ba0992f3a · cryptotaxi247/netdata-1

health/health.d/anomalies.conf

+2 -2

@@ -5,7 +5,7 @@ template: anomalies_anomaly_probabilities

5 lookup: average -2m foreach *

6 every: 1m

7 warn: $this > 50

8 - info: average anomaly probability > 50% for last 2 minutes

8 + info: average anomaly probability over the last 2 minutes

9

10 # raise a warning alarm if an anomaly flag is consistently firing

11

@@ -14,4 +14,4 @@ template: anomalies_anomaly_flags

14 lookup: sum -2m foreach *

15 every: 1m

16 warn: $this > 10

17 - info: count of anomalies > 10 for last 2 minutes

17 + info: number of anomalies in the last 2 minutes

health/health.d/apcupsd.conf

+2 -2

@@ -10,7 +10,7 @@ template: apcupsd_10min_ups_load

10 warn: $this > (($status >= $WARNING) ? (70) : (80))

11 crit: $this > (($status == $CRITICAL) ? (85) : (95))

12 delay: down 10m multiplier 1.5 max 1h

13 - info: average UPS load for the last 10 minutes

13 + info: average UPS load over the last 10 minutes

14 to: sitemgr

15

16 # Discussion in https://github.com/netdata/netdata/pull/3928:

@@ -25,7 +25,7 @@ template: apcupsd_ups_charge

25 warn: $this < 100

26 crit: $this < (($status == $CRITICAL) ? (60) : (50))

27 delay: down 10m multiplier 1.5 max 1h

28 - info: current UPS charge, averaged over the last 60 seconds to reduce measurement errors

28 + info: average UPS charge over the last minute

29 to: sitemgr

30

31 template: apcupsd_last_collected_secs

health/health.d/backend.conf

+1 -24

@@ -6,7 +6,7 @@

6 every: 1m

7 warn: $this > 0

8 delay: down 5m multiplier 1.5 max 1h

9 - info: The backends subsystem is deprecated and will be removed soon. Migrate your configuration to exporting.conf.

9 + info: the backends subsystem is deprecated and will be removed soon. Migrate your configuration to exporting.conf.

10 to: sysadmin

11

12 # make sure we are sending data to backend

@@ -31,26 +31,3 @@

31 delay: down 5m multiplier 1.5 max 1h

32 info: percentage of metrics sent to the backend server

33 to: dba

34 -

35 - alarm: backend_metrics_lost

36 - on: netdata.backend_metrics

37 - units: metrics

38 - calc: abs($lost)

39 - every: 10s

40 - crit: ($this != 0) || ($status == $CRITICAL && abs($sent) == 0)

41 - delay: down 5m multiplier 1.5 max 1h

42 - info: number of metrics lost due to repeating failures to contact the backend server

43 - to: dba

44 -

45 -

46 -# this chart has been removed from netdata

47 -# alarm: backend_slow

48 -# on: netdata.backend_latency

49 -# units: %

50 -# calc: $latency * 100 / ($update_every * 1000)

51 -# every: 10s

52 -# warn: $this > 50

53 -# crit: $this > 100

54 -# delay: down 5m multiplier 1.5 max 1h

55 -# info: the percentage of time between iterations needed by the backend time to process the data sent by netdata

56 -# to: dba

health/health.d/bcache.conf

+5 -2

@@ -6,7 +6,9 @@ template: bcache_cache_errors

6 every: 1m

7 warn: $this > 0

8 delay: up 2m down 1h multiplier 1.5 max 2h

9 - info: the number of times the data was being read from the cache, the bucket was reused and invalidated, during the last 10 mins (when this occurs the data is reread from the backing device)

9 + info: number of times data was read from the cache, \

10 + the bucket was reused and invalidated in the last 10 minutes \

11 + (when this occurs the data is reread from the backing device)

12 to: sysadmin

13

14 template: bcache_cache_dirty

@@ -17,5 +19,6 @@ template: bcache_cache_dirty

19 warn: $this > ( ($status >= $WARNING ) ? ( 70 ) : ( 90 ) )

20 crit: $this > ( ($status == $CRITICAL) ? ( 90 ) : ( 95 ) )

21 delay: up 1m down 1h multiplier 1.5 max 2h

20 - info: the percentage of cache space used for dirty and metadata (this usually means your SSD cache is too small)

22 + info: percentage of cache space used for dirty data and metadata \

23 + (this usually means your SSD cache is too small)

24 to: sysadmin

health/health.d/beanstalkd.conf

+3 -1

@@ -8,7 +8,9 @@ template: beanstalk_server_buried_jobs

8 warn: $this > 0

9 crit: $this > 10

10 delay: up 0 down 5m multiplier 1.2 max 1h

11 - info: the number of buried jobs aggregated across all tubes

11 + info: number of buried jobs across all tubes. \

12 + You need to manually kick them so they can be processed. \

13 + Presence of buried jobs in a tube does not affect new jobs.

14 to: sysadmin

15

16 # get the number of buried jobs per queue

health/health.d/bind_rndc.conf

+2 -2

@@ -1,9 +1,9 @@

1 - template: bind_rndc_stats_file_size

1 +template: bind_rndc_stats_file_size

2 on: bind_rndc.stats_size

3 units: megabytes

4 every: 60

5 calc: $stats_size

6 warn: $this > 512

7 crit: $this > 1024

8 - info: Bind stats file is very large! Consider to create logrotate conf file for it!

8 + info: BIND statistics-file size

9 to: sysadmin

health/health.d/boinc.conf

+4 -4

@@ -12,7 +12,7 @@ families: *

12 warn: $this > 0

13 crit: $this > 1

14 delay: up 1m down 5m multiplier 1.5 max 1h

15 - info: the total number of compute errors over the past 10 minutes

15 + info: average number of compute errors over the last 10 minutes

16 to: sysadmin

17

18 # Warn on lots of upload errors

@@ -27,7 +27,7 @@ families: *

27 warn: $this > 0

28 crit: $this > 1

29 delay: up 1m down 5m multiplier 1.5 max 1h

30 - info: the average number of failed uploads over the past 10 minutes

30 + info: average number of failed uploads over the last 10 minutes

31 to: sysadmin

32

33 # Warn on the task queue being empty

@@ -42,7 +42,7 @@ families: *

42 warn: $this < 1

43 crit: $this < 0.1

44 delay: up 5m down 10m multiplier 1.5 max 1h

45 - info: the total number of locally available tasks

45 + info: average number of total tasks over the last 10 minutes

46 to: sysadmin

47

48 # Warn on no active tasks with a non-empty queue

@@ -58,5 +58,5 @@ families: *

58 warn: $this < 1

59 crit: $this < 0.1

60 delay: up 5m down 10m multiplier 1.5 max 1h

61 - info: the total number of active tasks

61 + info: average number of active tasks over the last 10 minutes

62 to: sysadmin

health/health.d/btrfs.conf

+4 -5

@@ -10,7 +10,7 @@ families: *

10 warn: $this > (($status >= $WARNING) ? (90) : (95))

11 crit: $this > (($status == $CRITICAL) ? (95) : (98))

12 delay: up 1m down 15m multiplier 1.5 max 1h

13 - info: the percentage of allocated BTRFS physical disk space

13 + info: percentage of allocated BTRFS physical disk space

14 to: sysadmin

15

16 template: btrfs_data

@@ -24,7 +24,7 @@ families: *

24 warn: $this > (($status >= $WARNING) ? (90) : (95)) && $btrfs_allocated > 98

25 crit: $this > (($status == $CRITICAL) ? (95) : (98)) && $btrfs_allocated > 98

26 delay: up 1m down 15m multiplier 1.5 max 1h

27 - info: the percentage of used BTRFS data space

27 + info: utilization of BTRFS data space

28 to: sysadmin

29

30 template: btrfs_metadata

@@ -38,7 +38,7 @@ families: *

38 warn: $this > (($status >= $WARNING) ? (90) : (95)) && $btrfs_allocated > 98

39 crit: $this > (($status == $CRITICAL) ? (95) : (98)) && $btrfs_allocated > 98

40 delay: up 1m down 15m multiplier 1.5 max 1h

41 - info: the percentage of used BTRFS metadata space

41 + info: utilization of BTRFS metadata space

42 to: sysadmin

43

44 template: btrfs_system

@@ -52,6 +52,5 @@ families: *

52 warn: $this > (($status >= $WARNING) ? (90) : (95)) && $btrfs_allocated > 98

53 crit: $this > (($status == $CRITICAL) ? (95) : (98)) && $btrfs_allocated > 98

54 delay: up 1m down 15m multiplier 1.5 max 1h

55 - info: the percentage of used BTRFS system space

55 + info: utilization of BTRFS system space

56 to: sysadmin

57 -

health/health.d/ceph.conf

+1 -1

@@ -8,5 +8,5 @@ template: ceph_cluster_space_usage

8 warn: $this > (($status >= $WARNING ) ? (85) : (90))

