@cryptotaxi247 / netdata-1 / commits / 25586826d

Bugfix on alerts generation for yamls (#15420)

Fotis Voutsas committed Jul 18, 2023 at 11:00 UTC 25586826d42107952ead3348dbce0c0223adf61d
23 files changed +303 -41
collectors/cgroups.plugin/multi_metadata.yaml
+6 -3
@@ -616,20 +616,23 @@ modules:
616 metric: cgroup.net_packets
617 info: average number of packets received by the network interface ${label:device}
618 over the last minute
619 - os: "linux"
619 - name: cgroup_10s_received_packets_storm
620 link: https://github.com/netdata/netdata/blob/master/health/health.d/cgroups.conf
621 metric: cgroup.net_packets
622 info: ratio of average number of received packets for the network interface
623 ${label:device} over the last 10 seconds, compared to the rate over the
624 last minute
626 - os: "linux"
625 - name: k8s_cgroup_1m_received_packets_rate
626 link: https://github.com/netdata/netdata/blob/master/health/health.d/cgroups.conf
627 metric: k8s.cgroup.net_packets
628 info: average number of packets received by the network interface ${label:device}
629 over the last minute
632 - os: "linux"
630 + - name: k8s_cgroup_10s_received_packets_storm
631 + link: https://github.com/netdata/netdata/blob/master/health/health.d/cgroups.conf
632 + metric: k8s.cgroup.net_packets
633 + info: ratio of average number of received packets for the network interface
634 + ${label:device} over the last 10 seconds, compared to the rate over the
635 + last minute
636 metrics:
637 folding:
638 title: Metrics
collectors/charts.d.plugin/apcupsd/metadata.yaml
+4
@@ -63,6 +63,10 @@ alerts:
63 metric: apcupsd.load
64 info: average UPS load over the last 10 minutes
65 os: "*"
66 + - name: apcupsd_last_collected_secs
67 + link: https://github.com/netdata/netdata/blob/master/health/health.d/apcupsd.conf
68 + metric: apcupsd.load
69 + info: number of seconds since the last successful data collection
70 metrics:
71 folding:
72 title: Metrics
collectors/charts.d.plugin/nut/metadata.yaml
+4
@@ -63,6 +63,10 @@ alerts:
63 metric: nut.load
64 info: average UPS load over the last 10 minutes
65 os: "*"
66 + - name: nut_last_collected_secs
67 + link: https://github.com/netdata/netdata/blob/master/health/health.d/nut.conf
68 + metric: nut.load
69 + info: number of seconds since the last successful data collection
70 metrics:
71 folding:
72 title: Metrics
collectors/ebpf.plugin/multi_metadata.yaml
+8 -1
@@ -705,7 +705,14 @@ modules:
705 troubleshooting:
706 problems:
707 list: []
708 - alerts: []
708 + alerts:
709 + - name: sync_freq
710 + link: |
711 + https://github.com/netdata/netdata/blob/master/health/health.d/synchronization.conf
712 + metric: mem.sync
713 + info: number of sync() system calls. Every call causes all pending modifications
714 + to filesystem metadata and cached file data to be written to the underlying
715 + filesystems.
