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

Freeze lab-tested PostgreSQL plugin engine

Browse Source 
Extract PostgreSQL, Podman runtime and systemd lifecycle adapters while preserving existing lifecycle and scoring behavior. Update RPM layout and add guarded operator-run lab harnesses.

Record successful manual stop/start, promotion, demotion and rewind-only rejoin with pinned installed hashes. The unfenced lab does not validate automatic failover, Pacemaker-managed transitions or divergent-data rewind.

Validation: 103 offline tests, original-function differential checks, checksum manifest and whitespace checks passed.
This commit is contained in:
Lyncoln
2026-09-13 01:57:04 -04:00
parent 488a1672d7
commit ec2077f979
41 changed files with 1925 additions and 331 deletions
Download Patch File Download Diff File Expand all files Collapse all files
refactored/managed-container
+5 -4
View File
@@ -26,18 +26,19 @@ MC_PROMOTION_RESOURCE_INSTANCE="${OCF_RESOURCE_INSTANCE:-}"
# Resolve modules relative to this entrypoint, independent of Pacemaker's cwd.
MC_MODULE_DIR="$(CDPATH= cd -- "$(command dirname -- "${BASH_SOURCE[0]}")" && pwd)/managed-container.d"
for MC_MODULE in common container postgres auth replication notify promote demote rejoin; do
for MC_MODULE in common container engine; do
if ! . "${MC_MODULE_DIR}/${MC_MODULE}.sh"; then
ocf_exit_reason "Unable to load resource-agent module ${MC_MODULE_DIR}/${MC_MODULE}.sh"
exit "${OCF_ERR_CONFIGURED}"
fi
done
unset MC_MODULE
mc_engine_load || exit $?
case "$1" in
meta-data)
mc_promotion_metadata
exit "${OCF_SUCCESS}"
mc_engine_metadata
exit $?
;;
validate-all)
@@ -71,7 +72,7 @@ case "$1" in
;;
notify)
managed_notify
mc_application_notify
exit $?
;;
refactored/managed-container.d/auth.sh → refactored/managed-container.d/applications/postgresql/auth.sh
+1 -2
View File
@@ -2,8 +2,7 @@
pg_replication_exec()
{
as_service_user \
podman exec \
mc_runtime_exec \
--user "${PG_OS_USER}" \
"${CONTAINER_NAME}" \
sh -c '
refactored/managed-container.d/demote.sh → refactored/managed-container.d/applications/postgresql/demote.sh
+1 -2
View File
@@ -130,8 +130,7 @@ managed_demote()
ocf_log info \
"Configuring ${local_node} as cascading standby of ${target_node}"
if ! as_service_user \
podman exec \
if ! mc_runtime_exec \
--user "${PG_OS_USER}" \
--env "RA_PRIMARY_HOST=${target_addr}" \
--env "RA_PRIMARY_PORT=${target_port}" \
refactored/managed-container.d/notify.sh → refactored/managed-container.d/applications/postgresql/notify.sh
View File
refactored/managed-container.d/applications/postgresql/plugin.sh
+281
View File
@@ -0,0 +1,281 @@
# 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"
: "${OCF_RESKEY_service_user:=${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}}"
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}"
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="${OCF_RESKEY_replication_user_default}"/>
</parameter>
<parameter name="replication_slot" unique="0" required="0">
<longdesc lang="en">
Physical replication slot used by this standby.
</longdesc>
<shortdesc lang="en">Physical replication slot</shortdesc>
<content type="string" default="${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>
</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 "${OCF_ERR_GENERIC}"
fi
if ! mc_lifecycle_cat "${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 "${OCF_SUCCESS}"
