Fix and reformat several queries

* When no I/O activity has been reported in pg_statio_all_tables for a
  database, the queries resulted in a division by zero. Cange this to a
  NULL instead.  Still a problem for Zabbix, but maybe a little cleaner.

DEBIAN/control

@@ -3,7 +3,7 @@ Version: 1.0
 Section: utils
 Priority: optional
 Architecture: all
-Depends: logrotate, python3 (>= 3.6), python3-psycopg2, python3-yaml, systemd
+Depends: logrotate, python3 (>= 3.6), python3-psycopg2, python3-requests, python3-yaml, systemd
 Maintainer: James Campbell <james@commandprompt.com>
 Homepage: https://www.commandprompt.com
 Description: A bridge to sit between monitoring tools and PostgreSQL

GENTOO/pgmon-1.0.3.ebuild

@@ -0,0 +1,74 @@
+# Copyright 2024 Gentoo Authors
+# Distributed under the terms of the GNU General Public License v2
+
+EAPI=8
+
+PYTHON_COMPAT=( python3_{6..13} )
+
+inherit python-r1 systemd
+
+DESCRIPTION="PostgreSQL monitoring bridge"
+HOMEPAGE="None"
+
+LICENSE="BSD"
+SLOT="0"
+KEYWORDS="amd64"
+
+SRC_URI="https://code2.shh-dot-com.org/james/${PN}/releases/download/v${PV}/${P}.tar.bz2"
+
+IUSE="-systemd"
+
+DEPEND="
+	${PYTHON_DEPS}
+	dev-python/psycopg:2
+	dev-python/pyyaml
+	dev-python/requests
+	app-admin/logrotate
+	"
+RDEPEND="${DEPEND}"
+BDEPEND=""
+
+#RESTRICT="fetch"
+
+#S="${WORKDIR}/${PN}"
+
+#pkg_nofetch() {
+#	einfo "Please download"
+#	einfo "  - ${P}.tar.bz2"
+#	einfo "from ${HOMEPAGE} and place it in your DISTDIR directory."
+#	einfo "The file should be owned by portage:portage."
+#}
+
+src_compile() {
+	true
+}
+
+src_install() {
+	# Install init script
+	if ! use systemd ; then
+		newinitd "openrc/pgmon.initd" pgmon
+		newconfd "openrc/pgmon.confd" pgmon
+	fi
+
+	# Install systemd unit
+	if use systemd ; then
+		systemd_dounit "systemd/pgmon.service"
+	fi
+
+	# Install script
+	exeinto /usr/bin
+	newexe "src/pgmon.py" pgmon
+
+	# Install default config
+	diropts -o root -g root -m 0755
+	insinto /etc/pgmon
+	doins "sample-config/pgmon.yml"
+	doins "sample-config/pgmon-metrics.yml"
+
+	# Install logrotate config
+	insinto /etc/logrotate.d
+	newins "logrotate/pgmon.logrotate" pgmon
+
+	# Install man page
+	doman manpages/pgmon.1
+}

Makefile

@@ -23,7 +23,7 @@ SUPPORTED := ubuntu-20.04 \
 # These targets are the main ones to use for most things.
 ##
 
-.PHONY: all clean tgz test query-tests install
+.PHONY: all clean tgz test query-tests install-common install-openrc install-systemd
 
 
 # Build all packages
@@ -34,7 +34,7 @@ all: $(foreach distro_release, $(SUPPORTED), package-$(distro_release))
 .PHONY: package-gentoo
 package-gentoo:
 	mkdir -p $(BUILD_DIR)/gentoo
-	tar --transform "s,^\.,$(PACKAGE_NAME)-$(VERSION)," -acjf $(BUILD_DIR)/gentoo/$(PACKAGE_NAME)-$(VERSION).tar.bz2 --exclude .gitignore $(shell git ls-tree --full-tree --name-only -r HEAD)
+	tar --transform "s,^,$(PACKAGE_NAME)-$(VERSION)/," -acjf $(BUILD_DIR)/gentoo/$(PACKAGE_NAME)-$(VERSION).tar.bz2 --exclude .gitignore $(shell git ls-tree --full-tree --name-only -r HEAD)
 
 
 # Create a deb package
@@ -54,7 +54,7 @@ package-%:
 tgz:
 	rm -rf $(BUILD_DIR)/tgz/root
 	mkdir -p $(BUILD_DIR)/tgz/root
-	$(MAKE) install DESTDIR=$(BUILD_DIR)/tgz/root
+	$(MAKE) install-openrc DESTDIR=$(BUILD_DIR)/tgz/root
 	tar -cz -f $(BUILD_DIR)/tgz/$(PACKAGE_NAME)-$(VERSION).tgz -C $(BUILD_DIR)/tgz/root .
 