716 metrics:
717 folding:
718 title: Metrics
collectors/freebsd.plugin/multi_metadata.yaml
+63 -4
@@ -70,6 +70,11 @@ modules:
70 metric: system.load
71 info: system five-minute load average
72 os: "linux"
73 + - name: load_average_1
74 + link: https://github.com/netdata/netdata/blob/master/health/health.d/load.conf
75 + metric: system.load
76 + info: system one-minute load average
77 + os: "linux"
78 metrics:
79 folding:
80 title: Metrics
@@ -143,7 +148,11 @@ modules:
148 troubleshooting:
149 problems:
150 list: []
146 - alerts: []
151 + alerts:
152 + - name: active_processes
153 + link: https://github.com/netdata/netdata/blob/master/health/health.d/processes.conf
154 + metric: system.active_processes
155 + info: system process IDs (PID) space utilization
156 metrics:
157 folding:
158 title: Metrics
@@ -245,6 +254,11 @@ modules:
254 metric: system.cpu
255 info: average CPU steal time over the last 20 minutes
256 os: "linux"
257 + - name: 10min_cpu_usage
258 + link: https://github.com/netdata/netdata/blob/master/health/health.d/cpu.conf
259 + metric: system.cpu
260 + info: average CPU utilization over the last 10 minutes (excluding nice)
261 + os: "freebsd"
262 metrics:
263 folding:
264 title: Metrics
@@ -778,7 +792,12 @@ modules:
792 troubleshooting:
793 problems:
794 list: []
781 - alerts: []
795 + alerts:
796 + - name: used_swap
797 + link: https://github.com/netdata/netdata/blob/master/health/health.d/swap.conf
798 + metric: system.swap
799 + info: swap memory utilization
800 + os: "linux freebsd"
801 metrics:
802 folding:
803 title: Metrics
@@ -868,6 +887,12 @@ modules:
887 info: percentage of estimated amount of RAM available for userspace processes,
888 without causing swapping
889 os: "linux"
890 + - name: ram_available
891 + link: https://github.com/netdata/netdata/blob/master/health/health.d/ram.conf
892 + metric: mem.available
893 + info: percentage of estimated amount of RAM available for userspace processes,
894 + without causing swapping
895 + os: "freebsd"
896 metrics:
897 folding:
898 title: Metrics
@@ -1111,6 +1136,11 @@ modules:
1136 metric: system.ipc_semaphores
1137 info: IPC semaphore utilization
1138 os: "linux"
1139 + - name: semaphore_arrays_used
1140 + link: https://github.com/netdata/netdata/blob/master/health/health.d/ipc.conf
1141 + metric: system.ipc_semaphore_arrays
1142 + info: IPC semaphore arrays utilization
1143 + os: "linux"
1144 metrics:
1145 folding:
1146 title: Metrics
@@ -1437,6 +1467,12 @@ modules:
1467 or net.core.netdev_budget_usecs with work remaining over the last minute
1468 (this can be a cause for dropped packets)
1469 os: "linux"
1470 + - name: 10min_netisr_backlog_exceeded
1471 + link: https://github.com/netdata/netdata/blob/master/health/health.d/softnet.conf
1472 + metric: system.softnet_stat
1473 + info: average number of drops in the last minute due to exceeded sysctl net.route.netisr_maxqlen
1474 + (this can be a cause for dropped packets)
1475 + os: "freebsd"
1476 metrics:
1477 folding:
1478 title: Metrics
@@ -1668,7 +1704,12 @@ modules:
1704 troubleshooting:
1705 problems:
1706 list: []
1671 - alerts: []
1707 + alerts:
1708 + - name: tcp_connections
1709 + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_conn.conf
1710 + metric: ipv4.tcpsock
1711 + info: IPv4 TCP connections utilization
1712 + os: "linux"
1713 metrics:
1714 folding:
1715 title: Metrics
@@ -1758,6 +1799,13 @@ modules:
1799 metric: ipv4.tcphandshake
1800 info: average number of received TCP RESETS over the last minute
1801 os: "linux freebsd"
1802 + - name: 10s_ipv4_tcp_resets_received
1803 + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf
1804 + metric: ipv4.tcphandshake
1805 + info: average number of received TCP RESETS over the last 10 seconds. This
1806 + can be an indication that a service this host needs has crashed. Netdata
1807 + will not send a clear notification for this alarm.
