Checkpoint work on scheduler tool, few minor cleanups

.gitignore

@@ -162,6 +162,7 @@ src/tools/prte/prte
 src/tools/pcc/pcc
 src/tools/pcc/pcc-wrapper-data.txt
 src/tools/pterm/pterm
+src/tools/psched/psched
 
 src/util/hostfile/hostfile_lex.c
 src/util/keyval/keyval_lex.c

config/prte_config_files.m4

@@ -26,5 +26,6 @@ AC_DEFUN([PRTE_CONFIG_FILES],[
         src/tools/prte_info/Makefile
         src/tools/prte/Makefile
         src/tools/pterm/Makefile
+        src/tools/psched/Makefile
     ])
 ])

src/mca/ess/base/ess_base_std_prolog.c

@@ -11,7 +11,7 @@
  *                         All rights reserved.
  * Copyright (c) 2019      Intel, Inc.  All rights reserved.
  * Copyright (c) 2020      Cisco Systems, Inc.  All rights reserved
- * Copyright (c) 2021-2022 Nanook Consulting.  All rights reserved.
+ * Copyright (c) 2021-2023 Nanook Consulting.  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -60,8 +60,9 @@ int prte_ess_base_std_prolog(void)
     return PRTE_SUCCESS;
 
 error:
-    pmix_show_help("help-prte-runtime", "prte_init:startup:internal-failure", true, error,
-                   PRTE_ERROR_NAME(ret), ret);
+    pmix_show_help("help-prte-runtime",
+                   "prte_init:startup:internal-failure", true,
+                   error, PRTE_ERROR_NAME(ret), ret);
 
     return ret;
 }

src/mca/state/dvm/state_dvm.c

@@ -64,18 +64,18 @@ static void ready_for_debug(int fd, short args, void *cbata);
  * DVM module - used when mpirun is persistent
  ******************/
 prte_state_base_module_t prte_state_dvm_module = {
-    init,
-    finalize,
-    prte_state_base_activate_job_state,
-    prte_state_base_add_job_state,
-    prte_state_base_set_job_state_callback,
-    prte_state_base_set_job_state_priority,
-    prte_state_base_remove_job_state,
-    prte_state_base_activate_proc_state,
-    prte_state_base_add_proc_state,
-    prte_state_base_set_proc_state_callback,
-    prte_state_base_set_proc_state_priority,
-    prte_state_base_remove_proc_state
+    .init = init,
+    .finalize = finalize,
+    .activate_job_state = prte_state_base_activate_job_state,
+    .add_job_state = prte_state_base_add_job_state,
+    .set_job_state_callback = prte_state_base_set_job_state_callback,
+    .set_job_state_priority = prte_state_base_set_job_state_priority,
+    .remove_job_state = prte_state_base_remove_job_state,
+    .activate_proc_state = prte_state_base_activate_proc_state,
+    .add_proc_state = prte_state_base_add_proc_state,
+    .set_proc_state_callback = prte_state_base_set_proc_state_callback,
+    .set_proc_state_priority = prte_state_base_set_proc_state_priority,
+    .remove_proc_state = prte_state_base_remove_proc_state
 };
 
 static void dvm_notify(int sd, short args, void *cbdata);

src/mca/state/prted/state_prted.c

@@ -49,18 +49,18 @@ static int finalize(void);
  * PRTED module
  ******************/
 prte_state_base_module_t prte_state_prted_module = {
-    init,
-    finalize,
-    prte_state_base_activate_job_state,
-    prte_state_base_add_job_state,
-    prte_state_base_set_job_state_callback,
-    prte_state_base_set_job_state_priority,
-    prte_state_base_remove_job_state,
-    prte_state_base_activate_proc_state,
-    prte_state_base_add_proc_state,
-    prte_state_base_set_proc_state_callback,
-    prte_state_base_set_proc_state_priority,
-    prte_state_base_remove_proc_state
+    .init = init,
+    .finalize = finalize,
+    .activate_job_state = prte_state_base_activate_job_state,
+    .add_job_state = prte_state_base_add_job_state,
+    .set_job_state_callback = prte_state_base_set_job_state_callback,
+    .set_job_state_priority = prte_state_base_set_job_state_priority,
+    .remove_job_state = prte_state_base_remove_job_state,
+    .activate_proc_state = prte_state_base_activate_proc_state,
+    .add_proc_state = prte_state_base_add_proc_state,
+    .set_proc_state_callback = prte_state_base_set_proc_state_callback,
+    .set_proc_state_priority = prte_state_base_set_proc_state_priority,
+    .remove_proc_state = prte_state_base_remove_proc_state
 };
 
