Multiple commits

.github/workflows/close-stale-issues.yaml

@@ -0,0 +1,65 @@
+# The idea behind this Action is to prevent the situation where a user
+# files a Github Issue, someone asks for clarification / more
+# information, but the original poster never provides the information.
+# The issue then becomes forgotten and abondoned.
+#
+# Instead of that scenario, PMIx community members can assign a
+# label to Github Issues indicating that we're waiting for the user to
+# reply.  If too much time elapses with no reply, mark the Issue as
+# stale and emit a warning that we'll close the issue if we continue
+# to receive no reply.  If we timeout again with no reply after the
+# warning, close the Issue and emit a comment explaining why.
+#
+# If the user *does* reply, the label is removed, and this bot won't
+# touch the Issue.  Specifically: this bot will never mark stale /
+# close an Issue that doesn't have the specified label.
+#
+# Additionally, we are *only* marking stale / auto-closing Github
+# Issues -- not Pull Requests.
+#
+# This is a cron-based Action that runs a few times a day, just so
+# that we don't mark stale / close a bunch of issues all at once.
+#
+# While the actions/stale bot Action used here is capable of removing
+# the label when a user replies to the Issue, we actually use a 2nd
+# Action (removing-awaiting-user-info-label.yaml) to remove the label.
+# We do this because that 2nd Action runs whenever a comment is
+# created -- not via cron.  Hence, the 2nd Action will remove the
+# label effectively immediately when the user replies (vs. up to
+# several hours later).
+
+name: Close stale issues
+on:
+  schedule:
+    # Run it a few times a day so as not to necessarily mark stale /
+    # close a bunch of issues at once.
+    - cron: '0 1,5,9,13,17,21 * * *'
+
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    steps:
+      # https://github.com/marketplace/actions/close-stale-issues
+      - uses: actions/stale@v9
+        with:
+          # If there are no replies for 14 days, mark the issue as
+          # "stale" (and emit a warning).
+          days-before-stale: 14
+          # If there are no replies for 14 days after becoming stale,
+          # then close the issue (and emit a message explaining why).
+          days-before-close: 14
+
+          # Never close PRs
+          days-before-pr-close: -1
+
+          # We only close issues with this label
+          only-labels: "Awaiting response"
+          close-issue-label: Closed due to no reply
+
+          # Messages that we put in comments on issues
+          stale-issue-message: |
+            It looks like this issue is expecting a response, but hasn't gotten one yet.  If there are no responses in the next 2 weeks, we'll assume that the issue has been abandoned and will close it.
+          close-issue-message: |
+            Per the above comment, it has been a month with no reply on this issue.  It looks like this issue has been abandoned.
+
+            I'm going to close this issue.  If I'm wrong and this issue is *not* abandoned, please feel free to re-open it.  Thank you!

.github/workflows/remove-awaiting-user-info-label.yaml

@@ -0,0 +1,30 @@
+# This Action is run in conjunction with close-stale-issues.yaml.  See
+# that file for a more complete description of how they work together.
+
+name: 'Remove "Awaiting response" label when there has been a reply'
+on:
+  issue_comment:
+    types:
+      - created
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    # From
+    # https://github.com/marketplace/actions/close-issues-after-no-reply:
+    # only remove the label if someone replies to an issue who is not
+    # an owner or collaborator on the repo.
+    if: |
+      github.event.comment.author_association != 'OWNER' &&
+      github.event.comment.author_association != 'COLLABORATOR'
+    steps:
+      - name: 'Remove "Awaiting response" label'
+        uses: octokit/request-action@v2.x
+        continue-on-error: true
+        with:
+          route: DELETE /repos/:repository/issues/:issue/labels/:label
+          repository: ${{ github.repository }}
+          issue: ${{ github.event.issue.number }}
+          label: "Awaiting response"
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

configure.ac

@@ -27,7 +27,7 @@
 #                         All Rights reserved.
 # Copyright (c) 2021-2023 Nanook Consulting.  All rights reserved.
 # Copyright (c) 2021      FUJITSU LIMITED.  All rights reserved.
-# Copyright (c) 2023      Jeffrey M. Squyres.  All rights reserved.
+# Copyright (c) 2023-2024 Jeffrey M. Squyres.  All rights reserved.
 # $COPYRIGHT$
 #
 # Additional copyrights may follow
@@ -720,7 +720,8 @@ AC_INCLUDES_DEFAULT
 # Setup Sphinx processing
 #
 
