.gitignore

@@ -8,4 +8,3 @@ missing
 __pycache__
 venv
 build
-.coverage

GENTOO/pgmon-1.1.0-rc1.ebuild

@@ -1,74 +0,0 @@
-# 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

@@ -9,7 +9,6 @@ FULL_VERSION := $(shell grep -m 1 '^VERSION = ' "$(SCRIPT)" | sed -ne 's/.*"\(.*
 VERSION := $(shell echo $(FULL_VERSION) | sed -n 's/\(.*\)\(-rc.*\|$$\)/\1/p')
 RELEASE := $(shell echo $(FULL_VERSION) | sed -n 's/.*-rc\([0-9]\+\)$$/\1/p')
 
-# Package version formatting
 ifeq ($(RELEASE),)
 RPM_RELEASE := 1
 RPM_VERSION := $(VERSION)-$(RPM_RELEASE)
@@ -20,12 +19,6 @@ RPM_VERSION := $(VERSION)-$(RPM_RELEASE)
 DEB_VERSION := $(VERSION)~rc$(RELEASE)
 endif
 
-# Python stuff
-PYTHON ?= python3
-PYLINT ?= pylint
-BLACK ?= black
-
-HAVE_COVERAGE := $(shell $(PYTHON) -c 'import coverage' 2>/dev/null && echo yes)
 
 # Where packages are built
 BUILD_DIR := build
@@ -34,77 +27,68 @@ BUILD_DIR := build
 SUPPORTED := ubuntu-20.04 \
              ubuntu-22.04 \
              ubuntu-24.04 \
+	     debian-10 \
 	     debian-11 \
-	     debian-12 \
-	     debian-13 \
 	     rockylinux-8 \
 	     rockylinux-9 \
-	     rockylinux-10 \
 	     oraclelinux-7 \
-	     amazonlinux-2 \
-	     amazonlinux-2023 \
 	     gentoo
 
 ##
 # These targets are the main ones to use for most things.
 ##
 
-.PHONY: all clean tgz lint format test query-tests template-coverage
+.PHONY: all clean tgz test query-tests install-common install-openrc install-systemd
 
 all: package-all
 
-# Dump information related to the current version
 version:
 	@echo "full version=$(FULL_VERSION) version=$(VERSION) rel=$(RELEASE) rpm=$(RPM_VERSION) deb=$(DEB_VERSION)"
 
-# Clean up the build directory
+# Build all packages
-clean:
+.PHONY: package-all
-	rm -rf $(BUILD_DIR)
+package-all: $(foreach distro_release, $(SUPPORTED), package-$(distro_release))
 
-# Check for lint
+# Gentoo package (tar.gz) creation
-lint:
+.PHONY: package-gentoo
-	$(PYLINT) src/pgmon.py
+package-gentoo:
-	$(PYLINT) src/test_pgmon.py
+	mkdir -p $(BUILD_DIR)/gentoo
-	$(BLACK) --check --diff src/pgmon.py
+	tar --transform "s,^,$(PACKAGE_NAME)-$(FULL_VERSION)/," -acjf $(BUILD_DIR)/gentoo/$(PACKAGE_NAME)-$(FULL_VERSION).tar.bz2 --exclude .gitignore $(shell git ls-tree --full-tree --name-only -r HEAD)
-	$(BLACK) --check --diff src/test_pgmon.py
 
-# Format the code using black
-format:
-	$(BLACK) src/pgmon.py
-	$(BLACK) src/test_pgmon.py
 
-# Run unit tests for the script (with coverage if it's available)
+# Create a deb package
-test:
+.PHONY: package-%
-ifeq ($(HAVE_COVERAGE),yes)
+package-%: PARTS=$(subst -, ,$*)
-	cd src ; $(PYTHON) -m coverage run -m unittest && python3 -m coverage report -m
+package-%: DISTRO=$(word 1, $(PARTS))
-else
+package-%: RELEASE=$(word 2, $(PARTS))
-	cd src ; $(PYTHON) -m unittest
+package-%:
-endif
+	mkdir -p $(BUILD_DIR)
+	docker run --rm \
+	    -v .:/src:ro \
+	    -v ./$(BUILD_DIR):/output \
+	    --user $(shell id -u):$(shell id -g) \
+	    "$(DISTRO)-packager:$(RELEASE)"
 
-# Run query tests
+# Create a tarball
-query-tests:
-	cd tests ; ./run-tests.sh
-
-# Compare the sample metrics with the Zabbix template
-template-coverage:
-	$(PYTHON) zabbix_templates/coverage.py sample-config/pgmon-metrics.yml zabbix_templates/pgmon_templates.yaml
-
-# Create a tarball (openrc version)
 tgz:
 	rm -rf $(BUILD_DIR)/tgz/root
 	mkdir -p $(BUILD_DIR)/tgz/root
 	$(MAKE) install-openrc DESTDIR=$(BUILD_DIR)/tgz/root
 	tar -cz -f $(BUILD_DIR)/tgz/$(PACKAGE_NAME)-$(FULL_VERSION).tgz -C $(BUILD_DIR)/tgz/root .
 
+# Clean up the build directory
+clean:
+	rm -rf $(BUILD_DIR)
 
-##
+# Run unit tests for the script
-# Install targets
+test:
-#
+	cd src ; python3 -m unittest
-# These are mostly used by the various package building images to actually install the script
+
-##
+# Run query tests
+query-tests:
+	cd tests ; ./run-tests.sh
 
 # Install the script at the specified base directory (common components)
-.PHONY: install-common
 install-common:
 	# Set up directories
 	mkdir -p $(DESTDIR)/etc/$(PACKAGE_NAME)
@@ -127,7 +111,6 @@ install-common:
 	cp logrotate/${PACKAGE_NAME}.logrotate ${DESTDIR}/etc/logrotate.d/${PACKAGE_NAME}
 
 # Install for systemd
-.PHONY: install-systemd
 install-systemd:
 	# Install the common stuff
 	$(MAKE) install-common
@@ -139,7 +122,6 @@ install-systemd:
 	cp systemd/* $(DESTDIR)/lib/systemd/system/
 
 # Install for open-rc
-.PHONY: install-openrc
 install-openrc:
 	# Install the common stuff
 	$(MAKE) install-common
@@ -156,47 +138,11 @@ install-openrc:
 	cp openrc/pgmon.confd $(DESTDIR)/etc/conf.d/pgmon
 
 
-##
-# Packaging targets
-#
-# These targets create packages for the supported distro versions
-##
-
-# Build all packages
-.PHONY: package-all
-package-all: all-package-images $(foreach distro_release, $(SUPPORTED), package-$(distro_release))
-
-# Gentoo package (tar.bz2) creation
-.PHONY: package-gentoo
-package-gentoo:
-	mkdir -p $(BUILD_DIR)/gentoo
-	tar --transform "s,^,$(PACKAGE_NAME)-$(FULL_VERSION)/," -acjf $(BUILD_DIR)/gentoo/$(PACKAGE_NAME)-$(FULL_VERSION).tar.bz2 --exclude .gitignore $(shell git ls-tree --full-tree --name-only -r HEAD)
-	cp $(BUILD_DIR)/gentoo/$(PACKAGE_NAME)-$(FULL_VERSION).tar.bz2 $(BUILD_DIR)/
-
-# Create a deb/rpm package
-.PHONY: package-%
-package-%: PARTS=$(subst -, ,$*)
-package-%: DISTRO=$(word 1, $(PARTS))
-package-%: RELEASE=$(word 2, $(PARTS))
-package-%:
-	mkdir -p $(BUILD_DIR)
-	docker run --rm \
-	    -v .:/src:ro \
-	    -v ./$(BUILD_DIR):/output \
-	    --user $(shell id -u):$(shell id -g) \
-	    "$(DISTRO)-packager:$(RELEASE)"
-
-
-##
-# Install test targets
-#
-# These targets test installing the package on the supported distro versions
-##
-
 # Run all of the install tests
-.PHONY: install-tests debian-%-install-test rockylinux-%-install-test ubuntu-%-install-test amazonlinux-%-install-test gentoo-install-test
+.PHONY: install-tests debian-%-install-test rockylinux-%-install-test ubuntu-%-install-test gentoo-install-test
 install-tests: $(foreach distro_release, $(SUPPORTED), $(distro_release)-install-test)
 
+
 # Run a Debian install test
 debian-%-install-test:
 	docker run --rm \
@@ -208,7 +154,7 @@ debian-%-install-test:
 rockylinux-%-install-test:
 	docker run --rm \
 	     -v ./$(BUILD_DIR):/output \
-	     rockylinux/rockylinux:$* \
+	     rockylinux:$* \
 	     bash -c 'dnf makecache && dnf install -y /output/$(PACKAGE_NAME)-$(RPM_VERSION).el$*.noarch.rpm'
 