9 crit: $this > (($status == $CRITICAL) ? (90) : (98))

10 delay: down 5m multiplier 1.2 max 1h

11 - info: current ceph disk usage

11 + info: cluster disk space utilization

12 to: sysadmin

health/health.d/cgroups.conf

+2 -2

@@ -11,7 +11,7 @@ template: cgroup_10min_cpu_usage

11 warn: $this > (($status >= $WARNING) ? (75) : (85))

12 crit: $this > (($status == $CRITICAL) ? (85) : (95))

13 delay: down 15m multiplier 1.5 max 1h

14 - info: cpu utilization for the last 10 minutes

14 + info: average cgroup CPU utilization over the last 10 minutes

15 to: sysadmin

16

17 template: cgroup_ram_in_use

@@ -24,5 +24,5 @@ template: cgroup_ram_in_use

24 warn: $this > (($status >= $WARNING) ? (80) : (90))

25 crit: $this > (($status == $CRITICAL) ? (90) : (98))

26 delay: down 15m multiplier 1.5 max 1h

27 - info: RAM used by cgroup

27 + info: cgroup memory utilization

28 to: sysadmin

health/health.d/cockroachdb.conf

+3 -3

@@ -22,7 +22,7 @@ template: cockroachdb_used_storage_capacity

22 warn: $this > (($status >= $WARNING) ? (80) : (85))

23 crit: $this > (($status == $CRITICAL) ? (85) : (95))

24 delay: down 15m multiplier 1.5 max 1h

25 - info: entire disk usage percentage

25 + info: storage capacity utilization

26 to: dba

27

28 template: cockroachdb_used_usable_storage_capacity

@@ -33,7 +33,7 @@ template: cockroachdb_used_usable_storage_capacity

33 warn: $this > (($status >= $WARNING) ? (80) : (85))

34 crit: $this > (($status == $CRITICAL) ? (85) : (95))

35 delay: down 15m multiplier 1.5 max 1h

36 - info: usable space usage percentage

36 + info: storage usable space utilization

37 to: dba

38

39 # Replication

@@ -67,7 +67,7 @@ template: cockroachdb_open_file_descriptors_limit

67 every: 10s

68 warn: $this > 80

69 delay: down 15m multiplier 1.5 max 1h

70 - info: open file descriptors usage percentage

70 + info: open file descriptors utilization (against softlimit)

71 to: dba

72

73 # SQL

health/health.d/cpu.conf

+4 -4

@@ -11,7 +11,7 @@ template: 10min_cpu_usage

11 warn: $this > (($status >= $WARNING) ? (75) : (85))

12 crit: $this > (($status == $CRITICAL) ? (85) : (95))

13 delay: down 15m multiplier 1.5 max 1h

14 - info: average cpu utilization for the last 10 minutes (excluding iowait, nice and steal)

14 + info: average CPU utilization over the last 10 minutes (excluding iowait, nice and steal)

15 to: sysadmin

16

17 template: 10min_cpu_iowait

@@ -24,7 +24,7 @@ template: 10min_cpu_iowait

24 warn: $this > (($status >= $WARNING) ? (20) : (40))

25 crit: $this > (($status == $CRITICAL) ? (40) : (50))

26 delay: down 15m multiplier 1.5 max 1h

27 - info: average CPU wait I/O for the last 10 minutes

27 + info: average CPU iowait time over the last 10 minutes

28 to: sysadmin

29

30 template: 20min_steal_cpu

@@ -37,7 +37,7 @@ template: 20min_steal_cpu

37 warn: $this > (($status >= $WARNING) ? (5) : (10))

38 crit: $this > (($status == $CRITICAL) ? (20) : (30))

39 delay: down 1h multiplier 1.5 max 2h

40 - info: average CPU steal time for the last 20 minutes

40 + info: average CPU steal time over the last 20 minutes

41 to: sysadmin

42

43 ## FreeBSD

@@ -51,5 +51,5 @@ template: 10min_cpu_usage

51 warn: $this > (($status >= $WARNING) ? (75) : (85))

52 crit: $this > (($status == $CRITICAL) ? (85) : (95))

53 delay: down 15m multiplier 1.5 max 1h

54 - info: average cpu utilization for the last 10 minutes (excluding nice)

54 + info: average CPU utilization over the last 10 minutes (excluding nice)

55 to: sysadmin

health/health.d/dbengine.conf

+6 -4

@@ -10,7 +10,7 @@ lookup: sum -10m unaligned of fs_errors

10 every: 10s

11 crit: $this > 0

12 delay: down 15m multiplier 1.5 max 1h

13 - info: number of File-System errors dbengine came across the last 10 minutes (too many open files, wrong permissions etc)

13 + info: number of filesystem errors in the last 10 minutes (too many open files, wrong permissions, etc)

14 to: sysadmin

15

16 alarm: 10min_dbengine_global_io_errors

@@ -22,7 +22,7 @@ lookup: sum -10m unaligned of io_errors

22 every: 10s

23 crit: $this > 0

24 delay: down 1h multiplier 1.5 max 3h

25 - info: number of IO errors dbengine came across the last 10 minutes (CRC errors, out of space, bad disk etc)

25 + info: number of IO errors in the last 10 minutes (CRC errors, out of space, bad disk, etc)

26 to: sysadmin

27

28 alarm: 10min_dbengine_global_flushing_warnings

@@ -34,7 +34,8 @@ lookup: sum -10m unaligned of pg_cache_over_half_dirty_events

34 every: 10s

35 warn: $this > 0

36 delay: down 1h multiplier 1.5 max 3h

37 - info: number of times in the last 10 minutes that dbengine dirty pages were over 50% of the instance's page cache, metric data at risk of not being stored in the database, please reduce disk load or use faster disks

37 + info: number of times when dbengine dirty pages were over 50% of the instance's page cache in the last 10 minutes. \

38 + Metric data are at risk of not being stored in the database. To remedy, reduce disk load or use faster disks.

39 to: sysadmin

40

41 alarm: 10min_dbengine_global_flushing_errors

@@ -46,5 +47,6 @@ lookup: sum -10m unaligned of flushing_pressure_deletions

47 every: 10s

48 crit: $this != 0

49 delay: down 1h multiplier 1.5 max 3h

49 - info: number of pages deleted due to failure to flush data to disk in the last 10 minutes, metric data were lost to unblock data collection, please reduce disk load or use faster disks

50 + info: number of pages deleted due to failure to flush data to disk in the last 10 minutes. \

51 + Metric data were lost to unblock data collection. To fix, reduce disk load or use faster disks.

52 to: sysadmin

health/health.d/disks.conf

+4 -4

@@ -20,7 +20,7 @@ families: !/dev !/dev/* !/run !/run/* *

20 warn: $this > (($status >= $WARNING ) ? (80) : (90))

21 crit: $this > (($status == $CRITICAL) ? (90) : (98))

22 delay: up 1m down 15m multiplier 1.5 max 1h

23 - info: current disk space usage

23 + info: disk space utilization

24 to: sysadmin

25

26 template: disk_inode_usage

@@ -34,7 +34,7 @@ families: !/dev !/dev/* !/run !/run/* *

34 warn: $this > (($status >= $WARNING) ? (80) : (90))

35 crit: $this > (($status == $CRITICAL) ? (90) : (98))

36 delay: up 1m down 15m multiplier 1.5 max 1h

37 - info: current disk inode usage

37 + info: disk inode utilization

38 to: sysadmin

39

40

@@ -141,7 +141,7 @@ families: *

141 warn: $this > $green * (($status >= $WARNING) ? (0.7) : (1))

142 crit: $this > $red * (($status == $CRITICAL) ? (0.7) : (1))

143 delay: down 15m multiplier 1.2 max 1h

144 - info: the percentage of time the disk was busy, during the last 10 minutes

144 + info: average percentage of time the disk was busy over the last 10 minutes

145 to: silent

146

147

@@ -163,5 +163,5 @@ families: *

163 warn: $this > $green * (($status >= $WARNING) ? (0.7) : (1))

164 crit: $this > $red * (($status == $CRITICAL) ? (0.7) : (1))

165 delay: down 15m multiplier 1.2 max 1h

166 - info: average of the kernel estimated disk backlog, for the last 10 minutes

166 + info: average disk backlog size over the last 10 minutes

167 to: silent

health/health.d/dns_query.conf

+1 -1

@@ -8,5 +8,5 @@ template: dns_query_time_query_time

8 every: 10s

9 warn: $this == nan

10 delay: up 20s down 5m multiplier 1.5 max 1h

11 - info: query round trip time

11 + info: average DNS query round trip time over the last 10 seconds

12 to: sysadmin

health/health.d/dnsmasq_dhcp.conf

+1 -1

@@ -8,5 +8,5 @@ template: dnsmasq_dhcp_dhcp_range_utilization

8 warn: $this > ( ($status >= $WARNING ) ? ( 80 ) : ( 90 ) )

9 crit: $this > ( ($status == $CRITICAL) ? ( 90 ) : ( 95 ) )

10 delay: down 5m

11 - info: dhcp-range utilization above threshold!