 /* Local functions */

src/prted/pmix/pmix_server.c

@@ -554,6 +554,7 @@ static void regcbfunc(pmix_status_t status, size_t ref, void *cbdata)
     PRTE_HIDE_UNUSED_PARAMS(status, ref);
 
     PMIX_ACQUIRE_OBJECT(lock);
+    lock->status = status;
     PRTE_PMIX_WAKEUP_THREAD(lock);
 }
 
@@ -596,6 +597,7 @@ int pmix_server_init(void)
     PMIX_INFO_LIST_ADD(prc, ilist, PMIX_HOSTNAME, prte_process_info.nodename, PMIX_STRING);
     if (PMIX_SUCCESS != prc) {
         PMIX_INFO_LIST_RELEASE(ilist);
+        rc = prte_pmix_convert_status(prc);
         return rc;
     }
 
@@ -604,6 +606,7 @@ int pmix_server_init(void)
     PMIX_INFO_LIST_ADD(prc, ilist, PMIX_EXTERNAL_AUX_EVENT_BASE, prte_event_base, PMIX_POINTER);
     if (PMIX_SUCCESS != prc) {
         PMIX_INFO_LIST_RELEASE(ilist);
+        rc = prte_pmix_convert_status(prc);
         return rc;
     }
 #endif
@@ -620,12 +623,14 @@ int pmix_server_init(void)
     PMIX_INFO_LIST_INSERT(prc, ilist, &myinf);
     if (PMIX_SUCCESS != prc) {
         PMIX_INFO_LIST_RELEASE(ilist);
+        rc = prte_pmix_convert_status(prc);
         return rc;
     }
     // tell the server to share this topology for us
     PMIX_INFO_LIST_ADD(prc, ilist, PMIX_SERVER_SHARE_TOPOLOGY, NULL, PMIX_BOOL);
     if (PMIX_SUCCESS != prc) {
         PMIX_INFO_LIST_RELEASE(ilist);
+        rc = prte_pmix_convert_status(prc);
         return rc;
     }
 
@@ -838,6 +843,7 @@ int pmix_server_init(void)
     PMIX_INFO_LIST_ADD(prc, ilist, PMIX_HOSTNAME, prte_process_info.nodename, PMIX_STRING);
     if (PMIX_SUCCESS != rc) {
         PMIX_INFO_LIST_RELEASE(ilist);
+        rc = prte_pmix_convert_status(prc);
         return rc;
     }
 
@@ -848,6 +854,7 @@ int pmix_server_init(void)
         free(tmp);
         if (PMIX_SUCCESS != rc) {
             PMIX_INFO_LIST_RELEASE(ilist);
+            rc = prte_pmix_convert_status(prc);
             return rc;
         }
     }
@@ -871,7 +878,9 @@ int pmix_server_init(void)
     prc = PMIX_ERR_LOST_CONNECTION;
     PMIx_Register_event_handler(&prc, 1, NULL, 0, lost_connection_hdlr, regcbfunc, &lock);
     PRTE_PMIX_WAIT_THREAD(&lock);
+    prc = lock.status;
     PRTE_PMIX_DESTRUCT_LOCK(&lock);
+    rc = prte_pmix_convert_status(prc);
 
     return rc;
 }

src/runtime/prte_init.c

@@ -83,6 +83,7 @@
 #include "src/runtime/prte_globals.h"
 #include "src/runtime/prte_locks.h"
 #include "src/runtime/runtime.h"
+#include "src/runtime/runtime_internals.h"
 
 /*
  * Whether we have completed prte_init or we are in prte_finalize
@@ -116,8 +117,6 @@ static bool min_initialized = false;
 #endif
 const char prte_version_string[] = PRTE_IDENT_STRING;
 
-static void preload_default_mca_params(void);
-
 static bool check_exist(char *path)
 {
     struct stat buf;
@@ -222,7 +221,7 @@ int prte_init_util(prte_proc_type_t flags)
     }
 
     /* pre-load any default mca param files */
-    preload_default_mca_params();
+    prte_preload_default_mca_params();
 
