openmpi

db

Modify the multicast scheme so that applications have separate input and output channels to avoid cross-talk. Update the multicast test to conform.

2010-06-15 03:50:31 +00:00

debugger

Re-issue the read event so that multiple debugger attachments can occur

2010-07-15 15:35:26 +00:00

errmgr

Start reducing our dependency on the event library by removing at least one instance where we use it to redirect the program counter. Rolf reported occasional hangs of mpirun in very specific circumstances after all daemons were done. A review of MTT results indicates this may have been happening more generally in a small fraction of cases.

2010-07-17 21:03:27 +00:00

ess

Start reducing our dependency on the event library by removing at least one instance where we use it to redirect the program counter. Rolf reported occasional hangs of mpirun in very specific circumstances after all daemons were done. A review of MTT results indicates this may have been happening more generally in a small fraction of cases.

2010-07-17 21:03:27 +00:00

filem

Start reducing our dependency on the event library by removing at least one instance where we use it to redirect the program counter. Rolf reported occasional hangs of mpirun in very specific circumstances after all daemons were done. A review of MTT results indicates this may have been happening more generally in a small fraction of cases.

2010-07-17 21:03:27 +00:00

grpcomm

Start reducing our dependency on the event library by removing at least one instance where we use it to redirect the program counter. Rolf reported occasional hangs of mpirun in very specific circumstances after all daemons were done. A review of MTT results indicates this may have been happening more generally in a small fraction of cases.

2010-07-17 21:03:27 +00:00

iof

The --output-filename option currently mixes the output from all processes with the same rank, but different jobids. Thus, the output from comm_spawn'd processes gets intermingled with their parents and each other.

2010-07-12 21:43:49 +00:00

notifier

Need these header files for NetBSD. Thanks for the heads-up from

2010-07-02 17:38:57 +00:00

odls

Allow singletons to use ompi-server for rendezvous via pubsub as well as comm_spawn without starting their own local daemons

2010-07-13 06:33:07 +00:00

oob

Fix a major foopah that broke debugger attach. With the revisions in updating proc state, we dropped the recording of each proc's pid. Thus, attaching debuggers would find a proctable whose pids all equal 0.

2010-06-24 05:13:53 +00:00

plm

Start reducing our dependency on the event library by removing at least one instance where we use it to redirect the program counter. Rolf reported occasional hangs of mpirun in very specific circumstances after all daemons were done. A review of MTT results indicates this may have been happening more generally in a small fraction of cases.

2010-07-17 21:03:27 +00:00

ras

Cleanup pointer array addressing and protect against NULL

2010-07-19 18:30:04 +00:00

rmaps

Do not use nodes that are flagged as down or do-not-use for this map. Modify error output to reflect possible reasons no nodes would be available

2010-07-01 19:39:31 +00:00

rmcast

Add some new tags

2010-07-09 17:51:28 +00:00

rml

Start reducing our dependency on the event library by removing at least one instance where we use it to redirect the program counter. Rolf reported occasional hangs of mpirun in very specific circumstances after all daemons were done. A review of MTT results indicates this may have been happening more generally in a small fraction of cases.

2010-07-17 21:03:27 +00:00

routed

Start reducing our dependency on the event library by removing at least one instance where we use it to redirect the program counter. Rolf reported occasional hangs of mpirun in very specific circumstances after all daemons were done. A review of MTT results indicates this may have been happening more generally in a small fraction of cases.

2010-07-17 21:03:27 +00:00

sensor

Fix a major foopah that broke debugger attach. With the revisions in updating proc state, we dropped the recording of each proc's pid. Thus, attaching debuggers would find a proctable whose pids all equal 0.

2010-06-24 05:13:53 +00:00

snapc

add a few more missing SOS includes

2010-05-18 15:00:07 +00:00