1808 + os: "linux freebsd"
1809 metrics:
1810 folding:
1811 title: Metrics
@@ -1893,6 +1941,11 @@ modules:
1941 metric: ipv4.udperrors
1942 info: average number of UDP receive buffer errors over the last minute
1943 os: "linux freebsd"
1944 + - name: 1m_ipv4_udp_send_buffer_errors
1945 + link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf
1946 + metric: ipv4.udperrors
1947 + info: average number of UDP send buffer errors over the last minute
1948 + os: "linux"
1949 metrics:
1950 folding:
1951 title: Metrics
@@ -2553,6 +2606,13 @@ modules:
2606 info: average number of packets received by the network interface ${label:device}
2607 over the last minute
2608 os: "linux freebsd"
2609 + - name: 10s_received_packets_storm
2610 + link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2611 + metric: net.packets
2612 + info: ratio of average number of received packets for the network interface
2613 + ${label:device} over the last 10 seconds, compared to the rate over the
2614 + last minute
2615 + os: "linux freebsd"
2616 - name: interface_inbound_errors
2617 link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2618 metric: net.errors
@@ -2809,7 +2869,6 @@ modules:
2869 link: https://github.com/netdata/netdata/blob/master/health/health.d/zfs.conf
2870 metric: zfs.memory_ops
2871 info: number of times ZFS had to limit the ARC growth in the last 10 minutes
2812 - os: "*"
2872 metrics:
2873 folding:
2874 title: Metrics
collectors/freeipmi.plugin/multi_metadata.yaml
-1
@@ -131,7 +131,6 @@ modules:
131 link: https://github.com/netdata/netdata/blob/master/health/health.d/ipmi.conf
132 metric: ipmi.sensor_state
133 info: IPMI sensor ${label:sensor} (${label:component}) state
134 - os: "linux"
134 metrics:
135 folding:
136 title: Metrics
collectors/ioping.plugin/metadata.yaml
+5 -1
@@ -52,7 +52,11 @@ setup:
52 troubleshooting:
53 problems:
54 list: []
55 -alerts: []
55 +alerts:
56 + - name: ioping_disk_latency
57 + link: https://github.com/netdata/netdata/blob/master/health/health.d/ioping.conf
58 + metric: ioping.latency
59 + info: average I/O latency over the last 10 seconds
60 metrics:
61 folding:
62 title: Metrics
collectors/macos.plugin/multi_metadata.yaml
+34
@@ -71,6 +71,11 @@ modules:
71 metric: system.cpu
72 info: average CPU steal time over the last 20 minutes
73 os: "linux"
74 + - name: 10min_cpu_usage
75 + link: https://github.com/netdata/netdata/blob/master/health/health.d/cpu.conf
76 + metric: system.cpu
77 + info: average CPU utilization over the last 10 minutes (excluding nice)
78 + os: "freebsd"
79 - name: ram_in_use
80 link: https://github.com/netdata/netdata/blob/master/health/health.d/ram.conf
81 metric: system.ram
@@ -210,6 +215,16 @@ modules:
215 metric: system.load
216 info: system five-minute load average
217 os: "linux"
218 + - name: load_average_1
219 + link: https://github.com/netdata/netdata/blob/master/health/health.d/load.conf
220 + metric: system.load
221 + info: system one-minute load average
222 + os: "linux"
223 + - name: used_swap
224 + link: https://github.com/netdata/netdata/blob/master/health/health.d/swap.conf
225 + metric: system.swap
226 + info: swap memory utilization
227 + os: "linux freebsd"
228 - name: 1m_ipv4_tcp_resets_sent
229 link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf
230 metric: ipv4.tcphandshake
@@ -227,11 +242,23 @@ modules:
242 metric: ipv4.tcphandshake
243 info: average number of received TCP RESETS over the last minute
244 os: "linux freebsd"
245 + - name: 10s_ipv4_tcp_resets_received
246 + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf
247 + metric: ipv4.tcphandshake
248 + info: average number of received TCP RESETS over the last 10 seconds. This
249 + can be an indication that a service this host needs has crashed. Netdata
250 + will not send a clear notification for this alarm.