11 + info: DHCP range utilization

12 to: sysadmin

health/health.d/dockerd.conf

+1 -1

@@ -4,5 +4,5 @@ template: docker_unhealthy_containers

4 every: 10s

5 lookup: average -10s

6 crit: $this > 0

7 - info: number of unhealthy containers

7 + info: average number of unhealthy docker containers over the last 10 seconds

8 to: sysadmin

health/health.d/entropy.conf

+1 -1

@@ -12,5 +12,5 @@

12 every: 5m

13 warn: $this < (($status >= $WARNING) ? (200) : (100))

14 delay: down 1h multiplier 1.5 max 2h

15 - info: minimum entries in the random numbers pool in the last 10 minutes

15 + info: minimum number of entries in the random numbers pool in the last 5 minutes

16 to: silent

health/health.d/fping.conf

+3 -3

@@ -18,8 +18,8 @@ families: *

18 units: up/down

19 every: 10s

20 crit: $this == 0

21 - info: states if the remote host is reachable

21 delay: down 30m multiplier 1.5 max 2h

22 + info: reachability status of the network host (0: unreachable, 1: reachable)

23 to: sysadmin

24

25 template: fping_host_latency

@@ -32,8 +32,8 @@ families: *

32 red: 1000

33 warn: $this > $green OR $max > $red

34 crit: $this > $red

35 - info: average round trip delay during the last 10 seconds

35 delay: down 30m multiplier 1.5 max 2h

36 + info: average latency to the network host over the last 10 seconds

37 to: sysadmin

38

39 template: fping_packet_loss

@@ -47,6 +47,6 @@ families: *

47 every: 10s

48 warn: $this > $green

49 crit: $this > $red

50 - info: packet loss percentage

50 delay: down 30m multiplier 1.5 max 2h

51 + info: packet loss ratio to the network host over the last 10 minutes

52 to: sysadmin

health/health.d/gearman.conf

+2 -2

@@ -18,5 +18,5 @@ template: gearman_workers_queued

18 warn: $this > 30000

19 crit: $this > 100000

20 delay: down 5m multiplier 1.5 max 1h

21 - info: number of queued jobs

22 - to: sysadmin

\ No newline at end of file

21 + info: average number of queued jobs over the last 10 minutes

22 + to: sysadmin

health/health.d/haproxy.conf

+2 -2

@@ -4,7 +4,7 @@ template: haproxy_backend_server_status

4 every: 10s

5 lookup: average -10s

6 crit: $this > 0

7 - info: number of failed haproxy backend servers

7 + info: average number of failed haproxy backend servers over the last 10 seconds

8 to: sysadmin

9

10 template: haproxy_backend_status

@@ -13,7 +13,7 @@ template: haproxy_backend_status

13 every: 10s

14 lookup: average -10s

15 crit: $this > 0

16 - info: number of failed haproxy backends

16 + info: average number of failed haproxy backends over the last 10 seconds

17 to: sysadmin

18

19 template: haproxy_last_collected

health/health.d/hdfs.conf

+5 -5

@@ -23,7 +23,7 @@ template: hdfs_capacity_usage

23 warn: $this > (($status >= $WARNING) ? (70) : (80))

24 crit: $this > (($status == $CRITICAL) ? (80) : (98))

25 delay: down 15m multiplier 1.5 max 1h

26 - info: used capacity

26 + info: summary datanodes space capacity utilization

27 to: sysadmin

28

29

@@ -36,7 +36,7 @@ template: hdfs_missing_blocks

36 every: 10s

37 warn: $this > 0

38 delay: down 15m multiplier 1.5 max 1h

39 - info: missing blocks

39 + info: number of missing blocks

40 to: sysadmin

41

42

@@ -47,7 +47,7 @@ template: hdfs_stale_nodes

47 every: 10s

48 warn: $this > 0

49 delay: down 15m multiplier 1.5 max 1h

50 - info: stale data nodes

50 + info: number of datanodes marked stale due to delayed heartbeat

51 to: sysadmin

52

53

@@ -58,7 +58,7 @@ template: hdfs_dead_nodes

58 every: 10s

59 crit: $this > 0

60 delay: down 15m multiplier 1.5 max 1h

61 - info: dead data nodes

61 + info: number of datanodes which are currently dead

62 to: sysadmin

63

64

@@ -71,5 +71,5 @@ template: hdfs_num_failed_volumes

71 every: 10s

72 warn: $this > 0

73 delay: down 15m multiplier 1.5 max 1h

74 - info: failed volumes

74 + info: number of failed volumes

75 to: sysadmin

health/health.d/httpcheck.conf

+8 -8

@@ -18,7 +18,7 @@ families: *

18 calc: ($this < 75) ? (0) : ($this)

19 every: 5s

20 units: up/down

21 - info: at least 75% verified responses during last 60 seconds, ideal for badges

21 + info: average ratio of successful HTTP requests over the last minute (at least 75%)

22 to: silent

23

24 template: httpcheck_web_service_bad_content

@@ -30,7 +30,7 @@ families: *

30 warn: $this >= 10 AND $this < 40

31 crit: $this >= 40

32 delay: down 5m multiplier 1.5 max 1h

33 - info: average of unexpected http response content during the last 5 minutes

33 + info: average ratio of HTTP responses with unexpected content over the last 5 minutes

34 options: no-clear-notification

35 to: webmaster

36

@@ -43,7 +43,7 @@ families: *

43 warn: $this >= 10 AND $this < 40

44 crit: $this >= 40

45 delay: down 5m multiplier 1.5 max 1h

46 - info: average of unexpected http status during the last 5 minutes

46 + info: average ratio of HTTP responses with unexpected status over the last 5 minutes

47 options: no-clear-notification

48 to: webmaster

49

@@ -53,7 +53,7 @@ families: *

53 lookup: average -5m unaligned percentage of timeout

54 every: 10s

55 units: %

56 - info: average of timeouts during the last 5 minutes

56 + info: average ratio of HTTP request timeouts over the last 5 minutes

57

58 template: httpcheck_no_web_service_connections

59 families: *

@@ -61,7 +61,7 @@ families: *

61 lookup: average -5m unaligned percentage of no_connection

62 every: 10s

63 units: %

64 - info: average of failed requests during the last 5 minutes

64 + info: average ratio of failed requests during the last 5 minutes

65

66 # combined timeout & no connection alarm

67 template: httpcheck_web_service_unreachable

@@ -73,7 +73,7 @@ families: *

73 warn: ($httpcheck_no_web_service_connections >= 10 OR $httpcheck_web_service_timeouts >= 10) AND ($httpcheck_no_web_service_connections < 40 OR $httpcheck_web_service_timeouts < 40)

74 crit: $httpcheck_no_web_service_connections >= 40 OR $httpcheck_web_service_timeouts >= 40

75 delay: down 5m multiplier 1.5 max 1h

76 - info: average of failed requests either due to timeouts or no connection during the last 5 minutes

76 + info: ratio of failed requests either due to timeouts or no connection over the last 5 minutes

77 options: no-clear-notification

78 to: webmaster

79

@@ -83,7 +83,7 @@ families: *

83 lookup: average -1h unaligned of time

84 every: 30s

85 units: ms

86 - info: average response time over the last hour

86 + info: average HTTP response time over the last hour

87

88 template: httpcheck_web_service_slow

89 families: *

@@ -93,7 +93,7 @@ families: *

93 every: 10s

94 warn: ($this > ($httpcheck_1h_web_service_response_time * 2) )

95 crit: ($this > ($httpcheck_1h_web_service_response_time * 3) )

96 - info: average response time over the last 3 minutes, compared to the average over the last hour

96 delay: down 5m multiplier 1.5 max 1h

97 + info: average HTTP response time over the last 3 minutes, compared to the average over the last hour

98 options: no-clear-notification

99 to: webmaster

health/health.d/ioping.conf

+1 -1

@@ -8,6 +8,6 @@ families: *

8 red: 1000

9 warn: $this > $green OR $max > $red

10 crit: $this > $red

11 - info: average round trip delay during the last 10 seconds

11 delay: down 30m multiplier 1.5 max 2h

12 + info: average I/O latency over the last 10 seconds

13 to: sysadmin

health/health.d/ipc.conf

+2 -2

@@ -11,7 +11,7 @@

11 warn: $this > (($status >= $WARNING) ? (70) : (80))

12 crit: $this > (($status == $CRITICAL) ? (70) : (90))

13 delay: down 5m multiplier 1.5 max 1h

14 - info: the percentage of IPC semaphores used

14 + info: IPC semaphore utilization

15 to: sysadmin

16

17 alarm: semaphore_arrays_used

@@ -24,5 +24,5 @@

24 warn: $this > (($status >= $WARNING) ? (70) : (80))

