1
1
openmpi/orte/mca/odls/base/odls_private.h

200 строки
7.4 KiB
C
Исходник Обычный вид История

/*
* Copyright (c) 2004-2007 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2006 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:
*/
#ifndef MCA_ODLS_PRIVATE_H
#define MCA_ODLS_PRIVATE_H
/*
* includes
*/
#include "orte_config.h"
#include "opal/class/opal_list.h"
#include "opal/threads/mutex.h"
#include "opal/threads/condition.h"
#include "orte/dss/dss_types.h"
#include "orte/mca/ns/ns_types.h"
#include "orte/mca/rmgr/rmgr_types.h"
#include "orte/mca/smr/smr_types.h"
#include "orte/mca/rmaps/rmaps_types.h"
#include "orte/mca/rml/rml_types.h"
#include "orte/mca/gpr/gpr_types.h"
#include "orte/mca/odls/odls_types.h"
#if defined(c_plusplus) || defined(__cplusplus)
extern "C" {
#endif
/*
* General ODLS types
*/
/*
* List object to locally store the process names and pids of
* our children. This can subsequently be used to order termination
* or pass signals without looking the info up again.
*/
typedef struct orte_odls_child_t {
opal_list_item_t super; /* required to place this on a list */
orte_process_name_t *name; /* the OpenRTE name of the proc */
orte_vpid_t local_rank; /* local rank of the proc on this node */
orte_std_cntr_t num_procs; /* number of procs from this job on this node */
pid_t pid; /* local pid of the proc */
orte_std_cntr_t app_idx; /* index of the app_context for this proc */
bool alive; /* is this proc alive? */
orte_proc_state_t state; /* the state of the process */
int exit_code; /* process exit code */
unsigned long cpu_set;
These changes were mostly captured in a prior RFC (except for #2 below) and are aimed specifically at improving startup performance and setting up the remaining modifications described in that RFC. The commit has been tested for C/R and Cray operations, and on Odin (SLURM, rsh) and RoadRunner (TM). I tried to update all environments, but obviously could not test them. I know that Windows needs some work, and have highlighted what is know to be needed in the odls process component. This represents a lot of work by Brian, Tim P, Josh, and myself, with much advice from Jeff and others. For posterity, I have appended a copy of the email describing the work that was done: As we have repeatedly noted, the modex operation in MPI_Init is the single greatest consumer of time during startup. To-date, we have executed that operation as an ORTE stage gate that held the process until a startup message containing all required modex (and OOB contact info - see #3 below) info could be sent to it. Each process would send its data to the HNP's registry, which assembled and sent the message when all processes had reported in. In addition, ORTE had taken responsibility for monitoring process status as it progressed through a series of "stage gates". The process reported its status at each gate, and ORTE would then send a "release" message once all procs had reported in. The incoming changes revamp these procedures in three ways: 1. eliminating the ORTE stage gate system and cleanly delineating responsibility between the OMPI and ORTE layers for MPI init/finalize. The modex stage gate (STG1) has been replaced by a collective operation in the modex itself that performs an allgather on the required modex info. The allgather is implemented using the orte_grpcomm framework since the BTL's are not active at that point. At the moment, the grpcomm framework only has a "basic" component analogous to OMPI's "basic" coll framework - I would recommend that the MPI team create additional, more advanced components to improve performance of this step. The other stage gates have been replaced by orte_grpcomm barrier functions. We tried to use MPI barriers instead (since the BTL's are active at that point), but - as we discussed on the telecon - these are not currently true barriers so the job would hang when we fell through while messages were still in process. Note that the grpcomm barrier doesn't actually resolve that problem, but Brian has pointed out that we are unlikely to ever see it violated. Again, you might want to spend a little time on an advanced barrier algorithm as the one in "basic" is very simplistic. Summarizing this change: ORTE no longer tracks process state nor has direct responsibility for synchronizing jobs. This is now done via collective operations within the MPI layer, albeit using ORTE collective communication services. I -strongly- urge the MPI team to implement advanced collective algorithms to improve the performance of this critical procedure. 