251 + os: "linux freebsd"
252 - name: 1m_ipv4_udp_receive_buffer_errors
253 link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf
254 metric: ipv4.udperrors
255 info: average number of UDP receive buffer errors over the last minute
256 os: "linux freebsd"
257 + - name: 1m_ipv4_udp_send_buffer_errors
258 + link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf
259 + metric: ipv4.udperrors
260 + info: average number of UDP send buffer errors over the last minute
261 + os: "linux"
262 metrics:
263 folding:
264 title: Metrics
@@ -629,6 +656,13 @@ modules:
656 info: average number of packets received by the network interface ${label:device}
657 over the last minute
658 os: "linux freebsd"
659 + - name: 10s_received_packets_storm
660 + link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
661 + metric: net.packets
662 + info: ratio of average number of received packets for the network interface
663 + ${label:device} over the last 10 seconds, compared to the rate over the
664 + last minute
665 + os: "linux freebsd"
666 - name: interface_inbound_errors
667 link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
668 metric: net.errors
collectors/proc.plugin/multi_metadata.yaml
+117 -10
@@ -71,6 +71,11 @@ modules:
71 metric: system.cpu
72 info: average CPU steal time over the last 20 minutes
73 os: "linux"
74 + - name: 10min_cpu_usage
75 + link: https://github.com/netdata/netdata/blob/master/health/health.d/cpu.conf
76 + metric: system.cpu
77 + info: average CPU utilization over the last 10 minutes (excluding nice)
78 + os: "freebsd"
79 metrics:
80 folding:
81 title: Metrics
@@ -221,7 +226,12 @@ modules:
226 troubleshooting:
227 problems:
228 list: []
224 - alerts: []
229 + alerts:
230 + - name: lowest_entropy
231 + link: https://github.com/netdata/netdata/blob/master/health/health.d/entropy.conf
232 + metric: system.entropy
233 + info: minimum number of entries in the random numbers pool in the last 5 minutes
234 + os: "linux"
235 metrics:
236 folding:
237 title: Metrics
@@ -659,6 +669,15 @@ modules:
669 metric: system.load
670 info: system five-minute load average
671 os: "linux"
672 + - name: load_average_1
673 + link: https://github.com/netdata/netdata/blob/master/health/health.d/load.conf
674 + metric: system.load
675 + info: system one-minute load average
676 + os: "linux"
677 + - name: active_processes
678 + link: https://github.com/netdata/netdata/blob/master/health/health.d/processes.conf
679 + metric: system.active_processes
680 + info: system process IDs (PID) space utilization
681 metrics:
682 folding:
683 title: Metrics
@@ -986,6 +1005,12 @@ modules:
1005 or net.core.netdev_budget_usecs with work remaining over the last minute
1006 (this can be a cause for dropped packets)
1007 os: "linux"
1008 + - name: 10min_netisr_backlog_exceeded
1009 + link: https://github.com/netdata/netdata/blob/master/health/health.d/softnet.conf
1010 + metric: system.softnet_stat
1011 + info: average number of drops in the last minute due to exceeded sysctl net.route.netisr_maxqlen
1012 + (this can be a cause for dropped packets)
1013 + os: "freebsd"
1014 metrics:
1015 folding:
1016 title: Metrics
@@ -1092,6 +1117,22 @@ modules:
1117 info: percentage of estimated amount of RAM available for userspace processes,
1118 without causing swapping
1119 os: "linux"
1120 + - name: ram_available
1121 + link: https://github.com/netdata/netdata/blob/master/health/health.d/ram.conf
1122 + metric: mem.available
1123 + info: percentage of estimated amount of RAM available for userspace processes,
1124 + without causing swapping
1125 + os: "freebsd"
1126 + - name: used_swap
1127 + link: https://github.com/netdata/netdata/blob/master/health/health.d/swap.conf
1128 + metric: system.swap
1129 + info: swap memory utilization
1130 + os: "linux freebsd"
1131 + - name: 1hour_memory_hw_corrupted
1132 + link: https://github.com/netdata/netdata/blob/master/health/health.d/memory.conf
1133 + metric: mem.hwcorrupt
1134 + info: amount of memory corrupted due to a hardware failure
1135 + os: "linux"
1136 metrics:
1137 folding:
1138 title: Metrics
@@ -1677,6 +1718,11 @@ modules:
1718 metric: system.ipc_semaphores
1719 info: IPC semaphore utilization
1720 os: "linux"