 # Run an Ubuntu install test
@@ -219,30 +165,19 @@ ubuntu-%-install-test:
 	     bash -c 'apt-get update && apt-get install -y /output/$(PACKAGE_NAME)-$(DEB_VERSION)-ubuntu-$*.deb'
 
 # Run an OracleLinux install test (this is for EL7 since CentOS7 images no longer exist)
-oraclelinux-%-install-test: MGR=$(intcmp $*, 7, yum, yum, dnf)
 oraclelinux-%-install-test:
 	docker run --rm \
 	     -v ./$(BUILD_DIR):/output \
-	     oraclelinux:$* \
+	     oraclelinux:7 \
-	     bash -c '$(MGR) makecache && $(MGR) install -y /output/$(PACKAGE_NAME)-$(RPM_VERSION).el7.noarch.rpm'
+	     bash -c 'yum makecache && yum install -y /output/$(PACKAGE_NAME)-$(RPM_VERSION).el7.noarch.rpm'
-
-# Run a Amazon Linux install test
-# Note: AL2 is too old for dnf
-amazonlinux-%-install-test: MGR=$(intcmp $*, 2, yum, yum, dnf)
-amazonlinux-%-install-test:
-	docker run --rm \
-	     -v ./$(BUILD_DIR):/output \
-	     amazonlinux:$* \
-	     bash -c '$(MGR) makecache && $(MGR) install -y /output/$(PACKAGE_NAME)-$(RPM_VERSION).amzn$*.noarch.rpm'
 
 # Run a Gentoo install test
 gentoo-install-test:
 	# May impliment this in the future, but would require additional headaches to set up a repo
-	echo "This would take a while ... skipping for now"
+	true
-
 
 ##
-# Packaging image targets
+# Container targets
 #
 # These targets build the docker images used to create packages
 ##
@@ -251,11 +186,6 @@ gentoo-install-test:
 .PHONY: all-package-images
 all-package-images: $(foreach distro_release, $(SUPPORTED), package-image-$(distro_release))
 
-# Nothing needs to be created to build te tarballs for Gentoo
-.PHONY: package-image-gentoo
-package-image-gentoo:
-	echo "Noting to do"
-
 # Generic target for creating images that actually build the packages
 # The % is expected to be: distro-release
 # The build/.package-image-% target actually does the work and touches a state file to avoid excessive building
@@ -271,10 +201,11 @@ package-image-%:
 # Inside-container targets
 #
 # These targets are used inside containers.  They expect the repo to be mounted
-# at /src and the build directory to be mounted at /output.
+# at /src and the package manager specific build directory to be mounted at
+# /output.
 ##
 
-.PHONY: actually-package-debian-% actually-package-rockylinux-% actually-package-ubuntu-% actually-package-oraclelinux-% actually-package-amazonlinux-%
+.PHONY: actually-package-debian-% actually-package-rockylinux-% actually-package-ubuntu-% actually-package-oraclelinux-%
 
 # Debian package creation
 actually-package-debian-%:
@@ -298,36 +229,10 @@ actually-package-ubuntu-%:
 	dpkg-deb -Zgzip --build /output/ubuntu-$* "/output/$(PACKAGE_NAME)-$(DEB_VERSION)-ubuntu-$*.deb"
 
 # OracleLinux package creation
-# Note: This needs to work inside OEL7, so we can't use intcmp
-actually-package-oraclelinux-7:
-	mkdir -p /output/oraclelinux-7/{BUILD,RPMS,SOURCES,SPECS,SRPMS}
-	sed -e "s/@@VERSION@@/$(VERSION)/g" -e "s/@@RELEASE@@/$(RPM_RELEASE)/g" RPM/$(PACKAGE_NAME)-el7.spec > /output/oraclelinux-7/SPECS/$(PACKAGE_NAME).spec
-	rpmbuild --define '_topdir /output/oraclelinux-7' \
-	         --define 'version $(RPM_VERSION)' \
-	         -bb /output/oraclelinux-7/SPECS/$(PACKAGE_NAME).spec
-	cp /output/oraclelinux-7/RPMS/noarch/$(PACKAGE_NAME)-$(RPM_VERSION).el7.noarch.rpm /output/
 actually-package-oraclelinux-%:
 	mkdir -p /output/oraclelinux-$*/{BUILD,RPMS,SOURCES,SPECS,SRPMS}
-	sed -e "s/@@VERSION@@/$(VERSION)/g" -e "s/@@RELEASE@@/$(RPM_RELEASE)/g" RPM/$(PACKAGE_NAME).spec > /output/oraclelinux-$*/SPECS/$(PACKAGE_NAME).spec
+	sed -e "s/@@VERSION@@/$(VERSION)/g" -e "s/@@RELEASE@@/$(RPM_RELEASE)/g" RPM/$(PACKAGE_NAME)-el7.spec > /output/oraclelinux-$*/SPECS/$(PACKAGE_NAME).spec
 	rpmbuild --define '_topdir /output/oraclelinux-$*' \
 	         --define 'version $(RPM_VERSION)' \
 	         -bb /output/oraclelinux-$*/SPECS/$(PACKAGE_NAME).spec
 	cp /output/oraclelinux-$*/RPMS/noarch/$(PACKAGE_NAME)-$(RPM_VERSION).el$*.noarch.rpm /output/
-
-# Amazon Linux package creation
-# Note: This needs to work inside AL2, so we can't use intcmp
-actually-package-amazonlinux-2:
-	mkdir -p /output/amazonlinux-2/{BUILD,RPMS,SOURCES,SPECS,SRPMS}
-	sed -e "s/@@VERSION@@/$(VERSION)/g" -e "s/@@RELEASE@@/$(RPM_RELEASE)/g" RPM/$(PACKAGE_NAME)-el7.spec > /output/amazonlinux-2/SPECS/$(PACKAGE_NAME).spec
-	rpmbuild --define '_topdir /output/amazonlinux-2' \
-	         --define 'version $(RPM_VERSION)' \
-	         -bb /output/amazonlinux-2/SPECS/$(PACKAGE_NAME).spec
-	cp /output/amazonlinux-2/RPMS/noarch/$(PACKAGE_NAME)-$(RPM_VERSION).amzn2.noarch.rpm /output/
-actually-package-amazonlinux-%:
-	mkdir -p /output/amazonlinux-$*/{BUILD,RPMS,SOURCES,SPECS,SRPMS}
-	sed -e "s/@@VERSION@@/$(VERSION)/g" -e "s/@@RELEASE@@/$(RPM_RELEASE)/g" RPM/$(PACKAGE_NAME).spec > /output/amazonlinux-$*/SPECS/$(PACKAGE_NAME).spec
-	rpmbuild --define '_topdir /output/amazonlinux-$*' \
-	         --define 'version $(RPM_VERSION)' \
-	         -bb /output/amazonlinux-$*/SPECS/$(PACKAGE_NAME).spec
-	cp /output/amazonlinux-$*/RPMS/noarch/$(PACKAGE_NAME)-$(RPM_VERSION).amzn$*.noarch.rpm /output/
-

docker/Dockerfile-amazonlinux

@@ -1,22 +0,0 @@
-# Dockerfile.rpm
-
-ARG DISTRO=amazonlinux
-ARG RELEASE=2023
-
-FROM ${DISTRO}:${RELEASE}
-
-ARG DISTRO
-ARG RELEASE
-
-RUN if [ ${RELEASE} -le 2 ] ; then MGR=yum ; else MGR=dnf ; fi && \
-    ${MGR} install -y \
-    rpm-build \
-    make \
-    && ${MGR} clean all
-
-RUN echo -e "#!/bin/bash\nmake actually-package-${DISTRO}-${RELEASE}" > /init.sh \
-    && chmod 755 /init.sh
-
-WORKDIR /src
-
-CMD ["/bin/bash", "/init.sh"]

docker/Dockerfile-oraclelinux

@@ -8,12 +8,11 @@ FROM ${DISTRO}:${RELEASE}
 ARG DISTRO
 ARG RELEASE
 
-RUN if [ ${RELEASE} -le 7 ] ; then MGR=yum ; else MGR=dnf ; fi && \
+RUN yum install -y \
-    ${MGR} install -y \
     rpm-build \
     make \
-    oracle-epel-release-el${RELEASE} \
+    oracle-epel-release-el7 \
-    && ${MGR} clean all
+    && yum clean all
 
