summaryrefslogtreecommitdiffstats
path: root/conf.d/health.d
diff options
context:
space:
mode:
Diffstat (limited to 'conf.d/health.d')
-rw-r--r--conf.d/health.d/backend.conf2
-rw-r--r--conf.d/health.d/btrfs.conf57
-rw-r--r--conf.d/health.d/ceph.conf13
-rw-r--r--conf.d/health.d/cpu.conf14
-rw-r--r--conf.d/health.d/disks.conf51
-rw-r--r--conf.d/health.d/fronius.conf11
-rw-r--r--conf.d/health.d/httpcheck.conf99
-rw-r--r--conf.d/health.d/isc_dhcpd.conf14
-rw-r--r--conf.d/health.d/net.conf5
-rw-r--r--conf.d/health.d/nginx_plus.conf14
-rw-r--r--conf.d/health.d/portcheck.conf48
-rw-r--r--conf.d/health.d/ram.conf42
-rw-r--r--conf.d/health.d/softnet.conf14
-rw-r--r--conf.d/health.d/stiebeleltron.conf11
-rw-r--r--conf.d/health.d/swap.conf8
-rw-r--r--conf.d/health.d/tcp_resets.conf6
-rw-r--r--conf.d/health.d/udp_errors.conf4
-rw-r--r--conf.d/health.d/web_log.conf1
18 files changed, 387 insertions, 27 deletions
diff --git a/conf.d/health.d/backend.conf b/conf.d/health.d/backend.conf
index 9c193e7b9..7af100d8f 100644
--- a/conf.d/health.d/backend.conf
+++ b/conf.d/health.d/backend.conf
@@ -27,7 +27,7 @@
units: metrics
calc: abs($lost)
every: 10s
- crit: $this != 0
+ crit: ($this != 0) || ($status == $CRITICAL && abs($sent) == 0)
delay: down 5m multiplier 1.5 max 1h
info: number of metrics lost due to repeating failures to contact the backend server
to: dba
diff --git a/conf.d/health.d/btrfs.conf b/conf.d/health.d/btrfs.conf
new file mode 100644
index 000000000..b27aa544f
--- /dev/null
+++ b/conf.d/health.d/btrfs.conf
@@ -0,0 +1,57 @@
+
+template: btrfs_allocated
+ on: btrfs.disk
+ os: *
+ hosts: *
+families: *
+ calc: 100 - ($unallocated * 100 / ($unallocated + $data_used + $data_free + $meta_used + $meta_free + $sys_used + $sys_free))
+ units: %
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? (90) : (95))
+ crit: $this > (($status == $CRITICAL) ? (95) : (98))
+ delay: up 1m down 15m multiplier 1.5 max 1h
+ info: the percentage of allocated BTRFS physical disk space
+ to: sysadmin
+
+template: btrfs_data
+ on: btrfs.data
+ os: *
+ hosts: *
+families: *
+ calc: $used * 100 / ($used + $free)
+ units: %
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? (90) : (95)) && $btrfs_allocated > 98
+ crit: $this > (($status == $CRITICAL) ? (95) : (98)) && $btrfs_allocated > 98
+ delay: up 1m down 15m multiplier 1.5 max 1h
+ info: the percentage of used BTRFS data space
+ to: sysadmin
+
+template: btrfs_metadata
+ on: btrfs.metadata
+ os: *
+ hosts: *
+families: *
+ calc: ($used + $reserved) * 100 / ($used + $free + $reserved)
+ units: %
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? (90) : (95)) && $btrfs_allocated > 98
+ crit: $this > (($status == $CRITICAL) ? (95) : (98)) && $btrfs_allocated > 98
+ delay: up 1m down 15m multiplier 1.5 max 1h
+ info: the percentage of used BTRFS metadata space
+ to: sysadmin
+
+template: btrfs_system
+ on: btrfs.system
+ os: *
+ hosts: *
+families: *
+ calc: $used * 100 / ($used + $free)
+ units: %
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? (90) : (95)) && $btrfs_allocated > 98
+ crit: $this > (($status == $CRITICAL) ? (95) : (98)) && $btrfs_allocated > 98
+ delay: up 1m down 15m multiplier 1.5 max 1h
+ info: the percentage of used BTRFS system space
+ to: sysadmin
+
diff --git a/conf.d/health.d/ceph.conf b/conf.d/health.d/ceph.conf
new file mode 100644
index 000000000..de16f7b6f
--- /dev/null
+++ b/conf.d/health.d/ceph.conf
@@ -0,0 +1,13 @@
+# low ceph disk available
+
+template: cluster_space_usage
+ on: ceph.general_usage
+ calc: $avail * 100 / ($avail + $used)
+ units: %
+ every: 10s
+ warn: $this < 10
+ crit: $this < 1
+ delay: down 5m multiplier 1.2 max 1h
+ info: ceph disk usage is almost full
+ to: sysadmin
+
