1
1
openmpi/orte/tools/orte-restart/orte-restart.c

735 строки
22 KiB
C
Исходник Обычный вид История

/*
* Copyright (c) 2004-2009 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2007 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 (c) 2007 Los Alamos National Security, LLC. All rights
* reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
/**
* @file
* ORTE Restart Tool for restarting a previously checkpointed multiprocess job
*
*/
#include "orte_config.h"
#include "orte/constants.h"
#include <stdio.h>
#include <errno.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif /* HAVE_UNISTD_H */
#ifdef HAVE_STDLIB_H
#include <stdlib.h>
#endif /* HAVE_STDLIB_H */
#ifdef HAVE_SYS_STAT_H
#include <sys/stat.h>
#endif /* HAVE_SYS_STAT_H */
#ifdef HAVE_SYS_TYPES_H
#include <sys/types.h>
#endif /* HAVE_SYS_TYPES_H */
#ifdef HAVE_SYS_WAIT_H
#include <sys/wait.h>
#endif /* HAVE_SYS_WAIT_H */
#ifdef HAVE_STRING_H
#include <string.h>
#endif /* HAVE_STRING_H */
#include "opal/runtime/opal.h"
#include "opal/runtime/opal_cr.h"
#include "opal/util/cmd_line.h"
#include "opal/util/output.h"
#include "opal/util/argv.h"
#include "opal/util/opal_environ.h"
#include "opal/util/basename.h"
#include "opal/mca/base/base.h"
#include "opal/mca/base/mca_base_param.h"
#include "opal/mca/crs/crs.h"
#include "opal/mca/crs/base/base.h"
#include "orte/runtime/runtime.h"
#include "orte/runtime/orte_cr.h"
#include "orte/mca/snapc/snapc.h"
#include "orte/mca/snapc/base/base.h"
#include "orte/mca/filem/base/base.h"
#include "opal/util/show_help.h"
#include "orte/util/proc_info.h"
/******************
* Local Functions
******************/
static int initialize(int argc, char *argv[]);
static int finalize(void);
static int parse_args(int argc, char *argv[]);
static int check_file(orte_snapc_base_global_snapshot_t *snapshot);
static int create_appfile(orte_snapc_base_global_snapshot_t *snapshot);
static int spawn_children(orte_snapc_base_global_snapshot_t *snapshot, pid_t *child_pid);
static int snapshot_info(orte_snapc_base_global_snapshot_t *snapshot);
/*****************************************
* Global Vars for Command line Arguments
*****************************************/
typedef struct {
bool help;
char *filename;
char *appfile;
bool verbose;
bool forked;
bool preload;
int seq_number;
char *hostfile;
int output;
bool info_only;
bool app_only;
} orte_restart_globals_t;
orte_restart_globals_t orte_restart_globals;
opal_cmd_line_init_t cmd_line_opts[] = {
{ NULL, NULL, NULL,
'h', NULL, "help",
0,
&orte_restart_globals.help, OPAL_CMD_LINE_TYPE_BOOL,
"This help message" },
{ NULL, NULL, NULL,
'v', NULL, "verbose",
0,
&orte_restart_globals.verbose, OPAL_CMD_LINE_TYPE_BOOL,
"Be Verbose" },
{ NULL, NULL, NULL,
'p', NULL, "preload",
0,
&orte_restart_globals.preload, OPAL_CMD_LINE_TYPE_BOOL,
"Preload the checkpoint files before restarting (Default = Disabled)" },
{ NULL, NULL, NULL,
'\0', NULL, "fork",
0,
&orte_restart_globals.forked, OPAL_CMD_LINE_TYPE_BOOL,
"Fork off a new process which is the restarted process instead of "
"replacing orte_restart" },
{ NULL, NULL, NULL,
's', NULL, "seq",
1,
&orte_restart_globals.seq_number, OPAL_CMD_LINE_TYPE_INT,
"The sequence number of the checkpoint to start from. "
"(Default: -1, or most recent)" },
{ NULL, NULL, NULL,
'\0', "hostfile", "hostfile",
1,
&orte_restart_globals.hostfile, OPAL_CMD_LINE_TYPE_STRING,
"Provide a hostfile to use for launch" },
{ NULL, NULL, NULL,
'\0', "machinefile", "machinefile",
1,
&orte_restart_globals.hostfile, OPAL_CMD_LINE_TYPE_STRING,
"Provide a hostfile to use for launch" },
{ NULL, NULL, NULL,
'i', NULL, "info",
0,
&orte_restart_globals.info_only, OPAL_CMD_LINE_TYPE_BOOL,
"Display information about the checkpoint" },
{ NULL, NULL, NULL,
'a', NULL, "apponly",
0,
&orte_restart_globals.app_only, OPAL_CMD_LINE_TYPE_BOOL,
"Only create the app context file, do not restart from it" },
/* End of list */
{ NULL, NULL, NULL,
'\0', NULL, NULL,
0,
NULL, OPAL_CMD_LINE_TYPE_NULL,
NULL }
};
int
main(int argc, char *argv[])
{
int ret, exit_status = ORTE_SUCCESS;
pid_t child_pid = 0;