 RUN echo -e "#!/bin/bash\nmake actually-package-${DISTRO}-${RELEASE}" > /init.sh \
     && chmod 755 /init.sh

docker/Dockerfile-rockylinux

@@ -3,7 +3,7 @@
 ARG DISTRO=rockylinux
 ARG RELEASE=9
 
-FROM rockylinux/${DISTRO}:${RELEASE}
+FROM ${DISTRO}:${RELEASE}
 
 ARG DISTRO
 ARG RELEASE

pylintrc

@@ -1,4 +0,0 @@
-[MASTER]
-py-version=3.5
-
-disable=fixme

sample-config/pgmon-metrics.yml

@@ -18,7 +18,6 @@ metrics:
     query:
       0: >
         SELECT host(client_addr) || '_' || regexp_replace(application_name, '[ ,]', '_', 'g') AS repid,
-               application_name,
                client_addr,
                state
         FROM pg_stat_replication
@@ -196,28 +195,12 @@ metrics:
     type: set
     query:
       0: >
-        SELECT
+        SELECT state,
-          states.state,
+               count(*) AS backend_count,
-          COALESCE(a.backend_count, 0) AS backend_count,
+               COALESCE(EXTRACT(EPOCH FROM max(now() - state_change)), 0) AS max_state_time
-          COALESCE(a.max_state_time, 0) AS max_state_time
+        FROM pg_stat_activity
-        FROM (
+        WHERE datname = %(dbname)s
-          SELECT state,
+        GROUP BY state
-                 count(*) AS backend_count,
-                 COALESCE(EXTRACT(EPOCH FROM now() - min(state_change)), 0) AS max_state_time
-          FROM pg_stat_activity
-          WHERE datname = %(dbname)s
-          GROUP BY state
-        ) AS a
-        RIGHT JOIN
-          unnest(ARRAY[
-            'active',
-            'idle',
-            'idle in transaction',
-            'idle in transaction (aborted)',
-            'fastpath function call',
-            'disabled'
-          ]) AS states(state)
-        USING (state);
     test_args:
       dbname: postgres
 
@@ -246,19 +229,7 @@ metrics:
         SELECT COUNT(*) FILTER (WHERE has_sequence_privilege(c.oid, 'SELECT,USAGE')) AS visible_sequences,
                COUNT(*) AS total_sequences
         FROM pg_class AS c
-        WHERE relkind = 'S'
+        WHERE relkind = 'S';
-
-  locks:
-    type: row
-    query:
-      0: >
-        SELECT COUNT(*) AS total,
-               SUM(CASE WHEN granted THEN 1 ELSE 0 END) AS granted
-        FROM pg_locks
-      90400: >
-        SELECT COUNT(*) AS total,
-               COUNT(*) FILTER (WHERE granted) AS granted
-        FROM pg_locks
 
 
   ##
@@ -334,5 +305,3 @@ metrics:
     type: value
     query:
       0: SELECT count(*) AS ntables FROM pg_stat_user_tables
-
-  #sequence_usage:

src/pgmon.py

@@ -1,147 +1,105 @@
 #!/usr/bin/env python3
-"""
-pgmon is a monitoring intermediary that sits between a PostgreSQL cluster and a monitoring systen
-that is capable of parsing JSON responses over an HTTP connection.
-"""
-
-# pylint: disable=too-few-public-methods
 
+import yaml
 import json
 import time
 import os
 import sys
-import signal
+
 import argparse
 import logging
-import re
-
-from decimal import Decimal
-
-from urllib.parse import urlparse, parse_qs
-
-from contextlib import contextmanager
 
 from datetime import datetime, timedelta
 
-from http.server import BaseHTTPRequestHandler
-from http.server import ThreadingHTTPServer
-
-from threading import Lock
-
-import yaml
-
 import psycopg2
 from psycopg2.extras import RealDictCursor
 from psycopg2.pool import ThreadedConnectionPool
 
+from contextlib import contextmanager
+
+import signal
+from threading import Thread, Lock, Semaphore
+
+from http.server import BaseHTTPRequestHandler, HTTPServer
+from http.server import ThreadingHTTPServer
+from urllib.parse import urlparse, parse_qs
+
 import requests
+import re
 
+from decimal import Decimal
 
-VERSION = "1.1.0-rc1"
+VERSION = "1.0.4"
 
+# Configuration
+config = {}
 
-class Context:
+# Dictionary of current PostgreSQL connection pools
-    """
+connections_lock = Lock()
-    The global context for connections, config, version, nad IPC
+connections = {}
-    """
 
-    # Configuration
+# Dictionary of unhappy databases.  Keys are database names, value is the time
-    config = {}
+# the database was determined to be unhappy plus the cooldown setting.  So,
+# basically it's the time when we should try to connect to the database again.
+unhappy_cooldown = {}
 
-    # Dictionary of current PostgreSQL connection pools
+# Version information
-    connections_lock = Lock()
+cluster_version = None
-    connections = {}
+cluster_version_next_check = None
+cluster_version_lock = Lock()
 
-    # Dictionary of unhappy databases.  Keys are database names, value is the time
+# PostgreSQL latest version information
-    # the database was determined to be unhappy plus the cooldown setting.  So,
+latest_version = None
-    # basically it's the time when we should try to connect to the database again.
+latest_version_next_check = None
-    unhappy_cooldown = {}
+latest_version_lock = Lock()
+release_supported = None
 
-    # Version information
+# Running state (used to gracefully shut down)
-    cluster_version = None
+running = True
-    cluster_version_next_check = None
-    cluster_version_lock = Lock()
 
-    # PostgreSQL latest version information
+# The http server object
-    latest_version = None
+httpd = None
-    latest_version_next_check = None
-    latest_version_lock = Lock()
-    release_supported = None
 
-    # Running state (used to gracefully shut down)
+# Where the config file lives
-    running = True
+config_file = None
 
-    # The http server object
+# Configure logging
-    httpd = None
+log = logging.getLogger(__name__)
-
+formatter = logging.Formatter(
-    # Where the config file lives
+    "%(asctime)s - %(levelname)s - %(filename)s: %(funcName)s() line %(lineno)d: %(message)s"
-    config_file = None
+)
-
+console_log_handler = logging.StreamHandler()
-    # Configure logging
+console_log_handler.setFormatter(formatter)
-    log = logging.getLogger(__name__)
+log.addHandler(console_log_handler)
-
-    @classmethod
-    def init_logging(cls):
-        """
-        Actually initialize the logging framework.  Since we don't ever instantiate the Context
-        class, this provides a way to make a few modifications to the log handler.
-        """
-
-        formatter = logging.Formatter(
-            "%(asctime)s - %(levelname)s - %(filename)s: "
-            "%(funcName)s() line %(lineno)d: %(message)s"
-        )
-        console_log_handler = logging.StreamHandler()
-        console_log_handler.setFormatter(formatter)
-        cls.log.addHandler(console_log_handler)
 
 
 # Error types
 class ConfigError(Exception):
-    """
+    pass
-    Error type for all config related errors.
-    """
 
 
 class DisconnectedError(Exception):
-    """
+    pass
-    Error indicating a previously active connection to the database has been disconnected.
-    """
 
 
 class UnhappyDBError(Exception):
-    """
+    pass
-    Error indicating that a database the code has been asked to connect to is on the unhappy list.
-    """
 
 
 class UnknownMetricError(Exception):
-    """
+    pass
-    Error indicating that an undefined metric was requested.
-    """
 
 
 class MetricVersionError(Exception):
-    """
+    pass
-    Error indicating that there is no suitable query for a metric that was requested for the
-    version of PostgreSQL being monitored.
-    """
 
 
 class LatestVersionCheckError(Exception):
-    """
+    pass
-    Error indicating that there was a problem retrieving or parsing the latest version information.
-    """
-
-
-class InvalidDataError(Exception):
-    """
-    Error indicating query results were somehow invalid
-    """
 
 
 # Default config settings
-DEFAULT_CONFIG = {
+default_config = {
     # The address the agent binds to
     "address": "127.0.0.1",
     # The port the agent listens on for requests
@@ -219,60 +177,6 @@ def update_deep(d1, d2):
     return d1
 
