pcmk_sched_resource.c

Go to the documentation of this file.

/*
 * Copyright 2014-2023 the Pacemaker project contributors
 *
 * The version control history for this file may have further details.
 *
 * This source code is licensed under the GNU General Public License version 2
 * or later (GPLv2+) WITHOUT ANY WARRANTY.
 */

#include <crm_internal.h>

#include <stdlib.h>
#include <string.h>
#include <crm/msg_xml.h>
#include <pacemaker-internal.h>

#include "libpacemaker_private.h"

// Resource assignment methods by resource variant
static pcmk_assignment_methods_t assignment_methods[] = {
    {
        pcmk__primitive_assign,
        pcmk__primitive_create_actions,
        pcmk__probe_rsc_on_node,
        pcmk__primitive_internal_constraints,
        pcmk__primitive_apply_coloc_score,
        pcmk__colocated_resources,
        pcmk__with_primitive_colocations,
        pcmk__primitive_with_colocations,
        pcmk__add_colocated_node_scores,
        pcmk__apply_location,
        pcmk__primitive_action_flags,
        pcmk__update_ordered_actions,
        pcmk__output_resource_actions,
        pcmk__add_rsc_actions_to_graph,
        pcmk__primitive_add_graph_meta,
        pcmk__primitive_add_utilization,
        pcmk__primitive_shutdown_lock,
    },
    {
        pcmk__group_assign,
        pcmk__group_create_actions,
        pcmk__probe_rsc_on_node,
        pcmk__group_internal_constraints,
        pcmk__group_apply_coloc_score,
        pcmk__group_colocated_resources,
        pcmk__with_group_colocations,
        pcmk__group_with_colocations,
        pcmk__group_add_colocated_node_scores,
        pcmk__group_apply_location,
        pcmk__group_action_flags,
        pcmk__group_update_ordered_actions,
        pcmk__output_resource_actions,
        pcmk__add_rsc_actions_to_graph,
        pcmk__noop_add_graph_meta,
        pcmk__group_add_utilization,
        pcmk__group_shutdown_lock,
    },
    {
        pcmk__clone_assign,
        pcmk__clone_create_actions,
        pcmk__clone_create_probe,
        pcmk__clone_internal_constraints,
        pcmk__clone_apply_coloc_score,
        pcmk__colocated_resources,
        pcmk__with_clone_colocations,
        pcmk__clone_with_colocations,
        pcmk__add_colocated_node_scores,
        pcmk__clone_apply_location,
        pcmk__clone_action_flags,
        pcmk__instance_update_ordered_actions,
        pcmk__output_resource_actions,
        pcmk__clone_add_actions_to_graph,
        pcmk__clone_add_graph_meta,
        pcmk__clone_add_utilization,
        pcmk__clone_shutdown_lock,
    },
    {
        pcmk__bundle_assign,
        pcmk__bundle_create_actions,
        pcmk__bundle_create_probe,
        pcmk__bundle_internal_constraints,
        pcmk__bundle_apply_coloc_score,
        pcmk__colocated_resources,
        pcmk__with_bundle_colocations,
        pcmk__bundle_with_colocations,
        pcmk__add_colocated_node_scores,
        pcmk__bundle_apply_location,
        pcmk__bundle_action_flags,
        pcmk__instance_update_ordered_actions,
        pcmk__output_bundle_actions,
        pcmk__bundle_add_actions_to_graph,
        pcmk__noop_add_graph_meta,
        pcmk__bundle_add_utilization,
        pcmk__bundle_shutdown_lock,
    }
};

bool
pcmk__rsc_agent_changed(pcmk_resource_t *rsc, pcmk_node_t *node,
                        const xmlNode *rsc_entry, bool active_on_node)
{
    bool changed = false;
    const char *attr_list[] = {
        XML_ATTR_TYPE,
        XML_AGENT_ATTR_CLASS,
        XML_AGENT_ATTR_PROVIDER
    };

    for (int i = 0; i < PCMK__NELEM(attr_list); i++) {
        const char *value = crm_element_value(rsc->xml, attr_list[i]);
        const char *old_value = crm_element_value(rsc_entry, attr_list[i]);

