david/managed-container
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial managed-container HA resource agent baseline

Browse Source
This commit is contained in:
Lyncoln
2026-09-17 10:54:08 -04:00
commit b6c4fc848f
24 changed files with 4951 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ocf/loxthelion/managed-container.d/applications/postgresql/plugin.sh
Executable
+391
View File
@@ -0,0 +1,391 @@
# Sourced by managed-container; uses the shared OCF and parameter environment.
OCF_RESKEY_service_user_default="david"
OCF_RESKEY_service_name_default="postgres.service"
OCF_RESKEY_container_name_default="postgres"
OCF_RESKEY_pg_os_user_default="postgres"
OCF_RESKEY_db_user_default="david"
OCF_RESKEY_db_name_default="david"
OCF_RESKEY_rejoin_source_host_default=""
OCF_RESKEY_rejoin_source_port_default="5432"
OCF_RESKEY_replication_user_default="replicator"
OCF_RESKEY_replication_slot_default=""
OCF_RESKEY_application_name_default=""
OCF_RESKEY_rejoin_allow_basebackup_default="false"
OCF_RESKEY_rejoin_basebackup_headroom_percent_default="50"
: "${OCF_RESKEY_service_user:=${OCF_RESKEY_service_user_default}}"
: "${OCF_RESKEY_service_name:=${OCF_RESKEY_service_name_default}}"
: "${OCF_RESKEY_container_name:=${OCF_RESKEY_container_name_default}}"
: "${OCF_RESKEY_pg_os_user:=${OCF_RESKEY_pg_os_user_default}}"
: "${OCF_RESKEY_db_user:=${OCF_RESKEY_db_user_default}}"
: "${OCF_RESKEY_db_name:=${OCF_RESKEY_db_name_default}}"
: "${OCF_RESKEY_rejoin_source_host:=${OCF_RESKEY_rejoin_source_host_default}}"
: "${OCF_RESKEY_rejoin_source_port:=${OCF_RESKEY_rejoin_source_port_default}}"
: "${OCF_RESKEY_replication_user:=${OCF_RESKEY_replication_user_default}}"
: "${OCF_RESKEY_replication_slot:=${OCF_RESKEY_replication_slot_default}}"
: "${OCF_RESKEY_application_name:=${OCF_RESKEY_application_name_default}}"
: "${OCF_RESKEY_rejoin_allow_basebackup:=${OCF_RESKEY_rejoin_allow_basebackup_default}}"
: "${OCF_RESKEY_rejoin_basebackup_headroom_percent:=${OCF_RESKEY_rejoin_basebackup_headroom_percent_default}}"
SERVICE_USER="${OCF_RESKEY_service_user}"
SERVICE_NAME="${OCF_RESKEY_service_name}"
CONTAINER_NAME="${OCF_RESKEY_container_name}"
PG_OS_USER="${OCF_RESKEY_pg_os_user}"
DB_USER="${OCF_RESKEY_db_user}"
DB_NAME="${OCF_RESKEY_db_name}"
REJOIN_SOURCE_HOST="${OCF_RESKEY_rejoin_source_host}"
REJOIN_SOURCE_PORT="${OCF_RESKEY_rejoin_source_port}"
REPLICATION_USER="${OCF_RESKEY_replication_user}"
REPLICATION_SLOT="${OCF_RESKEY_replication_slot}"
APPLICATION_NAME="${OCF_RESKEY_application_name}"
REJOIN_ALLOW_BASEBACKUP="${OCF_RESKEY_rejoin_allow_basebackup}"
REJOIN_BASEBACKUP_HEADROOM_PERCENT="${OCF_RESKEY_rejoin_basebackup_headroom_percent}"
# Resolve PostgreSQL configuration from the managed service when Pacemaker has
# not explicitly supplied it. The application configuration remains the source
# of truth; no slot naming convention is inferred.
mc_pg_resolve_replication_slot()
