88aa45dd52
There is still a problem with OpenIB and threads (external to C/R functionality). It has been reported in Ticket #1539 Additionally: * Fix a file cleanup bug in CRS Base. * Fix a possible deadlock in the TCP ft_event function * Add a mca_base_param_deregister() function to MCA base * Add whole process checkpoint timers * Add support for BTL: OpenIB, MX, Shared Memory * Add support Mpool: rdma, sm * Sundry bounds checking an cleanup in some scattered functions This commit was SVN r19756.
53 строки
1.1 KiB
Plaintext
53 строки
1.1 KiB
Plaintext
#
|
|
# An Aggregate MCA Parameter Set to enable checkpoint/restart capabilities
|
|
# for a job.
|
|
#
|
|
# Usage:
|
|
# shell$ mpirun -am ft-enable-cr ./app
|
|
#
|
|
|
|
#
|
|
# OPAL Parameters
|
|
# - Turn off OPAL only checkpointing
|
|
# - Select only checkpoint ready components
|
|
# - Enable Additional FT infrastructure
|
|
# - Auto-select OPAL CRS component
|
|
# - If available, use the FT Thread (Default)
|
|
#
|
|
opal_cr_allow_opal_only=0
|
|
mca_base_component_distill_checkpoint_ready=1
|
|
ft_cr_enabled=1
|
|
crs=
|
|
opal_cr_use_thread=1
|
|
|
|
#
|
|
# ORTE Parameters
|
|
# - Wrap the RML
|
|
# - Use the 'full' Snapshot Coordinator
|
|
#
|
|
rml_wrapper=ftrm
|
|
snapc=full
|
|
#filem=rsh
|
|
|
|
#
|
|
# OMPI Parameters
|
|
# - Wrap the PML
|
|
# - Use a Bookmark Exchange Fully Coordinated Checkpoint/Restart Coordination Protocol
|
|
#
|
|
pml_wrapper=crcpw
|
|
crcp=bkmrk
|
|
|
|
#
|
|
# Temporary fix to force the event engine to use poll to behave well with BLCR
|
|
#
|
|
opal_event_include=poll
|
|
|
|
#
|
|
# We currently only support the following options to the OpenIB BTL
|
|
# Future development will attempt to eliminate many of these restrictions
|
|
#
|
|
btl_openib_want_fork_support=1
|
|
btl_openib_use_async_event_thread=0
|
|
btl_openib_use_eager_rdma=0
|
|
btl_openib_cpc_include=oob
|