2007-03-17 02:11:45 +03:00
|
|
|
/*
|
2010-03-13 02:57:50 +03:00
|
|
|
* Copyright (c) 2004-2010 The Trustees of Indiana University and Indiana
|
2007-03-17 02:11:45 +03:00
|
|
|
* University Research and Technology
|
|
|
|
|
* Corporation. All rights reserved.
|
|
|
|
|
* Copyright (c) 2004-2005 The University of Tennessee and The University
|
|
|
|
|
* of Tennessee Research Foundation. All rights
|
|
|
|
|
* reserved.
|
|
|
|
|
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
|
|
|
|
* University of Stuttgart. All rights reserved.
|
|
|
|
|
* Copyright (c) 2004-2005 The Regents of the University of California.
|
|
|
|
|
* All rights reserved.
|
|
|
|
|
* $COPYRIGHT$
|
|
|
|
|
*
|
|
|
|
|
* Additional copyrights may follow
|
|
|
|
|
*
|
|
|
|
|
* $HEADER$
|
|
|
|
|
*/
|
|
|
|
|
/**
|
|
|
|
|
* @file
|
|
|
|
|
*
|
|
|
|
|
* Checkpoint/Restart Coordination Protocol (CRCP) Interface
|
|
|
|
|
*
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef MCA_CRCP_H
|
|
|
|
|
#define MCA_CRCP_H
|
|
|
|
|
|
|
|
|
|
#include "ompi_config.h"
|
|
|
|
|
|
|
|
|
|
#include "opal/mca/mca.h"
|
|
|
|
|
#include "opal/mca/base/base.h"
|
|
|
|
|
#include "opal/mca/crs/crs.h"
|
|
|
|
|
#include "opal/mca/crs/base/base.h"
|
|
|
|
|
|
|
|
|
|
#include "opal/class/opal_object.h"
|
|
|
|
|
|
- Split the datatype engine into two parts: an MPI specific part in
OMPI
and a language agnostic part in OPAL. The convertor is completely
moved into OPAL. This offers several benefits as described in RFC
http://www.open-mpi.org/community/lists/devel/2009/07/6387.php
namely:
- Fewer basic types (int* and float* types, boolean and wchar
- Fixing naming scheme to ompi-nomenclature.
- Usability outside of the ompi-layer.
- Due to the fixed nature of simple opal types, their information is
completely
known at compile time and therefore constified
- With fewer datatypes (22), the actual sizes of bit-field types may be
reduced
from 64 to 32 bits, allowing reorganizing the opal_datatype
structure, eliminating holes and keeping data required in convertor
(upon send/recv) in one cacheline...
This has implications to the convertor-datastructure and other parts
of the code.
- Several performance tests have been run, the netpipe latency does not
change with
this patch on Linux/x86-64 on the smoky cluster.
- Extensive tests have been done to verify correctness (no new
regressions) using:
1. mpi_test_suite on linux/x86-64 using clean ompi-trunk and
ompi-ddt:
a. running both trunk and ompi-ddt resulted in no differences
(except for MPI_SHORT_INT and MPI_TYPE_MIX_LB_UB do now run
correctly).
b. with --enable-memchecker and running under valgrind (one buglet
when run with static found in test-suite, commited)
2. ibm testsuite on linux/x86-64 using clean ompi-trunk and ompi-ddt:
all passed (except for the dynamic/ tests failed!! as trunk/MTT)
3. compilation and usage of HDF5 tests on Jaguar using PGI and
PathScale compilers.
4. compilation and usage on Scicortex.
- Please note, that for the heterogeneous case, (-m32 compiled
binaries/ompi), neither
ompi-trunk, nor ompi-ddt branch would successfully launch.
This commit was SVN r21641.
2009-07-13 08:56:31 +04:00
|
|
|
#include "ompi/datatype/ompi_datatype.h"
|
2007-03-17 02:11:45 +03:00
|
|
|
#include "ompi/request/request.h"
|
|
|
|
|
|
|
|
|
|
#include "ompi/class/ompi_free_list.h"
|
|
|
|
|
|
|
|
|
|
#include "ompi/mca/pml/pml.h"
|
|
|
|
|
#include "ompi/mca/pml/base/base.h"
|
|
|
|
|
|
|
|
|
|
#include "ompi/mca/btl/btl.h"
|
|
|
|
|
#include "ompi/mca/btl/base/base.h"
|
|
|
|
|
|
2009-08-20 15:42:18 +04:00
|
|
|
BEGIN_C_DECLS
|
2007-03-20 17:12:13 +03:00
|
|
|
|
2007-03-17 02:11:45 +03:00
|
|
|
/**
|
|
|
|
|
* Module initialization function.
|
|
|
|
|
* Returns OMPI_SUCCESS
|
|
|
|
|
*/
|
|
|
|
|
typedef int (*ompi_crcp_base_module_init_fn_t)
|
|
|
|
|
(void);
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Module finalization function.
|
|
|
|
|
* Returns OMPI_SUCCESS
|
|
|
|
|
*/
|
|
|
|
|
typedef int (*ompi_crcp_base_module_finalize_fn_t)
|
|
|
|
|
(void);
|
|
|
|
|
|
A number of C/R enhancements per RFC below:
http://www.open-mpi.org/community/lists/devel/2010/07/8240.php
Documentation:
http://osl.iu.edu/research/ft/
Major Changes:
--------------
* Added C/R-enabled Debugging support.
