1
1
openmpi/orte
Ralph Castain 3dbd4d9be7 Squeeeeeeze the launch message. This is the message sent to the daemons that provides all the data required for launching their local procs. In reorganizing the ODLS framework, I discovered that we were sending a significant amount of unnecessary and repeated data. This commit resolves this by:
1. taking advantage of the fact that we no longer create the launch  message via a GPR trigger. In earlier times, we had the GPR create the launch message based on a subscription. In that mode of operation, we could not guarantee the order in which the data was stored in the message - hence, we had no choice but to parse the message in a loop that checked each value against a list of possible "keys" until the corresponding value was found.

Now, however, we construct the message "by hand", so we know precisely what data is in each location in the message. Thus, we no longer need to send the character string "keys" for each data value any more. This represents a rather large savings in the message size - to give you an example, we typically would use a 30-char "key" for a 2-byte data value. As you can see, the overhead can become very large.

2. sending node-specific data only once. Again, because we used to construct the message via subscriptions that were done on a per-proc basis, the data for each node (e.g., the daemon's name, whether or not the node was oversubscribed) would be included in the data for each proc. Thus, the node-specific data was repeated for every proc.

Now that we construct the message "by hand", there is no reason to do this any more. Instead, we can insert the data for a specific node only once, and then provide the per-proc data for that node. We therefore not only save all that extra data in the message, but we also only need to parse the per-node data once.

The savings become significant at scale. Here is a comparison between the revised trunk and the trunk prior to this commit (all data was taken on odin, using openib, 64 nodes, unity message routing, tested with application consisting of mpi_init/mpi_barrier/mpi_finalize, all execution times given in seconds, all launch message sizes in bytes):

Per-node scaling, taken at 1ppn:

#nodes           original trunk                         revised trunk
             time               size                time               size
      1      0.10                819                0.09                564
      2      0.14               1070                0.14                677
      3      0.15               1321                0.14                790
      4      0.15               1572                0.15                903
      8      0.17               2576                0.20               1355
     16      0.25               4584                0.21               2259
     32      0.28               8600                0.27               4067
     64      0.50              16632                0.39               7683

Per-proc scaling, taken at 64 nodes

   ppn             original trunk                         revised trunk
              time               size                time               size
      1       0.50              16669                0.40               7720
      2       0.55              32733                0.54              11048
      3       0.87              48797                0.81              14376
      4       1.0               64861                0.85              17704


Condensing those numbers, it appears we gained:

per-node message size: 251 bytes/node -> 113 bytes/node

per-proc message size: 251 bytes/proc  -> 52 bytes/proc

per-job message size:  568 bytes/job -> 399 bytes/job 
(job-specific data such as jobid, override oversubscribe flag, total #procs in job, total slots allocated)

The fact that the two pre-commit trunk numbers are the same confirms the fact that each proc was containing the node data as well. It isn't quite the 10x message reduction I had hoped to get, but it is significant and gives much better scaling.

Note that the timing info was, as usual, pretty chaotic - the numbers cited here were typical across several runs taken after the initial one to avoid NFS file positioning influences.

Also note that this commit removes the orte_process_info.vpid_start field and the handful of places that passed that useless value. By definition, all jobs start at vpid=0, so all we were doing is passing "0" around. In fact, many places simply hardwired it to "0" anyway rather than deal with it.

This commit was SVN r16428.
2007-10-11 15:57:26 +00:00
..
class reapply r15517 and r15520, which were removed in r15527 so that I could get 2007-07-20 02:34:29 +00:00
dss Roll in the Voltaire core/socket/etc process mapping implementation. Only change I made was to cleanup some of the diagnostic output in the odls_default component so it uses the -mca odls_base_verbose parameter. 2007-07-14 15:14:07 +00:00
etc remove defunct file 2007-07-20 02:10:38 +00:00
include reapply r15517 and r15520, which were removed in r15527 so that I could get 2007-07-20 02:34:29 +00:00
mca Squeeeeeeze the launch message. This is the message sent to the daemons that provides all the data required for launching their local procs. In reorganizing the ODLS framework, I discovered that we were sending a significant amount of unnecessary and repeated data. This commit resolves this by: 2007-10-11 15:57:26 +00:00
orted We do ''not'' want the orted to yield the processor more than 2007-10-06 09:24:51 +00:00
runtime This commit contains the following: 2007-10-08 20:53:02 +00:00
test These changes were mostly captured in a prior RFC (except for #2 below) and are aimed specifically at improving startup performance and setting up the remaining modifications described in that RFC. 2007-10-05 19:48:23 +00:00
tools This commit contains the following: 2007-10-08 20:53:02 +00:00
util Squeeeeeeze the launch message. This is the message sent to the daemons that provides all the data required for launching their local procs. In reorganizing the ODLS framework, I discovered that we were sending a significant amount of unnecessary and repeated data. This commit resolves this by: 2007-10-11 15:57:26 +00:00
Doxyfile Fix the broken Doxyfile so people can generate what little code base documentation we have :-) 2006-04-13 12:52:17 +00:00
Makefile.am Bring in an updated launch system for the orteds. This commit restores the ability to execute singletons and singleton comm_spawn, both in single node and multi-node environments. 2007-07-12 19:53:18 +00:00