{
local resolved
if [ -n "${REPLICATION_SLOT}" ]; then
return 0
fi
# Prefer PostgreSQL's effective setting when the server is already up.
# This asks PostgreSQL itself rather than reconstructing configuration.
if declare -F pg_running >/dev/null 2>&1 && pg_running; then
resolved="$(
mc_runtime_exec \
--user "${PG_OS_USER}" \
"${CONTAINER_NAME}" \
psql -X -U "${DB_USER}" -d "${DB_NAME}" -Atqc \
'SHOW primary_slot_name;' 2>/dev/null
)" || resolved=
if [ -n "${resolved}" ]; then
REPLICATION_SLOT=${resolved}
OCF_RESKEY_replication_slot=${resolved}
ocf_log debug "Resolved PostgreSQL replication slot from PostgreSQL effective configuration"
return 0
fi
fi
# When PostgreSQL is stopped but its maintenance container is running,
# obtain the exact value injected into the managed container. Runtime
# adapters own this lookup; the application plugin does not parse Quadlets.
if declare -F mc_runtime_environment >/dev/null 2>&1; then
resolved="$(
mc_runtime_environment \
"${CONTAINER_NAME}" \
POSTGRES_REPLICATION_SLOT
)" || resolved=
if [ -n "${resolved}" ]; then
REPLICATION_SLOT=${resolved}
OCF_RESKEY_replication_slot=${resolved}
ocf_log debug "Resolved PostgreSQL replication slot from managed container environment"
return 0
fi
fi
return 1
}
mc_pg_require_replication_slot()
{
mc_pg_resolve_replication_slot || {
ocf_exit_reason "PostgreSQL replication slot is required but could not be resolved from replication_slot, PostgreSQL, or the managed container environment"
return "${OCF_ERR_CONFIGURED}"
}
case "${REPLICATION_SLOT}" in
''|*[!a-z0-9_]*)
ocf_exit_reason "Resolved replication slot is invalid; expected lowercase letters, digits, and underscore"
return "${OCF_ERR_CONFIGURED}"
;;
esac
if [ ${#REPLICATION_SLOT} -gt 63 ]; then
ocf_exit_reason "Resolved replication slot exceeds PostgreSQL's 63-character identifier limit"
return "${OCF_ERR_CONFIGURED}"
fi
return 0
}
if [ -z "${APPLICATION_NAME}" ]; then
APPLICATION_NAME="$(hostname -s)"
fi
meta_data()
{
cat <<EOF_META
<?xml version="1.0"?>
<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
<resource-agent name="managed-container" version="0.4">
<version>1.0</version>
<longdesc lang="en">
Manage an application inside a persistent rootless container.
Version 0.4 implements role-aware monitoring, promotion, and demotion.
The systemd user Quadlet owns the container lifecycle while pg_ctl owns
the PostgreSQL lifecycle inside the container.
</longdesc>
<shortdesc lang="en">
Manage PostgreSQL independently inside a persistent container
</shortdesc>
<parameters>
<parameter name="service_user" unique="0" required="1">
<longdesc lang="en">
Linux user owning the rootless systemd/Podman service.
</longdesc>
<shortdesc lang="en">Rootless service owner</shortdesc>
<content type="string" default="${OCF_RESKEY_service_user_default}"/>
</parameter>
<parameter name="service_name" unique="0" required="1">
<longdesc lang="en">
systemd user service generated by Quadlet.
</longdesc>
<shortdesc lang="en">Quadlet service name</shortdesc>
<content type="string" default="${OCF_RESKEY_service_name_default}"/>
</parameter>
<parameter name="container_name" unique="0" required="1">
<longdesc lang="en">
Podman container containing PostgreSQL.
</longdesc>
<shortdesc lang="en">Container name</shortdesc>
<content type="string" default="${OCF_RESKEY_container_name_default}"/>
</parameter>
<parameter name="pg_os_user" unique="0" required="1">
<longdesc lang="en">
Operating-system user running PostgreSQL inside the container.
</longdesc>
<shortdesc lang="en">PostgreSQL OS user</shortdesc>
<content type="string" default="${OCF_RESKEY_pg_os_user_default}"/>
</parameter>
<parameter name="db_user" unique="0" required="1">
<longdesc lang="en">
PostgreSQL database user used for health queries.
