diff options
Diffstat (limited to 'collectors/proc.plugin/multi_metadata.yaml')
-rw-r--r-- | collectors/proc.plugin/multi_metadata.yaml | 143 |
1 files changed, 34 insertions, 109 deletions
diff --git a/collectors/proc.plugin/multi_metadata.yaml b/collectors/proc.plugin/multi_metadata.yaml index 3ca89969cf..e78ec795c1 100644 --- a/collectors/proc.plugin/multi_metadata.yaml +++ b/collectors/proc.plugin/multi_metadata.yaml @@ -3,7 +3,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/stat - alternative_monitored_instances: [] monitored_instance: name: proc /proc/stat link: '' @@ -58,8 +57,7 @@ modules: - 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 iowait, - nice and steal) + info: average CPU utilization over the last 10 minutes (excluding iowait, nice and steal) os: "linux" - name: 10min_cpu_iowait link: https://github.com/netdata/netdata/blob/master/health/health.d/cpu.conf @@ -175,7 +173,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/sys/kernel/random/entropy_avail - alternative_monitored_instances: [] monitored_instance: name: proc /proc/sys/kernel/random/entropy_avail link: '' @@ -252,7 +249,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/uptime - alternative_monitored_instances: [] monitored_instance: name: proc /proc/uptime link: '' @@ -324,7 +320,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/vmstat - alternative_monitored_instances: [] monitored_instance: name: proc /proc/vmstat link: '' @@ -518,7 +513,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/interrupts - alternative_monitored_instances: [] monitored_instance: name: proc /proc/interrupts link: '' @@ -602,7 +596,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/loadavg - alternative_monitored_instances: [] monitored_instance: name: proc /proc/loadavg link: '' @@ -706,7 +699,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/pressure - alternative_monitored_instances: [] monitored_instance: name: proc /proc/pressure link: '' @@ -856,7 +848,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/softirqs - alternative_monitored_instances: [] monitored_instance: name: proc /proc/softirqs link: '' @@ -940,7 +931,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/softnet_stat - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/softnet_stat link: '' @@ -995,21 +985,17 @@ modules: - name: 1min_netdev_backlog_exceeded link: https://github.com/netdata/netdata/blob/master/health/health.d/softnet.conf metric: system.softnet_stat - info: average number of dropped packets in the last minute due to exceeded - net.core.netdev_max_backlog + info: average number of dropped packets in the last minute due to exceeded net.core.netdev_max_backlog os: "linux" - name: 1min_netdev_budget_ran_outs link: https://github.com/netdata/netdata/blob/master/health/health.d/softnet.conf metric: system.softnet_stat - info: average number of times ksoftirq ran out of sysctl net.core.netdev_budget - or net.core.netdev_budget_usecs with work remaining over the last minute - (this can be a cause for dropped packets) + info: average number of times ksoftirq ran out of sysctl net.core.netdev_budget 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) + 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: @@ -1049,7 +1035,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/meminfo - alternative_monitored_instances: [] monitored_instance: name: proc /proc/meminfo link: '' @@ -1114,14 +1099,12 @@ modules: - 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 + 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 + 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 @@ -1224,7 +1207,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/pagetypeinfo - alternative_monitored_instances: [] monitored_instance: name: proc /proc/pagetypeinfo link: '' @@ -1312,7 +1294,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /sys/devices/system/edac/mc - alternative_monitored_instances: [] monitored_instance: name: proc /sys/devices/system/edac/mc link: '' @@ -1400,7 +1381,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /sys/devices/system/node - alternative_monitored_instances: [] monitored_instance: name: proc /sys/devices/system/node link: '' @@ -1479,7 +1459,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /sys/kernel/mm/ksm - alternative_monitored_instances: [] monitored_instance: name: proc /sys/kernel/mm/ksm link: '' @@ -1567,7 +1546,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /sys/block/zram - alternative_monitored_instances: [] monitored_instance: name: proc /sys/block/zram link: '' @@ -1661,7 +1639,6 @@ modules: - meta: plugin_name: proc.plugin module_name: ipc - alternative_monitored_instances: [] monitored_instance: name: proc ipc link: '' @@ -1773,7 +1750,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/diskstats - alternative_monitored_instances: [] monitored_instance: name: proc /proc/diskstats link: '' @@ -1833,20 +1809,16 @@ modules: - 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 + 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) + 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) + 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) metrics: folding: title: Metrics @@ -2050,7 +2022,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/mdstat - alternative_monitored_instances: [] monitored_instance: name: proc /proc/mdstat link: '' @@ -2109,13 +2080,11 @@ modules: - 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. + 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. - 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 + info: number of unsynchronized blocks for the ${label:device} ${label:raid_level} array - name: mdstat_nonredundant_last_collected link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf metric: md.nonredundant @@ -2188,7 +2157,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/dev - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/dev link: '' @@ -2248,81 +2216,67 @@ modules: - name: 1m_received_traffic_overflow link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.net - info: average inbound utilization for the network interface ${label:device} - over the last minute + info: average inbound utilization for the network interface ${label:device} over the last minute os: "linux" - name: 1m_sent_traffic_overflow link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.net - info: average outbound utilization for the network interface ${label:device} - over the last minute + info: average outbound utilization for the network interface ${label:device} over the last minute os: "linux" - name: inbound_packets_dropped_ratio link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.packets - info: ratio of inbound dropped packets for the network interface ${label:device} - over the last 10 minutes + info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes os: "linux" - name: outbound_packets_dropped_ratio link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.packets - info: ratio of outbound dropped packets for the network interface ${label:device} - over the last 10 minutes + info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes os: "linux" - name: wifi_inbound_packets_dropped_ratio link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.packets - info: ratio of inbound dropped packets for the network interface ${label:device} - over the last 10 minutes + info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes os: "linux" - name: wifi_outbound_packets_dropped_ratio link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.packets - info: ratio of outbound dropped packets for the network interface ${label:device} - over the last 10 minutes + info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes os: "linux" - name: 1m_received_packets_rate link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.packets - info: average number of packets received by the network interface ${label:device} - over the last minute + 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 + 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 - info: number of inbound errors for the network interface ${label:device} in - the last 10 minutes + info: number of inbound errors for the network interface ${label:device} in the last 10 minutes os: "freebsd" - name: interface_outbound_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.errors - info: number of outbound errors for the network interface ${label:device} - in the last 10 minutes + info: number of outbound errors for the network interface ${label:device} in the last 10 minutes os: "freebsd" - name: inbound_packets_dropped link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.drops - info: number of inbound dropped packets for the network interface ${label:device} - in the last 10 minutes + info: number of inbound dropped packets for the network interface ${label:device} in the last 10 minutes os: "linux" - name: outbound_packets_dropped link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.drops - info: number of outbound dropped packets for the network interface ${label:device} - in the last 10 minutes + info: number of outbound dropped packets for the network interface ${label:device} in the last 10 minutes os: "linux" - name: 10min_fifo_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.fifo - info: number of FIFO errors for the network interface ${label:device} in the - last 10 minutes + info: number of FIFO errors for the network interface ${label:device} in the last 10 minutes os: "linux" metrics: folding: @@ -2443,7 +2397,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/wireless - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/wireless link: '' @@ -2513,31 +2466,25 @@ modules: dimensions: - name: status - name: wireless.link_quality - description: Overall quality of the link. This is an aggregate value, - and depends on the driver and hardware. + description: Overall quality of the link. This is an aggregate value, and depends on the driver and hardware. unit: "value" chart_type: line dimensions: - name: link_quality - name: wireless.signal_level - description: The signal level is the wireless signal power level received - by the wireless client. The closer the value is to 0, the stronger - the signal. + description: The signal level is the wireless signal power level received by the wireless client. The closer the value is to 0, the stronger the signal. unit: "dBm" chart_type: line dimensions: - name: signal_level - name: wireless.noise_level - description: The