2. reducing the volume of data exchanged during modex. Data in the modex consisted of the process name, the name of the node where that process is located (expressed as a string), plus a string representation of all contact info. The nodename was required in order for the modex to determine if the process was local or not - in addition, some people like to have it to print pretty error messages when a connection failed. The size of this data has been reduced in three ways: (a) reducing the size of the process name itself. The process name consisted of two 32-bit fields for the jobid and vpid. This is far larger than any current system, or system likely to exist in the near future, can support. Accordingly, the default size of these fields has been reduced to 16-bits, which means you can have 32k procs in each of 32k jobs. Since the daemons must have a vpid, and we require one daemon/node, this also restricts the default configuration to 32k nodes. To support any future "mega-clusters", a configuration option --enable-jumbo-apps has been added. This option increases the jobid and vpid field sizes to 32-bits. Someday, if necessary, someone can add yet another option to increase them to 64-bits, I suppose. (b) replacing the string nodename with an integer nodeid. Since we have one daemon/node, the nodeid corresponds to the local daemon's vpid. This replaces an often lengthy string with only 2 (or at most 4) bytes, a substantial reduction. (c) when the mca param requesting that nodenames be sent to support pretty error messages, a second mca param is now used to request FQDN - otherwise, the domain name is stripped (by default) from the message to save space. If someone wants to combine those into a single param somehow (perhaps with an argument?), they are welcome to do so - I didn't want to alter what people are already using. While these may seem like small savings, they actually amount to a significant impact when aggregated across the entire modex operation. Since every proc must receive the modex data regardless of the collective used to send it, just reducing the size of the process name removes nearly 400MBytes of communication from a 32k proc job (admittedly, much of this comm may occur in parallel). So it does add up pretty quickly. 3. routing RML messages to reduce connections. The default messaging system remains point-to-point - i.e., each proc opens a socket to every proc it communicates with and sends its messages directly. A new option uses the orteds as routers - i.e., each proc only opens a single socket to its local orted. All messages are sent from the proc to the orted, which forwards the message to the orted on the node where the intended recipient proc is located - that orted then forwards the message to its local proc (the recipient). This greatly reduces the connection storm we have encountered during startup. It also has the benefit of removing the sharing of every proc's OOB contact with every other proc. The orted routing tables are populated during launch since every orted gets a map of where every proc is being placed. Each proc, therefore, only needs to know the contact info for its local daemon, which is passed in via the environment when the proc is fork/exec'd by the daemon. This alone removes ~50 bytes/process of communication that was in the current STG1 startup message - so for our 32k proc job, this saves us roughly 32k*50 = 1.6MBytes sent to 32k procs = 51GBytes of messaging. Note that you can use the new routing method by specifying -mca routed tree - if you so desire. This mode will become the default at some point in the future. There are a few minor additional changes in the commit that I'll just note in passing: * propagation of command line mca params to the orteds - fixes ticket #1073. See note there for details. * requiring of "finalize" prior to "exit" for MPI procs - fixes ticket #1144. See note there for details. * cleanup of some stale header files This commit was SVN r16364.
2007-10-05 19:48:23 +00:00
bool sync_required; /* require sync before termination */
} orte_odls_child_t;
ORTE_DECLSPEC OBJ_CLASS_DECLARATION(orte_odls_child_t);
/*
* List object to locally store app_contexts returned by the
* registry subscription. Since we don't know how many app_contexts will
* be returned, we need to store them on a list.