diff --git a/conf.d/health.d/cpu.conf b/conf.d/health.d/cpu.conf
index db6285561..fa8189856 100644
--- a/conf.d/health.d/cpu.conf
+++ b/conf.d/health.d/cpu.conf
@@ -39,3 +39,17 @@ template: 20min_steal_cpu
delay: down 1h multiplier 1.5 max 2h
info: average CPU steal time for the last 20 minutes
to: sysadmin
+
+## FreeBSD
+template: 10min_cpu_usage
+ on: system.cpu
+ os: freebsd
+ hosts: *
+ lookup: average -10m unaligned of user,system,interrupt
+ units: %
+ every: 1m
+ warn: $this > (($status >= $WARNING) ? (75) : (85))
+ crit: $this > (($status == $CRITICAL) ? (85) : (95))
+ delay: down 15m multiplier 1.5 max 1h
+ info: average cpu utilization for the last 10 minutes (excluding nice)
+ to: sysadmin
diff --git a/conf.d/health.d/disks.conf b/conf.d/health.d/disks.conf
index 63053491e..26f85848a 100644
--- a/conf.d/health.d/disks.conf
+++ b/conf.d/health.d/disks.conf
@@ -11,7 +11,7 @@
template: disk_space_usage
on: disk.space
- os: linux
+ os: linux freebsd
hosts: *
families: *
calc: $used * 100 / ($avail + $used)
@@ -25,7 +25,7 @@ families: *
template: disk_inode_usage
on: disk.inodes
- os: linux
+ os: linux freebsd
hosts: *
families: *
calc: $used * 100 / ($avail + $used)
@@ -51,7 +51,7 @@ families: *
template: disk_fill_rate
on: disk.space
- os: linux
+ os: linux freebsd
hosts: *
families: *
lookup: min -10m at -50m unaligned of avail
@@ -67,7 +67,7 @@ families: *
template: out_of_disk_space_time
on: disk.space
- os: linux
+ os: linux freebsd
hosts: *
families: *
calc: ($disk_fill_rate > 0) ? ($avail / $disk_fill_rate) : (inf)
@@ -81,6 +81,47 @@ families: *
# -----------------------------------------------------------------------------
+# disk inode fill rate
+
+# calculate the rate the disk inodes are allocated
+# use as base, the available inodes change
+# during the last hour
+
+# this is just a calculation - it has no alarm
+# we will use it in the next template to find
+# the hours remaining
+
+template: disk_inode_rate
+ on: disk.inodes
+ os: linux freebsd
+ hosts: *
+families: *
+ lookup: min -10m at -50m unaligned of avail
+ calc: ($this - $avail) / (($now - $after) / 3600)
+ every: 1m
+ units: inodes/hour
+ info: average rate at which disk inodes are allocated (positive), or freed (negative), for the last hour
+
+# calculate the hours remaining
+# if the disk inodes are allocated
+# in this rate
+
+template: out_of_disk_inodes_time
+ on: disk.inodes
+ os: linux freebsd
+ hosts: *
+families: *
+ calc: ($disk_inode_rate > 0) ? ($avail / $disk_inode_rate) : (inf)
+ units: hours
+ every: 10s
+ warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))
+ crit: $this > 0 and $this < (($status == $CRITICAL) ? (24) : (2))
+ delay: down 15m multiplier 1.2 max 1h
+ info: estimated time the disk will run out of inodes, if the system continues to allocate inodes with the rate of the last hour
+ to: sysadmin
+
+
+# -----------------------------------------------------------------------------
# disk congestion
# raise an alarm if the disk is congested
@@ -89,7 +130,7 @@ families: *
template: 10min_disk_utilization
on: disk.util
- os: linux
+ os: linux freebsd
hosts: *
families: *
lookup: average -10m unaligned
diff --git a/conf.d/health.d/fronius.conf b/conf.d/health.d/fronius.conf
new file mode 100644
index 000000000..cdf6c8fcb
--- /dev/null
+++ b/conf.d/health.d/fronius.conf
@@ -0,0 +1,11 @@
+template: fronius_last_collected_secs
+families: *
+ on: fronius.power
+ calc: $now - $last_collected_t
+ every: 10s
+ units: seconds ago
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of seconds since the last successful data collection
+ to: sitemgr
diff --git a/conf.d/health.d/httpcheck.conf b/conf.d/health.d/httpcheck.conf
new file mode 100644
index 000000000..0ddf35eab