1721 + - name: semaphore_arrays_used
1722 + link: https://github.com/netdata/netdata/blob/master/health/health.d/ipc.conf
1723 + metric: system.ipc_semaphore_arrays
1724 + info: IPC semaphore arrays utilization
1725 + os: "linux"
1726 metrics:
1727 folding:
1728 title: Metrics
@@ -1779,19 +1825,28 @@ modules:
1825 problems:
1826 list: []
1827 alerts:
1828 + - name: 10min_disk_backlog
1829 + link: https://github.com/netdata/netdata/blob/master/health/health.d/disks.conf
1830 + metric: disk.backlog
1831 + info: average backlog size of the ${label:device} disk over the last 10 minutes
1832 + os: "linux"
1833 - name: 10min_disk_utilization
1834 link: https://github.com/netdata/netdata/blob/master/health/health.d/disks.conf
1835 metric: disk.util
1836 info: average percentage of time ${label:device} disk was busy over the last
1837 10 minutes
1838 os: "linux freebsd"
1839 + - name: bcache_cache_dirty
1840 + link: https://github.com/netdata/netdata/blob/master/health/health.d/bcache.conf
1841 + metric: disk.bcache_cache_alloc
1842 + info: percentage of cache space used for dirty data and metadata (this usually
1843 + means your SSD cache is too small)
1844 - name: bcache_cache_errors
1845 link: https://github.com/netdata/netdata/blob/master/health/health.d/bcache.conf
1846 metric: disk.bcache_cache_read_races
1847 info: number of times data was read from the cache, the bucket was reused
1848 and invalidated in the last 10 minutes (when this occurs the data is reread
1849 from the backing device)
1794 - os: "freebsd"
1850 metrics:
1851 folding:
1852 title: Metrics
@@ -2051,19 +2106,20 @@ modules:
2106 link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf
2107 metric: md.disks
2108 info: number of seconds since the last successful data collection
2054 - os: "*"
2109 - name: mdstat_disks
2110 link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf
2111 metric: md.disks
2112 info: number of devices in the down state for the ${label:device} ${label:raid_level}
2113 array. Any number > 0 indicates that the array is degraded.
2060 - os: "*"
2114 - name: mdstat_mismatch_cnt
2115 link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf
2116 metric: md.mismatch_cnt
2117 info: number of unsynchronized blocks for the ${label:device} ${label:raid_level}
2118 array
2066 - os: "*"
2119 + - name: mdstat_nonredundant_last_collected
2120 + link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf
2121 + metric: md.nonredundant
2122 + info: number of seconds since the last successful data collection
2123 metrics:
2124 folding:
2125 title: Metrics
@@ -2231,6 +2287,13 @@ modules:
2287 info: average number of packets received by the network interface ${label:device}
2288 over the last minute
2289 os: "linux freebsd"
2290 + - name: 10s_received_packets_storm
2291 + link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2292 + metric: net.packets
2293 + info: ratio of average number of received packets for the network interface
2294 + ${label:device} over the last 10 seconds, compared to the rate over the
2295 + last minute
2296 + os: "linux freebsd"
2297 - name: interface_inbound_errors
2298 link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2299 metric: net.errors
@@ -2708,6 +2771,11 @@ modules:
2771 info: average number of dropped packets in the TCP accept queue over the last
2772 minute
2773 os: "linux"
2774 + - name: tcp_connections
2775 + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_conn.conf
2776 + metric: ipv4.tcpsock
2777 + info: IPv4 TCP connections utilization
2778 + os: "linux"
2779 - name: 1m_ipv4_tcp_resets_sent
2780 link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf
2781 metric: ipv4.tcphandshake
@@ -2725,11 +2793,23 @@ modules:
2793 metric: ipv4.tcphandshake
2794 info: average number of received TCP RESETS over the last minute
2795 os: "linux freebsd"
2796 + - name: 10s_ipv4_tcp_resets_received
2797 + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf
2798 + metric: ipv4.tcphandshake
2799 + info: average number of received TCP RESETS over the last 10 seconds. This
2800 + can be an indication that a service this host needs has crashed. Netdata
2801 + will not send a clear notification for this alarm.