 # Clean up the build directory
@@ -69,18 +69,17 @@ test:
 query-tests:
 	cd tests ; ./run-tests.sh
 
-# Install the script at the specified base directory
-install:
+# Install the script at the specified base directory (common components)
+install-common:
 	# Set up directories
 	mkdir -p $(DESTDIR)/etc/$(PACKAGE_NAME)
 	mkdir -p ${DESTDIR}/etc/logrotate.d
-	mkdir -p $(DESTDIR)/lib/systemd/system
-	mkdir -p $(DESTDIR)/usr/local/bin
+	mkdir -p $(DESTDIR)/usr/bin
 	mkdir -p $(DESTDIR)/usr/share/man/man1
 	
 	# Install script
-	cp $(SCRIPT) $(DESTDIR)/usr/local/bin/$(PACKAGE_NAME)
-	chmod 755 $(DESTDIR)/usr/local/bin/$(PACKAGE_NAME)
+	cp $(SCRIPT) $(DESTDIR)/usr/bin/$(PACKAGE_NAME)
+	chmod 755 $(DESTDIR)/usr/bin/$(PACKAGE_NAME)
 	
 	# Install manpage
 	cp manpages/* $(DESTDIR)/usr/share/man/man1/
@@ -89,12 +88,36 @@ install:
 	# Install sample config
 	cp sample-config/* $(DESTDIR)/etc/$(PACKAGE_NAME)/
 	
-	# Install systemd unit files
-	cp systemd/* $(DESTDIR)/lib/systemd/system/
-	
 	# Install logrotate config
 	cp logrotate/${PACKAGE_NAME}.logrotate ${DESTDIR}/etc/logrotate.d/${PACKAGE_NAME}
 
+# Install for systemd
+install-systemd:
+	# Install the common stuff
+	$(MAKE) install-common
+	
+	# Set up directories
+	mkdir -p $(DESTDIR)/lib/systemd/system
+	
+	# Install systemd unit files
+	cp systemd/* $(DESTDIR)/lib/systemd/system/
+
+# Install for open-rc
+install-openrc:
+	# Install the common stuff
+	$(MAKE) install-common
+	
+	# Set up directories
+	mkdir -p $(DESTDIR)/etc/init.d
+	mkdir -p $(DESTDIR)/etc/conf.d
+	
+	# Install init script
+	cp openrc/pgmon.initd $(DESTDIR)/etc/init.d/pgmon
+	chmod 755 $(DESTDIR)/etc/init.d/pgmon
+	
+	# Install init script config file
+	cp openrc/pgmon.confd $(DESTDIR)/etc/conf.d/pgmon
+
 
 # Run all of the install tests
 .PHONY: install-tests debian-%-install-test rockylinux-%-install-test ubuntu-%-install-test gentoo-install-test
@@ -167,7 +190,7 @@ package-image-%:
 
 # Debian package creation
 actually-package-debian-%:
-	$(MAKE) install DESTDIR=/output/debian-$*
+	$(MAKE) install-systemd DESTDIR=/output/debian-$*
 	cp -r --preserve=mode DEBIAN /output/debian-$*/
 	dpkg-deb -Zgzip --build /output/debian-$* "/output/$(PACKAGE_NAME)-$(VERSION)-debian-$*.deb"
 
@@ -182,7 +205,7 @@ actually-package-rockylinux-%:
 
 # Ubuntu package creation
 actually-package-ubuntu-%:
-	$(MAKE) install DESTDIR=/output/ubuntu-$*
+	$(MAKE) install-systemd DESTDIR=/output/ubuntu-$*
 	cp -r --preserve=mode DEBIAN /output/ubuntu-$*/
 	dpkg-deb -Zgzip --build /output/ubuntu-$* "/output/$(PACKAGE_NAME)-$(VERSION)-ubuntu-$*.deb"
 

RPM/pgmon-el7.spec

@@ -7,7 +7,7 @@ License: MIT
 URL: https://www.commandprompt.com
 
 BuildArch: noarch
-Requires: logrotate, python, python-psycopg2, PyYAML, systemd
+Requires: logrotate, python, python-psycopg2, PyYAML, python-requests, systemd
 
 %description
 A bridge to sit between monitoring tools and PostgreSQL
@@ -19,7 +19,7 @@ A bridge to sit between monitoring tools and PostgreSQL
 # Do nothing since we have nothing to build
 
 %install
-make -C /src install DESTDIR=%{buildroot}
+make -C /src install-systemd DESTDIR=%{buildroot}
 