--- /dev/null
+++ b/conf.d/health.d/httpcheck.conf
@@ -0,0 +1,99 @@
+template: httpcheck_last_collected_secs
+families: *
+ on: httpcheck.status
+ calc: $now - $last_collected_t
+ every: 10s
+ units: seconds ago
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of seconds since the last successful data collection
+ to: sysadmin
+
+# This is a fast-reacting no-notification alarm ideal for custom dashboards or badges
+template: web_service_up
+families: *
+ on: httpcheck.status
+ lookup: average -1m unaligned percentage of success
+ calc: ($this < 75) ? (0) : ($this)
+ every: 5s
+ units: up/down
+ info: at least 75% verified responses during last 60 seconds, ideal for badges
+ to: silent
+
+template: web_service_bad_content
+families: *
+ on: httpcheck.status
+ lookup: average -5m unaligned percentage of bad_content
+ every: 10s
+ units: %
+ warn: $this >= 10 AND $this < 40
+ crit: $this >= 40
+ delay: down 5m multiplier 1.5 max 1h
+ info: average of unexpected http response content during the last 5 minutes
+ options: no-clear-notification
+ to: webmaster
+
+template: web_service_bad_status
+families: *
+ on: httpcheck.status
+ lookup: average -5m unaligned percentage of bad_status
+ every: 10s
+ units: %
+ warn: $this >= 10 AND $this < 40
+ crit: $this >= 40
+ delay: down 5m multiplier 1.5 max 1h
+ info: average of unexpected http status during the last 5 minutes
+ options: no-clear-notification
+ to: webmaster
+
+template: web_service_timeouts
+families: *
+ on: httpcheck.status
+ lookup: average -5m unaligned percentage of timeout
+ every: 10s
+ units: %
+ info: average of timeouts during the last 5 minutes
+
+template: no_web_service_connections
+families: *
+ on: httpcheck.status
+ lookup: average -5m unaligned percentage of no_connection
+ every: 10s
+ units: %
+ info: average of failed requests during the last 5 minutes
+
+# combined timeout & no connection alarm
+template: web_service_unreachable
+families: *
+ on: httpcheck.status
+ calc: ($no_web_service_connections >= $web_service_timeouts) ? ($no_web_service_connections) : ($web_service_timeouts)
+ units: %
+ every: 10s
+ warn: ($no_web_service_connections >= 10 OR $web_service_timeouts >= 10) AND ($no_web_service_connections < 40 OR $web_service_timeouts < 40)
+ crit: $no_web_service_connections >= 40 OR $web_service_timeouts >= 40
+ delay: down 5m multiplier 1.5 max 1h
+ info: average of failed requests either due to timeouts or no connection during the last 5 minutes
+ options: no-clear-notification
+ to: webmaster
+
+template: 1h_web_service_response_time
+families: *
+ on: httpcheck.responsetime
+ lookup: average -1h unaligned of time
+ every: 30s
+ units: ms
+ info: average response time over the last hour
+
+template: web_service_slow
+families: *
+ on: httpcheck.responsetime
+ lookup: average -3m unaligned of time
+ units: ms
+ every: 10s
+ warn: ($this > ($1h_web_service_response_time * 2) )
+ crit: ($this > ($1h_web_service_response_time * 3) )
+ info: average response time over the last 3 minutes, compared to the average over the last hour
+ delay: down 5m multiplier 1.5 max 1h
+ options: no-clear-notification
+ to: webmaster
diff --git a/conf.d/health.d/isc_dhcpd.conf b/conf.d/health.d/isc_dhcpd.conf
index 4345619aa..8054656ff 100644
--- a/conf.d/health.d/isc_dhcpd.conf
+++ b/conf.d/health.d/isc_dhcpd.conf
@@ -1,10 +1,10 @@
- alarm: isc_dhcpd_parse_time
- on: isc_dhcpd.parse_time
- units: ms
+ template: isc_dhcpd_leases_size
+ on: isc_dhcpd.leases_total
+ units: KB
every: 60
- calc: $ptime
- warn: $this > 100
- crit: $this > 250
+ calc: $leases_size
+ warn: $this > 3072
+ crit: $this > 6144
delay: up 2m down 5m
- info: Parsing too slow! It can slow down your server. Check dhcpd.leases file size.
