2004-07-01 18:49:54 +04:00
|
|
|
/*
|
2005-11-05 22:57:48 +03:00
|
|
|
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
|
|
|
|
|
* 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.
|
2006-02-07 06:32:36 +03:00
|
|
|
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
2004-11-28 23:09:25 +03:00
|
|
|
* University of Stuttgart. All rights reserved.
|
2005-03-24 15:43:37 +03:00
|
|
|
* Copyright (c) 2004-2005 The Regents of the University of California.
|
|
|
|
|
* All rights reserved.
|
2013-02-28 05:35:55 +04:00
|
|
|
* Copyright (c) 2013 Los Alamos National Security, LLC. All rights reserved.
|
2004-11-22 04:38:40 +03:00
|
|
|
* $COPYRIGHT$
|
2006-02-07 06:32:36 +03:00
|
|
|
*
|
2004-11-22 04:38:40 +03:00
|
|
|
* Additional copyrights may follow
|
2006-02-07 06:32:36 +03:00
|
|
|
*
|
2004-02-01 00:43:26 +03:00
|
|
|
* $HEADER$
|
|
|
|
|
*/
|
2004-07-01 18:49:54 +04:00
|
|
|
/** @file:
|
|
|
|
|
*
|
2004-08-05 03:42:51 +04:00
|
|
|
* the oob framework
|
2004-07-01 18:49:54 +04:00
|
|
|
*/
|
2004-02-01 00:43:26 +03:00
|
|
|
|
2004-08-05 03:42:51 +04:00
|
|
|
#ifndef _MCA_OOB_BASE_H_
|
|
|
|
|
#define _MCA_OOB_BASE_H_
|
2005-03-14 23:57:21 +03:00
|
|
|
|
|
|
|
|
#include "orte_config.h"
|
|
|
|
|
|
2005-12-01 21:28:20 +03:00
|
|
|
#ifdef HAVE_UNISTD_H
|
|
|
|
|
#include <unistd.h>
|
|
|
|
|
#endif
|
2004-10-22 20:06:05 +04:00
|
|
|
#ifdef HAVE_SYS_UIO_H
|
2006-02-07 06:32:36 +03:00
|
|
|
#include <sys/uio.h>
|
2004-10-22 20:06:05 +04:00
|
|
|
#endif
|
2007-07-10 07:46:57 +04:00
|
|
|
#ifdef HAVE_NET_UIO_H
|
|
|
|
|
#include <net/uio.h>
|
|
|
|
|
#endif
|
2005-03-14 23:57:21 +03:00
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
#include "orte/mca/oob/oob.h"
|
2006-02-07 06:32:36 +03:00
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
#include "opal/mca/mca.h"
|
2008-02-28 04:57:57 +03:00
|
|
|
|
|
|
|
|
BEGIN_C_DECLS
|
2004-02-01 00:43:26 +03:00
|
|
|
|
2008-06-18 07:15:56 +04:00
|
|
|
ORTE_DECLSPEC int mca_oob_base_open(void);
|
|
|
|
|
|
2006-11-03 19:04:40 +03:00
|
|
|
/*
|
|
|
|
|
* global flag for use in timing tests
|
|
|
|
|
*/
|
Bring in the generalized xcast communication system along with the correspondingly revised orted launch. I will send a message out to developers explaining the basic changes. In brief:
1. generalize orte_rml.xcast to become a general broadcast-like messaging system. Messages can now be sent to any tag on the daemons or processes. Note that any message sent via xcast will be delivered to ALL processes in the specified job - you don't get to pick and choose. At a later date, we will introduce an augmented capability that will use the daemons as relays, but will allow you to send to a specified array of process names.
2. extended orte_rml.xcast so it supports more scalable message routing methodologies. At the moment, we support three: (a) direct, which sends the message directly to all recipients; (b) linear, which sends the message to the local daemon on each node, which then relays it to its own local procs; and (b) binomial, which sends the message via a binomial algo across all the daemons, each of which then relays to its own local procs. The crossover points between the algos are adjustable via MCA param, or you can simply demand that a specific algo be used.
3. orteds no longer exhibit two types of behavior: bootproxy or VM. Orteds now always behave like they are part of a virtual machine - they simply launch a job if mpirun tells them to do so. This is another step towards creating an "orteboot" functionality, but also provided a clean system for supporting message relaying.
Note one major impact of this commit: multiple daemons on a node cannot be supported any longer! Only a single daemon/node is now allowed.
This commit is known to break support for the following environments: POE, Xgrid, Xcpu, Windows. It has been tested on rsh, SLURM, and Bproc. Modifications for TM support have been made but could not be verified due to machine problems at LANL. Modifications for SGE have been made but could not be verified. The developers for the non-verified environments will be separately notified along with suggestions on how to fix the problems.
This commit was SVN r15007.