 %files
 /etc/logrotate.d/pgmon
@@ -28,7 +28,7 @@ make -C /src install DESTDIR=%{buildroot}
 /etc/pgmon/pgmon-service.conf
 /lib/systemd/system/pgmon.service
 /lib/systemd/system/pgmon@.service
-/usr/local/bin/pgmon
+/usr/bin/pgmon
 /usr/share/man/man1/pgmon.1.gz
 
 %post

RPM/pgmon.spec

@@ -7,7 +7,7 @@ License: MIT
 URL: https://www.commandprompt.com
 
 BuildArch: noarch
-Requires: logrotate, python3, python3-psycopg2, python3-pyyaml, systemd
+Requires: logrotate, python3, python3-psycopg2, python3-pyyaml, python3-requests, systemd
 
 %description
 A bridge to sit between monitoring tools and PostgreSQL
@@ -19,7 +19,7 @@ A bridge to sit between monitoring tools and PostgreSQL
 # Do nothing since we have nothing to build
 
 %install
-make -C /src install DESTDIR=%{buildroot}
+make -C /src install-systemd DESTDIR=%{buildroot}
 
 %files
 /etc/logrotate.d/pgmon
@@ -28,7 +28,7 @@ make -C /src install DESTDIR=%{buildroot}
 /etc/pgmon/pgmon-service.conf
 /lib/systemd/system/pgmon.service
 /lib/systemd/system/pgmon@.service
-/usr/local/bin/pgmon
+/usr/bin/pgmon
 /usr/share/man/man1/pgmon.1.gz
 
 %post

sample-config/pgmon-metrics.yml

@@ -1,63 +1,262 @@
 metrics:
+  ##
   # Discovery metrics
+  ##
   discover_dbs:
     type: set
     query:
-      0: SELECT datname AS dbname FROM pg_database
+      0: >
+        SELECT datname AS dbname
+        FROM pg_database
   discover_rep:
     type: set
     query:
-      0: SELECT client_addr || '_' || regexp_replace(application_name, '[ ,]', '_', 'g') AS repid, client_addr, state FROM pg_stat_replication
+      0: >
+        SELECT client_addr || '_' || regexp_replace(application_name, '[ ,]', '_', 'g') AS repid,
+               client_addr,
+               state
+        FROM pg_stat_replication
   discover_slots:
     type: set
     query:
-      90400: SELECT slot_name, plugin, slot_type, database, false as temporary, active FROM pg_replication_slots
-      100000: SELECT slot_name, plugin, slot_type, database, temporary, active FROM pg_replication_slots
+      90400: >
+        SELECT slot_name,
+               plugin,
+               slot_type,
+               database,
+               false as temporary,
+               active
+        FROM pg_replication_slots
+      100000: >
+        SELECT slot_name,
+               plugin,
+               slot_type,
+               database,
+               temporary,
+               active
+        FROM pg_replication_slots
 
+  ##
   # cluster-wide metrics
+  ##
   version:
     type: value
     query:
       0: SHOW server_version_num
+
   max_frozen_age:
     type: row
     query:
-      0: SELECT max(age(datfrozenxid)), max(mxid_age(datminmxid)) FROM pg_database
+      0: >
+        SELECT max(age(datfrozenxid)) AS xid_age,
+               0 AS mxid_age
+        FROM pg_database
+      90600: >
+        SELECT max(age(datfrozenxid)) AS xid_age,
+               max(mxid_age(datminmxid)) AS mxid_age
+        FROM pg_database
 