orte_snapc_base_global_snapshot_t *snapshot = NULL;
char *tmp_str = NULL;
/***************
* Initialize
***************/
if (ORTE_SUCCESS != (ret = initialize(argc, argv))) {
exit_status = ret;
goto cleanup;
}
snapshot = OBJ_NEW(orte_snapc_base_global_snapshot_t);
snapshot->reference_name = strdup(orte_restart_globals.filename);
orte_snapc_base_get_global_snapshot_directory(&tmp_str, snapshot->reference_name);
snapshot->local_location = opal_dirname(tmp_str);
free(tmp_str);
tmp_str = NULL;
/*
* Check for existence of the file
*/
if( ORTE_SUCCESS != (ret = check_file(snapshot)) ) {
opal_show_help("help-orte-restart.txt", "invalid_filename", true,
orte_restart_globals.filename);
exit_status = ret;
goto cleanup;
}
if(orte_restart_globals.info_only ) {
if (ORTE_SUCCESS != (ret = snapshot_info(snapshot))) {
exit_status = ret;
goto cleanup;
}
exit_status = ORTE_SUCCESS;
goto cleanup;
}
/******************************
* Create the app file to use with mpirun/orterun
******************************/
if( ORTE_SUCCESS != (ret = create_appfile(snapshot) ) ) {
exit_status = ret;
goto cleanup;
}
if( orte_restart_globals.app_only ) {
printf("Created Appfile:\n\t%s\n", orte_restart_globals.appfile);
exit_status = ORTE_SUCCESS;
goto cleanup;
}
/******************************
* Restart in this process [mpirun/orterun]
******************************/
if( orte_restart_globals.verbose ) {
opal_output_verbose(10, orte_restart_globals.output,
"Restarting from file (%s)",
orte_restart_globals.filename);
if( orte_restart_globals.forked ) {
opal_output_verbose(10, orte_restart_globals.output,
"\t Forking off a child");
} else {
opal_output_verbose(10, orte_restart_globals.output,
"\t Exec in self");
}
}
if( ORTE_SUCCESS != (ret = spawn_children(snapshot, &child_pid)) ) {
opal_show_help("help-orte-restart.txt", "restart_cmd_failure", true,
orte_restart_globals.filename, ret);
exit_status = ret;
goto cleanup;
}
opal_output_verbose(10, orte_restart_globals.output,
"orte_restart: Restarted Child with PID = %d\n", child_pid);
/***************
* Cleanup
***************/
cleanup:
if(NULL != snapshot ) {
OBJ_RELEASE(snapshot);
snapshot = NULL;
}
if (OPAL_SUCCESS != (ret = finalize())) {
return ret;
}
return exit_status;
}
static int initialize(int argc, char *argv[]) {
int ret, exit_status = ORTE_SUCCESS;
char * tmp_env_var = NULL;
/*
* Make sure to init util before parse_args
* to ensure installdirs is setup properly
* before calling mca_base_open();
*/
if( ORTE_SUCCESS != (ret = opal_init_util(&argc, &argv)) ) {
return ret;
}
/*
* Parse command line arguments
*/
if (ORTE_SUCCESS != (ret = parse_args(argc, argv))) {
exit_status = ret;
goto cleanup;
}
/*
* Setup OPAL Output handle from the verbose argument
*/
if( orte_restart_globals.verbose ) {
orte_restart_globals.output = opal_output_open(NULL);
opal_output_set_verbosity(orte_restart_globals.output, 10);
} else {
This commit represents a bunch of work on a Mercurial side branch. As such, the commit message back to the master SVN repository is fairly long. = ORTE Job-Level Output Messages = Add two new interfaces that should be used for all new code throughout the ORTE and OMPI layers (we already make the search-and-replace on the existing ORTE / OMPI layers): * orte_output(): (and corresponding friends ORTE_OUTPUT, orte_output_verbose, etc.) This function sends the output directly to the HNP for processing as part of a job-specific output channel. It supports all the same outputs as opal_output() (syslog, file, stdout, stderr), but for stdout/stderr, the output is sent to the HNP for processing and output. More on this below. * orte_show_help(): This function is a drop-in-replacement for opal_show_help(), with two differences in functionality: 1. the rendered text help message output is sent to the HNP for display (rather than outputting directly into the process' stderr stream) 1. the HNP detects duplicate help messages and does not display them (so that you don't see the same error message N times, once from each of your N MPI processes); instead, it counts "new" instances of the help message and displays a