Enabled with the --enable-crdebug flag. See the following website for more information:
http://osl.iu.edu/research/ft/crdebug/
* Added Stable Storage (SStore) framework for checkpoint storage
* 'central' component does a direct to central storage save
* 'stage' component stages checkpoints to central storage while the application continues execution.
* 'stage' supports offline compression of checkpoints before moving (sstore_stage_compress)
* 'stage' supports local caching of checkpoints to improve automatic recovery (sstore_stage_caching)
* Added Compression (compress) framework to support
* Add two new ErrMgr recovery policies
* {{{crmig}}} C/R Process Migration
* {{{autor}}} C/R Automatic Recovery
* Added the {{{ompi-migrate}}} command line tool to support the {{{crmig}}} ErrMgr component
* Added CR MPI Ext functions (enable them with {{{--enable-mpi-ext=cr}}} configure option)
* {{{OMPI_CR_Checkpoint}}} (Fixes trac:2342)
* {{{OMPI_CR_Restart}}}
* {{{OMPI_CR_Migrate}}} (may need some more work for mapping rules)
* {{{OMPI_CR_INC_register_callback}}} (Fixes trac:2192)
* {{{OMPI_CR_Quiesce_start}}}
* {{{OMPI_CR_Quiesce_checkpoint}}}
* {{{OMPI_CR_Quiesce_end}}}
* {{{OMPI_CR_self_register_checkpoint_callback}}}
* {{{OMPI_CR_self_register_restart_callback}}}
* {{{OMPI_CR_self_register_continue_callback}}}
* The ErrMgr predicted_fault() interface has been changed to take an opal_list_t of ErrMgr defined types. This will allow us to better support a wider range of fault prediction services in the future.
* Add a progress meter to:
* FileM rsh (filem_rsh_process_meter)
* SnapC full (snapc_full_progress_meter)
* SStore stage (sstore_stage_progress_meter)
* Added 2 new command line options to ompi-restart
* --showme : Display the full command line that would have been exec'ed.
* --mpirun_opts : Command line options to pass directly to mpirun. (Fixes trac:2413)
* Deprecated some MCA params:
* crs_base_snapshot_dir deprecated, use sstore_stage_local_snapshot_dir
* snapc_base_global_snapshot_dir deprecated, use sstore_base_global_snapshot_dir
* snapc_base_global_shared deprecated, use sstore_stage_global_is_shared
* snapc_base_store_in_place deprecated, replaced with different components of SStore
* snapc_base_global_snapshot_ref deprecated, use sstore_base_global_snapshot_ref
* snapc_base_establish_global_snapshot_dir deprecated, never well supported
* snapc_full_skip_filem deprecated, use sstore_stage_skip_filem
Minor Changes:
--------------
* Fixes trac:1924 : {{{ompi-restart}}} now recognizes path prefixed checkpoint handles and does the right thing.
* Fixes trac:2097 : {{{ompi-info}}} should now report all available CRS components
* Fixes trac:2161 : Manual checkpoint movement. A user can 'mv' a checkpoint directory from the original location to another and still restart from it.
* Fixes trac:2208 : Honor various TMPDIR varaibles instead of forcing {{{/tmp}}}
* Move {{{ompi_cr_continue_like_restart}}} to {{{orte_cr_continue_like_restart}}} to be more flexible in where this should be set.
* opal_crs_base_metadata_write* functions have been moved to SStore to support a wider range of metadata handling functionality.
* Cleanup the CRS framework and components to work with the SStore framework.
* Cleanup the SnapC framework and components to work with the SStore framework (cleans up these code paths considerably).
* Add 'quiesce' hook to CRCP for a future enhancement.
* We now require a BLCR version that supports {{{cr_request_file()}}} or {{{cr_request_checkpoint()}}} in order to make the code more maintainable. Note that {{{cr_request_file}}} has been deprecated since 0.7.0, so we prefer to use {{{cr_request_checkpoint()}}}.
* Add optional application level INC callbacks (registered through the CR MPI Ext interface).
* Increase the {{{opal_cr_thread_sleep_wait}}} parameter to 1000 microseconds to make the C/R thread less aggressive.
* {{{opal-restart}}} now looks for cache directories before falling back on stable storage when asked.