</longdesc>
<shortdesc lang="en">Database user</shortdesc>
<content type="string" default="${OCF_RESKEY_db_user_default}"/>
</parameter>
<parameter name="db_name" unique="0" required="1">
<longdesc lang="en">
PostgreSQL database used for health queries.
</longdesc>
<shortdesc lang="en">Database name</shortdesc>
<content type="string" default="${OCF_RESKEY_db_name_default}"/>
</parameter>
<parameter name="rejoin_source_host" unique="0" required="0">
<longdesc lang="en">
PostgreSQL primary host used as the source for rejoin operations.
</longdesc>
<shortdesc lang="en">Rejoin source host</shortdesc>
<content type="string" default="${OCF_RESKEY_rejoin_source_host_default}"/>
</parameter>
<parameter name="rejoin_source_port" unique="0" required="0">
<longdesc lang="en">
PostgreSQL port on the rejoin source.
</longdesc>
<shortdesc lang="en">Rejoin source port</shortdesc>
<content type="integer" default="${OCF_RESKEY_rejoin_source_port_default}"/>
</parameter>
<parameter name="replication_user" unique="0" required="0">
<longdesc lang="en">
PostgreSQL role used for replication and pg_rewind.
</longdesc>
<shortdesc lang="en">Replication user</shortdesc>
<content type="string" default="${OCF_RESKEY_replication_user_default}"/>
</parameter>
<parameter name="replication_slot" unique="0" required="0">
<longdesc lang="en">
Physical replication slot used by this standby. If unset, the agent
resolves the effective PostgreSQL primary_slot_name when available,
otherwise POSTGRES_REPLICATION_SLOT from the running managed container.
No slot name is derived or guessed.
</longdesc>
<shortdesc lang="en">Physical replication slot</shortdesc>
<content type="string" default="${OCF_RESKEY_replication_slot_default}"/>
</parameter>
<parameter name="application_name" unique="0" required="0">
<longdesc lang="en">
PostgreSQL replication application_name. Defaults to the local hostname.
</longdesc>
<shortdesc lang="en">Replication application name</shortdesc>
<content type="string" default="${OCF_RESKEY_application_name_default}"/>
</parameter>
<parameter name="rejoin_allow_basebackup" unique="0" required="0">
<longdesc lang="en">
Allow rejoin to fall back to pg_basebackup when pg_rewind cannot
repair the local PostgreSQL data directory. The old PGDATA is
preserved before replacement. This must only be enabled when the
operator has established that this node may safely discard its
divergent PostgreSQL history.
</longdesc>
<shortdesc lang="en">Allow pg_basebackup rejoin fallback</shortdesc>
<content type="boolean" default="${OCF_RESKEY_rejoin_allow_basebackup_default}"/>
</parameter>
<parameter name="rejoin_basebackup_headroom_percent" unique="0" required="0">
<longdesc lang="en">
Additional free-space headroom, as a percentage of the estimated
source database payload, required before pg_basebackup fallback.
The old PGDATA is renamed in place and therefore is not counted as
another free-space copy. A minimum 1 GiB headroom is always required.
