diff options
author | Fotis Voutsas <fotis@netdata.cloud> | 2023-07-18 11:00:23 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-07-18 11:00:23 +0300 |
commit | 25586826d42107952ead3348dbce0c0223adf61d (patch) | |
tree | d6af5389beeed5e459b463e2258ce699159bbd7c | |
parent | 489c3f5c66be6d3d63c3975bdbf6add861141998 (diff) |
Bugfix on alerts generation for yamls (#15420)
23 files changed, 303 insertions, 41 deletions
diff --git a/collectors/cgroups.plugin/multi_metadata.yaml b/collectors/cgroups.plugin/multi_metadata.yaml index 8a586127eb..b67749e8f2 100644 --- a/collectors/cgroups.plugin/multi_metadata.yaml +++ b/collectors/cgroups.plugin/multi_metadata.yaml @@ -616,20 +616,23 @@ modules: metric: cgroup.net_packets info: average number of packets received by the network interface ${label:device} over the last minute - os: "linux" - name: cgroup_10s_received_packets_storm link: https://github.com/netdata/netdata/blob/master/health/health.d/cgroups.conf metric: cgroup.net_packets 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 - os: "linux" - name: k8s_cgroup_1m_received_packets_rate link: https://github.com/netdata/netdata/blob/master/health/health.d/cgroups.conf metric: k8s.cgroup.net_packets info: average number of packets received by the network interface ${label:device} over the last minute - os: "linux" + - name: k8s_cgroup_10s_received_packets_storm + link: https://github.com/netdata/netdata/blob/master/health/health.d/cgroups.conf + metric: k8s.cgroup.net_packets + 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 metrics: folding: title: Metrics diff --git a/collectors/charts.d.plugin/apcupsd/metadata.yaml b/collectors/charts.d.plugin/apcupsd/metadata.yaml index 1661620a21..a0df692518 100644 --- a/collectors/charts.d.plugin/apcupsd/metadata.yaml +++ b/collectors/charts.d.plugin/apcupsd/metadata.yaml @@ -63,6 +63,10 @@ alerts: metric: apcupsd.load info: average UPS load over the last 10 minutes os: "*" + - name: apcupsd_last_collected_secs + link: https://github.com/netdata/netdata/blob/master/health/health.d/apcupsd.conf + metric: apcupsd.load + info: number of seconds since the last successful data collection metrics: folding: title: Metrics diff --git a/collectors/charts.d.plugin/nut/metadata.yaml b/collectors/charts.d.plugin/nut/metadata.yaml index 994c683f18..3991f67063 100644 --- a/collectors/charts.d.plugin/nut/metadata.yaml +++ b/collectors/charts.d.plugin/nut/metadata.yaml @@ -63,6 +63,10 @@ alerts: metric: nut.load info: average UPS load over the last 10 minutes os: "*" + - name: nut_last_collected_secs + link: https://github.com/netdata/netdata/blob/master/health/health.d/nut.conf + metric: nut.load + info: number of seconds since the last successful data collection metrics: folding: title: Metrics diff --git a/collectors/ebpf.plugin/multi_metadata.yaml b/collectors/ebpf.plugin/multi_metadata.yaml index ca4e51df12..cec161aff7 100644 --- a/collectors/ebpf.plugin/multi_metadata.yaml +++ b/collectors/ebpf.plugin/multi_metadata.yaml @@ -705,7 +705,14 @@ modules: troubleshooting: problems: list: [] - alerts: [] + alerts: + - name: sync_freq + link: | + https://github.com/netdata/netdata/blob/master/health/health.d/synchronization.conf + metric: mem.sync + info: number of sync() system calls. Every call causes all pending modifications + to filesystem metadata and cached file data to be written to the underlying + filesystems. metrics: folding: title: Metrics diff --git a/collectors/freebsd.plugin/multi_metadata.yaml b/collectors/freebsd.plugin/multi_metadata.yaml index a761d18b64..bd9ad964b2 100644 --- a/collectors/freebsd.plugin/multi_metadata.yaml +++ b/collectors/freebsd.plugin/multi_metadata.yaml @@ -70,6 +70,11 @@ modules: metric: system.load info: system five-minute load average os: "linux" + - name: load_average_1 + link: https://github.com/netdata/netdata/blob/master/health/health.d/load.conf + metric: system.load + info: system one-minute load average + os: "linux" metrics: folding: title: Metrics @@ -143,7 +148,11 @@ modules: troubleshooting: problems: list: [] - alerts: [] + alerts: + - name: active_processes + link: https://github.com/netdata/netdata/blob/master/health/health.d/processes.conf + metric: system.active_processes + info: system process IDs (PID) space utilization metrics: folding: title: Metrics @@ -245,6 +254,11 @@ modules: metric: system.cpu info: average CPU steal time over the last 20 minutes os: "linux" + - name: 10min_cpu_usage + link: https://github.com/netdata/netdata/blob/master/health/health.d/cpu.conf + metric: system.cpu + info: average CPU utilization over the last 10 minutes (excluding nice) + os: "freebsd" metrics: folding: title: Metrics @@ -778,7 +792,12 @@ modules: troubleshooting: problems: list: [] - alerts: [] + alerts: + - name: used_swap + link: https://github.com/netdata/netdata/blob/master/health/health.d/swap.conf + metric: system.swap + info: swap memory utilization + os: "linux freebsd" metrics: folding: title: Metrics @@ -868,6 +887,12 @@ modules: info: percentage of estimated amount of RAM available for userspace processes, without causing swapping os: "linux" + - name: ram_available + link: https://github.com/netdata/netdata/blob/master/health/health.d/ram.conf + metric: mem.available + info: percentage of estimated amount of RAM available for userspace processes, + without causing swapping + os: "freebsd" metrics: folding: title: Metrics @@ -1111,6 +1136,11 @@ modules: metric: system.ipc_semaphores info: IPC semaphore utilization os: "linux" + - name: semaphore_arrays_used + link: https://github.com/netdata/netdata/blob/master/health/health.d/ipc.conf + metric: system.ipc_semaphore_arrays + info: IPC semaphore arrays utilization + os: "linux" metrics: folding: title: Metrics @@ -1437,6 +1467,12 @@ modules: or net.core.netdev_budget_usecs with work remaining over the last minute (this can be a cause for dropped packets) os: "linux" + - name: 10min_netisr_backlog_exceeded + link: https://github.com/netdata/netdata/blob/master/health/health.d/softnet.conf + metric: system.softnet_stat + info: average number of drops in the last minute due to exceeded sysctl net.route.netisr_maxqlen + (this can be a cause for dropped packets) + os: "freebsd" metrics: folding: title: Metrics @@ -1668,7 +1704,12 @@ modules: troubleshooting: problems: list: [] - alerts: [] + alerts: + - name: tcp_connections + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_conn.conf + metric: ipv4.tcpsock + info: IPv4 TCP connections utilization + os: "linux" metrics: folding: title: Metrics @@ -1758,6 +1799,13 @@ modules: metric: ipv4.tcphandshake info: average number of received TCP RESETS over the last minute os: "linux freebsd" + - name: 10s_ipv4_tcp_resets_received + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf + metric: ipv4.tcphandshake + info: average number of received TCP RESETS over the last 10 seconds. This + can be an indication that a service this host needs has crashed. Netdata + will not send a clear notification for this alarm. + os: "linux freebsd" metrics: folding: title: Metrics @@ -1893,6 +1941,11 @@ modules: metric: ipv4.udperrors info: average number of UDP receive buffer errors over the last minute os: "linux freebsd" + - name: 1m_ipv4_udp_send_buffer_errors + link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf + metric: ipv4.udperrors + info: average number of UDP send buffer errors over the last minute + os: "linux" metrics: folding: title: Metrics @@ -2553,6 +2606,13 @@ modules: info: average number of packets received by the network interface ${label:device} over the last minute os: "linux freebsd" + - name: 10s_received_packets_storm + link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf + metric: net.packets + 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 + os: "linux freebsd" - name: interface_inbound_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.errors @@ -2809,7 +2869,6 @@ modules: link: https://github.com/netdata/netdata/blob/master/health/health.d/zfs.conf