* {{{opal-restart}}} also support local decompression before restarting
* {{{orte-checkpoint}}} now uses the SStore framework to work with the metadata
* {{{orte-restart}}} now uses the SStore framework to work with the metadata
* Remove the {{{orte-restart}}} preload option. This was removed since the user only needs to select the 'stage' component in order to support this functionality.
* Since the '-am' parameter is saved in the metadata, {{{ompi-restart}}} no longer hard codes {{{-am ft-enable-cr}}}.
* Fix {{{hnp}}} ErrMgr so that if a previous component in the stack has 'fixed' the problem, then it should be skipped.
* Make sure to decrement the number of 'num_local_procs' in the orted when one goes away.
* odls now checks the SStore framework to see if it needs to load any checkpoint files before launching (to support 'stage'). This separates the SStore logic from the --preload-[binary|files] options.
* Add unique IDs to the named pipes established between the orted and the app in SnapC. This is to better support migration and automatic recovery activities.
* Improve the checks for 'already checkpointing' error path.
* A a recovery output timer, to show how long it takes to restart a job
* Do a better job of cleaning up the old session directory on restart.
* Add a local module to the autor and crmig ErrMgr components. These small modules prevent the 'orted' component from attempting a local recovery (Which does not work for MPI apps at the moment)
* Add a fix for bounding the checkpointable region between MPI_Init and MPI_Finalize.
This commit was SVN r23587.
The following Trac tickets were found above:
Ticket 1924 --> https://svn.open-mpi.org/trac/ompi/ticket/1924
Ticket 2097 --> https://svn.open-mpi.org/trac/ompi/ticket/2097
Ticket 2161 --> https://svn.open-mpi.org/trac/ompi/ticket/2161
Ticket 2192 --> https://svn.open-mpi.org/trac/ompi/ticket/2192
Ticket 2208 --> https://svn.open-mpi.org/trac/ompi/ticket/2208
Ticket 2342 --> https://svn.open-mpi.org/trac/ompi/ticket/2342
Ticket 2413 --> https://svn.open-mpi.org/trac/ompi/ticket/2413
2010-08-11 00:51:11 +04:00
|
|
|
|
|
|
|
|
/************************
|
|
|
|
|
* MPI Quiesce Interface
|
|
|
|
|
************************/
|
|
|
|
|
/**
|
|
|
|
|
* MPI_Quiesce_start component interface
|
|
|
|
|
*/
|
|
|
|
|
typedef int (*ompi_crcp_base_quiesce_start_fn_t)
|
|
|
|
|
(MPI_Info *info);
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* MPI_Quiesce_end component interface
|
|
|
|
|
*/
|
|
|
|
|
typedef int (*ompi_crcp_base_quiesce_end_fn_t)
|
|
|
|
|
(MPI_Info *info);
|
|
|
|
|
|
|
|
|
|
|
2007-03-17 02:11:45 +03:00
|
|
|
/************************
|
|
|
|
|
* PML Wrapper hooks
|
|
|
|
|
* PML Wrapper is the CRCPW PML component
|
|
|
|
|
************************/
|
|
|
|
|
/**
|
|
|
|
|
* To allow us to work before and after a PML command
|
|
|
|
|
*/
|
|
|
|
|
enum ompi_crcp_base_pml_states_t {
|
|
|
|
|
OMPI_CRCP_PML_PRE,
|
|
|
|
|
OMPI_CRCP_PML_POST,
|
|
|
|
|
OMPI_CRCP_PML_SKIP,
|
|
|
|
|
OMPI_CRCP_PML_DONE
|
|
|
|
|
};
|
|
|
|
|
typedef enum ompi_crcp_base_pml_states_t ompi_crcp_base_pml_states_t;
|
|
|
|
|
|
2008-12-10 18:38:12 +03:00
|
|
|
struct ompi_crcp_base_pml_state_t {
|
2007-03-17 02:11:45 +03:00
|
|
|
ompi_free_list_item_t super;
|
|
|
|
|
ompi_crcp_base_pml_states_t state;
|
|
|
|
|
int error_code;
|
|
|
|
|
mca_pml_base_component_t *wrapped_pml_component;
|
|
|
|
|
mca_pml_base_module_t *wrapped_pml_module;
|
|
|
|
|
};
|
|
|
|
|
typedef struct ompi_crcp_base_pml_state_t ompi_crcp_base_pml_state_t;
|
2008-03-05 07:57:23 +03:00
|
|
|
OMPI_DECLSPEC OBJ_CLASS_DECLARATION(ompi_crcp_base_pml_state_t);