+  bgwriter:
+    type: row
+    query:
+      0: >
+        SELECT checkpoints_timed,
+               checkpoints_req,
+               checkpoint_write_time,
+               checkpoint_sync_time,
+               buffers_checkpoint,
+               buffers_clean,
+               maxwritten_clean,
+               buffers_backend,
+               buffers_backend_fsync,
+               buffers_alloc
+        FROM pg_stat_bgwriter
+      170000: >
+        SELECT cp.num_timed AS checkpoints_timed,
+               cp.num_requested AS checkpoints_req,
+               cp.write_time AS checkpoint_write_time,
+               cp.sync_time AS checkpoint_sync_time,
+               cp.buffers_written AS buffers_checkpoint,
+               bg.buffers_clean AS buffers_clean,
+               bg.maxwritten_clean AS maxwritten_clean,
+               NULL AS buffers_backend,
+               NULL AS buffers_backend_fsync,
+               bg.buffers_alloc AS buffers_alloc
+        FROM pg_stat_bgwriter bg
+        CROSS JOIN pg_stat_checkpointer cp
+
+
+  ##
   # Per-database metrics
+  ##
   db_stats:
     type: row
     query:
-      0: SELECT numbackends, xact_commit, xact_rollback, blks_read, blks_hit, tup_returned, tup_fetched, tup_inserted, tup_updated, tup_deleted, conflicts, temp_files, temp_bytes, deadlocks, blk_read_time, blk_write_time, extract('epoch' from stats_reset)::float FROM pg_stat_database WHERE datname = %(dbname)s
-      140000: SELECT numbackends, xact_commit, xact_rollback, blks_read, blks_hit, tup_returned, tup_fetched, tup_inserted, tup_updated, tup_deleted, conflicts, temp_files, temp_bytes, deadlocks, COALESCE(checksum_failures, 0) AS checksum_failures, blk_read_time, blk_write_time, session_time, active_time, idle_in_transaction_time, sessions, sessions_abandoned, sessions_fatal, sessions_killed, extract('epoch' from stats_reset)::float FROM pg_stat_database WHERE datname = %(dbname)s
+      0: >
+        SELECT numbackends,
+               xact_commit,
+               xact_rollback,
+               blks_read,
+               blks_hit,
+               tup_returned,
+               tup_fetched,
+               tup_inserted,
+               tup_updated,
+               tup_deleted,
+               conflicts,
+               temp_files,
+               temp_bytes,
+               deadlocks,
+               0 AS checksum_failures,
+               blk_read_time,
+               blk_write_time,
+               0 AS session_time,
+               0 AS active_time,
+               0 AS idle_in_transaction_time,
+               0 AS sessions,
+               0 AS sessions_abandoned,
+               0 AS sessions_fatal,
+               0 AS sessions_killed,
+               extract('epoch' from stats_reset)::float AS stats_reset
+        FROM pg_stat_database WHERE datname = %(dbname)s
+      140000: >
+        SELECT numbackends,
+               xact_commit,
+               xact_rollback,
+               blks_read,
+               blks_hit,
+               tup_returned,
+               tup_fetched,
+               tup_inserted,
+               tup_updated,
+               tup_deleted,
+               conflicts,
+               temp_files,
+               temp_bytes,
+               deadlocks,
+               COALESCE(checksum_failures,
+               0) AS checksum_failures,
+               blk_read_time,
+               blk_write_time,
+               session_time,
+               active_time,
+               idle_in_transaction_time,
+               sessions,
+               sessions_abandoned,
+               sessions_fatal,
+               sessions_killed,
+               extract('epoch' from stats_reset)::float AS stats_reset
+        FROM pg_stat_database WHERE datname = %(dbname)s
     test_args:
       dbname: postgres
 
