diff options
author | Ilya Mashchenko <ilya@netdata.cloud> | 2022-12-23 15:10:49 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2022-12-23 15:10:49 +0200 |
commit | 1a326fc1ce9ecbcce5ca4b4b72a3bea8f8da0f3b (patch) | |
tree | c586b5449a18308d5a065e1f9d946f877a8da75c | |
parent | 2bca08132a436409b59803e0026034dd4ef823f2 (diff) |
use specific charts labels instead of family in alarms (#14173)
-rw-r--r-- | collectors/proc.plugin/proc_spl_kstat_zfs.c | 2 | ||||
-rw-r--r-- | health/health.d/cgroups.conf | 8 | ||||
-rw-r--r-- | health/health.d/disks.conf | 8 | ||||
-rw-r--r-- | health/health.d/mdstat.conf | 4 | ||||
-rw-r--r-- | health/health.d/net.conf | 28 | ||||
-rw-r--r-- | health/health.d/zfs.conf | 4 |
6 files changed, 28 insertions, 26 deletions
diff --git a/collectors/proc.plugin/proc_spl_kstat_zfs.c b/collectors/proc.plugin/proc_spl_kstat_zfs.c index 8938d64319..58c84050a7 100644 --- a/collectors/proc.plugin/proc_spl_kstat_zfs.c +++ b/collectors/proc.plugin/proc_spl_kstat_zfs.c @@ -285,6 +285,8 @@ int update_zfs_pool_state_chart(const DICTIONARY_ITEM *item, void *pool_p, void pool->rd_offline = rrddim_add(pool->st, "offline", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); pool->rd_removed = rrddim_add(pool->st, "removed", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); pool->rd_unavail = rrddim_add(pool->st, "unavail", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + + rrdlabels_add(pool->st->rrdlabels, "pool", name, RRDLABEL_SRC_AUTO); } rrddim_set_by_pointer(pool->st, pool->rd_online, pool->online); diff --git a/health/health.d/cgroups.conf b/health/health.d/cgroups.conf index 4bfe38b65a..7bdd6d6b36 100644 --- a/health/health.d/cgroups.conf +++ b/health/health.d/cgroups.conf @@ -51,7 +51,7 @@ component: Network lookup: average -1m unaligned of received units: packets every: 10s - info: average number of packets received by the network interface $family over the last minute + info: average number of packets received by the network interface $label:device over the last minute template: cgroup_10s_received_packets_storm on: cgroup.net_packets @@ -66,7 +66,7 @@ component: Network warn: $this > (($status >= $WARNING)?(200):(5000)) crit: $this > (($status == $CRITICAL)?(5000):(6000)) options: no-clear-notification - info: ratio of average number of received packets for the network interface $family over the last 10 seconds, \ + info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \ compared to the rate over the last minute to: sysadmin @@ -121,7 +121,7 @@ component: Network lookup: average -1m unaligned of received units: packets every: 10s - info: average number of packets received by the network interface $family over the last minute + info: average number of packets received by the network interface $label:device over the last minute template: k8s_cgroup_10s_received_packets_storm on: k8s.cgroup.net_packets @@ -136,6 +136,6 @@ component: Network warn: $this > (($status >= $WARNING)?(200):(5000)) crit: $this > (($status == $CRITICAL)?(5000):(6000)) options: no-clear-notification - info: ratio of average number of received packets for the network interface $family over the last 10 seconds, \ + info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \ compared to the rate over the last minute to: sysadmin diff --git a/health/health.d/disks.conf b/health/health.d/disks.conf index 5daff61a14..dc5f3d4f9a 100644 --- a/health/health.d/disks.conf +++ b/health/health.d/disks.conf @@ -23,7 +23,7 @@ component: Disk warn: $this > (($status >= $WARNING ) ? (80) : (90)) crit: $this > (($status == $CRITICAL) ? (90) : (98)) delay: up 1m down 15m multiplier 1.5 max 1h - info: disk $family space utilization + info: disk $label:mount_point space utilization to: sysadmin template: disk_inode_usage @@ -40,7 +40,7 @@ component: Disk warn: $this > (($status >= $WARNING) ? (80) : (90)) crit: $this > (($status == $CRITICAL) ? (90) : (98)) delay: up 1m down 15m multiplier 1.5 max 1h - info: disk $family inode utilization + info: disk $label:mount_point inode utilization to: sysadmin @@ -147,7 +147,7 @@ component: Disk every: 1m warn: $this > 98 * (($status >= $WARNING) ? (0.7) : (1)) delay: down 15m multiplier 1.2 max 1h - info: average percentage of time $family disk was busy over the last 10 minutes + info: average percentage of time $label:device disk was busy over the last 10 minutes to: silent @@ -169,5 +169,5 @@ component: Disk every: 1m warn: $this > 5000 * (($status >= $WARNING) ? (0.7) : (1)) delay: down 15m multiplier 1.2 max 1h - info: average backlog size of the $family disk over the last 10 minutes + info: average backlog size of the $label:device disk over the last 10 minutes to: silent diff --git a/health/health.d/mdstat.conf b/health/health.d/mdstat.conf index cedaa000eb..3594cd043c 100644 --- a/health/health.d/mdstat.conf +++ b/health/health.d/mdstat.conf @@ -20,7 +20,7 @@ component: RAID every: 10s calc: $down crit: $this > 0 - info: number of devices in the down state for the $family array. \ + info: number of devices in the down state for the $label:device $label:raid_level array. \ Any number > 0 indicates that the array is degraded. to: sysadmin @@ -35,7 +35,7 @@ component: RAID every: 60s warn: $this > 1024 delay: up 30m - info: number of unsynchronized blocks for the $family array + info: number of unsynchronized blocks for the $label:device $label:raid_level array to: sysadmin template: mdstat_nonredundant_last_collected diff --git a/health/health.d/net.conf b/health/health.d/net.conf index 9d5b3b8d35..28aa617b9b 100644 --- a/health/health.d/net.conf +++ b/health/health.d/net.conf @@ -15,7 +15,7 @@ component: Network calc: ( $nic_speed_max > 0 ) ? ( $nic_speed_max) : ( nan ) units: Mbit