        if (!pcmk__str_eq(value, old_value, pcmk__str_none)) {
            changed = true;
            trigger_unfencing(rsc, node, "Device definition changed", NULL,
                              rsc->cluster);
            if (active_on_node) {
                crm_notice("Forcing restart of %s on %s "
                           "because %s changed from '%s' to '%s'",
                           rsc->id, pe__node_name(node), attr_list[i],
                           pcmk__s(old_value, ""), pcmk__s(value, ""));
            }
        }
    }
    if (changed && active_on_node) {
        // Make sure the resource is restarted
        custom_action(rsc, stop_key(rsc), PCMK_ACTION_STOP, node, FALSE,
                      rsc->cluster);
        pe__set_resource_flags(rsc, pcmk_rsc_start_pending);
    }
    return changed;
}

static GList *
add_rsc_if_matching(GList *result, pcmk_resource_t *rsc, const char *id)
{
    if ((strcmp(rsc->id, id) == 0)
        || ((rsc->clone_name != NULL) && (strcmp(rsc->clone_name, id) == 0))) {
        result = g_list_prepend(result, rsc);
    }
    for (GList *iter = rsc->children; iter != NULL; iter = iter->next) {
        pcmk_resource_t *child = (pcmk_resource_t *) iter->data;

        result = add_rsc_if_matching(result, child, id);
    }
    return result;
}

GList *
pcmk__rscs_matching_id(const char *id, const pcmk_scheduler_t *scheduler)
{
    GList *result = NULL;

    CRM_CHECK((id != NULL) && (scheduler != NULL), return NULL);
    for (GList *iter = scheduler->resources; iter != NULL; iter = iter->next) {
        result = add_rsc_if_matching(result, (pcmk_resource_t *) iter->data,
                                     id);
    }
    return result;
}

static void
set_assignment_methods_for_rsc(gpointer data, gpointer user_data)
{
    pcmk_resource_t *rsc = data;

    rsc->cmds = &assignment_methods[rsc->variant];
    g_list_foreach(rsc->children, set_assignment_methods_for_rsc, NULL);
}

void
pcmk__set_assignment_methods(pcmk_scheduler_t *scheduler)
{
    g_list_foreach(scheduler->resources, set_assignment_methods_for_rsc, NULL);
}

static inline void
add_colocated_resources(const pcmk_resource_t *rsc,
                        const pcmk_resource_t *orig_rsc, GList **list)
{
    *list = rsc->cmds->colocated_resources(rsc, orig_rsc, *list);
}

// Shared implementation of pcmk_assignment_methods_t:colocated_resources()
GList *
pcmk__colocated_resources(const pcmk_resource_t *rsc,
                          const pcmk_resource_t *orig_rsc,
                          GList *colocated_rscs)
{
    const GList *iter = NULL;
    GList *colocations = NULL;

    if (orig_rsc == NULL) {
        orig_rsc = rsc;
    }

    if ((rsc == NULL) || (g_list_find(colocated_rscs, rsc) != NULL)) {
        return colocated_rscs;
    }

    pe_rsc_trace(orig_rsc, "%s is in colocation chain with %s",
                 rsc->id, orig_rsc->id);
    colocated_rscs = g_list_prepend(colocated_rscs, (gpointer) rsc);

    // Follow colocations where this resource is the dependent resource
    colocations = pcmk__this_with_colocations(rsc);
    for (iter = colocations; iter != NULL; iter = iter->next) {
        const pcmk__colocation_t *constraint = iter->data;
        const pcmk_resource_t *primary = constraint->primary;

        if (primary == orig_rsc) {
            continue; // Break colocation loop
        }

        if ((constraint->score == INFINITY) &&
            (pcmk__colocation_affects(rsc, primary, constraint,
                                      true) == pcmk__coloc_affects_location)) {
            add_colocated_resources(primary, orig_rsc, &colocated_rscs);
        }
    }
    g_list_free(colocations);