</longdesc>
<shortdesc lang="en">pg_basebackup free-space headroom percent</shortdesc>
<content type="integer" default="${OCF_RESKEY_rejoin_basebackup_headroom_percent_default}"/>
</parameter>
</parameters>
<actions>
<action name="start" timeout="60s"/>
<action name="stop" timeout="60s"/>
<action name="promote" timeout="60s"/>
<action name="demote" timeout="60s"/>
<action name="notify" timeout="20s"/>
<action name="monitor" timeout="20s" interval="10s"/>
<action name="validate-all" timeout="20s"/>
<action name="meta-data" timeout="5s"/>
</actions>
</resource-agent>
EOF_META
}
validate_all()
{
if ! id "${SERVICE_USER}" >/dev/null 2>&1; then
ocf_exit_reason "Service user '${SERVICE_USER}' does not exist"
return "${OCF_ERR_CONFIGURED}"
fi
for cmd in runuser systemctl podman getent; do
if ! command -v "${cmd}" >/dev/null 2>&1; then
ocf_exit_reason "Required command '${cmd}' is not installed"
return "${OCF_ERR_INSTALLED}"
fi
done
if [ ! -d "/run/user/$(service_uid)" ]; then
ocf_exit_reason \
"Runtime directory /run/user/$(service_uid) does not exist"
return "${OCF_ERR_GENERIC}"
fi
case "${REJOIN_BASEBACKUP_HEADROOM_PERCENT}" in
""|*[!0-9]*)
ocf_exit_reason "rejoin_basebackup_headroom_percent must be a non-negative integer"
return "${OCF_ERR_CONFIGURED}"
;;
esac
if [ "${REJOIN_BASEBACKUP_HEADROOM_PERCENT}" -gt 500 ]; then
ocf_exit_reason "rejoin_basebackup_headroom_percent must be between 0 and 500"
return "${OCF_ERR_CONFIGURED}"
fi
if ! mc_lifecycle_cat "${SERVICE_NAME}" >/dev/null 2>&1
then
ocf_exit_reason \
"User service '${SERVICE_NAME}' cannot be found for ${SERVICE_USER}"
return "${OCF_ERR_CONFIGURED}"
fi
local podman_error
podman_error="$(
mc_runtime_info 2>&1 >/dev/null
)"
local podman_rc=$?
if [ "${podman_rc}" -ne 0 ]; then
ocf_exit_reason \
"Rootless Podman failed for ${SERVICE_USER}: ${podman_error}"
return "${OCF_ERR_GENERIC}"
fi
return "${OCF_SUCCESS}"
}
# Keep the original metadata function intact; advertise the added policy here.
mc_promotion_metadata()
{
meta_data | sed '/<\/parameters>/i\
<parameter name="disconnected_max_age" unique="0" required="0">\
<longdesc lang="en">Maximum age in seconds of a verified streaming observation for disconnected promotion eligibility. Default 300; 0 disables disconnected eligibility. Requires fencing managed by Pacemaker. PostgreSQL restart requires fresh streaming verification.</longdesc>\
<shortdesc lang="en">Disconnected standby observation lifetime</shortdesc>\
<content type="integer" default="300"/>\
</parameter>\
<parameter name="replication_peers" unique="0" required="0">\
<longdesc lang="en">Opt-in stable peer map: node=host:port,node=host:port. Include the local node; exclude the client VIP. IPv4 or DNS hosts only. Requires a configured per-node replication slot, supplied explicitly or resolved from PostgreSQL/the managed container environment, plus peer authentication and slots on every upstream. Uses native primary-only selection; demotion verifies final WAL then ready recovery before successor promotion.</longdesc>\
<shortdesc lang="en">Native replication peer map</shortdesc>\
<content type="string" default=""/>\
</parameter>'
}
MC_APPLICATION_API=1
MC_APPLICATION_DIR="${MC_MODULE_DIR}/applications/postgresql"
for MC_PG_MODULE in peer_config native_peers postgres auth replication notify promote demote rejoin; do
if ! . "${MC_APPLICATION_DIR}/${MC_PG_MODULE}.sh"; then
ocf_exit_reason "Unable to load resource-agent module ${MC_APPLICATION_DIR}/${MC_PG_MODULE}.sh"
return "${OCF_ERR_CONFIGURED}"
fi
done
unset MC_PG_MODULE
mc_application_monitor()
{
managed_monitor
}
mc_application_standby_score()
{
mc_pg_standby_score
}
mc_application_validate()
{
mc_pg_peer_validate || return "$?"
validate_all
}
mc_application_metadata()
{
mc_promotion_metadata
}
mc_application_notify()
{
managed_notify
}
mc_application_action()
{
mc_pg_peer_validate || return "$?"
if [ "$1" = demote ] && [ -n "${OCF_RESKEY_replication_peers:-}" ]; then
mc_pg_native_demote
return "$?"
fi
case "$1" in
start|stop|promote|demote|rejoin) "managed_$1" ;;
*) return "${OCF_ERR_UNIMPLEMENTED}" ;;
esac
}