metric: zfs.memory_ops info: number of times ZFS had to limit the ARC growth in the last 10 minutes - os: "*" metrics: folding: title: Metrics diff --git a/collectors/freeipmi.plugin/multi_metadata.yaml b/collectors/freeipmi.plugin/multi_metadata.yaml index 36eb7be237..473c8b2cb4 100644 --- a/collectors/freeipmi.plugin/multi_metadata.yaml +++ b/collectors/freeipmi.plugin/multi_metadata.yaml @@ -131,7 +131,6 @@ modules: link: https://github.com/netdata/netdata/blob/master/health/health.d/ipmi.conf metric: ipmi.sensor_state info: IPMI sensor ${label:sensor} (${label:component}) state - os: "linux" metrics: folding: title: Metrics diff --git a/collectors/ioping.plugin/metadata.yaml b/collectors/ioping.plugin/metadata.yaml index f21543fbe3..11c835d67f 100644 --- a/collectors/ioping.plugin/metadata.yaml +++ b/collectors/ioping.plugin/metadata.yaml @@ -52,7 +52,11 @@ setup: troubleshooting: problems: list: [] -alerts: [] +alerts: + - name: ioping_disk_latency + link: https://github.com/netdata/netdata/blob/master/health/health.d/ioping.conf + metric: ioping.latency + info: average I/O latency over the last 10 seconds metrics: folding: title: Metrics diff --git a/collectors/macos.plugin/multi_metadata.yaml b/collectors/macos.plugin/multi_metadata.yaml index 0608c41ad8..a853777e2f 100644 --- a/collectors/macos.plugin/multi_metadata.yaml +++ b/collectors/macos.plugin/multi_metadata.yaml @@ -71,6 +71,11 @@ modules: metric: system.cpu info: average CPU steal time over the last 20 minutes os: "linux" + - name: 10min_cpu_usage + link: https://github.com/netdata/netdata/blob/master/health/health.d/cpu.conf + metric: system.cpu + info: average CPU utilization over the last 10 minutes (excluding nice) + os: "freebsd" - name: ram_in_use link: https://github.com/netdata/netdata/blob/master/health/health.d/ram.conf metric: system.ram @@ -210,6 +215,16 @@ modules: metric: system.load info: system five-minute load average os: "linux" + - name: load_average_1 + link: https://github.com/netdata/netdata/blob/master/health/health.d/load.conf + metric: system.load + info: system one-minute load average + os: "linux" + - name: used_swap + link: https://github.com/netdata/netdata/blob/master/health/health.d/swap.conf + metric: system.swap + info: swap memory utilization + os: "linux freebsd" - name: 1m_ipv4_tcp_resets_sent link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf metric: ipv4.tcphandshake @@ -227,11 +242,23 @@ modules: metric: ipv4.tcphandshake info: average number of received TCP RESETS over the last minute os: "linux freebsd" + - name: 10s_ipv4_tcp_resets_received + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf + metric: ipv4.tcphandshake + info: average number of received TCP RESETS over the last 10 seconds. This + can be an indication that a service this host needs has crashed. Netdata + will not send a clear notification for this alarm. + os: "linux freebsd" - name: 1m_ipv4_udp_receive_buffer_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf metric: ipv4.udperrors info: average number of UDP receive buffer errors over the last minute os: "linux freebsd" + - name: 1m_ipv4_udp_send_buffer_errors + link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf + metric: ipv4.udperrors + info: average number of UDP send buffer errors over the last minute + os: "linux" metrics: folding: title: Metrics @@ -629,6 +656,13 @@ modules: info: average number of packets received by the network interface ${label:device} over the last minute os: "linux freebsd" + - name: 10s_received_packets_storm + link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf + metric: net.packets + 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 + os: "linux freebsd" - name: interface_inbound_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.errors diff --git a/collectors/proc.plugin/multi_metadata.yaml b/collectors/proc.plugin/multi_metadata.yaml index 61437dee47..3ca89969cf 100644 --- a/collectors/proc.plugin/multi_metadata.yaml +++ b/collectors/proc.plugin/multi_metadata.yaml @@ -71,6 +71,11 @@ modules: metric: system.cpu info: average CPU steal time over the last 20 minutes os: "linux" + - name: 10min_cpu_usage + link: https://github.com/netdata/netdata/blob/master/health/health.d/cpu.conf + metric: system.cpu + info: average CPU utilization over the last 10 minutes (excluding nice) + os: "freebsd" metrics: folding: title: Metrics @@ -221,7 +226,12 @@ modules: troubleshooting: problems: list: [] - alerts: [] + alerts: + - name: lowest_entropy + link: https://github.com/netdata/netdata/blob/master/health/health.d/entropy.conf + metric: system.entropy + info: minimum number of entries in the random numbers pool in the last 5 minutes + os: "linux" metrics: folding: title: Metrics @@ -659,6 +669,15 @@ modules: metric: system.load info: system five-minute load average os: "linux" + - name: load_average_1 + link: https://github.com/netdata/netdata/blob/master/health/health.d/load.conf + metric: system.load + info: system one-minute load average + os: "linux" + - name: active_processes + link: https://github.com/netdata/netdata/blob/master/health/health.d/processes.conf + metric: system.active_processes + info: system process IDs (PID) space utilization metrics: folding: title: Metrics @@ -986,6 +1005,12 @@ modules: or net.core.netdev_budget_usecs with work remaining over the last minute (this can be a cause for dropped packets) os: "linux" + - name: 10min_netisr_backlog_exceeded + link: https://github.com/netdata/netdata/blob/master/health/health.d/softnet.conf + metric: system.softnet_stat + info: average number of drops in the last minute due to exceeded sysctl net.route.netisr_maxqlen + (this can be a cause for dropped packets) + os: "freebsd" metrics: folding: title: Metrics @@ -1092,6 +1117,22 @@ modules: info: percentage of estimated amount of RAM available for userspace processes, without causing swapping os: "linux" + - name: ram_available + link: https://github.com/netdata/netdata/blob/master/health/health.d/ram.conf + metric: mem.available + info: percentage of estimated amount of RAM available for userspace processes, + without causing swapping + os: "freebsd" + - name: used_swap + link: https://github.com/netdata/netdata/blob/master/health/health.d/swap.conf + metric: system.swap + info: swap memory utilization + os: "linux freebsd" + - name: 1hour_memory_hw_corrupted + link: https://github.com/netdata/netdata/blob/master/health/health.d/memory.conf + metric: mem.hwcorrupt + info: amount of memory corrupted due to a hardware failure + os: "linux" metrics: folding: title: Metrics @@ -1677,6 +1718,11 @@ modules: metric: system.ipc_semaphores info: IPC semaphore utilization os: "linux" + - name: semaphore_arrays_used + link: https://github.com/netdata/netdata/blob/master/health/health.d/ipc.conf + metric: system.ipc_semaphore_arrays + info: IPC semaphore arrays utilization + os: "linux" metrics: folding: title: Metrics @@ -1779,19 +1825,28 @@ modules: problems: list: [] alerts: + - name: 10min_disk_backlog + link: https://github.com/netdata/netdata/blob/master/health/health.d/disks.conf + metric: disk.backlog + info: average backlog size of the ${label:device} disk over the last 10 minutes + os: "linux" - name: 10min_disk_utilization link: https://github.com/netdata/netdata/blob/master/health/health.d/disks.conf metric: disk.util info: average percentage of time ${label:device} disk was busy over the last 10 minutes os: "linux freebsd" + - name: bcache_cache_dirty + link: https://github.com/netdata/netdata/blob/master/health/health.d/bcache.conf + metric: disk.bcache_cache_alloc + info: percentage of cache space used for dirty data and metadata (this usually + means your SSD cache is too small) - name: bcache_cache_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/bcache.conf metric: disk.bcache_cache_read_races info: number of times data was read from the cache, the bucket was reused and invalidated in the last 10 minutes (when this occurs the data is reread from