25 crit: $this > (($status == $CRITICAL) ? (70) : (90))

26 delay: down 5m multiplier 1.5 max 1h

27 - info: the percentage of IPC semaphore arrays used

27 + info: IPC semaphore arrays utilization

28 to: sysadmin

health/health.d/ipfs.conf

+1 -1

@@ -7,5 +7,5 @@ template: ipfs_datastore_usage

7 warn: $this > (($status >= $WARNING) ? (80) : (90))

8 crit: $this > (($status == $CRITICAL) ? (90) : (98))

9 delay: down 15m multiplier 1.5 max 1h

10 - info: ipfs Datastore close to running out of space

10 + info: IPFS datastore utilization

11 to: sysadmin

health/health.d/ipmi.conf

+2 -2

@@ -6,7 +6,7 @@

6 warn: $this > 0

7 crit: $critical > 0

8 delay: up 5m down 15m multiplier 1.5 max 1h

9 - info: the number IPMI sensors in non-nominal state

9 + info: number of IPMI sensors in non-nominal state

10 to: sysadmin

11

12 alarm: ipmi_events

@@ -16,5 +16,5 @@

16 every: 10s

17 warn: $this > 0

18 delay: up 5m down 15m multiplier 1.5 max 1h

19 - info: the number of events in the IPMI System Event Log (SEL)

19 + info: number of events in the IPMI System Event Log (SEL)

20 to: sysadmin

health/health.d/isc_dhcpd.conf

+10 -10

@@ -1,10 +1,10 @@

1 - template: isc_dhcpd_leases_size

2 - on: isc_dhcpd.leases_total

3 - units: KB

4 - every: 60

5 - calc: $leases_size

6 - warn: $this > 3072

7 - crit: $this > 6144

8 - delay: up 2m down 5m

9 - info: dhcpd.leases file too big! Module can slow down your server.

10 - to: sysadmin

1 +# template: isc_dhcpd_leases_size

2 +# on: isc_dhcpd.leases_total

3 +# units: KB

4 +# every: 60

5 +# calc: $leases_size

6 +# warn: $this > 3072

7 +# crit: $this > 6144

8 +# delay: up 2m down 5m

9 +# info: dhcpd.leases file too big! Module can slow down your server.

10 +# to: sysadmin

health/health.d/kubelet.conf

+12 -9

@@ -11,7 +11,7 @@

11 every: 10s

12 warn: $this == 1

13 delay: down 1m multiplier 1.5 max 2h

14 - info: the node is experiencing a configuration-related error

14 + info: the node is experiencing a configuration-related error (0: false, 1: true)

15 to: sysadmin

16

17 # Failed Token() requests to the alternate token source

@@ -23,7 +23,7 @@

23 every: 10s

24 warn: $this > 0

25 delay: down 1m multiplier 1.5 max 2h

26 - info: failed token requests to alternate token source

26 + info: number of failed Token() requests to the alternate token source

27 to: sysadmin

28

29 # Docker and runtime operation errors

@@ -35,7 +35,7 @@

35 every: 10s

36 warn: $this > (($status >= $WARNING) ? (0) : (20))

37 delay: up 30s down 1m multiplier 1.5 max 2h

38 - info: operations error

38 + info: number of Docker or runtime operation errors

39 to: sysadmin

40

41 # -----------------------------------------------------------------------------

@@ -58,7 +58,7 @@ template: kubelet_1m_pleg_relist_latency_quantile_05

58 lookup: average -1m unaligned of kubelet_pleg_relist_latency_05

59 units: microseconds

60 every: 10s

61 - info: the average value of pleg relisting latency during the last minute (quantile 0.5)

61 + info: average Pod Lifecycle Event Generator relisting latency over the last minute (quantile 0.5)

62

63 template: kubelet_10s_pleg_relist_latency_quantile_05

64 on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds

@@ -69,7 +69,8 @@ template: kubelet_10s_pleg_relist_latency_quantile_05

69 warn: $this > (($status >= $WARNING)?(100):(200))

70 crit: $this > (($status >= $WARNING)?(200):(400))

71 delay: down 1m multiplier 1.5 max 2h

72 - info: the % of the pleg relisting latency in the last 10 seconds, compared to the last minute (quantile 0.5)

72 + info: ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \

73 + compared to the last minute (quantile 0.5)

74 to: sysadmin

75

76 # quantile 0.9

@@ -79,7 +80,7 @@ template: kubelet_1m_pleg_relist_latency_quantile_09

80 lookup: average -1m unaligned of kubelet_pleg_relist_latency_09

81 units: microseconds

82 every: 10s

82 - info: the average value of pleg relisting latency during the last minute (quantile 0.9)

83 + info: average Pod Lifecycle Event Generator relisting latency over the last minute (quantile 0.9)

84

85 template: kubelet_10s_pleg_relist_latency_quantile_09

86 on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds

@@ -90,7 +91,8 @@ template: kubelet_10s_pleg_relist_latency_quantile_09

91 warn: $this > (($status >= $WARNING)?(200):(400))

92 crit: $this > (($status >= $WARNING)?(400):(800))

93 delay: down 1m multiplier 1.5 max 2h

93 - info: the % of the pleg relisting latency in the last 10 seconds, compared to the last minute (quantile 0.9)

94 + info: ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \

95 + compared to the last minute (quantile 0.9)

96 to: sysadmin

97

98 # quantile 0.99

@@ -100,7 +102,7 @@ template: kubelet_1m_pleg_relist_latency_quantile_099

102 lookup: average -1m unaligned of kubelet_pleg_relist_latency_099

103 units: microseconds

104 every: 10s

103 - info: the average value of pleg relisting latency during the last minute (quantile 0.99)

105 + info: average Pod Lifecycle Event Generator relisting latency over the last minute (quantile 0.99)

106

107 template: kubelet_10s_pleg_relist_latency_quantile_099

108 on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds

@@ -111,5 +113,6 @@ template: kubelet_10s_pleg_relist_latency_quantile_099

113 warn: $this > (($status >= $WARNING)?(400):(800))

114 crit: $this > (($status >= $WARNING)?(800):(1200))

115 delay: down 1m multiplier 1.5 max 2h

114 - info: the % of the pleg relisting latency in the last 10 seconds, compared to the last minute (quantile 0.99)

116 + info: ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \

117 + compared to the last minute (quantile 0.99)

118 to: sysadmin

health/health.d/linux_power_supply.conf

+1 -1

@@ -8,5 +8,5 @@ template: linux_power_supply_capacity

8 warn: $this < 10

9 crit: $this < 5

10 delay: up 30s down 5m multiplier 1.2 max 1h

11 - info: the percentage remaining capacity of the power supply

11 + info: percentage of remaining power supply capacity

12 to: sysadmin

health/health.d/load.conf

+4 -4

@@ -11,7 +11,7 @@

11 calc: ($active_processors == nan or $active_processors == inf or $active_processors < 2) ? ( 2 ) : ( $active_processors )

12 units: cpus

13 every: 1m

14 - info: trigger point for load average alarms

14 + info: number of active CPU cores in the system

15

16 # Send alarms if the load average is unusually high.

17 # These intentionally _do not_ calculate the average over the sampled

@@ -26,7 +26,7 @@

26 every: 1m

27 warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 175 : 200)

28 delay: down 15m multiplier 1.5 max 1h

29 - info: fifteen-minute load average

29 + info: system fifteen-minute load average

30 to: sysadmin

31

32 alarm: load_average_5

@@ -38,7 +38,7 @@

38 every: 1m

39 warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 350 : 400)

40 delay: down 15m multiplier 1.5 max 1h

41 - info: five-minute load average

41 + info: system five-minute load average

42 to: sysadmin

43

44 alarm: load_average_1

@@ -50,5 +50,5 @@

50 every: 1m

51 warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 700 : 800)

52 delay: down 15m multiplier 1.5 max 1h

53 - info: one-minute load average

53 + info: system one-minute load average

54 to: sysadmin

health/health.d/mdstat.conf

+4 -3

@@ -14,7 +14,8 @@ template: mdstat_disks

14 every: 10s

15 calc: $down

16 crit: $this > 0

17 - info: Array is degraded!

17 + info: number of devices in the down state. \

18 + Any number > 0 indicates that the array is degraded.

19 to: sysadmin

20

21 template: mdstat_mismatch_cnt

@@ -24,7 +25,7 @@ template: mdstat_mismatch_cnt

25 every: 60s

26 warn: $this > 1024

27 delay: up 30m

27 - info: Mismatch count!

