ns [new Simulator]
$ns use-scheduler RealTime

set n0 [$ns node]
set n1 [$ns node]

$ns duplex-link $n0 $n1 10Mb 5ms DropTail
[$ns link $n0 $n1] set-ip 10.1.2.2
[$ns link $n1 $n0] set-ip 10.1.2.3

set rl0 [$ns rlink $n1 10.1.1.3 2Mb 40ms DropTail]
$rl0 set-ip 10.1.1.2

set tcp0 [new Agent/TCP]
# The last parameter specifies the port
$ns attach-agent $n0 $tcp0 20
$ns ip-connect $tcp0 10.1.3.3 20
set ftp0 [new Application/FTP]
$ftp0 attach-agent $tcp0

$n0 add-route-to-ip 10.1.3.3 10.1.2.3
$n1 add-route-to-ip 10.1.3.3 10.1.1.3

$ns at 1.0 "$ftp0 start"
$ns at 10.0 "$ftp0 stop"
-----------------end physnode0---------------------

---------------------physnode1---------------------
set ns [new Simulator]
$ns use-scheduler RealTime

set n2 [$ns node]
set n3 [$ns node]

$ns duplex-link $n2 $n3 10Mb 5ms DropTail
[$ns link $n2 $n3] set-ip 10.1.3.2
[$ns link $n3 $n2] set-ip 10.1.3.3

set rl1 [$ns rlink $n2 10.1.1.2 2Mb 40ms DropTail]
$rl1 set-ip 10.1.1.3

set tcpsink0 [new Agent/TCPSink]
$ns attach-agent $n3 $tcpsink0 20
$ns ip-connect $tcpsink0 10.1.2.2 20

$n3 add-route-to-ip 10.1.2.2 10.1.3.2
$n2 add-route-to-ip 10.1.2.2 10.1.1.2
-----------------end physnode1---------------------

Add install target to stick into the sbin directory.