-OAC_SETUP_SPHINX([$srcdir/docs/_build/html/index.html], [])
+OAC_SETUP_SPHINX([$srcdir/docs/_build/html/index.html], [],
+                 [$srcdir/docs/requirements.txt])
 AC_CHECK_PROGS(PYTHON, [python3 python python2])
 
 AS_IF([test -n "$OAC_MAKEDIST_DISABLE"],

src/docs/show-help-files/help-prte.rst

@@ -1,6 +1,6 @@
 .. -*- rst -*-
 
-   Copyright (c) 2021-2023 Nanook Consulting.  All rights reserved.
+   Copyright (c) 2021-2024 Nanook Consulting  All rights reserved.
    Copyright (c) 2023 Jeffrey M. Squyres.  All rights reserved.
 
    $COPYRIGHT$
@@ -79,9 +79,6 @@ option to the help request as ``--help <option>``.
    * - ``--leave-session-attached``
      - Do not discard stdout/stderr of remote PRRTE daemons
 
-   * - ``--test-suicide <arg0>``
-     - Direct that the specified daemon suicide after delay
-
    * - ``--display <arg0>``
      - Comma-delimited list of options for displaying information
 

src/docs/show-help-files/help-prterun.rst

@@ -1,6 +1,6 @@
 .. -*- rst -*-
 
-   Copyright (c) 2021-2023 Nanook Consulting.  All rights reserved.
+   Copyright (c) 2021-2024 Nanook Consulting  All rights reserved.
    Copyright (c) 2023 Jeffrey M. Squyres.  All rights reserved.
 
    $COPYRIGHT$
@@ -107,9 +107,6 @@ option to the help request as ``--help <option>``.
      - Direct the specified processes to stop at an
        application-controlled location
 
-   * - ``--test-suicide <arg0>``
-     - Direct that the specified daemon suicide after delay
-
    * - ``--do-not-launch``
      - Perform all necessary operations to prepare to launch the
        application, but do not actually launch it (usually used to

src/mca/errmgr/base/errmgr_base_fns.c

@@ -17,7 +17,7 @@
  * Copyright (c) 2014      Research Organization for Information Science
  *                         and Technology (RIST). All rights reserved.
  * Copyright (c) 2020      IBM Corporation.  All rights reserved.
- * Copyright (c) 2021-2022 Nanook Consulting.  All rights reserved.
+ * Copyright (c) 2021-2024 Nanook Consulting.  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -92,48 +92,3 @@ void prte_errmgr_base_log(int error_code, char *filename, int line)
     pmix_output(0, "%s PRTE_ERROR_LOG: %s in file %s at line %d",
                 PRTE_NAME_PRINT(PRTE_PROC_MY_NAME), errstring, filename, line);
 }
-
-void prte_errmgr_base_abort(int error_code, char *fmt, ...)
-{
-    va_list arglist;
-
-    /* If there was a message, output it */
-    va_start(arglist, fmt);
-    if (NULL != fmt) {
-        char *buffer = NULL;
-        pmix_vasprintf(&buffer, fmt, arglist);
-        pmix_output(0, "%s", buffer);
-        free(buffer);
-    }
-    va_end(arglist);
-
-    /* if I am a daemon or the HNP... */
-    if (PRTE_PROC_IS_MASTER || PRTE_PROC_IS_DAEMON) {
-        /* whack my local procs */
-        if (NULL != prte_odls.kill_local_procs) {
-            prte_odls.kill_local_procs(NULL);
-        }
-        /* whack any session directories */
-        prte_session_dir_cleanup(PRTE_JOBID_WILDCARD);
-    }
-
-    /* if a critical connection failed, or a sensor limit was exceeded, exit without dropping a core
-     */
-    if (PRTE_ERR_CONNECTION_FAILED == error_code || PRTE_ERR_SENSOR_LIMIT_EXCEEDED == error_code) {
-        prte_ess.abort(error_code, false);
-    } else {
-        prte_ess.abort(error_code, true);
-    }
-
-    /*
-     * We must exit in prte_ess.abort; all implementations of prte_ess.abort
-     * contain __prte_attribute_noreturn__
-     */
-    /* No way to reach here */
-}
-
-int prte_errmgr_base_abort_peers(pmix_proc_t *procs, int32_t num_procs, int error_code)
-{
-    PRTE_HIDE_UNUSED_PARAMS(procs, num_procs, error_code);
-    return PRTE_ERR_NOT_IMPLEMENTED;
-}