}
# Keep the original metadata function intact; advertise the added policy here.
mc_promotion_metadata()
{
meta_data | sed '/<\/parameters>/i\
<parameter name="disconnected_max_age" unique="0" required="0">\
<longdesc lang="en">Maximum age in seconds of a verified streaming observation for disconnected promotion eligibility. Default 300; 0 disables disconnected eligibility. Requires fencing managed by Pacemaker. PostgreSQL restart requires fresh streaming verification.</longdesc>\
<shortdesc lang="en">Disconnected standby observation lifetime</shortdesc>\
<content type="integer" default="300"/>\
</parameter>'
}
MC_APPLICATION_API=1
MC_APPLICATION_DIR="${MC_MODULE_DIR}/applications/postgresql"
for MC_PG_MODULE in 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()
{
validate_all
}
mc_application_metadata()
{
mc_promotion_metadata
}
mc_application_notify()
{
managed_notify
}
mc_application_action()
{
case "$1" in
start|stop|promote|demote|rejoin) "managed_$1" ;;
*) return "${OCF_ERR_UNIMPLEMENTED}" ;;
esac
}
refactored/managed-container.d/postgres.sh → refactored/managed-container.d/applications/postgresql/postgres.sh
+9 -17
View File
@@ -4,8 +4,7 @@ pg_command()
{
local command="$1"
as_service_user \
podman exec \
mc_runtime_exec \
--user "${PG_OS_USER}" \
"${CONTAINER_NAME}" \
sh -c "${command}"
@@ -32,8 +31,7 @@ pg_running()
pg_ready()
{
as_service_user \
podman exec \
mc_runtime_exec \
--user "${PG_OS_USER}" \
"${CONTAINER_NAME}" \
pg_isready -q \
@@ -43,8 +41,7 @@ pg_ready()
pg_role()
{
as_service_user \
podman exec \
mc_runtime_exec \
--user "${PG_OS_USER}" \
"${CONTAINER_NAME}" \
psql \
@@ -55,8 +52,7 @@ pg_role()
pg_wal_receiver_status()
{
as_service_user \
podman exec \
mc_runtime_exec \
--user "${PG_OS_USER}" \
"${CONTAINER_NAME}" \
psql \
@@ -153,8 +149,7 @@ managed_start()
"Ensuring container service ${SERVICE_NAME} is running"
if ! service_running; then
if ! as_service_user \
systemctl --user start "${SERVICE_NAME}"
if ! mc_lifecycle_start "${SERVICE_NAME}"
then
ocf_exit_reason \
"Failed to start ${SERVICE_NAME}"
@@ -260,8 +255,7 @@ managed_stop()
ocf_log info \
"Stopping container service ${SERVICE_NAME}"
if ! as_service_user \
systemctl --user stop "${SERVICE_NAME}"
if ! mc_lifecycle_stop "${SERVICE_NAME}"
then
ocf_exit_reason \
"Failed to stop ${SERVICE_NAME}"
@@ -299,8 +293,7 @@ mc_pg_promotion_eligible()
local eligible
eligible="$(
as_service_user timeout --kill-after=1s 3s \
podman exec --user "${PG_OS_USER}" \
mc_runtime_exec_bounded 3s --user "${PG_OS_USER}" \
--env 'PGOPTIONS=-c statement_timeout=2000' \
"${CONTAINER_NAME}" \
psql -X -v ON_ERROR_STOP=1 -U "${DB_USER}" -d "${DB_NAME}" -Atqc "
@@ -323,8 +316,7 @@ mc_pg_promotion_eligible()
# including a new basebackup sharing the same PostgreSQL system identifier.
mc_pg_standby_observation()
{
as_service_user timeout --kill-after=1s 3s \
podman exec --user "${PG_OS_USER}" \
mc_runtime_exec_bounded 3s --user "${PG_OS_USER}" \
--env 'PGOPTIONS=-c statement_timeout=2000' \
"${CONTAINER_NAME}" \
psql -X -v ON_ERROR_STOP=1 -U "${DB_USER}" -d "${DB_NAME}" -Atqc "
@@ -358,7 +350,7 @@ mc_pg_standby_score()