    // Follow colocations where this resource is the primary resource
    colocations = pcmk__with_this_colocations(rsc);
    for (iter = colocations; iter != NULL; iter = iter->next) {
        const pcmk__colocation_t *constraint = iter->data;
        const pcmk_resource_t *dependent = constraint->dependent;

        if (dependent == orig_rsc) {
            continue; // Break colocation loop
        }

        if (pe_rsc_is_clone(rsc) && !pe_rsc_is_clone(dependent)) {
            continue; // We can't be sure whether dependent will be colocated
        }

        if ((constraint->score == INFINITY) &&
            (pcmk__colocation_affects(dependent, rsc, constraint,
                                      true) == pcmk__coloc_affects_location)) {
            add_colocated_resources(dependent, orig_rsc, &colocated_rscs);
        }
    }
    g_list_free(colocations);

    return colocated_rscs;
}

// No-op function for variants that don't need to implement add_graph_meta()
void
pcmk__noop_add_graph_meta(const pcmk_resource_t *rsc, xmlNode *xml)
{
}

void
pcmk__output_resource_actions(pcmk_resource_t *rsc)
{
    pcmk_node_t *next = NULL;
    pcmk_node_t *current = NULL;
    pcmk__output_t *out = NULL;

    CRM_ASSERT(rsc != NULL);

    out = rsc->cluster->priv;
    if (rsc->children != NULL) {
        for (GList *iter = rsc->children; iter != NULL; iter = iter->next) {
            pcmk_resource_t *child = (pcmk_resource_t *) iter->data;

            child->cmds->output_actions(child);
        }
        return;
    }

    next = rsc->allocated_to;
    if (rsc->running_on) {
        current = pe__current_node(rsc);
        if (rsc->role == pcmk_role_stopped) {
            /* This can occur when resources are being recovered because
             * the current role can change in pcmk__primitive_create_actions()
             */
            rsc->role = pcmk_role_started;
        }
    }

    if ((current == NULL) && pcmk_is_set(rsc->flags, pcmk_rsc_removed)) {
        /* Don't log stopped orphans */
        return;
    }

    out->message(out, "rsc-action", rsc, current, next);
}

static inline void
add_assigned_resource(pcmk_node_t *node, pcmk_resource_t *rsc)
{
    node->details->allocated_rsc = g_list_prepend(node->details->allocated_rsc,
                                                  rsc);
}

bool
pcmk__assign_resource(pcmk_resource_t *rsc, pcmk_node_t *node, bool force,
                      bool stop_if_fail)
{
    bool changed = false;

    CRM_ASSERT(rsc != NULL);

    if (rsc->children != NULL) {
        for (GList *iter = rsc->children; iter != NULL; iter = iter->next) {
            pcmk_resource_t *child_rsc = iter->data;

            changed |= pcmk__assign_resource(child_rsc, node, force,
                                             stop_if_fail);
        }
        return changed;
    }

    // Assigning a primitive

    if (!force && (node != NULL)
        && ((node->weight < 0)
            // Allow graph to assume that guest node connections will come up
            || (!pcmk__node_available(node, true, false)
                && !pe__is_guest_node(node)))) {

        pe_rsc_debug(rsc,
                     "All nodes for resource %s are unavailable, unclean or "
                     "shutting down (%s can%s run resources, with score %s)",
                     rsc->id, pe__node_name(node),
                     (pcmk__node_available(node, true, false)? "" : "not"),
                     pcmk_readable_score(node->weight));

        if (stop_if_fail) {
            pe__set_next_role(rsc, pcmk_role_stopped, "node availability");
        }
        node = NULL;
    }

    if (rsc->allocated_to != NULL) {
        changed = !pe__same_node(rsc->allocated_to, node);
    } else {
        changed = (node != NULL);
    }
    pcmk__unassign_resource(rsc);
    pe__clear_resource_flags(rsc, pcmk_rsc_unassigned);

    if (node == NULL) {
        char *rc_stopped = NULL;

        pe_rsc_debug(rsc, "Could not assign %s to a node", rsc->id);

        if (!stop_if_fail) {
            return changed;
        }
        pe__set_next_role(rsc, pcmk_role_stopped, "unable to assign");

        for (GList *iter = rsc->actions; iter != NULL; iter = iter->next) {
            pcmk_action_t *op = (pcmk_action_t *) iter->data;

            pe_rsc_debug(rsc, "Updating %s for %s assignment failure",
                         op->uuid, rsc->id);

            if (pcmk__str_eq(op->task, PCMK_ACTION_STOP, pcmk__str_none)) {
                pe__clear_action_flags(op, pcmk_action_optional);

            } else if (pcmk__str_eq(op->task, PCMK_ACTION_START,
                                    pcmk__str_none)) {
                pe__clear_action_flags(op, pcmk_action_runnable);