2007-06-12 17:28:54 +04:00
|
|
|
ORTE_DECLSPEC extern int mca_oob_base_output;
|
2007-04-25 23:51:52 +04:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Flag indicating if this framework has been opened
|
|
|
|
|
*/
|
|
|
|
|
ORTE_DECLSPEC extern bool orte_oob_base_already_opened;
|
|
|
|
|
|
2004-08-05 03:42:51 +04:00
|
|
|
/*
|
2006-02-07 06:32:36 +03:00
|
|
|
* OOB API
|
2004-06-30 00:36:34 +04:00
|
|
|
*/
|
2004-07-01 18:49:54 +04:00
|
|
|
|
2004-08-05 03:42:51 +04:00
|
|
|
/*
|
|
|
|
|
* Non-blocking versions of send/recv.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
2007-07-20 05:34:02 +04:00
|
|
|
* associate a component and a module that belongs to it
|
|
|
|
|
*/
|
|
|
|
|
struct mca_oob_base_info_t {
|
|
|
|
|
opal_list_item_t super;
|
|
|
|
|
mca_oob_base_component_t *oob_component;
|
|
|
|
|
mca_oob_t *oob_module;
|
|
|
|
|
};
|
2004-11-20 22:12:43 +03:00
|
|
|
/**
|
2007-07-20 05:34:02 +04:00
|
|
|
* Convenience Typedef
|
2004-11-20 22:12:43 +03:00
|
|
|
*/
|
2007-07-20 05:34:02 +04:00
|
|
|
typedef struct mca_oob_base_info_t mca_oob_base_info_t;
|
2004-11-20 22:12:43 +03:00
|
|
|
|
2007-07-20 05:34:02 +04:00
|
|
|
/**
|
|
|
|
|
* declare the association structure as a class
|
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
The primary change that underlies all this is in the OOB. Specifically, the problem in the code until now has been that the OOB attempts to resolve an address when we call the "send" to an unknown recipient. The OOB would then wait forever if that recipient never actually started (and hence, never reported back its OOB contact info). In the case of an orted that failed to start, we would correctly detect that the orted hadn't started, but then we would attempt to order all orteds (including the one that failed to start) to die. This would cause the OOB to "hang" the system.
Unfortunately, revising how the OOB resolves addresses introduced a number of additional problems. Specifically, and most troublesome, was the fact that comm_spawn involved the immediate transmission of the rendezvous point from parent-to-child after the child was spawned. The current code used the OOB address resolution as a "barrier" - basically, the parent would attempt to send the info to the child, and then "hold" there until the child's contact info had arrived (meaning the child had started) and the send could be completed.
Note that this also caused comm_spawn to "hang" the entire system if the child never started... The app-failed-to-start helped improve that behavior - this code provides additional relief.
With this change, the OOB will return an ADDRESSEE_UNKNOWN error if you attempt to send to a recipient whose contact info isn't already in the OOB's hash tables. To resolve comm_spawn issues, we also now force the cross-sharing of connection info between parent and child jobs during spawn.
Finally, to aid in setting triggers to the right values, we introduce the "arith" API for the GPR. This function allows you to atomically change the value in a registry location (either divide, multiply, add, or subtract) by the provided operand. It is equivalent to first fetching the value using a "get", then modifying it, and then putting the result back into the registry via a "put".
This commit was SVN r14711.
2007-05-21 22:31:28 +04:00
|
|
|
*/
|
2007-07-20 05:34:02 +04:00
|
|
|
ORTE_DECLSPEC OBJ_CLASS_DECLARATION(mca_oob_base_info_t);
|
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
The primary change that underlies all this is in the OOB. Specifically, the problem in the code until now has been that the OOB attempts to resolve an address when we call the "send" to an unknown recipient. The OOB would then wait forever if that recipient never actually started (and hence, never reported back its OOB contact info). In the case of an orted that failed to start, we would correctly detect that the orted hadn't started, but then we would attempt to order all orteds (including the one that failed to start) to die. This would cause the OOB to "hang" the system.
Unfortunately, revising how the OOB resolves addresses introduced a number of additional problems. Specifically, and most troublesome, was the fact that comm_spawn involved the immediate transmission of the rendezvous point from parent-to-child after the child was spawned. The current code used the OOB address resolution as a "barrier" - basically, the parent would attempt to send the info to the child, and then "hold" there until the child's contact info had arrived (meaning the child had started) and the send could be completed.
Note that this also caused comm_spawn to "hang" the entire system if the child never started... The app-failed-to-start helped improve that behavior - this code provides additional relief.
With this change, the OOB will return an ADDRESSEE_UNKNOWN error if you attempt to send to a recipient whose contact info isn't already in the OOB's hash tables. To resolve comm_spawn issues, we also now force the cross-sharing of connection info between parent and child jobs during spawn.
Finally, to aid in setting triggers to the right values, we introduce the "arith" API for the GPR. This function allows you to atomically change the value in a registry location (either divide, multiply, add, or subtract) by the provided operand. It is equivalent to first fetching the value using a "get", then modifying it, and then putting the result back into the registry via a "put".