|
2007-03-17 02:11:45 +03:00
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_enable_fn_t)
|
|
|
|
|
(bool enable, ompi_crcp_base_pml_state_t* );
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_add_comm_fn_t)
|
|
|
|
|
( struct ompi_communicator_t* comm , ompi_crcp_base_pml_state_t*);
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_del_comm_fn_t)
|
|
|
|
|
( struct ompi_communicator_t* comm , ompi_crcp_base_pml_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_add_procs_fn_t)
|
|
|
|
|
( struct ompi_proc_t **procs, size_t nprocs , ompi_crcp_base_pml_state_t*);
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_del_procs_fn_t)
|
|
|
|
|
( struct ompi_proc_t **procs, size_t nprocs , ompi_crcp_base_pml_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_progress_fn_t)
|
|
|
|
|
(ompi_crcp_base_pml_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_iprobe_fn_t)
|
|
|
|
|
(int dst, int tag, struct ompi_communicator_t* comm, int *matched,
|
|
|
|
|
ompi_status_public_t* status, ompi_crcp_base_pml_state_t* );
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_probe_fn_t)
|
|
|
|
|
( int dst, int tag, struct ompi_communicator_t* comm,
|
|
|
|
|
ompi_status_public_t* status, ompi_crcp_base_pml_state_t* );
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_isend_init_fn_t)
|
|
|
|
|
( void *buf, size_t count, ompi_datatype_t *datatype, int dst, int tag,
|
|
|
|
|
mca_pml_base_send_mode_t mode, struct ompi_communicator_t* comm,
|
|
|
|
|
struct ompi_request_t **request, ompi_crcp_base_pml_state_t* );
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_isend_fn_t)
|
|
|
|
|
( void *buf, size_t count, ompi_datatype_t *datatype, int dst, int tag,
|
|
|
|
|
mca_pml_base_send_mode_t mode, struct ompi_communicator_t* comm,
|
|
|
|
|
struct ompi_request_t **request, ompi_crcp_base_pml_state_t* );
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_send_fn_t)
|
|
|
|
|
( void *buf, size_t count, ompi_datatype_t *datatype, int dst, int tag,
|
|
|
|
|
mca_pml_base_send_mode_t mode, struct ompi_communicator_t* comm,
|
|
|
|
|
ompi_crcp_base_pml_state_t* );
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_irecv_init_fn_t)
|
|
|
|
|
( void *buf, size_t count, ompi_datatype_t *datatype, int src, int tag,
|
|
|
|
|
struct ompi_communicator_t* comm, struct ompi_request_t **request,
|
|
|
|
|
ompi_crcp_base_pml_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_irecv_fn_t)
|
|
|
|
|
( void *buf, size_t count, ompi_datatype_t *datatype, int src, int tag,
|
|
|
|
|
struct ompi_communicator_t* comm, struct ompi_request_t **request,
|
|
|
|
|
ompi_crcp_base_pml_state_t* );
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_recv_fn_t)
|
|
|
|
|
( void *buf, size_t count, ompi_datatype_t *datatype, int src, int tag,
|
|
|
|
|
struct ompi_communicator_t* comm, ompi_status_public_t* status,
|
|
|
|
|
ompi_crcp_base_pml_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_dump_fn_t)
|
|
|
|
|
( struct ompi_communicator_t* comm, int verbose, ompi_crcp_base_pml_state_t* );
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_start_fn_t)
|
|
|
|
|
( size_t count, ompi_request_t** requests, ompi_crcp_base_pml_state_t* );
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_pml_state_t* (*ompi_crcp_base_pml_ft_event_fn_t)
|
|
|
|
|
(int state, ompi_crcp_base_pml_state_t*);
|
|
|
|
|
|
|
|
|
|
/* Request Interface */
|
|
|
|
|
typedef int (*ompi_crcp_base_request_complete_fn_t)
|
|
|
|
|
(struct ompi_request_t *request);
|
|
|
|
|
|
|
|
|
|
/************************
|
|
|
|
|
* BTL Wrapper hooks
|
|
|
|
|
* JJH: Wrapper BTL not currently implemented.