message every ~5 seconds when there are new ones ("I got X new copies of the help message...") opal_show_help and opal_output still exist, but they only output in the current process. The intent for the new orte_* functions is that they can apply job-level intelligence to the output. As such, we recommend that all new ORTE and OMPI code use the new orte_* functions, not thei opal_* functions. === New code === For ORTE and OMPI programmers, here's what you need to do differently in new code: * Do not include opal/util/show_help.h or opal/util/output.h. Instead, include orte/util/output.h (this one header file has declarations for both the orte_output() series of functions and orte_show_help()). * Effectively s/opal_output/orte_output/gi throughout your code. Note that orte_output_open() takes a slightly different argument list (as a way to pass data to the filtering stream -- see below), so you if explicitly call opal_output_open(), you'll need to slightly adapt to the new signature of orte_output_open(). * Literally s/opal_show_help/orte_show_help/. The function signature is identical. === Notes === * orte_output'ing to stream 0 will do similar to what opal_output'ing did, so leaving a hard-coded "0" as the first argument is safe. * For systems that do not use ORTE's RML or the HNP, the effect of orte_output_* and orte_show_help will be identical to their opal counterparts (the additional information passed to orte_output_open() will be lost!). Indeed, the orte_* functions simply become trivial wrappers to their opal_* counterparts. Note that we have not tested this; the code is simple but it is quite possible that we mucked something up. = Filter Framework = Messages sent view the new orte_* functions described above and messages output via the IOF on the HNP will now optionally be passed through a new "filter" framework before being output to stdout/stderr. The "filter" OPAL MCA framework is intended to allow preprocessing to messages before they are sent to their final destinations. The first component that was written in the filter framework was to create an XML stream, segregating all the messages into different XML tags, etc. This will allow 3rd party tools to read the stdout/stderr from the HNP and be able to know exactly what each text message is (e.g., a help message, another OMPI infrastructure message, stdout from the user process, stderr from the user process, etc.). Filtering is not active by default. Filter components must be specifically requested, such as: {{{ $ mpirun --mca filter xml ... }}} There can only be one filter component active. = New MCA Parameters = The new functionality described above introduces two new MCA parameters: * '''orte_base_help_aggregate''': Defaults to 1 (true), meaning that help messages will be aggregated, as described above. If set to 0, all help messages will be displayed, even if they are duplicates (i.e., the original behavior). * '''orte_base_show_output_recursions''': An MCA parameter to help debug one of the known issues, described below. It is likely that this MCA parameter will disappear before v1.3 final. = Known Issues = * The XML filter component is not complete. The current output from this component is preliminary and not real XML. A bit more work needs to be done to configure.m4 search for an appropriate XML library/link it in/use it at run time. * There are possible recursion loops in the orte_output() and orte_show_help() functions -- e.g., if RML send calls orte_output() or orte_show_help(). We have some ideas how to fix these, but figured that it was ok to commit before feature freeze with known issues. The code currently contains sub-optimal workarounds so that this will not be a problem, but it would be good to actually solve the problem rather than have hackish workarounds before v1.3 final. This commit was SVN r18434.
2008-05-14 00:00:55 +04:00
orte_restart_globals.output = 0; /* Default=STDERR */
}
/* Disable the checkpoint notification routine for this
* tool. As we will never need to checkpoint this tool.
* Note: This must happen before opal_init().