# The helper is root-owned alongside the modules; state never enters the
# rootless container. A failed/slow helper always withdraws eligibility.
printf '%s' "${observation}" | timeout --kill-after=1s 1s python3 \
"${MC_MODULE_DIR}/promotion_state.py" \
"${MC_APPLICATION_DIR}/promotion_state.py" \
"${MC_PROMOTION_RESOURCE_INSTANCE:-}" \
"${SERVICE_USER}" "${SERVICE_NAME}" "${CONTAINER_NAME}" \
"${OCF_RESKEY_disconnected_max_age:-300}"
refactored/managed-container.d/promote.sh → refactored/managed-container.d/applications/postgresql/promote.sh
View File
refactored/managed-container.d/promotion_state.py → refactored/managed-container.d/applications/postgresql/promotion_state.py
View File
refactored/managed-container.d/rejoin.sh → refactored/managed-container.d/applications/postgresql/rejoin.sh
+1 -2
View File
@@ -268,8 +268,7 @@ managed_rejoin()
ocf_log info \
"Configuring PostgreSQL as standby of ${REJOIN_SOURCE_HOST}"
if ! as_service_user \
podman exec \
if ! mc_runtime_exec \
--user "${PG_OS_USER}" \
--env "RA_PRIMARY_HOST=${REJOIN_SOURCE_HOST}" \
--env "RA_PRIMARY_PORT=${REJOIN_SOURCE_PORT}" \
refactored/managed-container.d/replication.sh → refactored/managed-container.d/applications/postgresql/replication.sh
View File
refactored/managed-container.d/common.sh
+6 -243
View File
@@ -1,230 +1,4 @@
# 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"
: "${OCF_RESKEY_service_user:=${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}}"
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}"
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="${OCF_RESKEY_replication_user_default}"/>
</parameter>
<parameter name="replication_slot" unique="0" required="0">
<longdesc lang="en">
Physical replication slot used by this standby.
</longdesc>
<shortdesc lang="en">Physical replication slot</shortdesc>
<content type="string" default="${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>
</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 "${OCF_ERR_GENERIC}"
fi
if ! as_service_user \
systemctl --user cat "${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="$(
as_service_user podman info 2>&1 >/dev/null
)"
local podman_rc=$?
if [ "${podman_rc}" -ne 0 ]; then
ocf_exit_reason \
"Rootless Podman failed for ${SERVICE_USER}: ${podman_error}"
return "${OCF_ERR_GENERIC}"
fi
return "${OCF_SUCCESS}"
}
# Shared OCF scoring wrappers; application policy is supplied by the plugin.
# Promotion scores are scoped by Pacemaker to OCF_RESOURCE_INSTANCE and the
# executing node. Do not construct a legacy attribute name or cache locally:
@@ -269,7 +43,7 @@ mc_promotion_score_from_monitor()
case "${monitor_rc}" in
"${OCF_RUNNING_PROMOTED}") score=1000 ;;
"${OCF_SUCCESS}")
score="$(mc_pg_standby_score)" || score=-INFINITY
score="$(mc_application_standby_score)" || score=-INFINITY
;;
esac
case "${score}" in
@@ -284,7 +58,7 @@ mc_promotion_monitor()
{
local monitor_rc
managed_monitor
mc_application_monitor
monitor_rc=$?
mc_promotion_score_from_monitor "${monitor_rc}" || true
return "${monitor_rc}"
@@ -310,10 +84,10 @@ mc_promotion_action()
[ "${action_rc}" -eq "${OCF_SUCCESS}" ] || return "${action_rc}"
fi
"managed_${action}"
mc_application_action "${action}"
action_rc=$?
if [ "${action_rc}" -eq "${OCF_SUCCESS}" ] && [ "${action}" != stop ]; then
managed_monitor
mc_application_monitor
monitor_rc=$?
mc_promotion_score_from_monitor "${monitor_rc}" || true
fi
@@ -335,16 +109,5 @@ mc_promotion_validate()
return "${OCF_ERR_INSTALLED}"
fi
done
validate_all
}
# 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>'
mc_application_validate
}
refactored/managed-container.d/container.sh
+2 -3
View File
@@ -37,8 +37,7 @@ as_service_user()
service_running()
{
as_service_user \
systemctl --user is-active --quiet "${SERVICE_NAME}"
mc_lifecycle_running "${SERVICE_NAME}"
}
container_running()
@@ -46,7 +45,7 @@ container_running()