+  hit_ratios:
+    type: row
+    query:
+      0: >
+        SELECT sum(heap_blks_read)::float / NULLIF(sum(heap_blks_read + heap_blks_hit), 0) AS avg_heap_hit_ratio,
+               sum(idx_blks_hit)::float / NULLIF(sum(idx_blks_read + idx_blks_hit), 0) AS avg_idx_hit_ratio,
+               sum(toast_blks_hit)::float / NULLIF(sum(toast_blks_read + toast_blks_hit), 0) AS avg_toast_hit_ratio,
+               sum(tidx_blks_hit)::float / NULLIF(sum(tidx_blks_read + tidx_blks_hit), 0) AS avg_tidx_hit_ratio
+        FROM pg_statio_all_tables
+    test_args:
+      dbname: postgres
+
+  activity:
+    type: set
+    query:
+      0: >
+        SELECT state,
+               count(*) AS backend_count,
+               COALESCE(EXTRACT(EPOCH FROM max(now() - state_change))::float, 0) AS max_state_time
+        FROM pg_stat_activity
+        WHERE datname = %(dbname)s
+        GROUP BY state
+    test_args:
+      dbname: postgres
+
+
+  ##
+  # Per-replication metrics
+  ##
+  rep_stats:
+    type: row
+    query:
+      90400: >
+        SELECT pid, usename,
+               EXTRACT(EPOCH FROM backend_start)::integer AS backend_start,
+               state,
+               pg_xlog_location_diff(pg_current_xlog_location(), sent_location) AS sent_lsn,
+               pg_xlog_location_diff(pg_current_xlog_location(), write_location) AS write_lsn,
+               pg_xlog_location_diff(pg_current_xlog_location(), flush_location) AS flush_lsn,
+               pg_xlog_location_diff(pg_current_xlog_location(), replay_location) AS replay_lsn,
+               NULL AS write_lag,
+               NULL AS flush_lag,
+               NULL AS replay_lag,
+               sync_state
+        FROM pg_stat_replication
+        WHERE client_addr || '_' || regexp_replace(application_name, '[ ,]', '_', 'g') = %(repid)s
+      90600: >
+        SELECT pid, usename,
+               EXTRACT(EPOCH FROM backend_start)::integer AS backend_start,
+               state,
+               pg_xlog_lsn_diff(pg_current_xlog_lsn(), sent_lsn) AS sent_lsn,
+               pg_xlog_lsn_diff(pg_current_xlog_lsn(), write_lsn) AS write_lsn,
+               pg_xlog_lsn_diff(pg_current_xlog_lsn(), flush_lsn) AS flush_lsn,
+               pg_xlog_lsn_diff(pg_current_xlog_lsn(), replay_lsn) AS replay_lsn,
+               COALESCE(EXTRACT(EPOCH FROM write_lag), 0)::integer AS write_lag,
+               COALESCE(EXTRACT(EPOCH FROM flush_lag), 0)::integer AS flush_lag,
+               COALESCE(EXTRACT(EPOCH FROM replay_lag), 0)::integer AS replay_lag,
+               sync_state
+        FROM pg_stat_replication WHERE client_addr || '_' || regexp_replace(application_name, '[ ,]', '_', 'g') = %(repid)s
+      100000: >
+        SELECT pid, usename,
+               EXTRACT(EPOCH FROM backend_start)::integer AS backend_start,
+               state,
+               pg_wal_lsn_diff(pg_current_wal_lsn(), sent_lsn) AS sent_lsn,
+               pg_wal_lsn_diff(pg_current_wal_lsn(), write_lsn) AS write_lsn,
+               pg_wal_lsn_diff(pg_current_wal_lsn(), flush_lsn) AS flush_lsn,
+               pg_wal_lsn_diff(pg_current_wal_lsn(), replay_lsn) AS replay_lsn,
+               COALESCE(EXTRACT(EPOCH FROM write_lag), 0)::integer AS write_lag,
+               COALESCE(EXTRACT(EPOCH FROM flush_lag), 0)::integer AS flush_lag,
+               COALESCE(EXTRACT(EPOCH FROM replay_lag), 0)::integer AS replay_lag,
+               sync_state
+        FROM pg_stat_replication WHERE client_addr || '_' || regexp_replace(application_name, '[ ,]', '_', 'g') = %(repid)s
+    test_args:
+      repid: 127.0.0.1_test_rep
+
+
+  ##
+  # Per-slot metrics
+  ##
+  slot_stats:
+    type: row
+    query:
+      90400: >
+        SELECT NULL as active_pid,
+               xmin,
+               pg_xlog_location_diff(pg_current_xlog_location(), restart_lsn) AS restart_bytes,
+               NULL AS confirmed_flush_bytes
+        FROM pg_replication_slots WHERE slot_name = %(slot)s
+      90600: >
+        SELECT active_pid,
+               xmin,
+               pg_xlog_location_diff(pg_current_xlog_location(), restart_lsn) AS restart_bytes,
+               pg_xlog_location_diff(pg_current_xlog_location(), confirmed_flush_lsn) AS confirmed_flush_bytes
+        FROM pg_replication_slots WHERE slot_name = %(slot)s
+      100000: >
+        SELECT active_pid,
+               xmin,
+               pg_wal_lsn_diff(pg_current_wal_lsn(), restart_lsn) AS restart_bytes,
+               pg_wal_lsn_diff(pg_current_wal_lsn(), confirmed_flush_lsn) AS confirmed_flush_bytes
+        FROM pg_replication_slots WHERE slot_name = %(slot)s
+    test_args:
+      slot: test_slot
+
+  ##
   # Debugging
+  ##
   ntables:
     type: value
     query:
       0: SELECT count(*) AS ntables FROM pg_stat_user_tables
-
-  # Per-replication metrics
-  rep_stats:
-    type: row
-    query:
-      90400: SELECT * FROM pg_stat_replication WHERE client_addr || '_' || regexp_replace(application_name, '[ ,]', '_', 'g') = '{repid}'
-    test_args:
-      repid: 127.0.0.1_test_rep
-
-  # Debugging
-  sleep:
-    type: value
-    query:
-      0: SELECT now(), pg_sleep(5);
-
-  # Per-slot metrics
-  slot_stats:
-    type: row
-    query:
-      90400: SELECT active_pid, xmin, pg_xlog_location_diff(pg_current_xlog_location(), restart_lsn) AS restart_bytes, pg_xlog_location_diff(pg_current_xlog_location(), confirmed_flush_lsn) AS confirmed_flush_bytes FROM pg_replication_slots WHERE slot_name = '{slot}'
-      100000: SELECT active_pid, xmin, pg_wal_lsn_diff(pg_current_wal_lsn(), restart_lsn) AS restart_bytes, pg_wal_lsn_diff(pg_current_wal_lsn(), confirmed_flush_lsn) AS confirmed_flush_bytes FROM pg_replication_slots WHERE slot_name = '{slot}'
-    test_args:
-      slot: test_slot

src/pgmon.py

@@ -518,7 +518,6 @@ def parse_version_rss(raw_rss, release):
 