|
|
|
|
|
************************/
|
|
|
|
|
/**
|
|
|
|
|
* To allow us to work before and after a BTL command
|
|
|
|
|
*/
|
|
|
|
|
enum ompi_crcp_base_btl_states_t {
|
|
|
|
|
OMPI_CRCP_BTL_PRE,
|
|
|
|
|
OMPI_CRCP_BTL_POST,
|
|
|
|
|
OMPI_CRCP_BTL_SKIP,
|
|
|
|
|
OMPI_CRCP_BTL_DONE
|
|
|
|
|
};
|
|
|
|
|
typedef enum ompi_crcp_base_btl_states_t ompi_crcp_base_btl_states_t;
|
|
|
|
|
|
|
|
|
|
struct ompi_crcp_base_btl_state_t {
|
|
|
|
|
ompi_free_list_item_t super;
|
|
|
|
|
ompi_crcp_base_btl_states_t state;
|
|
|
|
|
int error_code;
|
|
|
|
|
mca_btl_base_descriptor_t* des;
|
|
|
|
|
mca_btl_base_component_t *wrapped_btl_component;
|
|
|
|
|
mca_btl_base_module_t *wrapped_btl_module;
|
|
|
|
|
};
|
|
|
|
|
typedef struct ompi_crcp_base_btl_state_t ompi_crcp_base_btl_state_t;
|
|
|
|
|
OBJ_CLASS_DECLARATION(ompi_crcp_base_btl_state_t);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_add_procs_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
size_t nprocs,
|
|
|
|
|
struct ompi_proc_t** procs,
|
|
|
|
|
struct mca_btl_base_endpoint_t** endpoints,
|
2009-03-04 01:25:13 +03:00
|
|
|
struct opal_bitmap_t* reachable,
|
2007-03-17 02:11:45 +03:00
|
|
|
ompi_crcp_base_btl_state_t* );
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_del_procs_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
size_t nprocs,
|
|
|
|
|
struct ompi_proc_t** procs,
|
|
|
|
|
struct mca_btl_base_endpoint_t**,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_register_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
mca_btl_base_tag_t tag,
|
|
|
|
|
mca_btl_base_module_recv_cb_fn_t cbfunc,
|
|
|
|
|
void* cbdata,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_finalize_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_alloc_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
size_t size,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_free_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
mca_btl_base_descriptor_t* descriptor,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_prepare_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
struct mca_btl_base_endpoint_t* endpoint,
|
|
|
|
|
mca_mpool_base_registration_t* registration,
|
- Split the datatype engine into two parts: an MPI specific part in
OMPI
and a language agnostic part in OPAL. The convertor is completely
moved into OPAL. This offers several benefits as described in RFC
http://www.open-mpi.org/community/lists/devel/2009/07/6387.php
namely:
- Fewer basic types (int* and float* types, boolean and wchar
- Fixing naming scheme to ompi-nomenclature.
- Usability outside of the ompi-layer.
- Due to the fixed nature of simple opal types, their information is
completely
known at compile time and therefore constified
- With fewer datatypes (22), the actual sizes of bit-field types may be
reduced
from 64 to 32 bits, allowing reorganizing the opal_datatype
structure, eliminating holes and keeping data required in convertor
(upon send/recv) in one cacheline...
This has implications to the convertor-datastructure and other parts
of the code.
- Several performance tests have been run, the netpipe latency does not
change with
this patch on Linux/x86-64 on the smoky cluster.
- Extensive tests have been done to verify correctness (no new
regressions) using:
1. mpi_test_suite on linux/x86-64 using clean ompi-trunk and
ompi-ddt:
a. running both trunk and ompi-ddt resulted in no differences
(except for MPI_SHORT_INT and MPI_TYPE_MIX_LB_UB do now run
correctly).
b. with --enable-memchecker and running under valgrind (one buglet
when run with static found in test-suite, commited)
2. ibm testsuite on linux/x86-64 using clean ompi-trunk and ompi-ddt:
all passed (except for the dynamic/ tests failed!! as trunk/MTT)
3. compilation and usage of HDF5 tests on Jaguar using PGI and
PathScale compilers.
4. compilation and usage on Scicortex.
- Please note, that for the heterogeneous case, (-m32 compiled
binaries/ompi), neither
ompi-trunk, nor ompi-ddt branch would successfully launch.
This commit was SVN r21641.
2009-07-13 08:56:31 +04:00
|
|
|
struct opal_convertor_t* convertor,
|
2007-03-17 02:11:45 +03:00
|
|
|
size_t reserve,
|
|
|
|
|
size_t* size,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_send_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
struct mca_btl_base_endpoint_t* endpoint,
|
|
|
|
|
struct mca_btl_base_descriptor_t* descriptor,
|
|
|
|
|
mca_btl_base_tag_t tag,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_put_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
struct mca_btl_base_endpoint_t* endpoint,
|
|
|
|
|
struct mca_btl_base_descriptor_t* descriptor,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_get_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
struct mca_btl_base_endpoint_t* endpoint,
|
|
|
|
|
struct mca_btl_base_descriptor_t* descriptor,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_dump_fn_t)
|
|
|
|
|
( struct mca_btl_base_module_t* btl,
|
|
|
|
|
struct mca_btl_base_endpoint_t* endpoint,
|
|
|
|
|
int verbose,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
typedef ompi_crcp_base_btl_state_t* (*mca_crcp_base_btl_module_ft_event_fn_t)
|
|
|
|
|
(int state,
|
|
|
|
|
ompi_crcp_base_btl_state_t*);
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
2008-07-29 02:40:57 +04:00
|
|
|
* Structure for CRCP components.