            } else {
                // Cancel recurring actions, unless for stopped state
                const char *interval_ms_s = NULL;
                const char *target_rc_s = NULL;

                interval_ms_s = g_hash_table_lookup(op->meta,
                                                    XML_LRM_ATTR_INTERVAL_MS);
                target_rc_s = g_hash_table_lookup(op->meta,
                                                  XML_ATTR_TE_TARGET_RC);
                if (rc_stopped == NULL) {
                    rc_stopped = pcmk__itoa(PCMK_OCF_NOT_RUNNING);
                }

                if (!pcmk__str_eq(interval_ms_s, "0", pcmk__str_null_matches)
                    && !pcmk__str_eq(rc_stopped, target_rc_s, pcmk__str_none)) {

                    pe__clear_action_flags(op, pcmk_action_runnable);
                }
            }
        }
        free(rc_stopped);
        return changed;
    }

    pe_rsc_debug(rsc, "Assigning %s to %s", rsc->id, pe__node_name(node));
    rsc->allocated_to = pe__copy_node(node);

    add_assigned_resource(node, rsc);
    node->details->num_resources++;
    node->count++;
    pcmk__consume_node_capacity(node->details->utilization, rsc);

    if (pcmk_is_set(rsc->cluster->flags, pcmk_sched_show_utilization)) {
        pcmk__output_t *out = rsc->cluster->priv;

        out->message(out, "resource-util", rsc, node, __func__);
    }
    return changed;
}

void
pcmk__unassign_resource(pcmk_resource_t *rsc)
{
    pcmk_node_t *old = rsc->allocated_to;

    if (old == NULL) {
        crm_info("Unassigning %s", rsc->id);
    } else {
        crm_info("Unassigning %s from %s", rsc->id, pe__node_name(old));
    }

    pe__set_resource_flags(rsc, pcmk_rsc_unassigned);

    if (rsc->children == NULL) {
        if (old == NULL) {
            return;
        }
        rsc->allocated_to = NULL;

        /* We're going to free the pcmk_node_t, but its details member is shared
         * and will remain, so update that appropriately first.
         */
        old->details->allocated_rsc = g_list_remove(old->details->allocated_rsc,
                                                    rsc);
        old->details->num_resources--;
        pcmk__release_node_capacity(old->details->utilization, rsc);
        free(old);
        return;
    }

    for (GList *iter = rsc->children; iter != NULL; iter = iter->next) {
        pcmk__unassign_resource((pcmk_resource_t *) iter->data);
    }
}

bool
pcmk__threshold_reached(pcmk_resource_t *rsc, const pcmk_node_t *node,
                        pcmk_resource_t **failed)
{
    int fail_count, remaining_tries;
    pcmk_resource_t *rsc_to_ban = rsc;

    // Migration threshold of 0 means never force away
    if (rsc->migration_threshold == 0) {
        return false;
    }

    // If we're ignoring failures, also ignore the migration threshold
    if (pcmk_is_set(rsc->flags, pcmk_rsc_ignore_failure)) {
        return false;
    }

    // If there are no failures, there's no need to force away
    fail_count = pe_get_failcount(node, rsc, NULL,
                                  pcmk__fc_effective|pcmk__fc_fillers, NULL);
    if (fail_count <= 0) {
        return false;
    }

    // If failed resource is anonymous clone instance, we'll force clone away
    if (!pcmk_is_set(rsc->flags, pcmk_rsc_unique)) {
        rsc_to_ban = uber_parent(rsc);
    }

    // How many more times recovery will be tried on this node
    remaining_tries = rsc->migration_threshold - fail_count;

    if (remaining_tries <= 0) {
        crm_warn("%s cannot run on %s due to reaching migration threshold "
                 "(clean up resource to allow again)"
                 CRM_XS " failures=%d migration-threshold=%d",
                 rsc_to_ban->id, pe__node_name(node), fail_count,
                 rsc->migration_threshold);
        if (failed != NULL) {
            *failed = rsc_to_ban;
        }
        return true;
    }

    crm_info("%s can fail %d more time%s on "
             "%s before reaching migration threshold (%d)",
             rsc_to_ban->id, remaining_tries, pcmk__plural_s(remaining_tries),
             pe__node_name(node), rsc->migration_threshold);
    return false;
}