*/
opal_cr_set_enabled(false);
/* Select the none component, since we don't actually use a checkpointer */
tmp_env_var = mca_base_param_env_var("crs");
opal_setenv(tmp_env_var,
"none",
true, &environ);
free(tmp_env_var);
tmp_env_var = NULL;
/*
* Setup any ORTE stuff we might need
*/
if (OPAL_SUCCESS != (ret = orte_init(&argc, &argv, ORTE_PROC_TOOL))) {
exit_status = ret;
goto cleanup;
}
/* Unset these now that we no longer need them */
tmp_env_var = mca_base_param_env_var("crs");
opal_unsetenv(tmp_env_var, &environ);
free(tmp_env_var);
tmp_env_var = NULL;
tmp_env_var = mca_base_param_env_var("opal_cr_is_tool");
opal_unsetenv(tmp_env_var, &environ);
free(tmp_env_var);
tmp_env_var = NULL;
cleanup:
return exit_status;
}
static int finalize(void)
{
int ret;
if (OPAL_SUCCESS != (ret = orte_finalize())) {
return ret;
}
return ORTE_SUCCESS;
}
static int parse_args(int argc, char *argv[])
{
int i, ret, len;
opal_cmd_line_t cmd_line;
char **app_env = NULL, **global_env = NULL;
char * tmp_env_var = NULL;
orte_restart_globals_t tmp = { false, /* help */
NULL, /* filename */
NULL, /* appfile */
false, /* verbose */
false, /* forked */
false, /* preload */
-1, /* seq_number */
NULL, /* hostfile */
-1, /* output*/
false, /* info only */
false };/* app only */
orte_restart_globals = tmp;
/* Parse the command line options */
opal_cmd_line_create(&cmd_line, cmd_line_opts);
mca_base_open();
mca_base_cmd_line_setup(&cmd_line);
ret = opal_cmd_line_parse(&cmd_line, true, argc, argv);
/**
* Put all of the MCA arguments in the environment
*/
mca_base_cmd_line_process_args(&cmd_line, &app_env, &global_env);
len = opal_argv_count(app_env);
for(i = 0; i < len; ++i) {
putenv(app_env[i]);
}
len = opal_argv_count(global_env);
for(i = 0; i < len; ++i) {
putenv(global_env[i]);
}
tmp_env_var = mca_base_param_env_var("opal_cr_is_tool");
opal_setenv(tmp_env_var,
"1",
true, &environ);
free(tmp_env_var);
tmp_env_var = NULL;
/**
* Now start parsing our specific arguments
*/
#if OPAL_ENABLE_FT == 0
/* Warn and exit if not configured with Checkpoint/Restart */
{
char *args = NULL;
args = opal_cmd_line_get_usage_msg(&cmd_line);
opal_show_help("help-orte-restart.txt", "usage-no-cr",
true, args);
free(args);
return ORTE_ERROR;
}
#endif
if (OPAL_SUCCESS != ret ||
orte_restart_globals.help ||
1 >= argc) {
char *args = NULL;
args = opal_cmd_line_get_usage_msg(&cmd_line);
opal_show_help("help-orte-restart.txt", "usage", true,
args);
free(args);
return ORTE_ERROR;
}
/* get the remaining bits */
opal_cmd_line_get_tail(&cmd_line, &argc, &argv);
if ( 1 > argc ) {
char *args = NULL;
args = opal_cmd_line_get_usage_msg(&cmd_line);
opal_show_help("help-orte-restart.txt", "usage", true,
args);
free(args);
return ORTE_ERROR;
}
orte_restart_globals.filename = strdup(argv[0]);
if ( NULL == orte_restart_globals.filename ||
0 >= strlen(orte_restart_globals.filename) ) {
opal_show_help("help-orte-restart.txt", "invalid_filename", true,
orte_restart_globals.filename);
return ORTE_ERROR;
}
/* If we have arguments after the command, then assume they
* need to be grouped together.
*/
if(argc > 1) {
orte_restart_globals.filename = strdup(opal_argv_join(argv, ' '));
}
return ORTE_SUCCESS;
}
static int check_file(orte_snapc_base_global_snapshot_t *snapshot)
{
int ret, exit_status = ORTE_SUCCESS;
opal_output_verbose(10, orte_restart_globals.output,
"Checking for the existence of (%s)\n",
snapshot->local_location);
if (0 > (ret = access(snapshot->local_location, F_OK)) ) {
exit_status = ORTE_ERROR;
goto cleanup;
}
cleanup:
return exit_status;
}
static int create_appfile(orte_snapc_base_global_snapshot_t *snapshot)
{
int ret, exit_status = ORTE_SUCCESS;
FILE *appfile = NULL;
opal_list_item_t* item = NULL;
/*
* Extract the record information for the specified seq number.