|
2007-03-17 02:11:45 +03:00
|
|
|
*/
|
2008-07-29 02:40:57 +04:00
|
|
|
struct ompi_crcp_base_component_2_0_0_t {
|
2007-03-17 02:11:45 +03:00
|
|
|
/** MCA base component */
|
2008-05-06 22:08:45 +04:00
|
|
|
mca_base_component_t base_version;
|
2007-03-17 02:11:45 +03:00
|
|
|
/** MCA base data */
|
2008-07-29 02:40:57 +04:00
|
|
|
mca_base_component_data_t base_data;
|
2007-03-17 02:11:45 +03:00
|
|
|
|
|
|
|
|
/** Verbosity Level */
|
|
|
|
|
int verbose;
|
2008-06-09 18:53:58 +04:00
|
|
|
/** Output Handle for opal_output */
|
2007-03-17 02:11:45 +03:00
|
|
|
int output_handle;
|
|
|
|
|
/** Default Priority */
|
|
|
|
|
int priority;
|
|
|
|
|
|
|
|
|
|
};
|
2008-07-29 02:40:57 +04:00
|
|
|
typedef struct ompi_crcp_base_component_2_0_0_t ompi_crcp_base_component_2_0_0_t;
|
|
|
|
|
typedef struct ompi_crcp_base_component_2_0_0_t ompi_crcp_base_component_t;
|
2007-03-17 02:11:45 +03:00
|
|
|
|
|
|
|
|
/**
|
2008-07-29 02:40:57 +04:00
|
|
|
* Structure for CRCP modules
|
2007-03-17 02:11:45 +03:00
|
|
|
*/
|
|
|
|
|
struct ompi_crcp_base_module_1_0_0_t {
|
|
|
|
|
/** Initialization Function */
|
|
|
|
|
ompi_crcp_base_module_init_fn_t crcp_init;
|
|
|
|
|
/** Finalization Function */
|
|
|
|
|
ompi_crcp_base_module_finalize_fn_t crcp_finalize;
|
|
|
|
|
|
A number of C/R enhancements per RFC below:
http://www.open-mpi.org/community/lists/devel/2010/07/8240.php
Documentation:
http://osl.iu.edu/research/ft/
Major Changes:
--------------
* Added C/R-enabled Debugging support.
Enabled with the --enable-crdebug flag. See the following website for more information:
http://osl.iu.edu/research/ft/crdebug/
* Added Stable Storage (SStore) framework for checkpoint storage
* 'central' component does a direct to central storage save
* 'stage' component stages checkpoints to central storage while the application continues execution.
* 'stage' supports offline compression of checkpoints before moving (sstore_stage_compress)
* 'stage' supports local caching of checkpoints to improve automatic recovery (sstore_stage_caching)
* Added Compression (compress) framework to support
* Add two new ErrMgr recovery policies
* {{{crmig}}} C/R Process Migration
* {{{autor}}} C/R Automatic Recovery
* Added the {{{ompi-migrate}}} command line tool to support the {{{crmig}}} ErrMgr component
* Added CR MPI Ext functions (enable them with {{{--enable-mpi-ext=cr}}} configure option)
* {{{OMPI_CR_Checkpoint}}} (Fixes trac:2342)
* {{{OMPI_CR_Restart}}}
* {{{OMPI_CR_Migrate}}} (may need some more work for mapping rules)
* {{{OMPI_CR_INC_register_callback}}} (Fixes trac:2192)
* {{{OMPI_CR_Quiesce_start}}}
* {{{OMPI_CR_Quiesce_checkpoint}}}
* {{{OMPI_CR_Quiesce_end}}}
* {{{OMPI_CR_self_register_checkpoint_callback}}}
* {{{OMPI_CR_self_register_restart_callback}}}
* {{{OMPI_CR_self_register_continue_callback}}}
* The ErrMgr predicted_fault() interface has been changed to take an opal_list_t of ErrMgr defined types. This will allow us to better support a wider range of fault prediction services in the future.
* Add a progress meter to:
* FileM rsh (filem_rsh_process_meter)
* SnapC full (snapc_full_progress_meter)
* SStore stage (sstore_stage_progress_meter)
* Added 2 new command line options to ompi-restart
* --showme : Display the full command line that would have been exec'ed.
* --mpirun_opts : Command line options to pass directly to mpirun. (Fixes trac:2413)
* Deprecated some MCA params:
* crs_base_snapshot_dir deprecated, use sstore_stage_local_snapshot_dir
* snapc_base_global_snapshot_dir deprecated, use sstore_base_global_snapshot_dir
* snapc_base_global_shared deprecated, use sstore_stage_global_is_shared
* snapc_base_store_in_place deprecated, replaced with different components of SStore
* snapc_base_global_snapshot_ref deprecated, use sstore_base_global_snapshot_ref
* snapc_base_establish_global_snapshot_dir deprecated, never well supported
* snapc_full_skip_filem deprecated, use sstore_stage_skip_filem
Minor Changes:
--------------
* Fixes trac:1924 : {{{ompi-restart}}} now recognizes path prefixed checkpoint handles and does the right thing.