 
-def validate_metric(path, name, metric):
-    """
-    Validate a metric definition from a given file.  If any query definitions come from external
-    files, the metric dict will be updated with the actual query.
-
-    Params:
-        path: path to the file which contains this definition
-        name: name of the metric
-        metric: the dictionary containing the metric definition
-    """
-    # Validate return types
-    try:
-        if metric["type"] not in ["value", "row", "column", "set"]:
-            raise ConfigError(
-                "Invalid return type: {} for metric {} in {}".format(
-                    metric["type"], name, path
-                )
-            )
-    except KeyError as e:
-        raise ConfigError(
-            "No type specified for metric {} in {}".format(name, path)
-        ) from e
-
-    # Ensure queries exist
-    query_dict = metric.get("query", {})
-    if not isinstance(query_dict, dict):
-        raise ConfigError(
-            "Query definition should be a dictionary, got: {} for metric {} in {}".format(
-                query_dict, name, path
-            )
-        )
-
-    if len(query_dict) == 0:
-        raise ConfigError("Missing queries for metric {} in {}".format(name, path))
-
-    # Read external sql files and validate version keys
-    config_base = os.path.dirname(path)
-    for vers, query in metric["query"].items():
-        try:
-            int(vers)
-        except Exception as e:
-            raise ConfigError(
-                "Invalid version: {} for metric {} in {}".format(vers, name, path)
-            ) from e
-
-        # Read in the external query and update the definition in the metricdictionary
-        if query.startswith("file:"):
-            query_path = query[5:]
-            if not query_path.startswith("/"):
-                query_path = os.path.join(config_base, query_path)
-            with open(query_path, "r", encoding="utf-8") as f:
-                metric["query"][vers] = f.read()
-
-
 def read_config(path, included=False):
     """
     Read a config file.
@@ -281,21 +185,61 @@ def read_config(path, included=False):
         path: path to the file to read
         included: is this file included by another file?
     """
-
     # Read config file
-    Context.log.info("Reading log file: %s", path)
+    log.info("Reading log file: {}".format(path))
-    with open(path, "r", encoding="utf-8") as f:
+    with open(path, "r") as f:
         try:
             cfg = yaml.safe_load(f)
         except yaml.parser.ParserError as e:
-            raise ConfigError("Inavlid config file: {}: {}".format(path, e)) from e
+            raise ConfigError("Inavlid config file: {}: {}".format(path, e))
+
+    # Since we use it a few places, get the base directory from the config
+    config_base = os.path.dirname(path)
 
     # Read any external queries and validate metric definitions
     for name, metric in cfg.get("metrics", {}).items():
-        validate_metric(path, name, metric)
+        # Validate return types
+        try:
+            if metric["type"] not in ["value", "row", "column", "set"]:
+                raise ConfigError(
+                    "Invalid return type: {} for metric {} in {}".format(
+                        metric["type"], name, path
+                    )
+                )
+        except KeyError:
+            raise ConfigError(
+                "No type specified for metric {} in {}".format(name, path)
+            )
+
+        # Ensure queries exist
+        query_dict = metric.get("query", {})
+        if type(query_dict) is not dict:
+            raise ConfigError(
+                "Query definition should be a dictionary, got: {} for metric {} in {}".format(
+                    query_dict, name, path
+                )
+            )
+
+        if len(query_dict) == 0:
+            raise ConfigError("Missing queries for metric {} in {}".format(name, path))
+
+        # Read external sql files and validate version keys
+        for vers, query in metric["query"].items():
+            try:
+                int(vers)
+            except:
+                raise ConfigError(
+                    "Invalid version: {} for metric {} in {}".format(vers, name, path)
+                )
+
+            if query.startswith("file:"):
+                query_path = query[5:]
+                if not query_path.startswith("/"):
+                    query_path = os.path.join(config_base, query_path)
+                with open(query_path, "r") as f:
+                    metric["query"][vers] = f.read()
 
     # Read any included config files
-    config_base = os.path.dirname(path)
     for inc in cfg.get("include", []):
         # Prefix relative paths with the directory from the current config
         if not inc.startswith("/"):
@@ -306,37 +250,34 @@ def read_config(path, included=False):
     # config
     if included:
         return cfg
+    else:
+        new_config = {}
+        update_deep(new_config, default_config)
+        update_deep(new_config, cfg)
 
-    new_config = {}
+        # Minor sanity checks
-    update_deep(new_config, DEFAULT_CONFIG)
+        if len(new_config["metrics"]) == 0:
-    update_deep(new_config, cfg)
+            log.error("No metrics are defined")
+            raise ConfigError("No metrics defined")
 
-    # Minor sanity checks
+        # Validate the new log level before changing the config
-    if len(new_config["metrics"]) == 0:
+        if new_config["log_level"].upper() not in [
-        Context.log.error("No metrics are defined")
+            "DEBUG",
-        raise ConfigError("No metrics defined")
+            "INFO",
+            "WARNING",
+            "ERROR",
+            "CRITICAL",
+        ]:
+            raise ConfigError("Invalid log level: {}".format(new_config["log_level"]))
 
-    # Validate the new log level before changing the config
+        global config
-    if new_config["log_level"].upper() not in [
+        config = new_config
-        "DEBUG",
-        "INFO",
-        "WARNING",
-        "ERROR",
-        "CRITICAL",
-    ]:
-        raise ConfigError("Invalid log level: {}".format(new_config["log_level"]))
 
-    Context.config = new_config
+        # Apply changes to log level
-
+        log.setLevel(logging.getLevelName(config["log_level"].upper()))
-    # Apply changes to log level
-    Context.log.setLevel(logging.getLevelName(Context.config["log_level"].upper()))
-
-    # Return the config (mostly to make pylint happy, but also in case I opt to remove the side
-    # effect and make this more functional.
-    return Context.config
 
 
-def signal_handler(sig, frame):  # pylint: disable=unused-argument
+def signal_handler(sig, frame):
     """
     Function for handling signals
 
@@ -347,22 +288,19 @@ def signal_handler(sig, frame):  # pylint: disable=unused-argument
 
     # Signal everything to shut down
     if sig in [signal.SIGINT, signal.SIGTERM, signal.SIGQUIT]:
-        Context.log.info("Shutting down ...")
+        log.info("Shutting down ...")
-        Context.running = False
+        global running
-        if Context.httpd is not None:
+        running = False
-            Context.httpd.socket.close()
+        if httpd is not None:
+            httpd.socket.close()
 
     # Signal a reload
     if sig == signal.SIGHUP:
-        Context.log.warning("Received config reload signal")
+        log.warning("Received config reload signal")
-        read_config(Context.config_file)
+        read_config(config_file)
 
 
 class ConnectionPool(ThreadedConnectionPool):
-    """
-    Threaded connection pool that has a context manager.
-    """
-
     def __init__(self, dbname, minconn, maxconn, *args, **kwargs):
         # Make sure dbname isn't different in the kwargs
         kwargs["dbname"] = dbname
@@ -371,14 +309,7 @@ class ConnectionPool(ThreadedConnectionPool):
         self.name = dbname
 
     @contextmanager
-    def connection(self, timeout):
+    def connection(self, timeout=None):
-        """
-        Connection context manager for our connection pool.  This will attempt to retrieve a
-        connection until the timeout is reached.
-
-        Params:
-            timeout: how long to keep trying to get a connection bedore giving up
-        """
         conn = None
         timeout_time = datetime.now() + timedelta(timeout)
         # We will continue to try to get a connection slot until we time out
@@ -402,37 +333,34 @@ class ConnectionPool(ThreadedConnectionPool):
 def get_pool(dbname):
     """
     Get a database connection pool.
-
-    Params:
-        dbname: the name of the database for which a connection pool should be returned.
     """
     # Check if the db is unhappy and wants to be left alone
-    if dbname in Context.unhappy_cooldown:
+    if dbname in unhappy_cooldown:
-        if Context.unhappy_cooldown[dbname] > datetime.now():
+        if unhappy_cooldown[dbname] > datetime.now():
             raise UnhappyDBError()
 
     # Create a connection pool if it doesn't already exist
-    if dbname not in Context.connections:
+    if dbname not in connections:
-        with Context.connections_lock:
+        with connections_lock:
             # Make sure nobody created the pool while we were waiting on the
             # lock
-            if dbname not in Context.connections:
+            if dbname not in connections:
-                Context.log.info("Creating connection pool for: %s", dbname)
+                log.info("Creating connection pool for: {}".format(dbname))
                 # Actually create the connection pool
-                Context.connections[dbname] = ConnectionPool(
+                connections[dbname] = ConnectionPool(
                     dbname,
-                    int(Context.config["min_pool_size"]),
+                    int(config["min_pool_size"]),
-                    int(Context.config["max_pool_size"]),
+                    int(config["max_pool_size"]),
                     application_name="pgmon",
-                    host=Context.config["dbhost"],
+                    host=config["dbhost"],
-                    port=Context.config["dbport"],
+                    port=config["dbport"],
-                    user=Context.config["dbuser"],
+                    user=config["dbuser"],
-                    connect_timeout=int(Context.config["connect_timeout"]),
+                    connect_timeout=int(config["connect_timeout"]),
-                    sslmode=Context.config["ssl_mode"],
+                    sslmode=config["ssl_mode"],
                 )
             # Clear the unhappy indicator if present
-            Context.unhappy_cooldown.pop(dbname, None)
+            unhappy_cooldown.pop(dbname, None)
-    return Context.connections[dbname]
+    return connections[dbname]
 
 
 def handle_connect_failure(pool):
@@ -440,8 +368,8 @@ def handle_connect_failure(pool):
     Mark the database as being unhappy so we can leave it alone for a while
     """
     dbname = pool.name
-    Context.unhappy_cooldown[dbname] = datetime.now() + timedelta(
+    unhappy_cooldown[dbname] = datetime.now() + timedelta(
-        seconds=int(Context.config["reconnect_cooldown"])
+        seconds=int(config["reconnect_cooldown"])
     )
 