28 + info: number of unsynchronized blocks

29 to: sysadmin

30

31 template: mdstat_nonredundant_last_collected

@@ -35,4 +36,4 @@ template: mdstat_nonredundant_last_collected

36 warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))

37 crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))

38 info: number of seconds since the last successful data collection

38 - to: sysadmin

\ No newline at end of file

39 + to: sysadmin

health/health.d/megacli.conf

+7 -7

@@ -8,7 +8,7 @@ template: megacli_adapter_state

8 every: 10s

9 crit: $this > 0

10 delay: down 5m multiplier 2 max 10m

11 - info: adapter state is degraded

11 + info: adapter is in the degraded state (0: false, 1: true)

12 to: sysadmin

13

14 ## Physical Disks

@@ -20,7 +20,7 @@ template: megacli_pd_predictive_failures

20 every: 10s

21 warn: $this > 0

22 delay: up 1m down 5m multiplier 2 max 10m

23 - info: physical drive predictive failures

23 + info: number of physical drive predictive failures

24 to: sysadmin

25

26 template: megacli_pd_media_errors

@@ -30,27 +30,27 @@ template: megacli_pd_media_errors

30 every: 10s

31 warn: $this > 0

32 delay: up 1m down 5m multiplier 2 max 10m

33 - info: physical drive media errors

33 + info: number of physical drive media errors

34 to: sysadmin

35

36 ## Battery Backup Units (BBU)

37

38 template: megacli_bbu_relative_charge

39 on: megacli.bbu_relative_charge

40 - units: percent

40 lookup: average -10s

41 + units: percent

42 every: 10s

43 warn: $this <= (($status >= $WARNING) ? (85) : (80))

44 crit: $this <= (($status == $CRITICAL) ? (50) : (40))

45 - info: BBU relative state of charge

45 + info: average battery backup unit (BBU) relative state of charge over the last 10 seconds

46 to: sysadmin

47

48 template: megacli_bbu_cycle_count

49 on: megacli.bbu_cycle_count

50 - units: cycle count

50 lookup: average -10s

51 + units: cycles

52 every: 10s

53 warn: $this >= 100

54 crit: $this >= 500

55 - info: BBU cycle count

55 + info: average battery backup unit (BBU) charge cycles count over the last 10 seconds

56 to: sysadmin

health/health.d/memcached.conf

+4 -3

@@ -23,7 +23,7 @@ template: memcached_cache_memory_usage

23 warn: $this > (($status >= $WARNING) ? (70) : (80))

24 crit: $this > (($status == $CRITICAL) ? (80) : (90))

25 delay: up 0 down 15m multiplier 1.5 max 1h

26 - info: current cache memory usage

26 + info: cache memory utilization

27 to: dba

28

29

@@ -35,7 +35,7 @@ template: memcached_cache_fill_rate

35 calc: ($this - $available) / (($now - $after) / 3600)

36 units: KB/hour

37 every: 1m

38 - info: average rate the cache fills up (positive), or frees up (negative) space, for the last hour

38 + info: average rate the cache fills up (positive), or frees up (negative) space over the last hour

39

40

41 # find the hours remaining until memcached cache is full

@@ -48,5 +48,6 @@ template: memcached_out_of_cache_space_time

48 warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))

49 crit: $this > 0 and $this < (($status == $CRITICAL) ? (24) : (2))

50 delay: down 15m multiplier 1.5 max 1h

51 - info: estimated time the cache will run out of space, if the system continues to add data with the rate of the last hour

51 + info: estimated time the cache will run out of space \

52 + if the system continues to add data at the same rate as the past hour

53 to: dba

health/health.d/memory.conf

+2 -2

@@ -10,7 +10,7 @@

10 every: 1m

11 warn: $this > 0

12 delay: down 1h multiplier 1.5 max 1h

13 - info: number of ECC correctable errors during the last hour

13 + info: number of ECC correctable errors in the last 10 minutes

14 to: sysadmin

15

16 alarm: 1hour_ecc_memory_uncorrectable

@@ -22,7 +22,7 @@

22 every: 1m

23 crit: $this > 0

24 delay: down 1h multiplier 1.5 max 1h

25 - info: number of ECC uncorrectable errors during the last hour

25 + info: number of ECC uncorrectable errors in the last 10 minutes

26 to: sysadmin

27

28 alarm: 1hour_memory_hw_corrupted

health/health.d/mysql.conf

+15 -11

@@ -24,7 +24,7 @@ template: mysql_10s_slow_queries

24 warn: $this > (($status >= $WARNING) ? (5) : (10))

25 crit: $this > (($status == $CRITICAL) ? (10) : (20))

26 delay: down 5m multiplier 1.5 max 1h

27 - info: number of mysql slow queries over the last 10 seconds

27 + info: number of slow queries in the last 10 seconds

28 to: dba

29

30

@@ -36,7 +36,7 @@ template: mysql_10s_table_locks_immediate

36 lookup: sum -10s absolute of immediate

37 units: immediate locks

38 every: 10s

39 - info: number of table immediate locks over the last 10 seconds

39 + info: number of table immediate locks in the last 10 seconds

40 to: dba

41

42 template: mysql_10s_table_locks_waited

@@ -44,7 +44,7 @@ template: mysql_10s_table_locks_waited

44 lookup: sum -10s absolute of waited

45 units: waited locks

46 every: 10s

47 - info: number of table waited locks over the last 10 seconds

47 + info: number of table waited locks in the last 10 seconds

48 to: dba

49

50 template: mysql_10s_waited_locks_ratio

@@ -55,7 +55,7 @@ template: mysql_10s_waited_locks_ratio

55 warn: $this > (($status >= $WARNING) ? (10) : (25))

56 crit: $this > (($status == $CRITICAL) ? (25) : (50))

57 delay: down 30m multiplier 1.5 max 1h

58 - info: the ratio of mysql waited table locks, for the last 10 seconds

58 + info: ratio of waited table locks over the last 10 seconds

59 to: dba

60

61

@@ -70,7 +70,7 @@ template: mysql_connections

70 warn: $this > (($status >= $WARNING) ? (60) : (70))

71 crit: $this > (($status == $CRITICAL) ? (80) : (90))

72 delay: down 15m multiplier 1.5 max 1h

73 - info: the ratio of current active connections vs the maximum possible number of connections

73 + info: client connections utilization

74 to: dba

75

76

@@ -84,7 +84,7 @@ template: mysql_replication

84 every: 10s

85 crit: $this == 0

86 delay: down 5m multiplier 1.5 max 1h

87 - info: checks if mysql replication has stopped

87 + info: replication status (0: stopped, 1: working)

88 to: dba

89

90 template: mysql_replication_lag

@@ -95,7 +95,8 @@ template: mysql_replication_lag

95 warn: $this > (($status >= $WARNING) ? (5) : (10))

96 crit: $this > (($status == $CRITICAL) ? (10) : (30))

97 delay: down 15m multiplier 1.5 max 1h

98 - info: the number of seconds mysql replication is behind this master

98 + info: difference between the timestamp of the latest transaction processed by the SQL thread and \

99 + the timestamp of the same transaction when it was processed on the master

100 to: dba

101

102

@@ -107,7 +108,7 @@ template: mysql_galera_cluster_size_max_2m

108 lookup: max -2m absolute

109 units: nodes

110 every: 10s

110 - info: max cluster size 2 minute

111 + info: maximum galera cluster size in the last 2 minutes

112 to: dba

113

114 template: mysql_galera_cluster_size

@@ -118,7 +119,7 @@ template: mysql_galera_cluster_size

119 warn: $this > $mysql_galera_cluster_size_max_2m

120 crit: $this < $mysql_galera_cluster_size_max_2m

121 delay: up 20s down 5m multiplier 1.5 max 1h

121 - info: cluster size has changed

122 + info: current galera cluster size, compared to the maximum size in the last 2 minutes

123 to: dba

124

125 # galera node state

@@ -130,7 +131,8 @@ template: mysql_galera_cluster_state

131 warn: $this < 4

132 crit: $this < 2

133 delay: up 30s down 5m multiplier 1.5 max 1h

133 - info: node state (0: undefined, 1: joining, 2: donor/desynced, 3: joined, 4: synced)

134 + info: galera node state \

135 + (0: undefined, 1: joining, 2: donor/desynced, 3: joined, 4: synced)

136 to: dba

137

138

@@ -142,5 +144,7 @@ template: mysql_galera_cluster_status

144 every: 10s

145 crit: $mysql_galera_cluster_state != nan AND $this != 0

146 delay: up 30s down 5m multiplier 1.5 max 1h

145 - info: node and cluster status (-1: unknown, 0: primary/quorum present, 1: non-primary/quorum lost, 2: disconnected)

147 + info: galera node cluster component status \

148 + (-1: unknown, 0: primary/quorum present, 1: non-primary/quorum lost, 2: disconnected). \

149 + Any other value than primary indicates that the node is part of a nonoperational component.