+ info: dhcpd.leases file too big! Module can slow down your server.
to: sysadmin
diff --git a/conf.d/health.d/net.conf b/conf.d/health.d/net.conf
index 00a198612..22a88927d 100644
--- a/conf.d/health.d/net.conf
+++ b/conf.d/health.d/net.conf
@@ -98,7 +98,7 @@ families: *
template: 1m_received_packets_rate
on: net.packets
- os: linux
+ os: linux freebsd
hosts: *
families: *
lookup: average -1m of received
@@ -108,7 +108,7 @@ families: *
template: 10s_received_packets_storm
on: net.packets
- os: linux
+ os: linux freebsd
hosts: *
families: *
lookup: average -10s of received
@@ -120,4 +120,3 @@ families: *
options: no-clear-notification
info: the % of the rate of received packets in the last 10 seconds, compared to the rate of the last minute (clear notification for this alarm will not be sent)
to: sysadmin
-
diff --git a/conf.d/health.d/nginx_plus.conf b/conf.d/health.d/nginx_plus.conf
new file mode 100644
index 000000000..5a171a76d
--- /dev/null
+++ b/conf.d/health.d/nginx_plus.conf
@@ -0,0 +1,14 @@
+
+# make sure nginx_plus is running
+
+template: nginx_plus_last_collected_secs
+ on: nginx_plus.requests_total
+ calc: $now - $last_collected_t
+ units: seconds ago
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of seconds since the last successful data collection
+ to: webmaster
+
diff --git a/conf.d/health.d/portcheck.conf b/conf.d/health.d/portcheck.conf
new file mode 100644
index 000000000..f42b63d30
--- /dev/null
+++ b/conf.d/health.d/portcheck.conf
@@ -0,0 +1,48 @@
+template: portcheck_last_collected_secs
+families: *
+ on: portcheck.status
+ calc: $now - $last_collected_t
+ every: 10s
+ units: seconds ago
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of seconds since the last successful data collection
+ to: sysadmin
+
+# This is a fast-reacting no-notification alarm ideal for custom dashboards or badges
+template: service_reachable
+families: *
+ on: portcheck.status
+ lookup: average -1m unaligned percentage of success
+ calc: ($this < 75) ? (0) : ($this)
+ every: 5s
+ units: up/down
+ info: at least 75% successful connections during last 60 seconds, ideal for badges
+ to: silent
+
+template: connection_timeouts
+families: *
+ on: portcheck.status
+ lookup: average -5m unaligned percentage of timeout
+ every: 10s
+ units: %
+ warn: $this >= 10 AND $this < 40
+ crit: $this >= 40
+ delay: down 5m multiplier 1.5 max 1h
+ info: average of timeouts during the last 5 minutes
+ options: no-clear-notification
+ to: sysadmin
+
+template: connection_fails
+families: *
+ on: portcheck.status
+ lookup: average -5m unaligned percentage of no_connection
+ every: 10s
+ units: %
+ warn: $this >= 10 AND $this < 40
+ crit: $this >= 40
+ delay: down 5m multiplier 1.5 max 1h
+ info: average of failed connections during the last 5 minutes
+ options: no-clear-notification
+ to: sysadmin
diff --git a/conf.d/health.d/ram.conf b/conf.d/health.d/ram.conf
index 8d0e8838d..b6dc5f945 100644
--- a/conf.d/health.d/ram.conf
+++ b/conf.d/health.d/ram.conf
@@ -20,5 +20,45 @@
