George Bosilca e2bb4c9b8f Correct the handling of the pckt_pending list. The problem was that ...

we returned the pck before coping the values out. With this change
it seems to work at least on two architectures (even with the 
mpool size set back to 0).

This commit was SVN r20946.

2009-04-06 21:45:08 +00:00

..

allocator

- No need to declare struct mca_mpool_base_resources_t;

2009-03-12 20:27:16 +00:00

bml

- Revert r20740

2009-03-05 21:50:47 +00:00

btl

Per http://www.open-mpi.org/community/lists/announce/2009/03/0029.php

2009-04-01 17:52:16 +00:00

coll

Correctly deal with the error case. The problem is tricky: the MPI standard doesn't allow

2009-03-31 23:44:59 +00:00

common

Per http://www.open-mpi.org/community/lists/announce/2009/03/0029.php

2009-04-01 17:52:16 +00:00

crcp

We don't need the opal_bitmap definitions here.

2009-04-01 15:25:10 +00:00

dpm

- Revert r20739

2009-03-05 21:56:03 +00:00

io

- An intrusive commit yet again (sorry): with the separation we

2009-03-04 15:35:54 +00:00

mpool

Increase mpool_sm_min_size default to 64M so osu_bw will run.

2009-04-06 18:37:00 +00:00

mtl

- Last of intrusive commits (promised)... err for now.

2009-03-04 17:06:51 +00:00

op

Preparation work for another commit (after RFC):

2009-03-17 21:34:30 +00:00

osc

Preparation work for another commit (after RFC):

2009-03-17 21:34:30 +00:00

pml

Correct the handling of the pckt_pending list. The problem was that

2009-04-06 21:45:08 +00:00

pubsub

- Revert r20740

2009-03-05 21:50:47 +00:00

rcache

- An intrusive commit yet again (sorry): with the separation we

2009-03-04 15:35:54 +00:00

topo

- Get pgcc on XT to complain less:

2009-03-13 02:10:32 +00:00