351 lines
12 KiB
Bash
351 lines
12 KiB
Bash
# 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}"
|
|
}
|
|
|
|
# Promotion scores are scoped by Pacemaker to OCF_RESOURCE_INSTANCE and the
|
|
# executing node. Do not construct a legacy attribute name or cache locally:
|
|
# querying attrd on every observation also repairs a lost transient attribute.
|
|
mc_promotion_score_set()
|
|
{
|
|
local score="$1" current
|
|
local resource="${MC_PROMOTION_RESOURCE_INSTANCE:-}"
|
|
|
|
if [ -z "${resource}" ]; then
|
|
ocf_log warn "Cannot publish promotion score without OCF_RESOURCE_INSTANCE"
|
|
return 1
|
|
fi
|
|
|
|
case "${score}" in
|
|
1000|100|50|-INFINITY) ;;
|
|
*) return 1 ;;
|
|
esac
|
|
|
|
current="$(
|
|
timeout --kill-after=1s 2s crm_attribute \
|
|
--promotion="${resource}" --lifetime=reboot \
|
|
--query --quiet 2>/dev/null
|
|
)" || current=""
|
|
|
|
[ "${current}" = "${score}" ] && return 0
|
|
|
|
if ! timeout --kill-after=1s 2s crm_attribute \
|
|
--promotion="${resource}" --lifetime=reboot \
|
|
--update="${score}" >/dev/null 2>&1
|
|
then
|
|
ocf_log err "Unable to publish promotion score ${score} for ${resource}; prior score may remain"
|
|
return 1
|
|
fi
|
|
return 0
|
|
}
|
|
|
|
mc_promotion_score_from_monitor()
|
|
{
|
|
local monitor_rc="$1" score=-INFINITY
|
|
|
|
case "${monitor_rc}" in
|
|
"${OCF_RUNNING_PROMOTED}") score=1000 ;;
|
|
"${OCF_SUCCESS}")
|
|
score="$(mc_pg_standby_score)" || score=-INFINITY
|
|
;;
|
|
esac
|
|
case "${score}" in
|
|
1000|100|50|-INFINITY) ;;
|
|
*) score=-INFINITY ;;
|
|
esac
|
|
mc_promotion_score_set "${score}"
|
|
}
|
|
|
|
# Score publication must not change OCF role detection or its return code.
|
|
mc_promotion_monitor()
|
|
{
|
|
local monitor_rc
|
|
|
|
managed_monitor
|
|
monitor_rc=$?
|
|
mc_promotion_score_from_monitor "${monitor_rc}" || true
|
|
return "${monitor_rc}"
|
|
}
|
|
|
|
# Lifecycle functions retain their original checks, commands and return codes.
|
|
# Withdraw the previous score before any transition (including validation
|
|
# failure), then reassess only after success. Their internal monitor calls do
|
|
# not publish scores, so they cannot restore a positive score mid-transition.
|
|
mc_promotion_action()
|
|
{
|
|
local action="$1" action_rc monitor_rc
|
|
|
|
case "${action}" in
|
|
start|stop|promote|demote|rejoin) ;;
|
|
*) return "${OCF_ERR_UNIMPLEMENTED}" ;;
|
|
esac
|
|
|
|
mc_promotion_score_set -INFINITY || true
|
|
if [ "${action}" != stop ]; then
|
|
mc_promotion_validate
|
|
action_rc=$?
|
|
[ "${action_rc}" -eq "${OCF_SUCCESS}" ] || return "${action_rc}"
|
|
fi
|
|
|
|
"managed_${action}"
|
|
action_rc=$?
|
|
if [ "${action_rc}" -eq "${OCF_SUCCESS}" ] && [ "${action}" != stop ]; then
|
|
managed_monitor
|
|
monitor_rc=$?
|
|
mc_promotion_score_from_monitor "${monitor_rc}" || true
|
|
fi
|
|
return "${action_rc}"
|
|
}
|
|
|
|
mc_promotion_validate()
|
|
{
|
|
local utility
|
|
|
|
if ! [[ "${OCF_RESKEY_disconnected_max_age:-300}" =~ ^(0|[1-9][0-9]{0,4})$ ]]; then
|
|
ocf_exit_reason "disconnected_max_age must be an integer from 0 to 99999 seconds"
|
|
return "${OCF_ERR_CONFIGURED}"
|
|
fi
|
|
|
|
for utility in crm_attribute timeout python3; do
|
|
if ! command -v "${utility}" >/dev/null 2>&1; then
|
|
ocf_exit_reason "Required promotion scoring command '${utility}' is not installed"
|
|
return "${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>'
|
|
}
|