static int
get_node_score(const pcmk_node_t *node, GHashTable *nodes)
{
    pcmk_node_t *found_node = NULL;

    if ((node != NULL) && (nodes != NULL)) {
        found_node = g_hash_table_lookup(nodes, node->details->id);
    }
    return (found_node == NULL)? -INFINITY : found_node->weight;
}

static gint
cmp_resources(gconstpointer a, gconstpointer b, gpointer data)
{
    /* GLib insists that this function require gconstpointer arguments, but we
     * make a small, temporary change to each argument (setting the
     * pe_rsc_merging flag) during comparison
     */
    pcmk_resource_t *resource1 = (pcmk_resource_t *) a;
    pcmk_resource_t *resource2 = (pcmk_resource_t *) b;
    const GList *nodes = data;

    int rc = 0;
    int r1_score = -INFINITY;
    int r2_score = -INFINITY;
    pcmk_node_t *r1_node = NULL;
    pcmk_node_t *r2_node = NULL;
    GHashTable *r1_nodes = NULL;
    GHashTable *r2_nodes = NULL;
    const char *reason = NULL;

    // Resources with highest priority should be assigned first
    reason = "priority";
    r1_score = resource1->priority;
    r2_score = resource2->priority;
    if (r1_score > r2_score) {
        rc = -1;
        goto done;
    }
    if (r1_score < r2_score) {
        rc = 1;
        goto done;
    }

    // We need nodes to make any other useful comparisons
    reason = "no node list";
    if (nodes == NULL) {
        goto done;
    }

    // Calculate and log node scores
    resource1->cmds->add_colocated_node_scores(resource1, NULL, resource1->id,
                                               &r1_nodes, NULL, 1,
                                               pcmk__coloc_select_this_with);
    resource2->cmds->add_colocated_node_scores(resource2, NULL, resource2->id,
                                               &r2_nodes, NULL, 1,
                                               pcmk__coloc_select_this_with);
    pe__show_node_scores(true, NULL, resource1->id, r1_nodes,
                         resource1->cluster);
    pe__show_node_scores(true, NULL, resource2->id, r2_nodes,
                         resource2->cluster);

    // The resource with highest score on its current node goes first
    reason = "current location";
    if (resource1->running_on != NULL) {
        r1_node = pe__current_node(resource1);
    }
    if (resource2->running_on != NULL) {
        r2_node = pe__current_node(resource2);
    }
    r1_score = get_node_score(r1_node, r1_nodes);
    r2_score = get_node_score(r2_node, r2_nodes);
    if (r1_score > r2_score) {
        rc = -1;
        goto done;
    }
    if (r1_score < r2_score) {
        rc = 1;
        goto done;
    }

    // Otherwise a higher score on any node will do
    reason = "score";
    for (const GList *iter = nodes; iter != NULL; iter = iter->next) {
        const pcmk_node_t *node = (const pcmk_node_t *) iter->data;

        r1_score = get_node_score(node, r1_nodes);
        r2_score = get_node_score(node, r2_nodes);
        if (r1_score > r2_score) {
            rc = -1;
            goto done;
        }
        if (r1_score < r2_score) {
            rc = 1;
            goto done;
        }
    }

done:
    crm_trace("%s (%d)%s%s %c %s (%d)%s%s: %s",
              resource1->id, r1_score,
              ((r1_node == NULL)? "" : " on "),
              ((r1_node == NULL)? "" : r1_node->details->id),
              ((rc < 0)? '>' : ((rc > 0)? '<' : '=')),
              resource2->id, r2_score,
              ((r2_node == NULL)? "" : " on "),
              ((r2_node == NULL)? "" : r2_node->details->id),
              reason);
    if (r1_nodes != NULL) {
        g_hash_table_destroy(r1_nodes);
    }
    if (r2_nodes != NULL) {
        g_hash_table_destroy(r2_nodes);
    }
    return rc;
}

void
pcmk__sort_resources(pcmk_scheduler_t *scheduler)
{
    GList *nodes = g_list_copy(scheduler->nodes);

    nodes = pcmk__sort_nodes(nodes, NULL);
    scheduler->resources = g_list_sort_with_data(scheduler->resources,
                                                 cmp_resources, nodes);
    g_list_free(nodes);
}