warn: $this > (($status >= $WARNING) ? (80) : (90))
crit: $this > (($status == $CRITICAL) ? (90) : (98))
delay: down 15m multiplier 1.5 max 1h
- info: system RAM usage
+ info: system RAM used
to: sysadmin
+
+ alarm: ram_available
+ on: mem.available
+ os: linux
+ hosts: *
+ calc: ($avail + $used_ram_to_ignore) * 100 / ($system.ram.used + $system.ram.cached + $system.ram.free + $system.ram.buffers)
+ units: %
+ every: 10s
+ warn: $this < (($status >= $WARNING) ? ( 5) : (10))
+ crit: $this < (($status == $CRITICAL) ? (10) : ( 5))
+ delay: down 15m multiplier 1.5 max 1h
+ info: estimated amount of RAM available for userspace processes, without causing swapping
+ to: sysadmin
+
+## FreeBSD
+alarm: ram_in_use
+ on: system.ram
+ os: freebsd
+hosts: *
+ calc: (($active + $wired) - $used_ram_to_ignore) * 100 / (($active + $wired) - $used_ram_to_ignore + $cached + $free)
+units: %
+every: 10s
+ warn: $this > (($status >= $WARNING) ? (80) : (90))
+ crit: $this > (($status == $CRITICAL) ? (90) : (98))
+delay: down 15m multiplier 1.5 max 1h
+ info: system RAM usage
+ to: sysadmin
+
+ alarm: ram_available
+ on: system.ram
+ os: freebsd
+ hosts: *
+ calc: ($free + $inactive + $used_ram_to_ignore) * 100 / ($free + $active + $inactive + $wired + $cache + $buffers)
+ units: %
+ every: 10s
+ warn: $this < (($status >= $WARNING) ? ( 5) : (10))
+ crit: $this < (($status == $CRITICAL) ? (10) : ( 5))
+ delay: down 15m multiplier 1.5 max 1h
+ info: estimated amount of RAM available for userspace processes, without causing swapping
+ to: sysadmin
diff --git a/conf.d/health.d/softnet.conf b/conf.d/health.d/softnet.conf
index 64e1c6784..77c804bfd 100644
--- a/conf.d/health.d/softnet.conf
+++ b/conf.d/health.d/softnet.conf
@@ -24,5 +24,17 @@
every: 1m
warn: $this > (($status >= $WARNING) ? (0) : (10))
delay: down 1h multiplier 1.5 max 2h
- info: number of times, during the last 10min, ksoftirq ran out of sysctl net.core.netdev_budget or time slice, with work remaining (this can be a cause for dropped packets)
+ info: number of times, during the last 10min, ksoftirq ran out of sysctl net.core.netdev_budget or net.core.netdev_budget_usecs, with work remaining (this can be a cause for dropped packets)
to: silent
+
+ alarm: 10min_netisr_backlog_exceeded
+ on: system.softnet_stat
+ os: freebsd
+ hosts: *
+ lookup: sum -10m unaligned absolute of qdrops
+ units: packets
+ every: 1m
+ warn: $this > 0
+ delay: down 1h multiplier 1.5 max 2h
+ info: number of drops in the last 10min, because sysctl net.route.netisr_maxqlen was exceeded (this can be a cause for dropped packets)
+ to: sysadmin
diff --git a/conf.d/health.d/stiebeleltron.conf b/conf.d/health.d/stiebeleltron.conf
new file mode 100644
index 000000000..e0361eb20
--- /dev/null
+++ b/conf.d/health.d/stiebeleltron.conf
@@ -0,0 +1,11 @@
+template: stiebeleltron_last_collected_secs
+families: *
+ on: stiebeleltron.heating.hc1
+ calc: $now - $last_collected_t
+ every: 10s
+ units: seconds ago
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of seconds since the last successful data collection
