From 46043360de5b8526c489c79bccdec6d204833ef0 Mon Sep 17 00:00:00 2001
From: Evi Vanoost <vanooste@rcbi.rochester.edu>
Date: Sun, 25 Feb 2024 14:53:30 -0500
Subject: [PATCH] Removed queries that throw errors when systems are upgraded.
 Also fixed and simplified a few Postgres queries.

---
 _data/rules.yml | 102 +++++++++++++++++++++++++++---------------------
 1 file changed, 57 insertions(+), 45 deletions(-)

diff --git a/_data/rules.yml b/_data/rules.yml
index afd85dd..269dde5 100644
--- a/_data/rules.yml
+++ b/_data/rules.yml
@@ -137,37 +137,37 @@ groups:
             rules:
               - name: Host out of memory
                 description: Node memory is filling up (< 10% left)
-                query: '(node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < .10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < .10)'
                 severity: warning
                 for: 2m
               - name: Host memory under memory pressure
                 description: The node is under heavy memory pressure. High rate of loading memory pages from disk.
-                query: '(rate(node_vmstat_pgmajfault[5m]) > 1000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(rate(node_vmstat_pgmajfault[5m]) > 1000)'
                 severity: warning
               - name: Host Memory is underutilized
                 description: "Node memory usage is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})"
                 # We use MemFree, many buffers (ZFS, databases etc) are declared as available memory, but would perform poorly if reduced
-                query: '((avg_over_time(node_memory_MemFree_bytes[30m]) / node_memory_MemTotal_bytes) > .80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '((avg_over_time(node_memory_MemFree_bytes[30m]) / node_memory_MemTotal_bytes) > .80)'
                 severity: info
                 for: 1w
                 comments: |
                   You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
               - name: Host unusual network throughput in
                 description: "Host receive bandwidth is high (>80%)"
-                query: '((rate(node_network_receive_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '((rate(node_network_receive_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)'
                 severity: warning
               - name: Host unusual network throughput out
                 description: "Host transmit bandwidth is high (>80%)"
-                query: '((rate(node_network_transmit_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '((rate(node_network_transmit_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)'
                 severity: warning
               - name: Host unusual disk read rate
                 description: "Disk is too busy (IO wait > 80%)"
-                query: '(rate(node_disk_io_time_seconds_total[5m]) > .80) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(rate(node_disk_io_time_seconds_total[5m]) > .80)'
                 severity: warning
               - name: Host out of disk space
                 description: "Disk is almost full (< 10% left)"
                 # Network filesystems have quotas etc. and should not be included in this alert
-                query: '(node_filesystem_avail_bytes{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"} / node_filesystem_size_bytes < .10 and on (instance, device, mountpoint) node_filesystem_readonly == 0) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(node_filesystem_avail_bytes{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"} / node_filesystem_size_bytes < .10 and on (instance, device, mountpoint) node_filesystem_readonly == 0)'
                 severity: critical
                 comments: |
                   Please add ignored mountpoints in node_exporter parameters like
@@ -185,7 +185,7 @@ groups:
                 for: 2m
               - name: Host out of inodes
                 description: Disk is almost running out of available inodes (< 10% left)
-                query: '(node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} < .10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} < .10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0)'
                 severity: critical
                 for: 2m
               - name: Host filesystem device error
@@ -204,41 +204,41 @@ groups:
                 for: 2m
               - name: Host unusual disk read latency
                 description: Disk latency is growing (read operations > 100ms)
-                query: '(rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0)'
                 severity: warning
                 for: 2m
               - name: Host unusual disk write latency
                 description: Disk latency is growing (write operations > 100ms)
-                query: '(rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0)'
                 severity: warning
                 for: 2m
               - name: Host high CPU load
                 description: CPU load is > 80%
-                query: '((avg by (instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > .80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '((avg by (instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > .80)'
                 severity: warning
                 for: 10m
               - name: Host CPU is underutilized
                 description: "CPU load has been < 20% for 1 week. Consider reducing the number of CPUs."
-                query: '((avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > .80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > .80'
                 severity: info
                 for: 1w
                 comments: |
                   You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
               - name: Host CPU steal noisy neighbor
                 description: CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.
-                query: '(avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: 'avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10'
                 severity: warning
               - name: Host CPU high iowait
                 description: CPU iowait > 10%. Your CPU is idling waiting for storage to respond.
-                query: '(avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) > .10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: 'avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) > .10'
                 severity: warning
               - name: Host unusual disk IO
                 description: "Disk usage >80%. Check storage for issues or increase IOPS capabilities."
-                query: '(rate(node_disk_io_time_seconds_total[5m]) > 0.8) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: 'rate(node_disk_io_time_seconds_total[5m]) > 0.8'
                 severity: warning
               - name: Host context switching
                 description: Context switching is growing on the node (> 10000 / CPU / s)
-                query: '((rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 10000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 10000'
                 severity: warning
                 comments: |
                   10000 context switches is an arbitrary number.