the backing device) - os: "freebsd" metrics: folding: title: Metrics @@ -2051,19 +2106,20 @@ modules: link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf metric: md.disks info: number of seconds since the last successful data collection - os: "*" - name: mdstat_disks link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf metric: md.disks 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. - os: "*" - name: mdstat_mismatch_cnt link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf metric: md.mismatch_cnt info: number of unsynchronized blocks for the ${label:device} ${label:raid_level} array - os: "*" + - name: mdstat_nonredundant_last_collected + link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf + metric: md.nonredundant + info: number of seconds since the last successful data collection metrics: folding: title: Metrics @@ -2231,6 +2287,13 @@ modules: info: average number of packets received by the network interface ${label:device} over the last minute os: "linux freebsd" + - name: 10s_received_packets_storm + link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf + metric: net.packets + 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 + os: "linux freebsd" - name: interface_inbound_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.errors @@ -2708,6 +2771,11 @@ modules: info: average number of dropped packets in the TCP accept queue over the last minute os: "linux" + - name: tcp_connections + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_conn.conf + metric: ipv4.tcpsock + info: IPv4 TCP connections utilization + os: "linux" - name: 1m_ipv4_tcp_resets_sent link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf metric: ipv4.tcphandshake @@ -2725,11 +2793,23 @@ modules: metric: ipv4.tcphandshake info: average number of received TCP RESETS over the last minute os: "linux freebsd" + - name: 10s_ipv4_tcp_resets_received + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf + metric: ipv4.tcphandshake + info: average number of received TCP RESETS over the last 10 seconds. This + can be an indication that a service this host needs has crashed. Netdata + will not send a clear notification for this alarm. + os: "linux freebsd" - name: 1m_ipv4_udp_receive_buffer_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf metric: ipv4.udperrors info: average number of UDP receive buffer errors over the last minute os: "linux freebsd" + - name: 1m_ipv4_udp_send_buffer_errors + link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf + metric: ipv4.udperrors + info: average number of UDP send buffer errors over the last minute + os: "linux" metrics: folding: title: Metrics @@ -3264,7 +3344,17 @@ modules: troubleshooting: problems: list: [] - alerts: [] + alerts: + - name: tcp_orphans + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_orphans.conf + metric: ipv4.sockstat_tcp_sockets + info: orphan IPv4 TCP sockets utilization + os: "linux" + - name: tcp_memory + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_mem.conf + metric: ipv4.sockstat_tcp_mem + info: TCP memory utilization + os: "linux" metrics: folding: title: Metrics @@ -3902,7 +3992,12 @@ modules: troubleshooting: problems: list: [] - alerts: [] + alerts: + - name: netfilter_conntrack_full + link: https://github.com/netdata/netdata/blob/master/health/health.d/netfilter.conf + metric: netfilter.conntrack_sockets + info: netfilter connection tracker table size utilization + os: "linux" metrics: folding: title: Metrics @@ -4106,7 +4201,10 @@ modules: link: https://github.com/netdata/netdata/blob/master/health/health.d/zfs.conf metric: zfspool.state info: ZFS pool ${label:pool} state is degraded - os: "*" + - name: zfs_pool_state_crit + link: https://github.com/netdata/netdata/blob/master/health/health.d/zfs.conf + metric: zfspool.state + info: ZFS pool ${label:pool} state is faulted or unavail metrics: folding: title: Metrics @@ -4191,7 +4289,6 @@ modules: link: https://github.com/netdata/netdata/blob/master/health/health.d/zfs.conf