+ to: sitemgr
diff --git a/conf.d/health.d/swap.conf b/conf.d/health.d/swap.conf
index 830a9af95..f920b0807 100644
--- a/conf.d/health.d/swap.conf
+++ b/conf.d/health.d/swap.conf
@@ -3,7 +3,7 @@
alarm: 30min_ram_swapped_out
on: system.swapio
- os: linux
+ os: linux freebsd
hosts: *
lookup: sum -30m unaligned absolute of out
# we have to convert KB to MB by dividing $this (i.e. the result of the lookup) with 1024
@@ -25,19 +25,19 @@
every: 10s
warn: $this > (($status >= $WARNING) ? (15) : (20))
crit: $this > (($status == $CRITICAL) ? (40) : (50))
- delay: up 0 down 15m multiplier 1.5 max 1h
+ delay: up 30s down 15m multiplier 1.5 max 1h
info: the swap memory used, as a percentage of the system RAM
to: sysadmin
alarm: used_swap
on: system.swap
- os: linux
+ os: linux freebsd
hosts: *
calc: $used * 100 / ( $used + $free )
units: %
every: 10s
warn: $this > (($status >= $WARNING) ? (80) : (90))
crit: $this > (($status == $CRITICAL) ? (90) : (98))
- delay: up 0 down 15m multiplier 1.5 max 1h
+ delay: up 30s down 15m multiplier 1.5 max 1h
info: the percentage of swap memory used
to: sysadmin
diff --git a/conf.d/health.d/tcp_resets.conf b/conf.d/health.d/tcp_resets.conf
index e6cfd39ab..91dad3c6a 100644
--- a/conf.d/health.d/tcp_resets.conf
+++ b/conf.d/health.d/tcp_resets.conf
@@ -5,7 +5,7 @@
alarm: ipv4_tcphandshake_last_collected_secs
on: ipv4.tcphandshake
- os: linux
+ os: linux freebsd
hosts: *
calc: $now - $last_collected_t
units: seconds ago
@@ -46,7 +46,7 @@
alarm: 1m_ipv4_tcp_resets_received
on: ipv4.tcphandshake
- os: linux
+ os: linux freebsd
hosts: *
lookup: average -1m at -10s unaligned absolute of AttemptFails
units: tcp resets/s
@@ -55,7 +55,7 @@
alarm: 10s_ipv4_tcp_resets_received
on: ipv4.tcphandshake
- os: linux
+ os: linux freebsd
hosts: *
lookup: average -10s unaligned absolute of AttemptFails
units: tcp resets/s
diff --git a/conf.d/health.d/udp_errors.conf b/conf.d/health.d/udp_errors.conf
index 33338b83e..382b39658 100644
--- a/conf.d/health.d/udp_errors.conf
+++ b/conf.d/health.d/udp_errors.conf
@@ -5,7 +5,7 @@
alarm: ipv4_udperrors_last_collected_secs
on: ipv4.udperrors
- os: linux
+ os: linux freebsd
hosts: *
calc: $now - $last_collected_t
units: seconds ago
@@ -21,7 +21,7 @@
alarm: 1m_ipv4_udp_receive_buffer_errors
on: ipv4.udperrors
- os: linux
+ os: linux freebsd
hosts: *
lookup: sum -1m unaligned absolute of RcvbufErrors
units: errors
diff --git a/conf.d/health.d/web_log.conf b/conf.d/health.d/web_log.conf
index d18088172..d8be88b47 100644
--- a/conf.d/health.d/web_log.conf
+++ b/conf.d/health.d/web_log.conf
@@ -116,6 +116,7 @@ families: *
crit: ($1m_requests > 120) ? ($this > $red && $this > ($10m_response_time * 4) ) : ( 0 )
delay: down 15m multiplier 1.5 max 1h
info: the average time to respond to HTTP requests, over the last 1 minute
+ options: no-clear-notification
to: webmaster
# -----------------------------------------------------------------------------
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-01 13:21:45 +0000