@@ -246,81 +246,82 @@ groups:
                   Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
               - name: Host swap is filling up
                 description: Swap is filling up (>80%)
-                query: '((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80)'
                 severity: warning
                 for: 2m
               - name: Host systemd service crashed
                 description: "systemd service crashed"
-                query: '(node_systemd_unit_state{state="failed"} == 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(node_systemd_unit_state{state="failed"} == 1)'
                 severity: warning
               - name: Host physical component too hot
                 description: "Physical hardware component too hot"
-                query: '((node_hwmon_temp_celsius * ignoring(label) group_left(instance, job, node, sensor) node_hwmon_sensor_label{label!="tctl"} > 75)) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: 'node_hwmon_temp_celsius * ignoring(label) group_left(instance, job, node, sensor) node_hwmon_sensor_label{label!="tctl"} > 75'
                 severity: warning
                 for: 5m
               - name: Host node overtemperature alarm
                 description: "Physical node temperature alarm triggered"
-                query: '(node_hwmon_temp_crit_alarm_celsius == 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(node_hwmon_temp_crit_alarm_celsius == 1)'
                 severity: critical
               - name: Host Software RAID insufficient drives
                 description: "MD RAID array {{ $labels.device }} on {{ $labels.instance }} has insufficient drives remaining."
-                query: '((node_md_disks_required - on(device, instance) node_md_disks{state="active"}) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '((node_md_disks_required - on(device, instance) node_md_disks{state="active"}) > 0)'
                 severity: critical
               - name: Host Software RAID disk failure
                 description: "MD RAID array {{ $labels.device }} on {{ $labels.instance }} needs attention."
-                query: '(node_md_disks{state="failed"} > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(node_md_disks{state="failed"} > 0)'
                 severity: warning
                 for: 2m
               - name: Host kernel version deviations
                 description: Kernel version for {{ $labels.instance }} has changed
                 query: 'changes(node_uname_info[1h]) > 0'
+                comments: |
+                  This alert may happen when the host is rebooted after a software update.
                 severity: info
-                for: 6h
               - name: Host OOM kill detected
                 description: OOM kill detected
-                query: '(increase(node_vmstat_oom_kill[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
-                severity: warning
+                query: '(increase(node_vmstat_oom_kill[1m]) > 0)'
+                severity: critical
               - name: Host EDAC Correctable Errors detected
                 description: 'Host {{ $labels.instance }} has had {{ printf "%.0f" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'
-                query: '(increase(node_edac_correctable_errors_total[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(increase(node_edac_correctable_errors_total[1m]) > 0)'
                 severity: info
               - name: Host EDAC Uncorrectable Errors detected
                 description: 'Host {{ $labels.instance }} has had {{ printf "%.0f" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'
-                query: '(node_edac_uncorrectable_errors_total > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(node_edac_uncorrectable_errors_total > 0)'
                 severity: warning
               - name: Host Network Receive Errors
                 description: 'Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.'
-                query: '(rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01)'
                 severity: warning
                 for: 2m
               - name: Host Network Transmit Errors
                 description: 'Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.'
-                query: '(rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01)'
                 severity: warning
                 for: 2m
               - name: Host Network Bond Degraded
                 description: 'Bond "{{ $labels.device }}" degraded on "{{ $labels.instance }}".'
-                query: '((node_bonding_active - node_bonding_slaves) != 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '((node_bonding_active - node_bonding_slaves) != 0)'
                 severity: warning
                 for: 2m
               - name: Host conntrack limit
                 description: "The number of conntrack is approaching limit"
-                query: '(node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8)'
                 severity: warning
                 for: 5m
               - name: Host clock skew
                 description: "Clock skew detected. Clock is out of sync. Ensure NTP is configured correctly on this host."
-                query: '((node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '((node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0))'
                 severity: warning
                 for: 10m
               - name: Host clock not synchronising
                 description: "Clock not synchronising. Ensure NTP is configured on this host."
-                query: '(min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16)'
                 severity: warning
                 for: 2m
               - name: Host requires reboot
                 description: "{{ $labels.instance }} requires a reboot."