src/mca/errmgr/base/errmgr_base_frame.c

@@ -16,7 +16,7 @@
  * Copyright (c) 2014-2019 Research Organization for Information Science
  *                         and Technology (RIST).  All rights reserved.
  * Copyright (c) 2020      Cisco Systems, Inc.  All rights reserved
- * Copyright (c) 2021-2022 Nanook Consulting.  All rights reserved.
+ * Copyright (c) 2021-2024 Nanook Consulting.  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -48,27 +48,21 @@
 
 #include "src/mca/errmgr/base/static-components.h"
 
-/*
- * Globals
- */
-prte_errmgr_base_t prte_errmgr_base = {
-    .error_cbacks = PMIX_LIST_STATIC_INIT
-};
-
 /* Public module provides a wrapper around previous functions */
-prte_errmgr_base_module_t prte_errmgr_default_fns = {.init = NULL,     /* init     */
-                                                     .finalize = NULL, /* finalize */
-                                                     .logfn = prte_errmgr_base_log,
-                                                     .abort = prte_errmgr_base_abort,
-                                                     .abort_peers = prte_errmgr_base_abort_peers,
-                                                     .enable_detector = NULL};
+prte_errmgr_base_module_t prte_errmgr_default_fns = {
+    .init = NULL,     /* init     */
+    .finalize = NULL, /* finalize */
+    .logfn = prte_errmgr_base_log
+};
 
 /* NOTE: ABSOLUTELY MUST initialize this
  * struct to include the log function as it
  * gets called even if the errmgr hasn't been
  * opened yet due to error
  */
-prte_errmgr_base_module_t prte_errmgr = {.logfn = prte_errmgr_base_log};
+prte_errmgr_base_module_t prte_errmgr = {
+    .logfn = prte_errmgr_base_log
+};
 
 static int prte_errmgr_base_close(void)
 {
@@ -80,9 +74,6 @@ static int prte_errmgr_base_close(void)
     /* always leave a default set of fn pointers */
     prte_errmgr = prte_errmgr_default_fns;
 
-    /* destruct the callback list */
-    PMIX_LIST_DESTRUCT(&prte_errmgr_base.error_cbacks);
-
     return pmix_mca_base_framework_components_close(&prte_errmgr_base_framework, NULL);
 }
 
@@ -95,9 +86,6 @@ static int prte_errmgr_base_open(pmix_mca_base_open_flag_t flags)
     /* load the default fns */
     prte_errmgr = prte_errmgr_default_fns;
 
-    /* initialize the error callback list */
-    PMIX_CONSTRUCT(&prte_errmgr_base.error_cbacks, pmix_list_t);
-
     /* Open up all available components */
     return pmix_mca_base_framework_components_open(&prte_errmgr_base_framework, flags);
 }

src/mca/errmgr/base/errmgr_private.h

@@ -14,7 +14,7 @@
  *                         All rights reserved.
  * Copyright (c) 2017-2020 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) 2021-2024 Nanook Consulting.  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -48,13 +48,6 @@
  */
 BEGIN_C_DECLS
 
-/* define a struct to hold framework-global values */
-typedef struct {
-    pmix_list_t error_cbacks;
-} prte_errmgr_base_t;
-
-PRTE_EXPORT extern prte_errmgr_base_t prte_errmgr_base;
-
 /* declare the base default module */
 PRTE_EXPORT extern prte_errmgr_base_module_t prte_errmgr_default_fns;
 
@@ -63,9 +56,5 @@ PRTE_EXPORT extern prte_errmgr_base_module_t prte_errmgr_default_fns;
  */
 PRTE_EXPORT void prte_errmgr_base_log(int error_code, char *filename, int line);
 