This commit was SVN r14711.
2007-05-21 22:31:28 +04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
2007-07-20 05:34:02 +04:00
|
|
|
* Global functions for MCA overall collective open and close
|
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
The primary change that underlies all this is in the OOB. Specifically, the problem in the code until now has been that the OOB attempts to resolve an address when we call the "send" to an unknown recipient. The OOB would then wait forever if that recipient never actually started (and hence, never reported back its OOB contact info). In the case of an orted that failed to start, we would correctly detect that the orted hadn't started, but then we would attempt to order all orteds (including the one that failed to start) to die. This would cause the OOB to "hang" the system.
Unfortunately, revising how the OOB resolves addresses introduced a number of additional problems. Specifically, and most troublesome, was the fact that comm_spawn involved the immediate transmission of the rendezvous point from parent-to-child after the child was spawned. The current code used the OOB address resolution as a "barrier" - basically, the parent would attempt to send the info to the child, and then "hold" there until the child's contact info had arrived (meaning the child had started) and the send could be completed.
Note that this also caused comm_spawn to "hang" the entire system if the child never started... The app-failed-to-start helped improve that behavior - this code provides additional relief.
With this change, the OOB will return an ADDRESSEE_UNKNOWN error if you attempt to send to a recipient whose contact info isn't already in the OOB's hash tables. To resolve comm_spawn issues, we also now force the cross-sharing of connection info between parent and child jobs during spawn.
Finally, to aid in setting triggers to the right values, we introduce the "arith" API for the GPR. This function allows you to atomically change the value in a registry location (either divide, multiply, add, or subtract) by the provided operand. It is equivalent to first fetching the value using a "get", then modifying it, and then putting the result back into the registry via a "put".
This commit was SVN r14711.
2007-05-21 22:31:28 +04:00
|
|
|
*/
|
2007-07-20 05:34:02 +04:00
|
|
|
ORTE_DECLSPEC int mca_oob_base_init(void);
|
|
|
|
|
ORTE_DECLSPEC int mca_oob_base_module_init(void);
|
|
|
|
|
ORTE_DECLSPEC int mca_oob_base_close(void);
|
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start.
The primary change that underlies all this is in the OOB. Specifically, the problem in the code until now has been that the OOB attempts to resolve an address when we call the "send" to an unknown recipient. The OOB would then wait forever if that recipient never actually started (and hence, never reported back its OOB contact info). In the case of an orted that failed to start, we would correctly detect that the orted hadn't started, but then we would attempt to order all orteds (including the one that failed to start) to die. This would cause the OOB to "hang" the system.
Unfortunately, revising how the OOB resolves addresses introduced a number of additional problems. Specifically, and most troublesome, was the fact that comm_spawn involved the immediate transmission of the rendezvous point from parent-to-child after the child was spawned. The current code used the OOB address resolution as a "barrier" - basically, the parent would attempt to send the info to the child, and then "hold" there until the child's contact info had arrived (meaning the child had started) and the send could be completed.
Note that this also caused comm_spawn to "hang" the entire system if the child never started... The app-failed-to-start helped improve that behavior - this code provides additional relief.
With this change, the OOB will return an ADDRESSEE_UNKNOWN error if you attempt to send to a recipient whose contact info isn't already in the OOB's hash tables. To resolve comm_spawn issues, we also now force the cross-sharing of connection info between parent and child jobs during spawn.
Finally, to aid in setting triggers to the right values, we introduce the "arith" API for the GPR. This function allows you to atomically change the value in a registry location (either divide, multiply, add, or subtract) by the provided operand. It is equivalent to first fetching the value using a "get", then modifying it, and then putting the result back into the registry via a "put".
This commit was SVN r14711.
2007-05-21 22:31:28 +04:00
|
|
|
|
2004-11-20 22:12:43 +03:00
|
|
|
|
2005-10-06 23:39:20 +04:00
|
|
|
/*
|
2007-07-20 05:34:02 +04:00
|
|
|
* Global struct holding the selected module's function pointers
|
2005-10-06 23:39:20 +04:00
|
|
|
*/
|
2007-07-20 05:34:02 +04:00
|
|
|
ORTE_DECLSPEC extern int mca_oob_base_output;
|
|
|
|
|
extern char* mca_oob_base_include;
|
|
|
|
|
extern char* mca_oob_base_exclude;
|
|
|
|
|
ORTE_DECLSPEC extern opal_list_t mca_oob_base_components;
|
|
|
|
|
ORTE_DECLSPEC extern opal_list_t mca_oob_base_modules;
|
2005-10-06 23:39:20 +04:00
|
|
|
|
2008-02-28 04:57:57 +03:00
|
|
|
END_C_DECLS
|
2004-02-01 00:43:26 +03:00
|
|
|
#endif
|
2004-08-05 03:42:51 +04:00
|
|
|
|