* Fixes trac:2097 : {{{ompi-info}}} should now report all available CRS components
* Fixes trac:2161 : Manual checkpoint movement. A user can 'mv' a checkpoint directory from the original location to another and still restart from it.
* Fixes trac:2208 : Honor various TMPDIR varaibles instead of forcing {{{/tmp}}}
* Move {{{ompi_cr_continue_like_restart}}} to {{{orte_cr_continue_like_restart}}} to be more flexible in where this should be set.
* opal_crs_base_metadata_write* functions have been moved to SStore to support a wider range of metadata handling functionality.
* Cleanup the CRS framework and components to work with the SStore framework.
* Cleanup the SnapC framework and components to work with the SStore framework (cleans up these code paths considerably).
* Add 'quiesce' hook to CRCP for a future enhancement.
* We now require a BLCR version that supports {{{cr_request_file()}}} or {{{cr_request_checkpoint()}}} in order to make the code more maintainable. Note that {{{cr_request_file}}} has been deprecated since 0.7.0, so we prefer to use {{{cr_request_checkpoint()}}}.
* Add optional application level INC callbacks (registered through the CR MPI Ext interface).
* Increase the {{{opal_cr_thread_sleep_wait}}} parameter to 1000 microseconds to make the C/R thread less aggressive.
* {{{opal-restart}}} now looks for cache directories before falling back on stable storage when asked.
* {{{opal-restart}}} also support local decompression before restarting
* {{{orte-checkpoint}}} now uses the SStore framework to work with the metadata
* {{{orte-restart}}} now uses the SStore framework to work with the metadata
* Remove the {{{orte-restart}}} preload option. This was removed since the user only needs to select the 'stage' component in order to support this functionality.
* Since the '-am' parameter is saved in the metadata, {{{ompi-restart}}} no longer hard codes {{{-am ft-enable-cr}}}.
* Fix {{{hnp}}} ErrMgr so that if a previous component in the stack has 'fixed' the problem, then it should be skipped.
* Make sure to decrement the number of 'num_local_procs' in the orted when one goes away.
* odls now checks the SStore framework to see if it needs to load any checkpoint files before launching (to support 'stage'). This separates the SStore logic from the --preload-[binary|files] options.
* Add unique IDs to the named pipes established between the orted and the app in SnapC. This is to better support migration and automatic recovery activities.
* Improve the checks for 'already checkpointing' error path.
* A a recovery output timer, to show how long it takes to restart a job
* Do a better job of cleaning up the old session directory on restart.
* Add a local module to the autor and crmig ErrMgr components. These small modules prevent the 'orted' component from attempting a local recovery (Which does not work for MPI apps at the moment)
* Add a fix for bounding the checkpointable region between MPI_Init and MPI_Finalize.
This commit was SVN r23587.
The following Trac tickets were found above:
Ticket 1924 --> https://svn.open-mpi.org/trac/ompi/ticket/1924
Ticket 2097 --> https://svn.open-mpi.org/trac/ompi/ticket/2097
Ticket 2161 --> https://svn.open-mpi.org/trac/ompi/ticket/2161
Ticket 2192 --> https://svn.open-mpi.org/trac/ompi/ticket/2192
Ticket 2208 --> https://svn.open-mpi.org/trac/ompi/ticket/2208
Ticket 2342 --> https://svn.open-mpi.org/trac/ompi/ticket/2342
Ticket 2413 --> https://svn.open-mpi.org/trac/ompi/ticket/2413
2010-08-11 00:51:11 +04:00