2802 + os: "linux freebsd"
2803 - name: 1m_ipv4_udp_receive_buffer_errors
2804 link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf
2805 metric: ipv4.udperrors
2806 info: average number of UDP receive buffer errors over the last minute
2807 os: "linux freebsd"
2808 + - name: 1m_ipv4_udp_send_buffer_errors
2809 + link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf
2810 + metric: ipv4.udperrors
2811 + info: average number of UDP send buffer errors over the last minute
2812 + os: "linux"
2813 metrics:
2814 folding:
2815 title: Metrics
@@ -3264,7 +3344,17 @@ modules:
3344 troubleshooting:
3345 problems:
3346 list: []
3267 - alerts: []
3347 + alerts:
3348 + - name: tcp_orphans
3349 + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_orphans.conf
3350 + metric: ipv4.sockstat_tcp_sockets
3351 + info: orphan IPv4 TCP sockets utilization
3352 + os: "linux"
3353 + - name: tcp_memory
3354 + link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_mem.conf
3355 + metric: ipv4.sockstat_tcp_mem
3356 + info: TCP memory utilization
3357 + os: "linux"
3358 metrics:
3359 folding:
3360 title: Metrics
@@ -3902,7 +3992,12 @@ modules:
3992 troubleshooting:
3993 problems:
3994 list: []
3905 - alerts: []
3995 + alerts:
3996 + - name: netfilter_conntrack_full
3997 + link: https://github.com/netdata/netdata/blob/master/health/health.d/netfilter.conf
3998 + metric: netfilter.conntrack_sockets
3999 + info: netfilter connection tracker table size utilization
4000 + os: "linux"
4001 metrics:
4002 folding:
4003 title: Metrics
@@ -4106,7 +4201,10 @@ modules:
4201 link: https://github.com/netdata/netdata/blob/master/health/health.d/zfs.conf
4202 metric: zfspool.state
4203 info: ZFS pool ${label:pool} state is degraded
4109 - os: "*"
4204 + - name: zfs_pool_state_crit
4205 + link: https://github.com/netdata/netdata/blob/master/health/health.d/zfs.conf
4206 + metric: zfspool.state
4207 + info: ZFS pool ${label:pool} state is faulted or unavail
4208 metrics:
4209 folding:
4210 title: Metrics
@@ -4191,7 +4289,6 @@ modules:
4289 link: https://github.com/netdata/netdata/blob/master/health/health.d/zfs.conf
4290 metric: zfs.memory_ops
4291 info: number of times ZFS had to limit the ARC growth in the last 10 minutes
4194 - os: "*"
4292 metrics:
4293 folding:
4294 title: Metrics
@@ -4490,6 +4587,11 @@ modules:
4587 metric: btrfs.device_errors
4588 info: number of encountered BTRFS corruption errors
4589 os: "*"
4590 + - name: btrfs_device_generation_errors
4591 + link: https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf
4592 + metric: btrfs.device_errors
4593 + info: number of encountered BTRFS generation errors
4594 + os: "*"
4595 metrics:
4596 folding:
4597 title: Metrics
@@ -4632,7 +4734,12 @@ modules:
4734 troubleshooting:
4735 problems:
4736 list: []
4635 - alerts: []
4737 + alerts:
4738 + - name: linux_power_supply_capacity
4739 + link: |
4740 + https://github.com/netdata/netdata/blob/master/health/health.d/linux_power_supply.conf
4741 + metric: powersupply.capacity
4742 + info: percentage of remaining power supply capacity
4743 metrics:
4744 folding:
4745 title: Metrics
collectors/python.d.plugin/adaptec_raid/metadata.yaml
+4 -1
@@ -57,7 +57,10 @@ alerts:
57 link: https://github.com/netdata/netdata/blob/master/health/health.d/adaptec_raid.conf
58 metric: adaptec_raid.ld_status
59 info: logical device status is failed or degraded
60 - os: "linux"
60 + - name: adaptec_raid_pd_state
61 + link: https://github.com/netdata/netdata/blob/master/health/health.d/adaptec_raid.conf
62 + metric: adaptec_raid.pd_state
63 + info: physical device state is not online
64 metrics:
65 folding:
66 title: Metrics
collectors/python.d.plugin/anomalies/metadata.yaml
+4 -1
@@ -57,7 +57,10 @@ alerts:
57 link: https://github.com/netdata/netdata/blob/master/health/health.d/anomalies.conf
58 metric: anomalies.probability
59 info: average anomaly probability over the last 2 minutes
60 - os: "linux"
60 + - name: anomalies_anomaly_flags
61 + link: https://github.com/netdata/netdata/blob/master/health/health.d/anomalies.conf
62 + metric: anomalies.anomaly
63 + info: number of anomalies in the last 2 minutes
64 metrics:
65 folding:
66 title: Metrics
collectors/python.d.plugin/beanstalk/metadata.yaml
-1
@@ -59,7 +59,6 @@ alerts:
59 info: number of buried jobs across all tubes. You need to manually kick them so
60 they can be processed. Presence of buried jobs in a tube does not affect new
61 jobs.