     This sets these global variables:
         latest_version
-        latest_version_next_check
         release_supported
 
     It is expected that the caller already holds the latest_version_lock lock.
@@ -528,7 +527,6 @@ def parse_version_rss(raw_rss, release):
         release: The PostgreSQL release we care about (ex: 9.2, 14)
     """
     global latest_version
-    global latest_version_next_check
     global release_supported
 
     # Regular expressions for parsing the RSS document
@@ -583,6 +581,8 @@ def get_latest_version():
     Get the latest supported version of the major PostgreSQL release running on the server being monitored.
     """
 
+    global latest_version_next_check
+
     # If we don't know the latest version or it's past the recheck time, get the
     # version from the PostgreSQL RSS feed.  Only one thread needs to do this, so
     # they all try to grab the lock, and then make sure nobody else beat them to it.
@@ -655,8 +655,13 @@ def test_queries():
     for name, metric in config["metrics"].items():
         # If the metric has arguments to use while testing, grab those
         args = metric.get("test_args", {})
+        print("Testing {} [{}]".format(name, ", ".join(["{}={}".format(key, value) for key, value in args.items()])))
         # Run the query without the ability to retry.
-        res = sample_metric(dbname, name, args, retry=False)
+        try:
+            res = sample_metric(dbname, name, args, retry=False)
+        except MetricVersionError:
+            print("{} -> Unsupported for this version".format(name))
+            continue
         # Compare the result to the provided sample results
         # TODO
         print("{} -> {}".format(name, res))
@@ -705,12 +710,16 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
                 self._reply(
                     200,
                     json.dumps(
-                        {"latest": latest_version, "supported": 1 if release_supported else 0}
+                        {
+                            "latest": latest_version,
+                            "supported": 1 if release_supported else 0,
+                        }
                     ),
                 )
             except LatestVersionCheckError as e:
                 log.error("Failed to retrieve latest version information: {}".format(e))
                 self._reply(503, "Failed to retrieve latest version info")
+            return
 
         # Note: parse_qs returns the values as a list.  Since we always expect
         #       single values, just grab the first from each.

systemd/pgmon@.service

@@ -7,7 +7,7 @@ After=network.target
 [Service]
 EnvironmentFile=/etc/pgmon/%i-service.conf
 User=${SERVICE_USER:-postgres}
-ExecStart=/usr/local/bin/pgmon -c /etc/pgmon/%i.yml
+ExecStart=/usr/bin/pgmon -c /etc/pgmon/%i.yml
 ExecReload=kill -HUP $MAINPID
 Restart=on-failure
 Type=exec

tests/Dockerfile

@@ -2,6 +2,7 @@ FROM alpine:3.21
 
 RUN apk update && \
     apk add py3-psycopg2 \
+            py3-requests \
             py3-yaml \
             tini
 

tests/docker-compose.yml

@@ -23,7 +23,7 @@ services:
       test: [ "CMD-SHELL", "pg_controldata /var/lib/postgresql/data/ | grep -q 'in production'" ]
       interval: 5s
       timeout: 2s
-      retries: 20
+      retries: 40
     command: >
       postgres -c ssl=on
                -c ssl_cert_file='/etc/ssl/certs/ssl-cert-snakeoil.pem'

tests/run-tests.sh

@@ -6,12 +6,15 @@ versions=( $@ )
 # If we weren't given any versions, test them all
 if [ ${#versions[@]} -eq 0 ]
 then
-    versions=( 9.2 9.6 10 11 12 13 14 15 16 17 )
+    versions=( 9.2 9.4 9.6 10 11 12 13 14 15 16 17 )
 fi
 
