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 /collectors/proc.plugin | |
parent | 489c3f5c66be6d3d63c3975bdbf6add861141998 (diff) |
Bugfix on alerts generation for yamls (#15420)
Diffstat (limited to 'collectors/proc.plugin')
-rw-r--r-- | collectors/proc.plugin/multi_metadata.yaml | 127 |
1 files changed, 117 insertions, 10 deletions
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 |