62 - os: "freebsd"
62 metrics:
63 folding:
64 title: Metrics
collectors/python.d.plugin/bind_rndc/metadata.yaml
+5 -1
@@ -52,7 +52,11 @@ setup:
52 troubleshooting:
53 problems:
54 list: []
55 -alerts: []
55 +alerts:
56 + - name: bind_rndc_stats_file_size
57 + link: https://github.com/netdata/netdata/blob/master/health/health.d/bind_rndc.conf
58 + metric: bind_rndc.stats_size
59 + info: BIND statistics-file size
60 metrics:
61 folding:
62 title: Metrics
collectors/python.d.plugin/boinc/metadata.yaml
+5
@@ -58,6 +58,11 @@ alerts:
58 metric: boinc.tasks
59 info: average number of total tasks over the last 10 minutes
60 os: "*"
61 + - name: boinc_active_tasks
62 + link: https://github.com/netdata/netdata/blob/master/health/health.d/boinc.conf
63 + metric: boinc.tasks
64 + info: average number of active tasks over the last 10 minutes
65 + os: "*"
66 - name: boinc_compute_errors
67 link: https://github.com/netdata/netdata/blob/master/health/health.d/boinc.conf
68 metric: boinc.states
collectors/python.d.plugin/ceph/metadata.yaml
+5 -1
@@ -52,7 +52,11 @@ setup:
52 troubleshooting:
53 problems:
54 list: []
55 -alerts: []
55 +alerts:
56 + - name: ceph_cluster_space_usage
57 + link: https://github.com/netdata/netdata/blob/master/health/health.d/ceph.conf
58 + metric: ceph.general_usage
59 + info: cluster disk space utilization
60 metrics:
61 folding:
62 title: Metrics
collectors/python.d.plugin/gearman/metadata.yaml
+5 -1
@@ -52,7 +52,11 @@ setup:
52 troubleshooting:
53 problems:
54 list: []
55 -alerts: []
55 +alerts:
56 + - name: gearman_workers_queued
57 + link: https://github.com/netdata/netdata/blob/master/health/health.d/gearman.conf
58 + metric: gearman.single_job
59 + info: average number of queued jobs over the last 10 minutes
60 metrics:
61 folding:
62 title: Metrics
collectors/python.d.plugin/haproxy/metadata.yaml
+4 -1
@@ -57,7 +57,10 @@ alerts:
57 link: https://github.com/netdata/netdata/blob/master/health/health.d/haproxy.conf
58 metric: haproxy_hs.down
59 info: average number of failed haproxy backend servers over the last 10 seconds
60 - os: "linux freebsd"
60 + - name: haproxy_backend_status
61 + link: https://github.com/netdata/netdata/blob/master/health/health.d/haproxy.conf
62 + metric: haproxy_hb.down
63 + info: average number of failed haproxy backends over the last 10 seconds
64 metrics:
65 folding:
66 title: Metrics
collectors/python.d.plugin/ipfs/metadata.yaml
+5 -1
@@ -52,7 +52,11 @@ setup:
52 troubleshooting:
53 problems:
54 list: []
55 -alerts: []
55 +alerts:
56 + - name: ipfs_datastore_usage
57 + link: https://github.com/netdata/netdata/blob/master/health/health.d/ipfs.conf
58 + metric: ipfs.repo_size
59 + info: IPFS datastore utilization
60 metrics:
61 folding:
62 title: Metrics
collectors/python.d.plugin/megacli/metadata.yaml
+4 -4
@@ -57,23 +57,23 @@ alerts:
57 link: https://github.com/netdata/netdata/blob/master/health/health.d/megacli.conf
58 metric: megacli.adapter_degraded
59 info: 'adapter is in the degraded state (0: false, 1: true)'
60 - os: "linux"
60 - name: megacli_pd_media_errors
61 link: https://github.com/netdata/netdata/blob/master/health/health.d/megacli.conf
62 metric: megacli.pd_media_error
63 info: number of physical drive media errors
65 - os: "linux"
64 - name: megacli_pd_predictive_failures
65 link: https://github.com/netdata/netdata/blob/master/health/health.d/megacli.conf
66 metric: megacli.pd_predictive_failure
67 info: number of physical drive predictive failures
70 - os: "linux"
68 - name: megacli_bbu_relative_charge
69 link: https://github.com/netdata/netdata/blob/master/health/health.d/megacli.conf
70 metric: megacli.bbu_relative_charge