150 to: dba

health/health.d/net.conf

+15 -14

@@ -12,7 +12,7 @@

12 calc: ( $nic_speed_max > 0 ) ? ( $nic_speed_max) : ( nan )

13 units: Mbit

14 every: 10s

15 - info: The current speed of the physical network interface

15 + info: network interface current speed

16

17 template: 1m_received_traffic_overflow

18 on: net.net

@@ -25,7 +25,7 @@

25 every: 10s

26 warn: $this > (($status >= $WARNING) ? (85) : (90))

27 delay: up 1m down 1m multiplier 1.5 max 1h

28 - info: interface received bandwidth usage over net device speed max

28 + info: average inbound utilization for the network interface over the last minute

29 to: sysadmin

30

31 template: 1m_sent_traffic_overflow

@@ -39,7 +39,7 @@

39 every: 10s

40 warn: $this > (($status >= $WARNING) ? (85) : (90))

41 delay: up 1m down 1m multiplier 1.5 max 1h

42 - info: interface sent bandwidth usage over net device speed max

42 + info: average outbound utilization for the network interface over the last minute

43 to: sysadmin

44

45 # -----------------------------------------------------------------------------

@@ -60,7 +60,7 @@ families: !net* *

60 lookup: sum -10m unaligned absolute of inbound

61 units: packets

62 every: 1m

63 - info: interface inbound dropped packets in the last 10 minutes

63 + info: number of inbound dropped packets for the network interface in the last 10 minutes

64

65 template: outbound_packets_dropped

66 on: net.drops

@@ -70,7 +70,7 @@ families: !net* *

70 lookup: sum -10m unaligned absolute of outbound

71 units: packets

72 every: 1m

73 - info: interface outbound dropped packets in the last 10 minutes

73 + info: number of outbound dropped packets for the network interface in the last 10 minutes

74

75 template: inbound_packets_dropped_ratio

76 on: net.packets

@@ -83,7 +83,7 @@ families: !net* !wl* *

83 every: 1m

84 warn: $this >= 2

85 delay: up 1m down 1h multiplier 1.5 max 2h

86 - info: the ratio of inbound dropped packets vs the total number of received packets of the network interface, during the last 10 minutes

86 + info: ratio of inbound dropped packets for the network interface over the last 10 minutes

87 to: sysadmin

88

89 template: outbound_packets_dropped_ratio

@@ -97,7 +97,7 @@ families: !net* !wl* *

97 every: 1m

98 warn: $this >= 2

99 delay: up 1m down 1h multiplier 1.5 max 2h

100 - info: the ratio of outbound dropped packets vs the total number of sent packets of the network interface, during the last 10 minutes

100 + info: ratio of outbound dropped packets for the network interface over the last 10 minutes

101 to: sysadmin

102

103 template: wifi_inbound_packets_dropped_ratio

@@ -111,7 +111,7 @@ families: wl*

111 every: 1m

112 warn: $this >= 10

113 delay: up 1m down 1h multiplier 1.5 max 2h

114 - info: the ratio of inbound dropped packets vs the total number of received packets of the network interface, during the last 10 minutes

114 + info: ratio of inbound dropped packets for the network interface over the last 10 minutes

115 to: sysadmin

116

117 template: wifi_outbound_packets_dropped_ratio

@@ -125,7 +125,7 @@ families: wl*

125 every: 1m

126 warn: $this >= 10

127 delay: up 1m down 1h multiplier 1.5 max 2h

128 - info: the ratio of outbound dropped packets vs the total number of sent packets of the network interface, during the last 10 minutes

128 + info: ratio of outbound dropped packets for the network interface over the last 10 minutes

129 to: sysadmin

130

131 # -----------------------------------------------------------------------------

@@ -141,7 +141,7 @@ families: *

141 every: 1m

142 warn: $this >= 5

143 delay: down 1h multiplier 1.5 max 2h

144 - info: interface inbound errors in the last 10 minutes

144 + info: number of inbound errors for the network interface in the last 10 minutes

145 to: sysadmin

146

147 template: interface_outbound_errors

@@ -154,7 +154,7 @@ families: *

154 every: 1m

155 warn: $this >= 5

156 delay: down 1h multiplier 1.5 max 2h

157 - info: interface outbound errors in the last 10 minutes

157 + info: number of outbound errors for the network interface in the last 10 minutes

158 to: sysadmin

159

160 # -----------------------------------------------------------------------------

@@ -175,7 +175,7 @@ families: *

175 every: 1m

176 warn: $this > 0

177 delay: down 1h multiplier 1.5 max 2h

178 - info: interface fifo errors in the last 10 minutes

178 + info: number of FIFO errors for the network interface in the last 10 minutes

179 to: sysadmin

180

181 # -----------------------------------------------------------------------------

@@ -195,7 +195,7 @@ families: *

195 lookup: average -1m unaligned of received

196 units: packets

197 every: 10s

198 - info: the average number of packets received during the last minute

198 + info: average number of packets received by the network interface over the last minute

199

200 template: 10s_received_packets_storm

201 on: net.packets

@@ -209,5 +209,6 @@ families: *

209 warn: $this > (($status >= $WARNING)?(200):(5000))

210 crit: $this > (($status == $CRITICAL)?(5000):(6000))

211 options: no-clear-notification

212 - info: the % of the rate of received packets in the last 10 seconds, compared to the rate of the last minute (clear notification for this alarm will not be sent)

212 + info: ratio of average number of received packets for the network interface over the last 10 seconds, \

213 + compared to the rate over the last minute

214 to: sysadmin

health/health.d/netfilter.conf

+1 -1

@@ -12,5 +12,5 @@

12 warn: $this > (($status >= $WARNING) ? (85) : (90))

13 crit: $this > (($status == $CRITICAL) ? (90) : (95))

14 delay: down 5m multiplier 1.5 max 1h

15 - info: the number of connections tracked by the netfilter connection tracker, as a percentage of the connection tracker table size

15 + info: netfilter connection tracker table size utilization

16 to: sysadmin

health/health.d/pihole.conf

+4 -4

@@ -22,7 +22,7 @@ template: pihole_blocked_queries

22 warn: $this > ( ($status >= $WARNING ) ? ( 45 ) : ( 55 ) )

23 crit: $this > ( ($status == $CRITICAL) ? ( 55 ) : ( 75 ) )

24 delay: up 2m down 5m

25 - info: percentage of blocked dns queries for the last 24 hour

25 + info: percentage of blocked dns queries over the last 24 hour

26 to: sysadmin

27

28

@@ -36,7 +36,7 @@ template: pihole_blocklist_last_update

36 calc: $ago

37 warn: $this > 60 * 60 * 24 * 8

38 crit: $this > 60 * 60 * 24 * 8 * 2

39 - info: blocklist last update time

39 + info: gravity.list (blocklist) file last update time

40 to: sysadmin

41

42 # Gravity file check (gravity.list).

@@ -48,7 +48,7 @@ template: pihole_blocklist_gravity_file

48 calc: $file_exists

49 crit: $this != 1

50 delay: up 2m down 5m

51 - info: gravity file existence

51 + info: gravity.list (blocklist) file existence state (0: exists, 1: not-exists)

52 to: sysadmin

53

54 # Pi-hole's ability to block unwanted domains.

@@ -61,5 +61,5 @@ template: pihole_status

61 calc: $enabled

62 warn: $this != 1

63 delay: up 2m down 5m

64 - info: unwanted domains blocking status

64 + info: unwanted domains blocking status (0: enabled, 1: disabled)

65 to: sysadmin

health/health.d/portcheck.conf

+3 -3

@@ -18,7 +18,7 @@ families: *

18 calc: ($this < 75) ? (0) : ($this)

19 every: 5s

20 units: up/down

21 - info: at least 75% successful connections during last 60 seconds, ideal for badges

21 + info: average ratio of successful connections over the last minute (at least 75%)

22 to: silent

23

24 template: portcheck_connection_timeouts

@@ -30,7 +30,7 @@ families: *

30 warn: $this >= 10 AND $this < 40

31 crit: $this >= 40

32 delay: down 5m multiplier 1.5 max 1h

33 - info: average of timeouts during the last 5 minutes

33 + info: average ratio of timeouts over the last 5 minutes

34 to: sysadmin

35

36 template: portcheck_connection_fails

@@ -42,5 +42,5 @@ families: *

42 warn: $this >= 10 AND $this < 40

43 crit: $this >= 40

44 delay: down 5m multiplier 1.5 max 1h

45 - info: average of failed connections during the last 5 minutes

45 + info: average ratio of failed connections over the last 5 minutes

46 to: sysadmin

health/health.d/processes.conf

+1 -1

@@ -9,5 +9,5 @@

9 warn: $this > (($status >= $WARNING) ? (85) : (90))

10 crit: $this > (($status == $CRITICAL) ? (90) : (95))

11 delay: down 5m multiplier 1.5 max 1h

12 - info: the percentage of active processes

12 + info: system process IDs (PID) space utilization

13 to: sysadmin

health/health.d/ram.conf

+6 -5

@@ -7,7 +7,8 @@

7 hosts: *

8 calc: ($zfs.arc_size.arcsz = nan)?(0):($zfs.arc_size.arcsz - $zfs.arc_size.min)