-PRTE_EXPORT void prte_errmgr_base_abort(int error_code, char *fmt, ...)
-    __prte_attribute_format__(__printf__, 2, 3);
-PRTE_EXPORT int prte_errmgr_base_abort_peers(pmix_proc_t *procs, int32_t num_procs, int error_code);
-
 END_C_DECLS
 #endif

src/mca/errmgr/dvm/errmgr_dvm.c

@@ -11,7 +11,7 @@
  *                         All rights reserved.
  * Copyright (c) 2014-2020 Intel, Inc.  All rights reserved.
  * Copyright (c) 2017      IBM Corporation.  All rights reserved.
- * Copyright (c) 2021-2023 Nanook Consulting.  All rights reserved.
+ * Copyright (c) 2021-2024 Nanook Consulting.  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -71,9 +71,7 @@ static int finalize(void);
 prte_errmgr_base_module_t prte_errmgr_dvm_module = {
     .init = init,
     .finalize = finalize,
-    .logfn = prte_errmgr_base_log,
-    .abort = prte_errmgr_base_abort,
-    .abort_peers = prte_errmgr_base_abort_peers
+    .logfn = prte_errmgr_base_log
 };
 
 /*
@@ -488,14 +486,14 @@ static void proc_errors(int fd, short args, void *cbdata)
             PRTE_FLAG_SET(jdata, PRTE_JOB_FLAG_ABORTED);
             /* kill the job */
             _terminate_job(jdata->nspace);
+            PRTE_ACTIVATE_JOB_STATE(jdata, PRTE_JOB_STATE_FAILED_TO_START);
         }
         /* if this was a daemon, report it */
         if (PMIX_CHECK_NSPACE(jdata->nspace, PRTE_PROC_MY_NAME->nspace)) {
             /* output a message indicating we failed to launch a daemon */
             pmix_show_help("help-errmgr-base.txt", "failed-daemon-launch",
                            true, prte_tool_basename);
         }
-        PRTE_ACTIVATE_JOB_STATE(jdata, PRTE_JOB_STATE_FAILED_TO_START);
         break;
 
     case PRTE_PROC_STATE_CALLED_ABORT:

src/mca/errmgr/errmgr.h

@@ -16,7 +16,7 @@
  *                         reserved.
  * Copyright (c) 2013-2020 Intel, Inc.  All rights reserved.
  * Copyright (c) 2014      NVIDIA Corporation.  All rights reserved.
- * Copyright (c) 2021-2022 Nanook Consulting.  All rights reserved.
+ * Copyright (c) 2021-2024 Nanook Consulting.  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -99,27 +99,6 @@ typedef int (*prte_errmgr_base_module_finalize_fn_t)(void);
  */
 typedef void (*prte_errmgr_base_module_log_fn_t)(int error_code, char *filename, int line);
 
-/**
- * Alert - self aborting
- * This function is called when a process is aborting due to some internal error.
- * It will finalize the process
- * itself, and then exit - it takes no other actions. The intent here is to provide
- * a last-ditch exit procedure that attempts to clean up a little.
- */
-typedef void (*prte_errmgr_base_module_abort_fn_t)(int error_code, char *fmt, ...)
-    __prte_attribute_format_funcptr__(__printf__, 2, 3);
-
-/**
- * Alert - abort peers
- *  This function is called when a process wants to abort one or more peer processes.
- *  For example, MPI_Abort(comm) will use this function to terminate peers in the
- *  communicator group before aborting itself.
- */
-typedef int (*prte_errmgr_base_module_abort_peers_fn_t)(pmix_proc_t *procs, int32_t num_procs,
-                                                        int error_code);
-
-typedef void (*prte_errmgr_base_module_enable_detector_fn_t)(bool flag);
-
 /*
  * Module Structure
  */
@@ -130,11 +109,6 @@ struct prte_errmgr_base_module_2_3_0_t {
     prte_errmgr_base_module_finalize_fn_t finalize;
 
     prte_errmgr_base_module_log_fn_t logfn;
-    prte_errmgr_base_module_abort_fn_t abort;
-    prte_errmgr_base_module_abort_peers_fn_t abort_peers;
-
-    /* start error detector and propagator */
-    prte_errmgr_base_module_enable_detector_fn_t enable_detector;
 };
 typedef struct prte_errmgr_base_module_2_3_0_t prte_errmgr_base_module_2_3_0_t;
 typedef prte_errmgr_base_module_2_3_0_t prte_errmgr_base_module_t;