metric: zfs.memory_ops info: number of times ZFS had to limit the ARC growth in the last 10 minutes - os: "*" metrics: folding: title: Metrics @@ -4490,6 +4587,11 @@ modules: metric: btrfs.device_errors info: number of encountered BTRFS corruption errors os: "*" + - name: btrfs_device_generation_errors + link: https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf + metric: btrfs.device_errors + info: number of encountered BTRFS generation errors + os: "*" metrics: folding: title: Metrics @@ -4632,7 +4734,12 @@ modules: troubleshooting: problems: list: [] - alerts: [] + alerts: + - name: linux_power_supply_capacity + link: | + https://github.com/netdata/netdata/blob/master/health/health.d/linux_power_supply.conf + metric: powersupply.capacity + info: percentage of remaining power supply capacity metrics: folding: title: Metrics diff --git a/collectors/python.d.plugin/adaptec_raid/metadata.yaml b/collectors/python.d.plugin/adaptec_raid/metadata.yaml index 22dcc1e007..9e2a7de7c7 100644 --- a/collectors/python.d.plugin/adaptec_raid/metadata.yaml +++ b/collectors/python.d.plugin/adaptec_raid/metadata.yaml @@ -57,7 +57,10 @@ alerts: link: https://github.com/netdata/netdata/blob/master/health/health.d/adaptec_raid.conf metric: adaptec_raid.ld_status info: logical device status is failed or degraded - os: "linux" + - name: adaptec_raid_pd_state + link: https://github.com/netdata/netdata/blob/master/health/health.d/adaptec_raid.conf + metric: adaptec_raid.pd_state + info: physical device state is not online metrics: folding: title: Metrics diff --git a/collectors/python.d.plugin/anomalies/metadata.yaml b/collectors/python.d.plugin/anomalies/metadata.yaml index 6d643ceb49..415159d966 100644 --- a/collectors/python.d.plugin/anomalies/metadata.yaml +++ b/collectors/python.d.plugin/anomalies/metadata.yaml @@ -57,7 +57,10 @@ alerts: link: https://github.com/netdata/netdata/blob/master/health/health.d/anomalies.conf metric: anomalies.probability info: average anomaly probability over the last 2 minutes - os: "linux" + - name: anomalies_anomaly_flags + link: https://github.com/netdata/netdata/blob/master/health/health.d/anomalies.conf + metric: anomalies.anomaly + info: number of anomalies in the last 2 minutes metrics: folding: title: Metrics diff --git a/collectors/python.d.plugin/beanstalk/metadata.yaml b/collectors/python.d.plugin/beanstalk/metadata.yaml index 1d04a1649e..d5b927fac6 100644 --- a/collectors/python.d.plugin/beanstalk/metadata.yaml +++ b/collectors/python.d.plugin/beanstalk/metadata.yaml @@ -59,7 +59,6 @@ alerts: info: number of buried jobs across all tubes. You need to manually kick them so they can be processed. Presence of buried jobs in a tube does not affect new jobs. - os: "freebsd" metrics: folding: title: Metrics diff --git a/collectors/python.d.plugin/bind_rndc/metadata.yaml b/collectors/python.d.plugin/bind_rndc/metadata.yaml index 2677e13068..dfc8964a8b 100644 --- a/collectors/python.d.plugin/bind_rndc/metadata.yaml +++ b/collectors/python.d.plugin/bind_rndc/metadata.yaml @@ -52,7 +52,11 @@ setup: troubleshooting: problems: list: [] -alerts: [] +alerts: + - name: bind_rndc_stats_file_size + link: https://github.com/netdata/netdata/blob/master/health/health.d/bind_rndc.conf + metric: bind_rndc.stats_size + info: BIND statistics-file size metrics: folding: title: Metrics diff --git a/collectors/python.d.plugin/boinc/metadata.yaml b/collectors/python.d.plugin/boinc/metadata.yaml index 1a7487f47c..da59dfd0fd 100644 --- a/collectors/python.d.plugin/boinc/metadata.yaml +++ b/collectors/python.d.plugin/boinc/metadata.yaml @@ -58,6 +58,11 @@ alerts: metric: boinc.tasks info: average number of total tasks over the last 10 minutes os: "*" + - name: boinc_active_tasks + link: https://github.com/netdata/netdata/blob/master/health/health.d/boinc.conf + metric: boinc.tasks + info: average number of active tasks over the last 10 minutes + os: "*" - name: boinc_compute_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/boinc.conf |