9 every: 10s

10 - info: the amount of memory that is reported as used, but it is actually capable for resizing itself based on the system needs (eg. ZFS ARC)

10 + info: amount of memory reported as used, \

11 + but it is actually capable for resizing itself based on the system needs (eg. ZFS ARC)

12

13 alarm: ram_in_use

14 on: system.ram

@@ -20,7 +21,7 @@

21 warn: $this > (($status >= $WARNING) ? (80) : (90))

22 crit: $this > (($status == $CRITICAL) ? (90) : (98))

23 delay: down 15m multiplier 1.5 max 1h

23 - info: system RAM used

24 + info: system memory utilization

25 to: sysadmin

26

27 alarm: ram_available

@@ -33,7 +34,7 @@

34 warn: $this < (($status >= $WARNING) ? (15) : (10))

35 crit: $this < (($status == $CRITICAL) ? (10) : ( 5))

36 delay: down 15m multiplier 1.5 max 1h

36 - info: estimated amount of RAM available for userspace processes, without causing swapping

37 + info: percentage of estimated amount of RAM available for userspace processes, without causing swapping

38 to: sysadmin

39

40 ## FreeBSD

@@ -47,7 +48,7 @@

48 warn: $this > (($status >= $WARNING) ? (80) : (90))

49 crit: $this > (($status == $CRITICAL) ? (90) : (98))

50 delay: down 15m multiplier 1.5 max 1h

50 - info: system RAM usage

51 + info: system memory utilization

52 to: sysadmin

53

54 alarm: ram_available

@@ -60,5 +61,5 @@

61 warn: $this < (($status >= $WARNING) ? (15) : (10))

62 crit: $this < (($status == $CRITICAL) ? (10) : ( 5))

63 delay: down 15m multiplier 1.5 max 1h

63 - info: estimated amount of RAM available for userspace processes, without causing swapping

64 + info: percentage of estimated amount of RAM available for userspace processes, without causing swapping

65 to: sysadmin

health/health.d/redis.conf

+2 -2

@@ -18,7 +18,7 @@ families: *

18 every: 10s

19 crit: $rdb_last_bgsave_status != 0

20 units: ok/failed

21 - info: states if redis bgsave is working

21 + info: status of the last RDB save operation (0: ok, 1: error)

22 delay: down 5m multiplier 1.5 max 1h

23 to: dba

24

@@ -29,6 +29,6 @@ families: *

29 warn: $rdb_bgsave_in_progress > 600

30 crit: $rdb_bgsave_in_progress > 1200

31 units: seconds

32 - info: the time redis needs to save its database

32 + info: duration of the on-going RDB save operation

33 delay: down 5m multiplier 1.5 max 1h

34 to: dba

health/health.d/retroshare.conf

+1 -1

@@ -21,5 +21,5 @@ template: retroshare_dht_working

21 warn: $this < (($status >= $WARNING) ? (120) : (100))

22 crit: $this < (($status == $CRITICAL) ? (10) : (1))

23 delay: up 0 down 15m multiplier 1.5 max 1h

24 - info: Checks if the DHT has enough peers to operate

24 + info: number of DHT peers

25 to: sysadmin

health/health.d/riakkv.conf

+11 -5

@@ -29,7 +29,8 @@ template: riakkv_1h_kv_get_mean_latency

29 lookup: average -1h unaligned of time

30 every: 30s

31 units: ms

32 - info: mean average KV GET latency over the last hour

32 + info: average time between reception of client GET request and \

33 + subsequent response to client over the last hour

34

35 template: riakkv_kv_get_slow

36 on: riak.kv.latency.get

@@ -39,7 +40,9 @@ template: riakkv_kv_get_slow

40 every: 10s

41 warn: ($this > ($riakkv_1h_kv_get_mean_latency * 2) )

42 crit: ($this > ($riakkv_1h_kv_get_mean_latency * 3) )

42 - info: average KV GET time over the last 3 minutes, compared to the average over the last hour

43 + info: average time between reception of client GET request and \

44 + subsequent response to the client over the last 3 minutes, \

45 + compared to the average over the last hour

46 delay: down 5m multiplier 1.5 max 1h

47 to: dba

48

@@ -50,7 +53,8 @@ template: riakkv_1h_kv_put_mean_latency

53 lookup: average -1h unaligned of time

54 every: 30s

55 units: ms

53 - info: mean average KV PUT latency over the last hour

56 + info: average time between reception of client PUT request and \

57 + subsequent response to the client over the last hour

58

59 template: riakkv_kv_put_slow

60 on: riak.kv.latency.put

@@ -60,7 +64,9 @@ template: riakkv_kv_put_slow

64 every: 10s

65 warn: ($this > ($riakkv_1h_kv_put_mean_latency * 2) )

66 crit: ($this > ($riakkv_1h_kv_put_mean_latency * 3) )

63 - info: average KV PUT time over the last 3 minutes, compared to the average over the last hour

67 + info: average time between reception of client PUT request and \

68 + subsequent response to the client over the last 3 minutes, \

69 + compared to the average over the last hour

70 delay: down 5m multiplier 1.5 max 1h

71 to: dba

72

@@ -76,5 +82,5 @@ template: riakkv_vm_high_process_count

82 every: 10s

83 warn: $this > 10000

84 crit: $this > 100000

79 - info: number of processes running in the Erlang VM (the default limit on ERTS 10.2.4 is 262144)

85 + info: number of processes running in the Erlang VM

86 to: dba

health/health.d/scaleio.conf

+2 -2

@@ -22,7 +22,7 @@ template: scaleio_storage_pool_capacity_utilization

22 warn: $this > (($status >= $WARNING) ? (80) : (90))

23 crit: $this > (($status == $CRITICAL) ? (90) : (98))

24 delay: down 15m multiplier 1.5 max 1h

25 - info: Storage Pool capacity utilization

25 + info: storage pool capacity utilization

26 to: sysadmin

27

28

@@ -34,5 +34,5 @@ template: scaleio_sdc_mdm_connection_state

34 every: 10s

35 warn: $this != 1

36 delay: up 30s down 5m multiplier 1.5 max 1h

37 - info: Sdc connection to MDM state

37 + info: Data Client (SDC) to Metadata Manager (MDM) connection state (0: disconnected, 1: connected)

38 to: sysadmin

health/health.d/softnet.conf

+8 -3

@@ -12,7 +12,8 @@

12 every: 10s

13 warn: $this > (($status >= $WARNING) ? (0) : (10))

14 delay: down 1h multiplier 1.5 max 2h

15 - info: average number of packets dropped in the last 1min, because sysctl net.core.netdev_max_backlog was exceeded (this can be a cause for dropped packets)

15 + info: average number of dropped packets in the last minute \

16 + due to exceeded net.core.netdev_max_backlog

17 to: sysadmin

18

19 alarm: 1min_netdev_budget_ran_outs

@@ -24,7 +25,9 @@

25 every: 10s

26 warn: $this > (($status >= $WARNING) ? (0) : (10))

27 delay: down 1h multiplier 1.5 max 2h

27 - info: average number of times, during the last 1min, ksoftirq ran out of sysctl net.core.netdev_budget or net.core.netdev_budget_usecs, with work remaining (this can be a cause for dropped packets)

28 + info: average number of times ksoftirq ran out of sysctl net.core.netdev_budget or \

29 + net.core.netdev_budget_usecs with work remaining over the last minute \

30 + (this can be a cause for dropped packets)

31 to: silent

32

33 alarm: 10min_netisr_backlog_exceeded

@@ -36,5 +39,7 @@

39 every: 10s

40 warn: $this > (($status >= $WARNING) ? (0) : (10))

41 delay: down 1h multiplier 1.5 max 2h

39 - info: average number of drops in the last 1min, because sysctl net.route.netisr_maxqlen was exceeded (this can be a cause for dropped packets)

42 + info: average number of drops in the last minute \

43 + due to exceeded sysctl net.route.netisr_maxqlen \

44 + (this can be a cause for dropped packets)

45 to: sysadmin

health/health.d/swap.conf

+2 -2

@@ -12,7 +12,7 @@

12 every: 1m

13 warn: $this > (($status >= $WARNING) ? (20) : (30))

14 delay: down 15m multiplier 1.5 max 1h

15 - info: the amount of memory swapped in the last 30 minutes, as a percentage of the system RAM

15 + info: percentage of the system RAM swapped in the last 30 minutes

16 to: sysadmin

17

18 alarm: used_swap

@@ -25,5 +25,5 @@

25 warn: $this > (($status >= $WARNING) ? (80) : (90))

26 crit: $this > (($status == $CRITICAL) ? (90) : (98))

27 delay: up 30s down 15m multiplier 1.5 max 1h

28 - info: the percentage of swap memory used

28 + info: swap memory utilization

29 to: sysadmin

health/health.d/synchronization.conf

+5 -3

@@ -1,10 +1,12 @@

1 alarm: sync_freq

2 on: mem.sync

3 - lookup: sum -1m

3 + lookup: sum -1m of sync

4 units: calls

5 plugin: ebpf.plugin

6 every: 1m

7 warn: $this > 6

8 - delay: down 10m multiplier 1.5 max 1h

9 - info: Your OS is making a considerable number of synchronization to file descriptor in a short period of time.