 
@@ -472,67 +400,41 @@ def json_encode_special(obj):
     """
     if isinstance(obj, Decimal):
         return float(obj)
-    raise TypeError("Cannot serialize object of {}".format(type(obj)))
+    raise TypeError(f'Cannot serialize object of {type(obj)}')
-
-
-def json_encode_result(return_type, res):
-    """
-    Return a json string encoding of the results of a query.
-
-    params:
-        return_type: the expected structure to return.  One of:
-                     value, row, column, set
-        res: the query results
-
-    returns: a json string form of the results
-
-    raises:
-        ConfigError: when an invalid return_type is given
-        InvalidDataError: when the query results don't match the return type
-    """
-    try:
-        if return_type == "value":
-            if len(res) == 0:
-                return ""
-            return str(list(res[0].values())[0])
-
-        if return_type == "row":
-            return json.dumps(
-                res[0] if len(res) > 0 else {}, default=json_encode_special
-            )
-
-        if return_type == "column":
-            return json.dumps(
-                [list(r.values())[0] for r in res], default=json_encode_special
-            )
-
-        if return_type == "set":
-            return json.dumps(res, default=json_encode_special)
-    except IndexError as e:
-        raise InvalidDataError(e) from e
-
-    # If we got to this point, the return type is invalid
-    raise ConfigError("Invalid query return type: {}".format(return_type))
 
 
 def run_query_no_retry(pool, return_type, query, args):
     """
     Run the query with no explicit retry code
     """
-    with pool.connection(float(Context.config["connect_timeout"])) as conn:
+    with pool.connection(float(config["connect_timeout"])) as conn:
         try:
             with conn.cursor(cursor_factory=RealDictCursor) as curs:
                 curs.execute(query, args)
                 res = curs.fetchall()
 
-                return json_encode_result(return_type, res)
+                if return_type == "value":
-        except Exception as e:
+                    if len(res) == 0:
+                        return ""
+                    return str(list(res[0].values())[0])
+                elif return_type == "row":
+                    if len(res) == 0:
+                        return "[]"
+                    return json.dumps(res[0], default=json_encode_special)
+                elif return_type == "column":
+                    if len(res) == 0:
+                        return "[]"
+                    return json.dumps([list(r.values())[0] for r in res], default=json_encode_special)
+                elif return_type == "set":
+                    return json.dumps(res, default=json_encode_special)
+        except:
             dbname = pool.name
-            if dbname in Context.unhappy_cooldown:
+            if dbname in unhappy_cooldown:
-                raise UnhappyDBError() from e
+                raise UnhappyDBError()
-            if conn.closed != 0:
+            elif conn.closed != 0:
-                raise DisconnectedError() from e
+                raise DisconnectedError()
-            raise
+            else:
+                raise
 
 
 def run_query(pool, return_type, query, args):
@@ -553,7 +455,7 @@ def run_query(pool, return_type, query, args):
     try:
         return run_query_no_retry(pool, return_type, query, args)
     except DisconnectedError:
-        Context.log.warning("Stale PostgreSQL connection found ... trying again")
+        log.warning("Stale PostgreSQL connection found ... trying again")
         # This sleep is an annoying hack to give the pool workers time to
         # actually mark the connection, otherwise it can be given back in the
         # next connection() call
@@ -561,9 +463,9 @@ def run_query(pool, return_type, query, args):
         time.sleep(1)
         try:
             return run_query_no_retry(pool, return_type, query, args)
-        except Exception as e:
+        except:
             handle_connect_failure(pool)
-            raise UnhappyDBError() from e
+            raise UnhappyDBError()
 
 
 def get_cluster_version():
@@ -571,39 +473,40 @@ def get_cluster_version():
     Get the PostgreSQL version if we don't already know it, or if it's been
     too long sice the last time it was checked.
     """
+    global cluster_version
+    global cluster_version_next_check
 
     # If we don't know the version or it's past the recheck time, get the
     # version from the database.  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.
     if (
-        Context.cluster_version is None
+        cluster_version is None
-        or Context.cluster_version_next_check is None
+        or cluster_version_next_check is None
-        or Context.cluster_version_next_check < datetime.now()
+        or cluster_version_next_check < datetime.now()
     ):
-        with Context.cluster_version_lock:
+        with cluster_version_lock:
             # Only check if nobody already got the version before us
             if (
-                Context.cluster_version is None
+                cluster_version is None
-                or Context.cluster_version_next_check is None
+                or cluster_version_next_check is None
-                or Context.cluster_version_next_check < datetime.now()
+                or cluster_version_next_check < datetime.now()
             ):
-                Context.log.info("Checking PostgreSQL cluster version")
+                log.info("Checking PostgreSQL cluster version")
-                pool = get_pool(Context.config["dbname"])
+                pool = get_pool(config["dbname"])
-                Context.cluster_version = int(
+                cluster_version = int(
                     run_query(pool, "value", "SHOW server_version_num", None)
                 )
-                Context.cluster_version_next_check = datetime.now() + timedelta(
+                cluster_version_next_check = datetime.now() + timedelta(
-                    seconds=int(Context.config["version_check_period"])
+                    seconds=int(config["version_check_period"])
                 )
-                Context.log.info(
+                log.info("Got PostgreSQL cluster version: {}".format(cluster_version))
-                    "Got PostgreSQL cluster version: %s", Context.cluster_version
+                log.debug(
-                )
+                    "Next PostgreSQL cluster version check will be after: {}".format(
-                Context.log.debug(
+                        cluster_version_next_check
-                    "Next PostgreSQL cluster version check will be after: %s",
+                    )
-                    Context.cluster_version_next_check,
                 )
 
-    return Context.cluster_version
+    return cluster_version
 
 
 def version_num_to_release(version_num):
@@ -616,7 +519,8 @@ def version_num_to_release(version_num):
     """
     if version_num // 10000 < 10:
         return version_num // 10000 + (version_num % 10000 // 100 / 10)
-    return version_num // 10000
+    else:
+        return version_num // 10000
 
 
 def parse_version_rss(raw_rss, release):
@@ -624,7 +528,7 @@ def parse_version_rss(raw_rss, release):
     Parse the raw RSS from the versions.rss feed to extract the latest version of
     PostgreSQL that's availabe for the cluster being monitored.
 
-    This sets these Context variables:
+    This sets these global variables:
         latest_version
         release_supported
 
@@ -634,6 +538,8 @@ def parse_version_rss(raw_rss, release):
         raw_rss: The raw rss text from versions.rss
         release: The PostgreSQL release we care about (ex: 9.2, 14)
     """
+    global latest_version
+    global release_supported
 
     # Regular expressions for parsing the RSS document
     version_line = re.compile(
@@ -653,75 +559,75 @@ def parse_version_rss(raw_rss, release):
             version = m.group(1)
             parts = list(map(int, version.split(".")))
             if parts[0] < 10:
-                Context.latest_version = int(
+                latest_version = int(
                     "{}{:02}{:02}".format(parts[0], parts[1], parts[2])
                 )
             else:
-                Context.latest_version = int("{}00{:02}".format(parts[0], parts[1]))
+                latest_version = int("{}00{:02}".format(parts[0], parts[1]))
         elif release_found:
             # The next line after the version tells if the version is supported
             if unsupported_line.match(line):
-                Context.release_supported = False
+                release_supported = False
             else:
-                Context.release_supported = True
+                release_supported = True
             break
 
     # Make sure we actually found it
     if not release_found:
         raise LatestVersionCheckError("Current release ({}) not found".format(release))
 
-    Context.log.info(
+    log.info(
-        "Got latest PostgreSQL version: %s supported=%s",
+        "Got latest PostgreSQL version: {} supported={}".format(
-        Context.latest_version,
+            latest_version, release_supported
-        Context.release_supported,
+        )
     )
-    Context.log.debug(
+    log.debug(
-        "Next latest PostgreSQL version check will be after: %s",
+        "Next latest PostgreSQL version check will be after: {}".format(
-        Context.latest_version_next_check,
+            latest_version_next_check
+        )
     )
 
 
 def get_latest_version():
     """
-    Get the latest supported version of the major PostgreSQL release running on the server being
+    Get the latest supported version of the major PostgreSQL release running on the server being monitored.
-    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.
     if (
-        Context.latest_version is None
+        latest_version is None
-        or Context.latest_version_next_check is None
+        or latest_version_next_check is None
-        or Context.latest_version_next_check < datetime.now()
+        or latest_version_next_check < datetime.now()
     ):
         # Note: we get the cluster version here before grabbing the latest_version_lock
         #       lock so it's not held while trying to talk with the DB.
         release = version_num_to_release(get_cluster_version())
 