71 info: average battery backup unit (BBU) relative state of charge over the last
72 10 seconds
76 - os: "linux"
73 + - name: megacli_bbu_cycle_count
74 + link: https://github.com/netdata/netdata/blob/master/health/health.d/megacli.conf
75 + metric: megacli.bbu_cycle_count
76 + info: average battery backup unit (BBU) charge cycles count over the last 10 seconds
77 metrics:
78 folding:
79 title: Metrics
collectors/python.d.plugin/memcached/metadata.yaml
+5 -2
@@ -57,13 +57,16 @@ alerts:
57 link: https://github.com/netdata/netdata/blob/master/health/health.d/memcached.conf
58 metric: memcached.cache
59 info: cache memory utilization
60 - os: "freebsd"
60 - name: memcached_cache_fill_rate
61 link: https://github.com/netdata/netdata/blob/master/health/health.d/memcached.conf
62 metric: memcached.cache
63 info: average rate the cache fills up (positive), or frees up (negative) space
64 over the last hour
66 - os: "freebsd"
65 + - name: memcached_out_of_cache_space_time
66 + link: https://github.com/netdata/netdata/blob/master/health/health.d/memcached.conf
67 + metric: memcached.cache
68 + info: estimated time the cache will run out of space if the system continues to
69 + add data at the same rate as the past hour
70 metrics:
71 folding:
72 title: Metrics
collectors/python.d.plugin/retroshare/metadata.yaml
+5 -1
@@ -52,7 +52,11 @@ setup:
52 troubleshooting:
53 problems:
54 list: []
55 -alerts: []
55 +alerts:
56 + - name: retroshare_dht_working
57 + link: https://github.com/netdata/netdata/blob/master/health/health.d/retroshare.conf
58 + metric: retroshare.dht
59 + info: number of DHT peers
60 metrics:
61 folding:
62 title: Metrics
collectors/python.d.plugin/riakkv/metadata.yaml
+4 -5
@@ -58,32 +58,31 @@ alerts:
58 metric: riak.kv.latency.get
59 info: average time between reception of client GET request and subsequent response
60 to client over the last hour
61 - os: "*"
61 - name: riakkv_kv_get_slow
62 link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
63 metric: riak.kv.latency.get
64 info: average time between reception of client GET request and subsequent response
65 to the client over the last 3 minutes, compared to the average over the last
66 hour
68 - os: "*"
67 - name: riakkv_1h_kv_put_mean_latency
68 link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
69 metric: riak.kv.latency.put
70 info: average time between reception of client PUT request and subsequent response
71 to the client over the last hour
74 - os: "*"
72 - name: riakkv_kv_put_slow
73 link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
74 metric: riak.kv.latency.put
75 info: average time between reception of client PUT request and subsequent response
76 to the client over the last 3 minutes, compared to the average over the last
77 hour
81 - os: "*"
78 + - name: riakkv_vm_high_process_count
79 + link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
80 + metric: riak.vm
81 + info: number of processes running in the Erlang VM
82 - name: riakkv_list_keys_active
83 link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
84 metric: riak.core.fsm_active
85 info: number of currently running list keys finite state machines
86 - os: "*"
86 metrics:
87 folding:
88 title: Metrics
collectors/timex.plugin/metadata.yaml
+7 -1
@@ -52,7 +52,13 @@ setup:
52 troubleshooting:
53 problems:
54 list: []
55 -alerts: []
55 +alerts:
56 + - name: system_clock_sync_state
57 + link: https://github.com/netdata/netdata/blob/master/health/health.d/timex.conf
58 + metric: system.clock_sync_state
59 + info: when set to 0, the system kernel believes the system clock is not properly
60 + synchronized to a reliable server
61 + os: "linux"
62 metrics:
63 folding:
64 title: Metrics