 # Image tags to use
 declare -A images=()
 images["9.2"]='9.2'
+images["9.3"]='9.3'
+images["9.4"]='9.4'
+images["9.5"]='9.5'
 images["9.6"]='9.6-bullseye'
 images["10"]='10-bullseye'
 images["11"]='11-bookworm'

zabbix_templates/pgmon_templates.yaml

@@ -11,6 +11,44 @@ zabbix_export:
       groups:
         - name: 'My Templates'
       items:
+        - uuid: cc4a50ca681b4c4fb8c1c98f4bc81c96
+          name: 'Max Frozen MXID Age'
+          type: DEPENDENT
+          key: pgmon.age.mxid
+          delay: '0'
+          history: 90d
+          description: 'Maximum age of any frozen MXID in any database'
+          preprocessing:
+            - type: JSONPATH
+              parameters:
+                - $.mxid_age
+            - type: MATCHES_REGEX
+              parameters:
+                - '^[0-9]+$'
+          master_item:
+            key: 'pgmon[max_frozen_age]'
+          tags:
+            - tag: Application
+              value: PostgreSQL
+        - uuid: 2fa86d8c4a3a481e856a9414c5c70216
+          name: 'Max Frozen XID Age'
+          type: DEPENDENT
+          key: pgmon.age.xid
+          delay: '0'
+          history: 90d
+          description: 'Maximum age of any frozen XID in any database'
+          preprocessing:
+            - type: JSONPATH
+              parameters:
+                - $.xid_age
+            - type: MATCHES_REGEX
+              parameters:
+                - '^[0-9]+$'
+          master_item:
+            key: 'pgmon[max_frozen_age]'
+          tags:
+            - tag: Application
+              value: PostgreSQL
         - uuid: de1fa757395440118026f4c7a7c4ebbe
           name: 'PostgreSQL latest supported version'
           type: DEPENDENT
@@ -66,24 +104,27 @@ zabbix_export:
           value_type: TEXT
           trends: '0'
           description: 'Information about the latest PostgreSQL version in the current series'
-          url: 'http://localhost:{$AGENT_PORT}/version'
+          url: 'http://localhost:{$AGENT_PORT}/latest_version_info'
           tags:
             - tag: Application
               value: PostgreSQL
+            - tag: Type
+              value: Raw
         - uuid: 8706eccb7edc4fa394f552fc31f401a9
-          name: 'Max Frozen XID Age'
+          name: 'PostgreSQL ID Age Info'
           type: HTTP_AGENT
           key: 'pgmon[max_frozen_age]'
-          history: 90d
-          description: 'Maximum age of any frozen XID in any database'
-          preprocessing:
-            - type: MATCHES_REGEX
-              parameters:
-                - '^[0-9]+$'
+          delay: 5m
+          history: '0'
+          value_type: TEXT
+          trends: '0'
+          description: 'Maximum age of any frozen XID and MXID in any database'
           url: 'http://localhost:{$AGENT_PORT}/max_frozen_age'
           tags:
             - tag: Application
               value: PostgreSQL
+            - tag: Type
+              value: Raw
         - uuid: ee88f5f4d2384f97946d049af5af4502
           name: 'PostgreSQL version'
           type: HTTP_AGENT
@@ -636,6 +677,100 @@ zabbix_export:
                   value: '{#DBNAME}'
                 - tag: Type
                   value: Calculated
+            - uuid: bb0690e123e94e35a9bbd0f05ee322b4
+              name: 'Database Hit Ratios for {#DBNAME}'
+              type: HTTP_AGENT
+              key: 'pgmon_db_hit_ratios[{#DBNAME}]'
+              history: '0'
+              value_type: TEXT
+              trends: '0'
+              url: 'http://localhost:{$AGENT_PORT}/hit_ratios'
+              query_fields:
+                - name: dbname
+                  value: '{#DBNAME}'
+              tags:
+                - tag: Application
+                  value: PostgreSQL
+                - tag: Database
+                  value: '{#DBNAME}'
+                - tag: Type
+                  value: Raw
+            - uuid: e0edbaf6f98249a6b357ade2ab41a76a
+              name: 'Average heap hit ratio on {#DBNAME}'
+              type: DEPENDENT
+              key: 'pgmon_db_hit_ratio[heap,{#DBNAME}]'
+              delay: '0'
+              history: 90d
+              value_type: FLOAT
+              description: 'The cache (shared_buffers) hit ratio for heap entries for the given database'
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.avg_heap_hit_ratio
+              master_item:
+                key: 'pgmon_db_hit_ratios[{#DBNAME}]'
+              tags:
+                - tag: Application
+                  value: PostgreSQL
+                - tag: Database
+                  value: '{#DBNAME}'
+            - uuid: e4956d433a47455ca0c00d67a0f59355
+              name: 'Average index hit ratio on {#DBNAME}'
+              type: DEPENDENT
+              key: 'pgmon_db_hit_ratio[index,{#DBNAME}]'
+              delay: '0'
+              history: 90d
+              value_type: FLOAT