-        with Context.latest_version_lock:
+        with latest_version_lock:
             # Only check if nobody already got the version before us
             if (
-                Context.latest_version is None
+                latest_version is None
-                or Context.latest_version_next_check is None
+                or latest_version_next_check is None
-                or Context.latest_version_next_check < datetime.now()
+                or latest_version_next_check < datetime.now()
             ):
-                Context.log.info("Checking latest PostgreSQL version")
+                log.info("Checking latest PostgreSQL version")
-                Context.latest_version_next_check = datetime.now() + timedelta(
+                latest_version_next_check = datetime.now() + timedelta(
-                    seconds=int(Context.config["latest_version_check_period"])
+                    seconds=int(config["latest_version_check_period"])
                 )
 
                 # Grab the RSS feed
-                raw_rss = requests.get(
+                raw_rss = requests.get("https://www.postgresql.org/versions.rss")
-                    "https://www.postgresql.org/versions.rss", timeout=30
-                )
                 if raw_rss.status_code != 200:
-                    raise LatestVersionCheckError("code={}".format(raw_rss.status_code))
+                    raise LatestVersionCheckError("code={}".format(r.status_code))
 
-                # Parse the RSS body and set Context variables
+                # Parse the RSS body and set global variables
                 parse_version_rss(raw_rss.text, release)
 
-    return Context.latest_version
+    return latest_version
 
 
 def sample_metric(dbname, metric_name, args, retry=True):
@@ -730,9 +636,9 @@ def sample_metric(dbname, metric_name, args, retry=True):
     """
     # Get the metric definition
     try:
-        metric = Context.config["metrics"][metric_name]
+        metric = config["metrics"][metric_name]
-    except KeyError as e:
+    except KeyError:
-        raise UnknownMetricError("Unknown metric: {}".format(metric_name)) from e
+        raise UnknownMetricError("Unknown metric: {}".format(metric_name))
 
     # Get the connection pool for the database, or create one if it doesn't
     # already exist.
@@ -747,7 +653,8 @@ def sample_metric(dbname, metric_name, args, retry=True):
     # Execute the quert
     if retry:
         return run_query(pool, metric["type"], query, args)
-    return run_query_no_retry(pool, metric["type"], query, args)
+    else:
+        return run_query_no_retry(pool, metric["type"], query, args)
 
 
 def test_queries():
@@ -755,17 +662,12 @@ def test_queries():
     Run all of the metric queries against a database and check the results
     """
     # We just use the default db for tests
-    dbname = Context.config["dbname"]
+    dbname = config["dbname"]
     # Loop through all defined metrics.
-    for name, metric in Context.config["metrics"].items():
+    for name, metric in config["metrics"].items():
         # If the metric has arguments to use while testing, grab those
         args = metric.get("test_args", {})
-        print(
+        print("Testing {} [{}]".format(name, ", ".join(["{}={}".format(key, value) for key, value in args.items()])))
-            "Testing {} [{}]".format(
-                name,
-                ", ".join(["{}={}".format(key, value) for key, value in args.items()]),
-            )
-        )
         # When testing against a docker container, we may end up connecting
         # before the service is truly up (it restarts during the initialization
         # phase).  To cope with this, we'll allow a few connection failures.
@@ -802,8 +704,9 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
         """
         Override to suppress standard request logging
         """
+        pass
 
-    def do_GET(self):  # pylint: disable=invalid-name
+    def do_GET(self):
         """
         Handle a request.  This is just a wrapper around the actual handler
         code to keep things more readable.
@@ -811,7 +714,7 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
         try:
             self._handle_request()
         except BrokenPipeError:
-            Context.log.error("Client disconnected, exiting handler")
+            log.error("Client disconnected, exiting handler")
 
     def _handle_request(self):
         """
@@ -824,6 +727,7 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
 
         if metric_name == "agent_version":
             self._reply(200, VERSION)
+            return
         elif metric_name == "latest_version_info":
             try:
                 get_latest_version()
@@ -831,40 +735,46 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
                     200,
                     json.dumps(
                         {
-                            "latest": Context.latest_version,
+                            "latest": latest_version,
-                            "supported": 1 if Context.release_supported else 0,
+                            "supported": 1 if release_supported else 0,
                         }
                     ),
                 )
             except LatestVersionCheckError as e:
-                Context.log.error(
+                log.error("Failed to retrieve latest version information: {}".format(e))
-                    "Failed to retrieve latest version information: %s", e
-                )
                 self._reply(503, "Failed to retrieve latest version info")
-        else:
+            return
-            # Note: parse_qs returns the values as a list.  Since we always expect
-            #       single values, just grab the first from each.
-            args = {key: values[0] for key, values in parsed_query.items()}
 
-            # Get the dbname.  If none was provided, use the default from the
+        # Note: parse_qs returns the values as a list.  Since we always expect
-            # config.
+        #       single values, just grab the first from each.
-            dbname = args.get("dbname", Context.config["dbname"])
+        args = {key: values[0] for key, values in parsed_query.items()}
 
-            # Sample the metric
+        # Get the dbname.  If none was provided, use the default from the
-            try:
+        # config.
-                self._reply(200, sample_metric(dbname, metric_name, args))
+        dbname = args.get("dbname", config["dbname"])
-            except UnknownMetricError:
+
-                Context.log.error("Unknown metric: %s", metric_name)
+        # Sample the metric
-                self._reply(404, "Unknown metric")
+        try:
-            except MetricVersionError:
+            self._reply(200, sample_metric(dbname, metric_name, args))
-                Context.log.error("Failed to find an query version for %s", metric_name)
+            return
-                self._reply(404, "Unsupported version")
+        except UnknownMetricError as e:
-            except UnhappyDBError:
+            log.error("Unknown metric: {}".format(metric_name))
-                Context.log.info("Database %s is unhappy, please be patient", dbname)
+            self._reply(404, "Unknown metric")
-                self._reply(503, "Database unavailable")
+            return
-            except Exception as e:  # pylint: disable=broad-exception-caught
+        except MetricVersionError as e:
-                Context.log.error("Error running query: %s", e)
+            log.error(
-                self._reply(500, "Unexpected error: {}".format(e))
+                "Failed to find a version of {} for {}".format(metric_name, version)
+            )
+            self._reply(404, "Unsupported version")
+            return
+        except UnhappyDBError as e:
+            log.info("Database {} is unhappy, please be patient".format(dbname))
+            self._reply(503, "Database unavailable")
+            return
+        except Exception as e:
+            log.error("Error running query: {}".format(e))
+            self._reply(500, "Unexpected error: {}".format(e))
+            return
 
     def _reply(self, code, content):
         """
@@ -877,14 +787,7 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
         self.wfile.write(bytes(content, "utf-8"))
 
 
-def main():
+if __name__ == "__main__":
-    """
-    Main application routine
-    """
-
-    # Initialize the logging framework
-    Context.init_logging()
-
     # Handle cli args
     parser = argparse.ArgumentParser(
         prog="pgmon", description="A PostgreSQL monitoring agent"
@@ -905,35 +808,33 @@ def main():
     args = parser.parse_args()
 
     # Set the config file path
-    Context.config_file = args.config_file
+    config_file = args.config_file
 
     # Read the config file
-    read_config(Context.config_file)
+    read_config(config_file)
 
     # Run query tests and exit if test mode is enabled
     if args.test:
-        if test_queries() > 0:
+        errors = test_queries()
+        if errors > 0:
             sys.exit(1)
-        sys.exit(0)
+        else:
+            sys.exit(0)
 
     # Set up the http server to receive requests
-    server_address = (Context.config["address"], Context.config["port"])
+    server_address = (config["address"], config["port"])
-    Context.httpd = ThreadingHTTPServer(server_address, SimpleHTTPRequestHandler)
+    httpd = ThreadingHTTPServer(server_address, SimpleHTTPRequestHandler)
 
     # Set up the signal handler
     signal.signal(signal.SIGINT, signal_handler)
     signal.signal(signal.SIGHUP, signal_handler)
 
     # Handle requests.
-    Context.log.info("Listening on port %s...", Context.config["port"])
+    log.info("Listening on port {}...".format(config["port"]))
-    while Context.running:
+    while running:
-        Context.httpd.handle_request()
+        httpd.handle_request()
 