noise level indicates the amount of background noise - in your environment. The closer the value to 0, the greater the noise - level. + description: The noise level indicates the amount of background noise in your environment. The closer the value to 0, the greater the noise level. unit: "dBm" chart_type: line dimensions: - name: noise_level - name: wireless.discarded_packets - description: Packet discarded in the wireless adapter due to wireless - specific problems. + description: Packet discarded in the wireless adapter due to wireless specific problems. unit: "packets/s" chart_type: line dimensions: @@ -2555,7 +2502,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /sys/class/infiniband - alternative_monitored_instances: [] monitored_instance: name: proc /sys/class/infiniband link: '' @@ -2696,7 +2642,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/netstat - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/netstat link: '' @@ -2751,14 +2696,12 @@ modules: - name: 1m_tcp_syn_queue_drops link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_listen.conf metric: ip.tcp_syn_queue - info: average number of SYN requests was dropped due to the full TCP SYN queue - over the last minute (SYN cookies were not enabled) + info: average number of SYN requests was dropped due to the full TCP SYN queue over the last minute (SYN cookies were not enabled) os: "linux" - name: 1m_tcp_syn_queue_cookies link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_listen.conf metric: ip.tcp_syn_queue - info: average number of sent SYN cookies due to the full TCP SYN queue over - the last minute + info: average number of sent SYN cookies due to the full TCP SYN queue over the last minute os: "linux" - name: 1m_tcp_accept_queue_overflows link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_listen.conf @@ -2768,8 +2711,7 @@ modules: - name: 1m_tcp_accept_queue_drops link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_listen.conf metric: ip.tcp_accept_queue - info: average number of dropped packets in the TCP accept queue over the last - minute + 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 @@ -2784,9 +2726,7 @@ modules: - name: 10s_ipv4_tcp_resets_sent link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf metric: ipv4.tcphandshake - info: average number of sent TCP RESETS over the last 10 seconds. This can - indicate a port scan, or that a service running on this host has crashed. - Netdata will not send a clear notification for this alarm. + info: average number of sent TCP RESETS over the last 10 seconds. This can indicate a port scan, or that a service running on this host has crashed. Netdata will not send a clear notification for this alarm. os: "linux" - name: 1m_ipv4_tcp_resets_received link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf @@ -2796,9 +2736,7 @@ modules: - 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. + 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 @@ -3293,7 +3231,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/sockstat - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/sockstat link: '' @@ -3426,7 +3363,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/sockstat6 - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/sockstat6 link: '' @@ -3522,7 +3458,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/ip_vs_stats - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/ip_vs_stats link: '' @@ -3608,7 +3543,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/rpc/nfs - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/rpc/nfs link: '' @@ -3707,7 +3641,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/rpc/nfsd - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/rpc/nfsd link: '' @@ -3839,7 +3772,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/sctp/snmp - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/sctp/snmp link: '' @@ -3941,7 +3873,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/stat/nf_conntrack - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/stat/nf_conntrack link: '' @@ -4059,7 +3990,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/net/stat/synproxy - alternative_monitored_instances: [] monitored_instance: name: proc /proc/net/stat/synproxy link: '' @@ -4145,7 +4075,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/spl/kstat/zfs - alternative_monitored_instances: [] monitored_instance: name: proc /proc/spl/kstat/zfs link: '' @@ -4233,7 +4162,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /proc/spl/kstat/zfs/arcstats - alternative_monitored_instances: [] monitored_instance: name: proc /proc/spl/kstat/zfs/arcstats link: '' @@ -4495,7 +4423,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /sys/fs/btrfs - alternative_monitored_instances: [] monitored_instance: name: proc /sys/fs/btrfs link: '' @@ -4683,7 +4610,6 @@ modules: - meta: plugin_name: proc.plugin module_name: /sys/class/power_supply - alternative_monitored_instances: [] monitored_instance: name: proc /sys/class/power_supply link: '' @@ -4736,8 +4662,7 @@ modules: list: [] alerts: - name: linux_power_supply_capacity - link: | - https://github.com/netdata/netdata/blob/master/health/health.d/linux_power_supply.conf + 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: |