From d916b7c6aba888a64535cb6d051070aeb9cd1a8e Mon Sep 17 00:00:00 2001 From: Samuel Berthe Date: Tue, 28 Jan 2025 05:58:49 +0100 Subject: [PATCH] Fix from #405 --- _data/rules.yml | 179 +++++++++++++++++++++--------------------------- 1 file changed, 79 insertions(+), 100 deletions(-) diff --git a/_data/rules.yml b/_data/rules.yml index eab61c2..88e0785 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -27,7 +27,7 @@ groups: severity: critical - name: Prometheus target missing with warmup time description: Allow a job time to start up (10 minutes) before alerting that it's down. - query: "sum by (instance, job) ((up == 0) * on (instance) group_right(job) (node_time_seconds - node_boot_time_seconds > 600))" + query: "sum by (instance, job) ((up == 0) * on (instance) group_left(__name__) (node_time_seconds - node_boot_time_seconds > 600))" severity: critical - name: Prometheus configuration reload failure description: Prometheus configuration reload error @@ -137,53 +137,43 @@ groups: rules: - name: Host out of memory description: Node memory is filling up (< 10% left) - query: '(node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 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 major page faults - query: '(rate(node_vmstat_pgmajfault[1m]) > 1000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + description: The node is under heavy memory pressure. High rate of loading memory pages from disk. + query: '(rate(node_vmstat_pgmajfault[5m]) > 1000)' severity: warning - for: 2m - name: Host Memory is underutilized - description: "Node memory is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})" - query: '(100 - (avg_over_time(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + description: "Node memory usage is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})" + query: 'min_over_time(node_memory_MemFree_bytes[1w]) > node_memory_MemTotal_bytes * .8' 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 network interfaces are probably receiving too much data (> 100 MB/s) - query: '(sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + description: Host receive bandwidth is high (>80%). + query: '((rate(node_network_receive_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)' severity: warning - for: 5m - name: Host unusual network throughput out - description: Host network interfaces are probably sending too much data (> 100 MB/s) - query: '(sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + description: Host transmit bandwidth is high (>80%) + query: '((rate(node_network_transmit_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)' severity: warning - for: 5m - name: Host unusual disk read rate - description: Disk is probably reading too much data (> 50 MB/s) - query: '(sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + description: Disk is too busy (IO wait > 80%) + query: '(rate(node_disk_io_time_seconds_total[5m]) > .80)' severity: warning - for: 5m - - name: Host unusual disk write rate - description: Disk is probably writing too much data (> 50 MB/s) - query: '(sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' - severity: warning - for: 2m - name: Host out of disk space description: Disk is almost full (< 10% left) - query: '((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' - severity: warning + 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 "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)". Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users. for: 2m - - name: Host disk will fill in 24 hours - description: Filesystem is predicted to run out of space within the next 24 hours at current write rate - query: '((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + - name: Host disk may fill in 24 hours + description: Filesystem will likely run out of space within the next 24 hours. + query: 'predict_linear(node_filesystem_avail_bytes{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"}[1h], 86400) <= 0 and node_filesystem_avail_bytes > 0' severity: warning comments: | Please add ignored mountpoints in node_exporter parameters like @@ -192,52 +182,52 @@ 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"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' - severity: warning - for: 2m - - name: Host filesystem device error - description: "{{ $labels.instance }}: Device error with the {{ $labels.mountpoint }} filesystem" - query: "node_filesystem_device_error == 1" + 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 inodes will fill in 24 hours - description: Filesystem is predicted to run out of inodes within the next 24 hours at current write rate - query: '(node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{fstype!="msdosfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{fstype!="msdosfs"} == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + - name: Host filesystem device error + description: "Error stat-ing the {{ $labels.mountpoint }} filesystem" + query: "node_filesystem_device_error{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"} == 1" + severity: critical + for: 2m + - name: Host inodes may fill in 24 hours + description: Filesystem will likely run out of inodes within the next 24 hours at current write rate + query: 'predict_linear(node_filesystem_files_free{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"}[1h], 86400) <= 0 and node_filesystem_files_free > 0' severity: warning 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: '(sum by (instance) (avg by (mode, instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > 0.8) * 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 is < 20% for 1 week. Consider reducing the number of CPUs." - query: '(100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + description: "CPU load has been < 20% for 1 week. Consider reducing the number of CPUs." + query: '(min by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > 0.8' 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%. A high iowait means that you are disk or network bound. - query: '(avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + 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' severity: warning - name: Host unusual disk IO - description: "Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues." - query: '(rate(node_disk_io_time_seconds_total[1m]) > 0.5) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + description: "Disk usage >80%. Check storage for issues or increase IOPS capabilities. Check storage for issues." + query: 'rate(node_disk_io_time_seconds_total[5m]) > 0.8' severity: warning for: 5m - name: Host context switching high @@ -250,86 +240,80 @@ 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 > node_hwmon_temp_max_celsius' severity: warning for: 5m - name: Host node overtemperature alarm description: "Physical node temperature alarm triggered" - query: '((node_hwmon_temp_crit_alarm_celsius == 1) or (node_hwmon_temp_alarm == 1)) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + query: '((node_hwmon_temp_crit_alarm_celsius == 1) or (node_hwmon_temp_alarm == 1))' severity: critical - - name: Host RAID array got inactive - description: "RAID array {{ $labels.device }} is in a degraded state due to one or more disk failures. The number of spare drives is insufficient to fix the issue automatically." - query: '(node_md_state{state="inactive"} > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + - 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)' severity: critical - - name: Host RAID disk failure - description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap" - query: '(node_md_disks{state="failed"} > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + - name: Host software RAID disk failure + description: "MD RAID array {{ $labels.device }} on {{ $labels.instance }} needs attention." + query: '(node_md_disks{state="failed"} > 0)' severity: warning for: 2m - name: Host kernel version deviations - description: Different kernel versions are running - query: '(count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+.[0-9]+).*")) by (kernel)) > 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' - severity: warning - for: 6h + description: Kernel version for {{ $labels.instance }} has changed. + query: 'changes(node_uname_info[1h]) > 0' + severity: info - 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=~".+"}' + query: '(increase(node_vmstat_oom_kill[1m]) > 0)' severity: warning - 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 Interface Saturated - description: 'The network interface "{{ $labels.device }}" on "{{ $labels.instance }}" is getting overloaded.' - query: '((rate(node_network_receive_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"} > 0.8 < 10000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' # < to 10Gb to prevent +inf when max speed is unknown - severity: warning - for: 1m - 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 @@ -339,31 +323,26 @@ groups: slug: smartctl-exporter doc_url: https://github.com/prometheus-community/smartctl_exporter rules: - - name: Smart device temperature warning - description: Device temperature warning (instance {{ $labels.instance }}) - query: smartctl_device_temperature > 60 + - name: SMART device temperature warning + 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 - for: 2m - - name: Smart device temperature critical - description: Device temperature critical (instance {{ $labels.instance }}) - query: smartctl_device_temperature > 80 + - name: SMART device temperature critical + 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 - for: 2m - - name: Smart critical warning - description: device has critical warning (instance {{ $labels.instance }}) - query: smartctl_device_critical_warning > 0 + - name: SMART critical warning + description: Disk controller has critical warning on {{ $labels.instance }} drive {{ $labels.device }}) + query: 'smartctl_device_critical_warning > 0' severity: critical - for: 15m - - name: Smart media errors - description: device has media errors (instance {{ $labels.instance }}) - query: smartctl_device_media_errors > 0 + - name: SMART media errors + description: Disk controller detected media errors on {{ $labels.instance }} drive {{ $labels.device }}) + query: 'smartctl_device_media_errors > 0' severity: critical - for: 15m - - name: Smart NVME Wearout Indicator - description: NVMe device is wearing out (instance {{ $labels.instance }}) - query: smartctl_device_available_spare{device=~"nvme.*"} < smartctl_device_available_spare_threshold{device=~"nvme.*"} + - name: SMART Wearout Indicator + description: Device is wearing out on {{ $labels.instance }} drive {{ $labels.device }}) + query: 'smartctl_device_available_spare < smartctl_device_available_spare_threshold' severity: critical - for: 15m - name: Docker containers exporters: @@ -646,11 +625,11 @@ groups: severity: critical - name: Postgresql table not auto vacuumed description: Table {{ $labels.relname }} has not been auto vacuumed for 10 days - query: "(pg_stat_user_tables_last_autovacuum > 0) and (time() - pg_stat_user_tables_last_autovacuum) > 60 * 60 * 24 * 10" + query: "((pg_stat_user_tables_n_tup_del + pg_stat_user_tables_n_tup_upd + pg_stat_user_tables_n_tup_hot_upd) > pg_settings_autovacuum_vacuum_threshold) and (time() - pg_stat_user_tables_last_autovacuum) > 60 * 60 * 24 * 10" severity: warning - name: Postgresql table not auto analyzed description: Table {{ $labels.relname }} has not been auto analyzed for 10 days - query: "(pg_stat_user_tables_last_autoanalyze > 0) and (time() - pg_stat_user_tables_last_autoanalyze) > 24 * 60 * 60 * 10" + query: "((pg_stat_user_tables_n_tup_del + pg_stat_user_tables_n_tup_upd + pg_stat_user_tables_n_tup_hot_upd) > pg_settings_autovacuum_analyze_threshold) and (time() - pg_stat_user_tables_last_autoanalyze) > 24 * 60 * 60 * 10" severity: warning - name: Postgresql too many connections description: PostgreSQL instance has too many connections (> 80%). @@ -660,7 +639,7 @@ groups: - 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 - name: Postgresql dead locks description: PostgreSQL has dead-locks @@ -672,7 +651,7 @@ 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"}[5m]) < 5" severity: critical for: 2m - name: Postgresql low XID consumption @@ -703,7 +682,7 @@ groups: query: '{__name__=~"pg_settings_.*"} != ON(__name__, instance) {__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' 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. This may add significant jitter in replication delay. Replicas should turn off SSL compression via `sslcompression=0` in `recovery.conf`. query: "sum(pg_stat_ssl_compression) > 0" severity: critical - name: Postgresql too many locks acquired