     # Clean up PostgreSQL connections
     # TODO: Improve this ... not sure it actually closes all the connections cleanly
-    for pool in Context.connections.values():
+    for pool in connections.values():
         pool.close()
-
-
-if __name__ == "__main__":
-    main()

tests/docker-compose.yml

@@ -20,7 +20,7 @@ services:
       POSTGRES_PASSWORD: secret
     healthcheck:
       #test: [ "CMD", "pg_isready", "-U", "postgres" ]
-      test: [ "CMD-SHELL", "pg_controldata $(psql -At -U postgres -c 'show data_directory') | grep -q 'in production'" ]
+      test: [ "CMD-SHELL", "pg_controldata /var/lib/postgresql/data/ | grep -q 'in production'" ]
       interval: 5s
       timeout: 2s
       retries: 40

tests/run-tests.sh

@@ -24,7 +24,6 @@ images["14"]='14-bookworm'
 images["15"]='15-bookworm'
 images["16"]='16-bookworm'
 images["17"]='17-bookworm'
-images["18"]='18-trixie'
 
 declare -A results=()
 

zabbix_templates/coverage.py

@@ -1,129 +0,0 @@
-#!/usr/bin/env python3
-
-# Compare the items defined in a Zabbix template with the metrics defined in a config file.
-
-import sys
-
-import yaml
-
-# Special built in metrics
-SPECIAL = {
-    "agent_version",
-    "latest_version_info"
-}
-
-
-class NonMetricItemError(Exception):
-    """
-    A given item does not directly use a metric
-    """
-
-
-def read_metrics(file):
-    """
-    Read the metrics from a config file and return the list of names
-
-    params:
-        file: the name of the file to read
-
-    returns:
-        list of metric named defined in the file
-
-    raises:
-        yaml.parser.ParserError: invalid yaml file
-    """
-    names = set()
-    config = None
-
-    with open(file, "r", encoding="utf-8") as f:
-        config = yaml.safe_load(f)
-
-    try:
-        for m in config["metrics"].keys():
-            names.add(m)
-    except KeyError:
-        pass
-
-    return names
-
-
-def extract_metric(item):
-    """
-    Extract the metric from an item definition
-
-    params:
-        item: the item/discovery/prototype definition dict
-
-    returns:
-        the name of the metric used in the item
-
-    raises:
-        NonMetricItemError: the item does not directly use a metric
-    """
-    try:
-        if item["type"] == "HTTP_AGENT":
-            url = item["url"]
-            if url.startswith("http://localhost:{$AGENT_PORT}"):
-                return url.split("/")[-1]
-    except KeyError:
-        raise NonMetricItemError()
-
-    raise NonMetricItemError()
-
-
-def read_template(file):
-    """
-    Read the items from a Zabbix template and return the list of metric names
-
-    params:
-        file: the name of the file to read
-
-    returns:
-        list of metric named used in the file
-
-    raises:
-        yaml.parser.ParserError: invalid yaml file
-    """
-    names = set()
-    config = None
-
-    with open(file, "r", encoding="utf-8") as f:
-        config = yaml.safe_load(f)
-
-    try:
-        for template in config["zabbix_export"]["templates"]:
-            for item in template["items"]:
-                try:
-                    names.add(extract_metric(item))
-                except NonMetricItemError:
-                    pass
-
-            for rule in template["discovery_rules"]:
-                try:
-                    names.add(extract_metric(rule))
-                except NonMetricItemError:
-                    pass
-
-                for proto in rule["item_prototypes"]:
-                    try:
-                        names.add(extract_metric(proto))
-                    except NonMetricItemError:
-                        pass
-    except KeyError:
-        pass
-
-    return names
-
-
-if __name__ == '__main__':
-    config_file = sys.argv[1]
-    config_metrics = read_metrics(config_file)
-
-    template_file = sys.argv[2]
-    template_metrics = read_template(template_file) - SPECIAL
-
-    config_only = config_metrics - template_metrics
-    template_only = template_metrics - config_metrics
-
-    print("Config only: {}".format(sorted(list(config_only))))
-    print("Template only: {}".format(sorted(list(template_only))))