local state
state="$(
as_service_user podman inspect \
mc_runtime_inspect \
--format '{{.State.Running}}' \
"${CONTAINER_NAME}" 2>/dev/null
)" || return 1
refactored/managed-container.d/engine.sh
+59
View File
@@ -0,0 +1,59 @@
# Engine API 1. Selection is an allowlist of packaged implementations, never a
# filename, shell fragment or a plugin downloaded from cluster configuration.
mc_engine_load()
{
local plugin hook
if [ "${OCF_RESKEY_application:-postgresql}" != postgresql ] ||
[ "${OCF_RESKEY_container_runtime:-podman}" != podman ] ||
[ "${OCF_RESKEY_lifecycle_manager:-systemd}" != systemd ]; then
ocf_exit_reason "Supported plugin combination: application=postgresql container_runtime=podman lifecycle_manager=systemd"
return "${OCF_ERR_CONFIGURED}"
fi
unset MC_RUNTIME_API MC_LIFECYCLE_API MC_APPLICATION_API
for plugin in runtimes/podman lifecycles/systemd applications/postgresql/plugin; do
if ! . "${MC_MODULE_DIR}/${plugin}.sh"; then
ocf_exit_reason "Unable to load resource-agent module ${MC_MODULE_DIR}/${plugin}.sh"
return "${OCF_ERR_CONFIGURED}"
fi
done
if [ "${MC_RUNTIME_API:-}" != 1 ] || [ "${MC_LIFECYCLE_API:-}" != 1 ] ||
[ "${MC_APPLICATION_API:-}" != 1 ]; then
ocf_exit_reason "Incompatible plugin interface; API 1 required"
return "${OCF_ERR_CONFIGURED}"
fi
for hook in mc_runtime_exec mc_runtime_exec_bounded mc_runtime_inspect mc_runtime_info \
mc_lifecycle_start mc_lifecycle_stop mc_lifecycle_running mc_lifecycle_cat \
mc_application_monitor mc_application_standby_score mc_application_validate \
mc_application_metadata mc_application_notify mc_application_action; do
if ! declare -F "${hook}" >/dev/null; then
ocf_exit_reason "Required plugin hook is missing: ${hook}"
return "${OCF_ERR_CONFIGURED}"
fi
done
}
mc_engine_metadata()
{
# Metadata discovery works without configured resource instance attributes.
# Capture the plugin's status before transforming XML; avoid a pipeline
# masking a metadata failure. No runtime/service/cluster access is required.
local metadata
metadata="$(mc_application_metadata)" || return "$?"
printf '%s\n' "${metadata}" | sed '/<\/parameters>/i\
<parameter name="application" unique="0" required="0">\
<longdesc lang="en">Packaged application plugin. Only postgresql is supported.</longdesc>\
<shortdesc lang="en">Application plugin</shortdesc>\
<content type="string" default="postgresql"/>\
</parameter>\
<parameter name="container_runtime" unique="0" required="0">\
<longdesc lang="en">Packaged runtime adapter. Only podman is supported.</longdesc>\
<shortdesc lang="en">Container runtime</shortdesc>\
<content type="string" default="podman"/>\
</parameter>\
<parameter name="lifecycle_manager" unique="0" required="0">\
<longdesc lang="en">Container lifecycle owner. Only systemd with the existing user service is supported.</longdesc>\
<shortdesc lang="en">Lifecycle manager</shortdesc>\
<content type="string" default="systemd"/>\
</parameter>'
}
refactored/managed-container.d/lifecycles/systemd.sh
+23
View File
@@ -0,0 +1,23 @@
# Lifecycle adapter API 1. Quadlet remains the owner of container construction,
# init/maintenance command, signal settings and service restart/exit policies.
MC_LIFECYCLE_API=1
mc_lifecycle_start()
{
as_service_user systemctl --user start "$1"
}
mc_lifecycle_stop()
{
as_service_user systemctl --user stop "$1"
}
mc_lifecycle_running()
{
as_service_user systemctl --user is-active --quiet "$1"
}
mc_lifecycle_cat()
{
as_service_user systemctl --user cat "$1"
}
refactored/managed-container.d/runtimes/podman.sh
+24
View File
@@ -0,0 +1,24 @@
# Runtime adapter API 1. The existing rootless privilege boundary is unchanged.
MC_RUNTIME_API=1
mc_runtime_exec()
{
as_service_user podman exec "$@"
}
mc_runtime_exec_bounded()
{
local duration="$1"
shift
as_service_user timeout --kill-after=1s "${duration}" podman exec "$@"
}
mc_runtime_inspect()
{
as_service_user podman inspect "$@"
}
mc_runtime_info()
{
as_service_user podman info "$@"
}