*/
typedef struct orted_odls_app_context_t {
opal_list_item_t super; /* required to place this on a list */
orte_app_context_t *app_context;
} orte_odls_app_context_t;
OBJ_CLASS_DECLARATION(orte_odls_app_context_t);
typedef struct orte_odls_globals_t {
/** Verbose/debug output stream */
int output;
/** Time to allow process to forcibly die */
int timeout_before_sigkill;
/* mutex */
opal_mutex_t mutex;
/* condition variable */
opal_condition_t cond;
/* list of children for this orted */
opal_list_t children;
} orte_odls_globals_t;
ORTE_DECLSPEC extern orte_odls_globals_t orte_odls_globals;
ORTE_DECLSPEC int orte_odls_base_report_spawn(opal_list_t *children);
ORTE_DECLSPEC void orte_odls_base_purge_mca_params(char ***env);
/*
* Default functions that are common to most environments - can
* be overridden by specific environments if they need something
* different (e.g., bproc)
*/
ORTE_DECLSPEC int
orte_odls_base_default_get_add_procs_data(orte_gpr_notify_data_t **data,
orte_job_map_t *map);
ORTE_DECLSPEC int
orte_odls_base_default_construct_child_list(orte_gpr_notify_data_t *data,
orte_jobid_t *job,
orte_vpid_t *vpid_start,
orte_vpid_t *vpid_range,
orte_std_cntr_t *total_slots_allocated,
bool *node_included,
bool *oversubscribed,
bool *override_oversubscribed,
opal_list_t *app_context_list);
/* define a function that will fork a local proc */
typedef int (*orte_odls_base_fork_local_proc_fn_t)(orte_app_context_t *context,
orte_odls_child_t *child,
char **environ_copy);
ORTE_DECLSPEC int
orte_odls_base_default_launch_local(orte_jobid_t job, opal_list_t *app_context_list,
orte_vpid_t vpid_start, orte_vpid_t vpid_range,
orte_std_cntr_t total_slots_allocated,
bool oversubscribed,
bool override_oversubscribed,
orte_odls_base_fork_local_proc_fn_t fork_local);
ORTE_DECLSPEC int
orte_odls_base_default_extract_proc_map_info(orte_process_name_t *daemon,
orte_process_name_t *proc,
orte_gpr_value_t *value);
ORTE_DECLSPEC int
orte_odls_base_default_deliver_message(orte_jobid_t job, orte_buffer_t *buffer, orte_rml_tag_t tag);
ORTE_DECLSPEC void odls_base_default_wait_local_proc(pid_t pid, int status, void* cbdata);
/* define a function type to signal a local proc */
typedef int (*orte_odls_base_signal_local_fn_t)(pid_t pid, int signum);
ORTE_DECLSPEC int
orte_odls_base_default_signal_local_procs(const orte_process_name_t *proc, int32_t signal,
orte_odls_base_signal_local_fn_t signal_local);
/* define a function type for killing a local proc */
typedef int (*orte_odls_base_kill_local_fn_t)(pid_t pid, int signum);
/* define a function type to detect that a child died */
typedef bool (*orte_odls_base_child_died_fn_t)(pid_t pid, unsigned int timeout, int *exit_status);
ORTE_DECLSPEC int
orte_odls_base_default_kill_local_procs(orte_jobid_t job, bool set_state,
orte_odls_base_kill_local_fn_t kill_local,
orte_odls_base_child_died_fn_t child_died);
ORTE_DECLSPEC int orte_odls_base_default_require_sync(orte_process_name_t *proc);
/*
* data type functions
*/
ORTE_DECLSPEC int
orte_odls_compare_daemon_cmd(orte_daemon_cmd_flag_t *value1, orte_daemon_cmd_flag_t *value2, orte_data_type_t type);
ORTE_DECLSPEC int
orte_odls_copy_daemon_cmd(orte_daemon_cmd_flag_t **dest, orte_daemon_cmd_flag_t *src, orte_data_type_t type);
ORTE_DECLSPEC int
orte_odls_pack_daemon_cmd(orte_buffer_t *buffer, const void *src,
orte_std_cntr_t num_vals, orte_data_type_t type);
ORTE_DECLSPEC int
orte_odls_print_daemon_cmd(char **output, char *prefix, orte_daemon_cmd_flag_t *src, orte_data_type_t type);
ORTE_DECLSPEC void orte_odls_std_release(orte_data_value_t *value);
ORTE_DECLSPEC int
orte_odls_size_daemon_cmd(size_t *size, orte_daemon_cmd_flag_t *src, orte_data_type_t type);
ORTE_DECLSPEC int
orte_odls_unpack_daemon_cmd(orte_buffer_t *buffer, void *dest,
orte_std_cntr_t *num_vals, orte_data_type_t type);
2007-09-27 13:13:29 +00:00
/*
* Preload binary/files functions
*/
ORTE_DECLSPEC int orte_odls_base_preload_files_app_context(orte_app_context_t* context);
#if defined(c_plusplus) || defined(__cplusplus)
}
#endif
#endif