* Note: If the seq # passed is -1, then the largest seq # is selected,
* ow the seq # requested is selected if available
*/
snapshot->seq_num = orte_restart_globals.seq_number;
if( ORTE_SUCCESS != (ret = orte_snapc_base_extract_metadata( snapshot ) ) ) {
opal_show_help("help-orte-restart.txt", "invalid_seq_num", true,
orte_restart_globals.filename,
(int)orte_restart_globals.seq_number);
exit_status = ret;
goto cleanup;
}
/*
* Create the appfile
*/
asprintf(&orte_restart_globals.appfile, "%s/%s",
snapshot->local_location,
strdup("restart-appfile"));
if (NULL == (appfile = fopen(orte_restart_globals.appfile, "w")) ) {
exit_status = ret;
goto cleanup;
}
for(item = opal_list_get_first(&snapshot->local_snapshots);
item != opal_list_get_end(&snapshot->local_snapshots);
item = opal_list_get_next(item) ) {
orte_snapc_base_local_snapshot_t *vpid_snapshot;
vpid_snapshot = (orte_snapc_base_local_snapshot_t*)item;
fprintf(appfile, "#\n");
fprintf(appfile, "# Old Process Name: %u.%u\n",
vpid_snapshot->process_name.jobid,
vpid_snapshot->process_name.vpid);
fprintf(appfile, "#\n");
fprintf(appfile, "-np 1 ");
if(orte_restart_globals.preload) {
fprintf(appfile, "--preload-files %s/%s ",
vpid_snapshot->local_location,
vpid_snapshot->reference_name);
fprintf(appfile, "--preload-files-dest-dir . ");
}
/* JJH: Make this match what the user originally specified on the command line */
fprintf(appfile, "-am ft-enable-cr ");
fprintf(appfile, " opal-restart ");
/* JJH: Make sure this changes if ever the default location of the local file is changed,
* currently it is safe to assume that it is in the current working directory.
*
* JJH: If we allow inplace restarting then this may be another directory... */
if(orte_restart_globals.preload) {
/* If we preloaded the files then they are in the current working
* directory. */
fprintf(appfile, "-mca crs_base_snapshot_dir . ");
}
else {
/* If we are *not* preloading the files, the point to the original checkpoint
* directory to access the checkpoint files. */
fprintf(appfile, "-mca crs_base_snapshot_dir %s ", vpid_snapshot->local_location);
}
fprintf(appfile, "%s\n", vpid_snapshot->reference_name);
}
cleanup:
if(NULL != appfile)
fclose(appfile);
return exit_status;
}
static int spawn_children(orte_snapc_base_global_snapshot_t *snapshot, pid_t *child_pid)
{
int ret, exit_status = ORTE_SUCCESS;
char **argv = NULL;
int argc = 0;
int status;
if( ORTE_SUCCESS != (ret = opal_argv_append(&argc, &argv, "mpirun")) ) {
exit_status = ret;
goto cleanup;
}
if( ORTE_SUCCESS != (ret = opal_argv_append(&argc, &argv, "-am")) ) {
exit_status = ret;
goto cleanup;
}
if( ORTE_SUCCESS != (ret = opal_argv_append(&argc, &argv, "ft-enable-cr")) ) {
exit_status = ret;
goto cleanup;
}
if( NULL != orte_restart_globals.hostfile ) {
if( ORTE_SUCCESS != (ret = opal_argv_append(&argc, &argv, "--default-hostfile")) ) {
exit_status = ret;
goto cleanup;
}
if( ORTE_SUCCESS != (ret = opal_argv_append(&argc, &argv, orte_restart_globals.hostfile)) ) {
exit_status = ret;
goto cleanup;
}
}
if( ORTE_SUCCESS != (ret = opal_argv_append(&argc, &argv, "--app")) ) {
exit_status = ret;
goto cleanup;
}
if( ORTE_SUCCESS != (ret = opal_argv_append(&argc, &argv, orte_restart_globals.appfile)) ) {
exit_status = ret;
goto cleanup;
}
/* To fork off a child */
if( orte_restart_globals.forked ) {
*child_pid = fork();
if( 0 == *child_pid) {
/* Child Process */