zabbix_templates/pgmon_templates.yaml

@@ -49,206 +49,6 @@ zabbix_export:
           tags:
             - tag: Application
               value: PostgreSQL
-        - uuid: 1dd74025ca0e463bb9eee5cb473f30db
-          name: 'Total buffers allocated'
-          type: DEPENDENT
-          key: 'pgmon.bgwriter[buffers_alloc,total]'
-          delay: '0'
-          history: 90d
-          description: 'Total number of shared buffers that have been allocated'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.buffers_alloc
-          master_item:
-            key: 'pgmon[bgwriter]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: 4ab405996e71444a8113b95c65d73be2
-          name: 'Total buffers written by backends'
-          type: DEPENDENT
-          key: 'pgmon.bgwriter[buffers_backend,total]'
-          delay: '0'
-          history: 90d
-          description: 'Total number of shared buffers written by backends'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.buffers_backend
-          master_item:
-            key: 'pgmon[bgwriter]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: e8b440a1d6ff4ca6b3cb27e2e76f9d06
-          name: 'Total number of fsyncs from backends'
-          type: DEPENDENT
-          key: 'pgmon.bgwriter[buffers_backend_fsync,total]'
-          delay: '0'
-          history: 90d
-          description: 'Total number of times backends have issued their own fsync calls'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.buffers_backend_fsync
-          master_item:
-            key: 'pgmon[bgwriter]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: f8a14885edf34b5cbf2e92432e8fa4c2
-          name: 'Total buffers written during checkpoints'
-          type: DEPENDENT
-          key: 'pgmon.bgwriter[buffers_checkpoint,total]'
-          delay: '0'
-          history: 90d
-          description: 'Total number of shared buffers written during checkpoints'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.buffers_checkpoint
-          master_item:
-            key: 'pgmon[bgwriter]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: f09956f7aaad4b99b0d67339edf26dcf
-          name: 'Total buffers written by the background writer'
-          type: DEPENDENT
-          key: 'pgmon.bgwriter[buffers_clean,total]'
-          delay: '0'
-          history: 90d
-          description: 'Total number of shared buffers written by the background writer'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.buffers_clean
-          master_item:
-            key: 'pgmon[bgwriter]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: f1c6bd9346b14964bd492d7ccf8baf50
-          name: 'Total checkpoints due to changes'
-          type: DEPENDENT
-          key: 'pgmon.bgwriter[checkpoints_changes,total]'
-          delay: '0'
-          history: 90d
-          description: 'Total number of checkpoints that have occurred due to the number of row changes'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.checkpoints_req
-          master_item:
-            key: 'pgmon[bgwriter]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: 04c4587d2f2f4f5fbad866d70938cbb3
-          name: 'Total checkpoints due to time limit'
-          type: DEPENDENT
-          key: 'pgmon.bgwriter[checkpoints_timed,total]'
-          delay: '0'
-          history: 90d
-          description: 'Total number of checkpoints that have occurred due to the configured time limit'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.checkpoints_timed
-          master_item:
-            key: 'pgmon[bgwriter]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: 580a7e632b644aafa1166c534185ba92
-          name: 'Total time spent syncing files for checkpoints'
-          type: DEPENDENT
-          key: 'pgmon.bgwriter[checkpoint_sync_time,total]'
-          delay: '0'
-          history: 90d
-          units: s
-          description: 'Total time spent syncing files for checkpoints'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.checkpoint_sync_time
-            - type: MULTIPLIER
-              parameters:
-                - '0.001'
-          master_item:
-            key: 'pgmon[bgwriter]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: 4faa33b55fae4fc68561020636573a46
-          name: 'Total time spent writing checkpoints'
-          type: DEPENDENT
-          key: 'pgmon.bgwriter[checkpoint_write_time,total]'
-          delay: '0'
-          history: 90d
-          units: s
-          description: 'Total time spent writing checkpoints'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.checkpoint_write_time
-            - type: MULTIPLIER
-              parameters:
-                - '0.001'
-          master_item:
-            key: 'pgmon[bgwriter]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: c0c829c6cdc046a4b5d216e10362e4bb
-          name: 'Total number of times the background writer stopped'
-          type: DEPENDENT
-          key: 'pgmon.bgwriter[maxwritten_clean,total]'
-          delay: '0'
-          history: 90d
-          description: 'Total number of times the background writer stopped due to reaching the maximum  number of buffers it''s allowed to write in a single scan'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.maxwritten_clean
-          master_item:
-            key: 'pgmon[bgwriter]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: 645fef7b55cd48c69b11de3201e88d78
-          name: 'Number of locks'
-          type: DEPENDENT
-          key: pgmon.locks.count
-          delay: '0'
-          history: 90d
-          description: 'Total number of locks in any database'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.total
-          master_item:
-            key: 'pgmon[locks]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-        - uuid: a56ad753b1f341928867a47b14ed8b77
-          name: 'Number of granted locks'
-          type: DEPENDENT
-          key: pgmon.locks.granted
-          delay: '0'
-          history: 90d
-          description: 'Total number of granted locks in any database'
-          preprocessing:
-            - type: JSONPATH
-              parameters:
-                - $.granted
-          master_item:
-            key: 'pgmon[locks]'
-          tags:
-            - tag: Application
-              value: PostgreSQL
         - uuid: de1fa757395440118026f4c7a7c4ebbe
           name: 'PostgreSQL latest supported version'
           type: DEPENDENT
@@ -295,21 +95,6 @@ zabbix_export:
           tags:
             - tag: Application
               value: PostgreSQL
-        - uuid: 91baea76ebb240b19c5a5d3913d0b989
-          name: 'PostgreSQL BGWriter Info'
-          type: HTTP_AGENT
-          key: 'pgmon[bgwriter]'
-          delay: 5m
-          history: '0'
-          value_type: TEXT
-          trends: '0'
-          description: 'Maximum age of any frozen XID and MXID in any database'
-          url: 'http://localhost:{$AGENT_PORT}/bgwriter'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-            - tag: Type
-              value: Raw
         - uuid: 06b1d082ed1e4796bc31cc25f7db6326
           name: 'PostgreSQL Backend IO Info'
           type: HTTP_AGENT
@@ -339,21 +124,6 @@ zabbix_export:
               value: PostgreSQL
             - tag: Type
               value: Raw
-        - uuid: 4627c156923f4d53bc04789b9b88c133
-          name: 'PostgreSQL Lock Info'
-          type: HTTP_AGENT
-          key: 'pgmon[locks]'
-          delay: 5m
-          history: '0'
-          value_type: TEXT
-          trends: '0'
-          description: 'Maximum age of any frozen XID and MXID in any database'
-          url: 'http://localhost:{$AGENT_PORT}/locks'
-          tags:
-            - tag: Application
-              value: PostgreSQL
-            - tag: Type
-              value: Raw
         - uuid: 8706eccb7edc4fa394f552fc31f401a9
           name: 'PostgreSQL ID Age Info'
           type: HTTP_AGENT
@@ -397,286 +167,8 @@ zabbix_export:
                 operator: NOT_MATCHES_REGEX
                 formulaid: A
           lifetime: 30d
-          enabled_lifetime_type: DISABLE_AFTER
+          enabled_lifetime_type: DISABLE_NEVER
-          enabled_lifetime: 1d
           item_prototypes:
-            - uuid: 28d5fe3a4f6848149afed33aa645f677
-              name: 'Max connection age: active on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[active,age,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              value_type: FLOAT
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "active")].max_state_time.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: ff1b817c3d1f43dc8b49bfd0dcb0d10a
-              name: 'Connection count: active on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[active,count,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "active")].backend_count.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 4c0b9ca43adb45b895e3ba2e200e501e
-              name: 'Max connection age: disabled on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[disabled,age,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              value_type: FLOAT
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "disabled")].max_state_time.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 280dfc9a84e8425399164e6f3e91cf92
-              name: 'Connection count: disabled on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[disabled,count,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "disabled")].backend_count.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 63e62108657f47aaa29f7ec6499e45fc
-              name: 'Max connection age: fastpath function call on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[fastpath_function,age,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              value_type: FLOAT
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "fastpath function call")].max_state_time.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 33193e62f1ad4da5b2e30677581e5305
-              name: 'Connection count: fastpath function call on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[fastpath_function,count,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "fastpath function call")].backend_count.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 92e2366a56424bc18a88606417eae6e4
-              name: 'Max connection age: idle on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[idle,age,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              value_type: FLOAT
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "idle")].max_state_time.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 505bbbb4c7b745d8bab8f3b33705b76b
-              name: 'Connection count: idle on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[idle,count,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "idle")].backend_count.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 282494d5900c4c2e8abd298160c7cbb6
-              name: 'Max connection age: idle in transaction (aborted) on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[idle_aborted,age,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              value_type: FLOAT
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "idle in transaction (aborted)")].max_state_time.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 0da5075d79234602836fc7967a31f1cc
-              name: 'Connection count: idle in transaction (aborted) on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[idle_aborted,count,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "idle in transaction (aborted)")].backend_count.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 47aa3f7f4ff1473aae425b4c89472ab4
-              name: 'Max connection age: idle in transaction on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[idle_transaction,age,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              value_type: FLOAT
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "idle in transaction")].max_state_time.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 95519bf0aefd49799601e1bbb488ec90
-              name: 'Connection count: idle in transaction on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[idle_transaction,count,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "idle in transaction")].backend_count.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: b2ae38a5733d49ceb1a31e774c11785b
-              name: 'Max connection age: starting on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[starting,age,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              value_type: FLOAT
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "starting")].max_state_time.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: c1890f2d7ce84a7ebaaadf266d3ffc51
-              name: 'Connection count: starting on {#DBNAME}'
-              type: DEPENDENT
-              key: 'pgmon_connection_states[starting,count,{#DBNAME}]'
-              delay: '0'
-              history: 90d
-              description: 'Number of disk blocks read in this database'
-              preprocessing:
-                - type: JSONPATH
-                  parameters:
-                    - '$[?(@.state == "starting")].backend_count.first()'
-              master_item:
-                key: 'pgmon_connection_states[{#DBNAME}]'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-            - uuid: 131653f883f448a7b861b16bc4366dfd
-              name: 'Database Connection States for {#DBNAME}'
-              type: HTTP_AGENT
-              key: 'pgmon_connection_states[{#DBNAME}]'
-              history: '0'
-              value_type: TEXT
-              trends: '0'
-              url: 'http://localhost:{$AGENT_PORT}/activity'
-              query_fields:
-                - name: dbname
-                  value: '{#DBNAME}'
-              tags:
-                - tag: Application
-                  value: PostgreSQL
-                - tag: Database
-                  value: '{#DBNAME}'
-                - tag: Type
-                  value: Raw
             - uuid: a30babe4a6f4440bba2a3ee46eff7ce2
               name: 'Time spent executing statements on {#DBNAME}'
               type: DEPENDENT
@@ -1490,9 +982,6 @@ zabbix_export:
           type: DEPENDENT
           key: pgmon_discover_io_backend_types
           delay: '0'
-          lifetime: 30d
-          enabled_lifetime_type: DISABLE_AFTER
-          enabled_lifetime: 1h
           item_prototypes:
             - uuid: b1ac2e56b30f4812bf33ce973ef16b10
               name: 'I/O Evictions by {#BACKEND_TYPE}'
@@ -2083,15 +1572,8 @@ zabbix_export:
           type: HTTP_AGENT
           key: pgmon_discover_rep
           delay: 10m
-          filter:
-            conditions:
-              - macro: '{#APPLICATION_NAME}'
-                value: '^pg_[0-9]+_sync_[0-9]+_[0-9]+$'
-                operator: NOT_MATCHES_REGEX
-                formulaid: A
           lifetime: 30d
-          enabled_lifetime_type: DISABLE_AFTER
+          enabled_lifetime_type: DISABLE_NEVER
-          enabled_lifetime: 7d
           item_prototypes:
             - uuid: 3a5a60620e6a4db694e47251148d82f5
               name: 'Flush lag for {#REPID}'
@@ -2293,8 +1775,6 @@ zabbix_export:
                   value: Raw
           url: 'http://localhost:{$AGENT_PORT}/discover_rep'
           lld_macro_paths:
-            - lld_macro: '{#APPLICATION_NAME}'
-              path: $.application_name
             - lld_macro: '{#CLIENT_ADDR}'
               path: $.client_addr
             - lld_macro: '{#REPID}'
@@ -2306,15 +1786,6 @@ zabbix_export:
           type: HTTP_AGENT
           key: pgmon_discover_slots
           delay: 10m
-          filter:
-            conditions:
-              - macro: '{#SLOT_NAME}'
-                value: '^pg_[0-9]+_sync_[0-9]+_[0-9]+$'
-                operator: NOT_MATCHES_REGEX
-                formulaid: A
-          lifetime: 30d
-          enabled_lifetime_type: DISABLE_AFTER
-          enabled_lifetime: 7d
           item_prototypes:
             - uuid: 536c5f82e3074ddfbfd842b3a2e8d46c
               name: 'Slot {#SLOT_NAME} - Confirmed Flushed Bytes Lag'