     /* Register all MCA Params */
     if (PRTE_SUCCESS != (ret = prte_register_params())) {
@@ -417,7 +416,7 @@ static bool check_pmix_overlap(char *var, char *value)
     return false;
 }
 
-static void preload_default_mca_params(void)
+void prte_preload_default_mca_params(void)
 {
     char *file, *home, *tmp;
     pmix_list_t params, params2, pfinal;

src/runtime/runtime_internals.h

@@ -37,6 +37,8 @@ BEGIN_C_DECLS
  */
 PRTE_EXPORT int prte_dt_init(void);
 
+PRTE_EXPORT void prte_preload_default_mca_params(void);
+
 END_C_DECLS
 
 #endif /* PRTE_RUNTIME_INTERNALS_H */

src/tools/Makefile.am

@@ -31,12 +31,14 @@ SUBDIRS += \
 	tools/pcc \
     tools/prte_info \
     tools/prte \
-    tools/pterm
+    tools/pterm \
+    tools/psched
 
 DIST_SUBDIRS += \
 	tools/prted \
 	tools/prun \
 	tools/pcc \
     tools/prte_info \
     tools/prte \
-    tools/pterm
+    tools/pterm \
+    tools/psched

src/tools/psched/Makefile.am

@@ -0,0 +1,68 @@
+#
+# 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.
+# Copyright (c) 2004-2009 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) 2007-2020 Cisco Systems, Inc.  All rights reserved
+# Copyright (c) 2008      Sun Microsystems, Inc.  All rights reserved.
+# Copyright (c) 2016-2020 Intel, Inc.  All rights reserved.
+# Copyright (c) 2021-2023 Nanook Consulting.  All rights reserved.
+# $COPYRIGHT$
+#
+# Additional copyrights may follow
+#
+# $HEADER$
+#
+
+AM_LDFLAGS = $(prte_hwloc_LDFLAGS) $(prte_libevent_LDFLAGS) $(prte_pmix_LDFLAGS)
+AM_CFLAGS = \
+            -DPRTE_CONFIGURE_USER="\"@PRTE_CONFIGURE_USER@\"" \
+            -DPRTE_CONFIGURE_HOST="\"@PRTE_CONFIGURE_HOST@\"" \
+            -DPRTE_CONFIGURE_DATE="\"@PRTE_CONFIGURE_DATE@\"" \
+            -DPRTE_BUILD_USER="\"$$USER\"" \
+            -DPRTE_BUILD_HOST="\"$${HOSTNAME:-`(hostname || uname -n) | sed 1q`}\"" \
+            -DPRTE_BUILD_DATE="\"`$(top_srcdir)/config/getdate.sh`\"" \
+            -DPRTE_BUILD_CFLAGS="\"@CFLAGS@\"" \
+            -DPRTE_BUILD_CPPFLAGS="\"@CPPFLAGS@\"" \
+            -DPRTE_BUILD_LDFLAGS="\"@LDFLAGS@\"" \
+            -DPRTE_BUILD_LIBS="\"@LIBS@\"" \
+            -DPRTE_CC_ABSOLUTE="\"@PRTE_CC_ABSOLUTE@\"" \
+            -DPRTE_GREEK_VERSION="\"@PRTE_GREEK_VERSION@\"" \
+            -DPRTE_REPO_REV="\"@PRTE_REPO_REV@\"" \
+            -DPMIX_RELEASE_DATE="\"@PMIX_RELEASE_DATE@\""
+
+bin_PROGRAMS = psched
+
+dist_prtedata_DATA = help-psched.txt
+
+psched_SOURCES = \
+	psched.h \
+	psched.c \
+	errmgr.c \
+	state.c \
+	server.c \
+	scheduler.c \
+	backend.c \
+	event.c \
+	queries.c \
+	schizo.c \
+	session.c
+
+# the following empty psched_LDFLAGS is used
+#  so that the psched can be compiled statically
+#  by simply changing the value of this from
+#  nothing to -all-static in the Makefile.in
+#  nice for systems that don't have all the shared
+#  libraries on the computes
+psched_LDFLAGS =
+psched_LDADD = \
+    $(prte_libevent_LIBS) \
+    $(prte_hwloc_LIBS) \
+    $(prte_pmix_LIBS) \
+	$(top_builddir)/src/libprrte.la