status = execvp(strdup(argv[0]), argv);
if( 0 > status) {
opal_output(orte_restart_globals.output,
"orte_restart: execv failed with status = %d\n",
status);
}
exit_status = status;
goto cleanup;
}
else if(0 < *child_pid) {
/* Parent is done once it is started */
;
}
else {
opal_output(orte_restart_globals.output,
"orte_restart: fork failed: This should never happen!");
/* Fork failed :( */
exit_status = *child_pid;
goto cleanup;
}
}
/* ... or not to fork off a child */
else {
/* Make sure to finalize so we don't leave our session directory */
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 23:48:23 +04:00
orte_finalize();
status = execvp(strdup(argv[0]), argv);
if( 0 > status) {
/* execv failed */
}
exit_status = status;
goto cleanup;
}
cleanup:
if( NULL != argv)
opal_argv_free(argv);
return exit_status;
}
int snapshot_info(orte_snapc_base_global_snapshot_t *snapshot)
{
int ret, exit_status = ORTE_SUCCESS;
int num_seqs, processes, i;
int *snapshot_ref_seqs;
opal_list_item_t* item = NULL;
orte_snapc_base_local_snapshot_t *vpid_snapshot;
if (orte_restart_globals.seq_number == -1) {
if( ORTE_SUCCESS != (ret = orte_snapc_base_get_all_snapshot_ref_seqs(NULL, orte_restart_globals.filename, &num_seqs, &snapshot_ref_seqs) ) ) {
exit_status = ret;
goto cleanup;
}
opal_output(orte_restart_globals.output,
"Sequences: %d\n",
num_seqs);
} else {
num_seqs = 1;
snapshot_ref_seqs = &orte_restart_globals.seq_number;
}
for (i=0; i<num_seqs; i++) {
snapshot->seq_num = snapshot_ref_seqs[i];
while (NULL != (item = opal_list_remove_first(&snapshot->local_snapshots))) {
OBJ_RELEASE(item);
}
if( NULL != snapshot->start_time ) {
free( snapshot->start_time );
snapshot->start_time = NULL;
}
if( NULL != snapshot->end_time ) {
free( snapshot->end_time );
snapshot->end_time = NULL;
}
opal_output(orte_restart_globals.output,
"Seq: %d\n",
snapshot->seq_num);
if( ORTE_SUCCESS != (ret = orte_snapc_base_extract_metadata( snapshot ) ) ) {
exit_status = ret;
goto cleanup;
}
item = opal_list_get_first(&snapshot->local_snapshots);
vpid_snapshot = (orte_snapc_base_local_snapshot_t*)item;
if (NULL != snapshot->start_time ) {
opal_output(orte_restart_globals.output,
"Begin Timestamp: %s\n",
snapshot->start_time);
}
if (NULL != vpid_snapshot->opal_crs ) {
opal_output(orte_restart_globals.output,
"OPAL CRS Component: %s\n",
vpid_snapshot->opal_crs);
}
if (NULL != snapshot->reference_name) {
opal_output(orte_restart_globals.output,
"Snapshot Reference: %s\n",
snapshot->reference_name);
}
if (NULL != snapshot->local_location) {
opal_output(orte_restart_globals.output,
"Snapshot Location: %s\n",
snapshot->local_location);
}
if (NULL != snapshot->end_time ) {
opal_output(orte_restart_globals.output,
"End Timestamp: %s\n",
snapshot->end_time);
}
processes = 0;
for(item = opal_list_get_first(&snapshot->local_snapshots);
item != opal_list_get_end(&snapshot->local_snapshots);
item = opal_list_get_next(item) ) {
processes++;
}
opal_output(orte_restart_globals.output,
"Processes: %d\n",
processes);
for(item = opal_list_get_first(&snapshot->local_snapshots);
item != opal_list_get_end(&snapshot->local_snapshots);
item = opal_list_get_next(item) ) {
vpid_snapshot = (orte_snapc_base_local_snapshot_t*)item;
opal_output_verbose(10, orte_restart_globals.output,
"Process: %u.%u",
vpid_snapshot->process_name.jobid,
vpid_snapshot->process_name.vpid);
}
}
cleanup:
return exit_status;
}