+              description: 'The cache (shared_buffers) hit ratio for index entries for the given database'
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.avg_idx_hit_ratio
+              master_item:
+                key: 'pgmon_db_hit_ratios[{#DBNAME}]'
+              tags:
+                - tag: Application
+                  value: PostgreSQL
+                - tag: Database
+                  value: '{#DBNAME}'
+            - uuid: 0335267c14a8410a80a16b38167efcb3
+              name: 'Average toast hit ratio on {#DBNAME}'
+              type: DEPENDENT
+              key: 'pgmon_db_hit_ratio[toast,{#DBNAME}]'
+              delay: '0'
+              history: 90d
+              value_type: FLOAT
+              description: 'The cache (shared_buffers) hit ratio for heap entries for the given database'
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.avg_toast_hit_ratio
+              master_item:
+                key: 'pgmon_db_hit_ratios[{#DBNAME}]'
+              tags:
+                - tag: Application
+                  value: PostgreSQL
+                - tag: Database
+                  value: '{#DBNAME}'
+            - uuid: 3f7da45e351443528c6c36145d38f9b8
+              name: 'Average toast index hit ratio on {#DBNAME}'
+              type: DEPENDENT
+              key: 'pgmon_db_hit_ratio[toast_index,{#DBNAME}]'
+              delay: '0'
+              history: 90d
+              value_type: FLOAT
+              description: 'The cache (shared_buffers) hit ratio for toast index entries for the given database'
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.avg_tidx_hit_ratio
+              master_item:
+                key: 'pgmon_db_hit_ratios[{#DBNAME}]'
+              tags:
+                - tag: Application
+                  value: PostgreSQL
+                - tag: Database
+                  value: '{#DBNAME}'
             - uuid: 492b3cac15f348c2b85f97b69c114d1b
               name: 'Database Stats for {#DBNAME}'
               type: HTTP_AGENT
@@ -652,6 +787,8 @@ zabbix_export:
                   value: PostgreSQL
                 - tag: Database
                   value: '{#DBNAME}'
+                - tag: Type
+                  value: Raw
           graph_prototypes:
             - uuid: 1f7de43b77714f819e61c31273712b70
               name: 'DML Totals for {#DBNAME}'
@@ -949,6 +1086,8 @@ zabbix_export:
                   value: Replication
                 - tag: Database
                   value: '{#DBNAME}'
+                - tag: Type
+                  value: Raw
           url: 'http://localhost:{$AGENT_PORT}/discover_rep'
           lld_macro_paths:
             - lld_macro: '{#CLIENT_ADDR}'
@@ -963,6 +1102,40 @@ zabbix_export:
           key: pgmon_discover_slots
           delay: 10m
           item_prototypes:
+            - uuid: 536c5f82e3074ddfbfd842b3a2e8d46c
+              name: 'Slot {#SLOT_NAME} - Confirmed Flushed Bytes Lag'
+              type: DEPENDENT
+              key: 'pgmon_slot[confirmed_flush_bytes,{#SLOT_NAME}]'
+              delay: '0'
+              description: 'The lag in bytes for the slot.  This metric is how far behind the consumer has reported to be with regard to flushing writes to disk (or equivalent).'
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.confirmed_flush_bytes
+              master_item:
+                key: 'pgmon_slot_stats[{#SLOT_NAME}]'
+              tags:
+                - tag: Application
+                  value: PostgreSQL
+                - tag: Slot
+                  value: '{#SLOT_NAME}'
+            - uuid: f239449d8e9e4ce79965528400f1669a
+              name: 'Slot {#SLOT_NAME} - Restart Bytes Lag'
+              type: DEPENDENT
+              key: 'pgmon_slot[restart_bytes,{#SLOT_NAME}]'
+              delay: '0'
+              description: 'The lag in bytes for the slot.  This metric is how far behind the restart location is, as reported by the consumer.'
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.restart_bytes
+              master_item:
+                key: 'pgmon_slot_stats[{#SLOT_NAME}]'
+              tags:
+                - tag: Application
+                  value: PostgreSQL
+                - tag: Slot
+                  value: '{#SLOT_NAME}'
             - uuid: a9f53efdce0a4bdc970925f8588e01c5
               name: 'Replication Slot Stats for {#SLOT_NAME}'
               type: HTTP_AGENT
@@ -974,6 +1147,13 @@ zabbix_export:
               query_fields:
                 - name: slot
                   value: '{#SLOT_NAME}'
+              tags:
+                - tag: Application
+                  value: PostgreSQL
+                - tag: Slot
+                  value: '{#SLOT_NAME}'
+                - tag: Type
+                  value: Raw
           url: 'http://localhost:{$AGENT_PORT}/discover_slots'
           lld_macro_paths:
             - lld_macro: '{#ACTIVE}'