|
|
|
/**< MPI_Quiesce Interface Functions ******************/
|
|
|
|
|
ompi_crcp_base_quiesce_start_fn_t quiesce_start;
|
|
|
|
|
ompi_crcp_base_quiesce_end_fn_t quiesce_end;
|
|
|
|
|
|
2007-03-17 02:11:45 +03:00
|
|
|
/**< PML Wrapper Functions ****************************/
|
|
|
|
|
ompi_crcp_base_pml_enable_fn_t pml_enable;
|
|
|
|
|
|
|
|
|
|
ompi_crcp_base_pml_add_comm_fn_t pml_add_comm;
|
|
|
|
|
ompi_crcp_base_pml_del_comm_fn_t pml_del_comm;
|
|
|
|
|
|
|
|
|
|
ompi_crcp_base_pml_add_procs_fn_t pml_add_procs;
|
|
|
|
|
ompi_crcp_base_pml_del_procs_fn_t pml_del_procs;
|
|
|
|
|
|
|
|
|
|
ompi_crcp_base_pml_progress_fn_t pml_progress;
|
|
|
|
|
|
|
|
|
|
ompi_crcp_base_pml_iprobe_fn_t pml_iprobe;
|
|
|
|
|
ompi_crcp_base_pml_probe_fn_t pml_probe;
|
|
|
|
|
|
|
|
|
|
ompi_crcp_base_pml_isend_init_fn_t pml_isend_init;
|
|
|
|
|
ompi_crcp_base_pml_isend_fn_t pml_isend;
|
|
|
|
|
ompi_crcp_base_pml_send_fn_t pml_send;
|
|
|
|
|
|
|
|
|
|
ompi_crcp_base_pml_irecv_init_fn_t pml_irecv_init;
|
|
|
|
|
ompi_crcp_base_pml_irecv_fn_t pml_irecv;
|
|
|
|
|
ompi_crcp_base_pml_recv_fn_t pml_recv;
|
|
|
|
|
|
|
|
|
|
ompi_crcp_base_pml_dump_fn_t pml_dump;
|
|
|
|
|
ompi_crcp_base_pml_start_fn_t pml_start;
|
|
|
|
|
|
|
|
|
|
ompi_crcp_base_pml_ft_event_fn_t pml_ft_event;
|
|
|
|
|
|
|
|
|
|
/**< Request complete Function ****************************/
|
|
|
|
|
ompi_crcp_base_request_complete_fn_t request_complete;
|
|
|
|
|
|
|
|
|
|
/**< BTL Wrapper Functions ****************************/
|
|
|
|
|
mca_crcp_base_btl_module_add_procs_fn_t btl_add_procs;
|
|
|
|
|
mca_crcp_base_btl_module_del_procs_fn_t btl_del_procs;
|
|
|
|
|
|
|
|
|
|
mca_crcp_base_btl_module_register_fn_t btl_register;
|
|
|
|
|
mca_crcp_base_btl_module_finalize_fn_t btl_finalize;
|
|
|
|
|
|
|
|
|
|
mca_crcp_base_btl_module_alloc_fn_t btl_alloc;
|
|
|
|
|
mca_crcp_base_btl_module_free_fn_t btl_free;
|
|
|
|
|
|
|
|
|
|
mca_crcp_base_btl_module_prepare_fn_t btl_prepare_src;
|
|
|
|
|
mca_crcp_base_btl_module_prepare_fn_t btl_prepare_dst;
|
|
|
|
|
|
|
|
|
|
mca_crcp_base_btl_module_send_fn_t btl_send;
|
|
|
|
|
mca_crcp_base_btl_module_put_fn_t btl_put;
|
|
|
|
|
mca_crcp_base_btl_module_get_fn_t btl_get;
|
|
|
|
|
|
|
|
|
|
mca_crcp_base_btl_module_dump_fn_t btl_dump;
|
|
|
|
|
|
|
|
|
|
mca_crcp_base_btl_module_ft_event_fn_t btl_ft_event;
|
|
|
|
|
};
|
|
|
|
|
typedef struct ompi_crcp_base_module_1_0_0_t ompi_crcp_base_module_1_0_0_t;
|
|
|
|
|
typedef struct ompi_crcp_base_module_1_0_0_t ompi_crcp_base_module_t;
|
|
|
|
|
|
|
|
|
|
OMPI_DECLSPEC extern ompi_crcp_base_module_t ompi_crcp;
|
|
|
|
|
|
|
|
|
|
/**
|
2008-07-29 02:40:57 +04:00
|
|
|
* Macro for use in components that are of type CRCP
|
2007-03-17 02:11:45 +03:00
|
|
|
*/
|
2008-07-29 02:40:57 +04:00
|
|
|
#define OMPI_CRCP_BASE_VERSION_2_0_0 \
|
|
|
|
|
MCA_BASE_VERSION_2_0_0, \
|
|
|
|
|
"crcp", 2, 0, 0
|
2007-03-17 02:11:45 +03:00
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Macro to call the CRCP Request Complete function
|
|
|
|
|
*/
|
2010-03-13 02:57:50 +03:00
|
|
|
#if OPAL_ENABLE_FT_CR == 1
|
2007-03-17 02:11:45 +03:00
|
|
|
#define OMPI_CRCP_REQUEST_COMPLETE(req) \
|
|
|
|
|
if( NULL != ompi_crcp.request_complete) { \
|
|
|
|
|
ompi_crcp.request_complete(req); \
|
|
|
|
|
}
|
|
|
|
|
#else
|
|
|
|
|
#define OMPI_CRCP_REQUEST_COMPLETE(req) ;
|
|
|
|
|
#endif
|
|
|
|
|
|
2009-08-20 15:42:18 +04:00
|
|
|
END_C_DECLS
|
2007-03-20 17:12:13 +03:00
|
|
|
|
2007-03-17 02:11:45 +03:00
|
|
|
#endif /* OMPI_CRCP_H */
|