every: 10s - info: network interface $family current speed + info: network interface $label:device current speed template: 1m_received_traffic_overflow on: net.net @@ -31,7 +31,7 @@ component: Network every: 10s warn: $this > (($status >= $WARNING) ? (85) : (90)) delay: up 1m down 1m multiplier 1.5 max 1h - info: average inbound utilization for the network interface $family over the last minute + info: average inbound utilization for the network interface $label:device over the last minute to: sysadmin template: 1m_sent_traffic_overflow @@ -48,7 +48,7 @@ component: Network every: 10s warn: $this > (($status >= $WARNING) ? (85) : (90)) delay: up 1m down 1m multiplier 1.5 max 1h - info: average outbound utilization for the network interface $family over the last minute + info: average outbound utilization for the network interface $label:device over the last minute to: sysadmin # ----------------------------------------------------------------------------- @@ -72,7 +72,7 @@ component: Network lookup: sum -10m unaligned absolute of inbound units: packets every: 1m - info: number of inbound dropped packets for the network interface $family in the last 10 minutes + info: number of inbound dropped packets for the network interface $label:device in the last 10 minutes template: outbound_packets_dropped on: net.drops @@ -85,7 +85,7 @@ component: Network lookup: sum -10m unaligned absolute of outbound units: packets every: 1m - info: number of outbound dropped packets for the network interface $family in the last 10 minutes + info: number of outbound dropped packets for the network interface $label:device in the last 10 minutes template: inbound_packets_dropped_ratio on: net.packets @@ -101,7 +101,7 @@ component: Network every: 1m warn: $this >= 2 delay: up 1m down 1h multiplier 1.5 max 2h - info: ratio of inbound dropped packets for the network interface $family over the last 10 minutes + info: ratio of inbound dropped packets for the network interface $label:device over the last 10 minutes to: sysadmin template: outbound_packets_dropped_ratio @@ -118,7 +118,7 @@ component: Network every: 1m warn: $this >= 2 delay: up 1m down 1h multiplier 1.5 max 2h - info: ratio of outbound dropped packets for the network interface $family over the last 10 minutes + info: ratio of outbound dropped packets for the network interface $label:device over the last 10 minutes to: sysadmin template: wifi_inbound_packets_dropped_ratio @@ -135,7 +135,7 @@ component: Network every: 1m warn: $this >= 10 delay: up 1m down 1h multiplier 1.5 max 2h - info: ratio of inbound dropped packets for the network interface $family over the last 10 minutes + info: ratio of inbound dropped packets for the network interface $label:device over the last 10 minutes to: sysadmin template: wifi_outbound_packets_dropped_ratio @@ -152,7 +152,7 @@ component: Network every: 1m warn: $this >= 10 delay: up 1m down 1h multiplier 1.5 max 2h - info: ratio of outbound dropped packets for the network interface $family over the last 10 minutes + info: ratio of outbound dropped packets for the network interface $label:device over the last 10 minutes to: sysadmin # ----------------------------------------------------------------------------- @@ -171,7 +171,7 @@ component: Network every: 1m warn: $this >= 5 delay: down 1h multiplier 1.5 max 2h - info: number of inbound errors for the network interface $family in the last 10 minutes + info: number of inbound errors for the network interface $label:device in the last 10 minutes to: sysadmin template: interface_outbound_errors @@ -187,7 +187,7 @@ component: Network every: 1m warn: $this >= 5 delay: down 1h multiplier 1.5 max 2h - info: number of outbound errors for the network interface $family in the last 10 minutes + info: number of outbound errors for the network interface $label:device in the last 10 minutes to: sysadmin # ----------------------------------------------------------------------------- @@ -211,7 +211,7 @@ component: Network every: 1m warn: $this > 0 delay: down 1h multiplier 1.5 max 2h - info: number of FIFO errors for the network interface $family in the last 10 minutes + info: number of FIFO errors for the network interface $label:device in the last 10 minutes to: sysadmin # ----------------------------------------------------------------------------- @@ -234,7 +234,7 @@ component: Network lookup: average -1m unaligned of received units: packets every: 10s - info: average number of packets received by the network interface $family over the last minute + info: average number of packets received by the network interface $label:device over the last minute template: 10s_received_packets_storm on: net.packets @@ -251,6 +251,6 @@ component: Network warn: $this > (($status >= $WARNING)?(200):(5000)) crit: $this > (($status == $CRITICAL)?(5000):(6000)) options: no-clear-notification - info: ratio of average number of received packets for the network interface $family over the last 10 seconds, \ + info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \ compared to the rate over the last minute to: sysadmin diff --git a/health/health.d/zfs.conf b/health/health.d/zfs.conf index 785838d477..c53f8032ea 100644 --- a/health/health.d/zfs.conf +++ b/health/health.d/zfs.conf @@ -24,7 +24,7 @@ component: File system every: 10s warn: $this > 0 delay: down 1m multiplier 1.5 max 1h - info: ZFS pool $family state is degraded + info: ZFS pool $label:pool state is degraded to: sysadmin template: zfs_pool_state_crit @@ -37,5 +37,5 @@ component: File system every: 10s crit: $this > 0 delay: down 1m multiplier 1.5 max 1h - info: ZFS pool $family state is faulted or unavail + info: ZFS pool $label:pool state is faulted or unavail to: sysadmin |