-                query: '(node_reboot_required > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+                query: '(node_reboot_required > 0)'
                 severity: info
                 for: 4h
 
@@ -331,18 +332,22 @@ groups:
             doc_url: https://github.com/prometheus-community/smartctl_exporter
             rules:
               - name: SMART device temperature warning
-                description: Device temperature warning on {{ $labels.instance }} drive {{ $labels.device }})
-                query: avg_over_time(smartctl_device_temperature{temperature_type="current"} [5m]) > 60
+                description: Device temperature warning on {{ $labels.instance }} drive {{ $labels.device }} over 60°C
+                query: (avg_over_time(smartctl_device_temperature{temperature_type="current"} [5m]) unless on (instance, device) smartctl_device_temperature{temperature_type="drive_trip"}) > 60
                 severity: warning
               - name: SMART device temperature critical
-                description: Device temperature critical on {{ $labels.instance }} drive {{ $labels.device }})
-                query: max_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) >= 70
+                description: Device temperature critical on {{ $labels.instance }} drive {{ $labels.device }} over 70°C
+                query: (max_over_time(smartctl_device_temperature{temperature_type="current"} [5m]) unless on (instance, device) smartctl_device_temperature{temperature_type="drive_trip"}) > 70
                 severity: critical
               # Datacenter drives have a trip temperature
-              - name: SMART device temperature was over trip value
+              - name: SMART device temperature over trip value
                 description: Device temperature over trip value on {{ $labels.instance }} drive {{ $labels.device }})
                 query: max_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) >= on(device, instance) smartctl_device_temperature{temperature_type="drive_trip"}
                 severity: critical
+              - name: SMART device temperature nearing trip value
+                description: Device temperature at 80% of trip value on {{ $labels.instance }} drive {{ $labels.device }})
+                query: max_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) >= on(device, instance) (smartctl_device_temperature{temperature_type="drive_trip"} * .80)
+                severity: warning
               - name: SMART status
                 description: Device has a SMART status failure on {{ $labels.instance }} drive {{ $labels.device }})
                 query: smartctl_device_smart_status != 1
@@ -355,6 +360,8 @@ groups:
                 description: Disk controller detected media errors on {{ $labels.instance }} drive {{ $labels.device }})
                 query: smartctl_device_media_errors > 0
                 severity: critical
+                comments: |
+                  Media errors are a sign of a failing disk. Replace the disk as soon as possible.
               - name: SMART Wearout Indicator
                 description: Device is wearing out on {{ $labels.instance }} drive {{ $labels.device }})
                 # The threshold is not present on devices that do not support it
@@ -646,13 +653,15 @@ groups:
               - name: Postgresql too many connections
                 description: PostgreSQL instance has too many connections (> 80%).
                 query: "sum by (instance, job, server) (pg_stat_activity_count) > min by (instance, job, server) (pg_settings_max_connections * 0.8)"
-                severity: warning
+                severity: critical
                 for: 2m
               - name: Postgresql not enough connections
                 description: PostgreSQL instance should have more connections (> 5)
                 query: 'sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) < 5'
-                severity: warning
+                severity: critical
                 for: 2m
+                comments: |
+                  If the number of connections is too low, it may indicate that the application has died.
               - name: Postgresql dead locks
                 description: PostgreSQL has dead-locks
                 query: 'increase(pg_stat_database_deadlocks{datname!~"template.*|postgres"}[1m]) > 5'
@@ -663,9 +672,9 @@ groups:
                 severity: warning
               - name: Postgresql commit rate low
                 description: Postgresql seems to be processing very few transactions
-                query: "rate(pg_stat_database_xact_commit[1m]) < 10"
+                query: 'increase(pg_stat_database_xact_commit{datname!~"template.*|postgres",datid!="0"}[1m]) < 5'
                 severity: critical
-                for: 2m
+                for: 5m
               - name: Postgresql low XID consumption
                 description: Postgresql seems to be consuming transaction IDs very slowly
                 query: "rate(pg_txid_current[1m]) < 5"
@@ -691,12 +700,15 @@ groups:
                 for: 2m
               - name: Postgresql configuration changed
                 description: Postgres Database configuration change has occurred
-                query: '{__name__=~"pg_settings_.*"} != ON(__name__) {__name__=~"pg_settings_([^t]|t[^r]|tr[^a]|tra[^n]|tran[^s]|trans[^a]|transa[^c]|transac[^t]|transact[^i]|transacti[^o]|transactio[^n]|transaction[^_]|transaction_[^r]|transaction_r[^e]|transaction_re[^a]|transaction_rea[^d]|transaction_read[^_]|transaction_read_[^o]|transaction_read_o[^n]|transaction_read_on[^l]|transaction_read_onl[^y]).*"} OFFSET 5m'
+                query: 'changes(label_replace({__name__=~"pg_settings_.*"},"name","$1","__name__", "(.+)")[1h:]) > 0'
                 severity: info
               - name: Postgresql SSL compression active
-                description: Database connections with SSL compression enabled. This may add significant jitter in replication delay. Replicas should turn off SSL compression via `sslcompression=0` in `recovery.conf`.
+                description: Database allows connections with SSL compression enabled.
                 query: "sum(pg_stat_ssl_compression) > 0"
                 severity: critical
+                comments: |
+                  TLS compression is a security risk and should be disabled. It has been removed for TLSv1.3.
+                  https://www.bytebase.com/docs/slow-query/enable-pg-stat-statements-for-postgresql/
               - name: Postgresql too many locks acquired
                 description: Too many locks acquired on the database. If this alert happens frequently, we may need to increase the postgres setting max_locks_per_transaction.
                 query: "((sum (pg_locks_count)) / (pg_settings_max_locks_per_transaction * pg_settings_max_connections)) > 0.20"