8 + delay: up 1m down 10m multiplier 1.5 max 1h

9 + info: number of sync() system calls. \

10 + Every call causes all pending modifications to filesystem metadata and \

11 + cached file data to be written to the underlying filesystems.

12 to: sysadmin

health/health.d/tcp_conn.conf

+1 -1

@@ -15,5 +15,5 @@

15 warn: $this > (($status >= $WARNING ) ? ( 60 ) : ( 80 ))

16 crit: $this > (($status == $CRITICAL) ? ( 80 ) : ( 90 ))

17 delay: up 0 down 5m multiplier 1.5 max 1h

18 - info: the percentage of IPv4 TCP connections over the max allowed

18 + info: IPv4 TCP connections utilization

19 to: sysadmin

health/health.d/tcp_listen.conf

+5 -4

@@ -28,7 +28,7 @@

28 warn: $this > 1

29 crit: $this > (($status == $CRITICAL) ? (1) : (5))

30 delay: up 0 down 5m multiplier 1.5 max 1h

31 - info: the average number of times the TCP accept queue of the kernel overflown, during the last minute

31 + info: average number of overflows in the TCP accept queue over the last minute

32 to: sysadmin

33

34 # THIS IS TOO GENERIC

@@ -43,7 +43,7 @@

43 warn: $this > 1

44 crit: $this > (($status == $CRITICAL) ? (1) : (5))

45 delay: up 0 down 5m multiplier 1.5 max 1h

46 - info: the average number of times the TCP accept queue of the kernel dropped packets, during the last minute (includes bogus packets received)

46 + info: average number of dropped packets in the TCP accept queue over the last minute

47 to: sysadmin

48

49

@@ -65,7 +65,8 @@

65 warn: $this > 1

66 crit: $this > (($status == $CRITICAL) ? (0) : (5))

67 delay: up 10 down 5m multiplier 1.5 max 1h

68 - info: the number of times the TCP SYN queue of the kernel was full and dropped packets, during the last minute

68 + info: average number of SYN requests was dropped due to the full TCP SYN queue over the last minute \

69 + (SYN cookies were not enabled)

70 to: sysadmin

71

72 alarm: 1m_tcp_syn_queue_cookies

@@ -78,6 +79,6 @@

79 warn: $this > 1

80 crit: $this > (($status == $CRITICAL) ? (0) : (5))

81 delay: up 10 down 5m multiplier 1.5 max 1h

81 - info: the number of times the TCP SYN queue of the kernel was full and sent SYN cookies, during the last minute

82 + info: average number of sent SYN cookies due to the full TCP SYN queue over the last minute

83 to: sysadmin

84

health/health.d/tcp_mem.conf

+1 -1

@@ -16,5 +16,5 @@

16 warn: ${mem} > (($status >= $WARNING ) ? ( ${tcp_mem_pressure} * 0.8 ) : ( ${tcp_mem_pressure} ))

17 crit: ${mem} > (($status == $CRITICAL ) ? ( ${tcp_mem_pressure} ) : ( ${tcp_mem_high} * 0.9 ))

18 delay: up 0 down 5m multiplier 1.5 max 1h

19 - info: the amount of TCP memory as a percentage of its max memory limit

19 + info: TCP memory utilization

20 to: sysadmin

health/health.d/tcp_orphans.conf

+1 -1

@@ -17,5 +17,5 @@

17 warn: $this > (($status >= $WARNING ) ? ( 20 ) : ( 25 ))

18 crit: $this > (($status == $CRITICAL) ? ( 25 ) : ( 50 ))

19 delay: up 0 down 5m multiplier 1.5 max 1h

20 - info: the percentage of orphan IPv4 TCP sockets over the max allowed (this may lead to too-many-orphans errors)

20 + info: orphan IPv4 TCP sockets utilization

21 to: sysadmin

health/health.d/tcp_resets.conf

+9 -4

@@ -11,7 +11,7 @@

11 lookup: average -1m at -10s unaligned absolute of OutRsts

12 units: tcp resets/s

13 every: 10s

14 - info: average TCP RESETS this host is sending, over the last minute

14 + info: average number of sent TCP RESETS over the last minute

15

16 alarm: 10s_ipv4_tcp_resets_sent

17 on: ipv4.tcphandshake

@@ -23,7 +23,10 @@

23 warn: $this > ((($1m_ipv4_tcp_resets_sent < 5)?(5):($1m_ipv4_tcp_resets_sent)) * (($status >= $WARNING) ? (1) : (20)))

24 delay: up 20s down 60m multiplier 1.2 max 2h

25 options: no-clear-notification

26 - info: average TCP RESETS this host is sending, over the last 10 seconds (this can be an indication that a port scan is made, or that a service running on this host has crashed; clear notification for this alarm will not be sent)

26 + info: average number of sent TCP RESETS over the last 10 seconds. \

27 + This can indicate a port scan, \

28 + or that a service running on this host has crashed. \

29 + Netdata will not send a clear notification for this alarm.

30 to: sysadmin

31

32 # -----------------------------------------------------------------------------

@@ -36,7 +39,7 @@

39 lookup: average -1m at -10s unaligned absolute of AttemptFails

40 units: tcp resets/s

41 every: 10s

39 - info: average TCP RESETS this host is sending, over the last minute

42 + info: average number of received TCP RESETS over the last minute

43

44 alarm: 10s_ipv4_tcp_resets_received

45 on: ipv4.tcphandshake

@@ -48,5 +51,7 @@

51 warn: $this > ((($1m_ipv4_tcp_resets_received < 5)?(5):($1m_ipv4_tcp_resets_received)) * (($status >= $WARNING) ? (1) : (10)))

52 delay: up 20s down 60m multiplier 1.2 max 2h

53 options: no-clear-notification

51 - info: average TCP RESETS this host is receiving, over the last 10 seconds (this can be an indication that a service this host needs, has crashed; clear notification for this alarm will not be sent)

54 + info: average number of received TCP RESETS over the last 10 seconds. \

55 + This can be an indication that a service this host needs has crashed. \

56 + Netdata will not send a clear notification for this alarm.

57 to: sysadmin

health/health.d/udp_errors.conf

+2 -2

@@ -12,7 +12,7 @@

12 units: errors

13 every: 10s

14 warn: $this > (($status >= $WARNING) ? (0) : (10))

15 - info: average number of UDP receive buffer errors during the last minute

15 + info: average number of UDP receive buffer errors over the last minute

16 delay: up 1m down 60m multiplier 1.2 max 2h

17 to: sysadmin

18

@@ -27,6 +27,6 @@

27 units: errors

28 every: 10s

29 warn: $this > (($status >= $WARNING) ? (0) : (10))

30 - info: number of UDP send buffer errors during the last minute

30 + info: average number of UDP send buffer errors over the last minute

31 delay: up 1m down 60m multiplier 1.2 max 2h

32 to: sysadmin

health/health.d/unbound.conf

+2 -2

@@ -21,7 +21,7 @@ template: unbound_request_list_overwritten

21 every: 10s

22 warn: $this > 5

23 delay: up 10 down 5m multiplier 1.5 max 1h

24 - info: the number of overwritten queries in the request-list

24 + info: number of overwritten queries in the request-list

25 to: sysadmin

26

27 template: unbound_request_list_dropped

@@ -31,5 +31,5 @@ template: unbound_request_list_dropped

31 every: 10s

32 warn: $this > 0

33 delay: up 10 down 5m multiplier 1.5 max 1h

34 - info: the number of dropped queries in the request-list

34 + info: number of dropped queries in the request-list

35 to: sysadmin

health/health.d/vcsa.conf

+16 -8

@@ -27,7 +27,8 @@ template: vcsa_system_health

27 warn: ($this == 1) || ($this == 2)

28 crit: $this == 3

29 delay: down 1m multiplier 1.5 max 1h

30 - info: overall system health status

30 + info: overall system health status \

31 + (-1: unknown, 0: green, 1: yellow, 2: orange, 3: red, 4: grey)

32 to: sysadmin

33

34 # Components health:

@@ -45,7 +46,8 @@ template: vcsa_swap_health

46 warn: $this == 1

47 crit: ($this == 2) || ($this == 3)

48 delay: down 1m multiplier 1.5 max 1h

48 - info: swap health status

49 + info: swap health status \

50 + (-1: unknown, 0: green, 1: yellow, 2: orange, 3: red, 4: grey)

51 to: sysadmin

52

53 template: vcsa_storage_health

@@ -56,7 +58,8 @@ template: vcsa_storage_health

58 warn: $this == 1

59 crit: ($this == 2) || ($this == 3)

60 delay: down 1m multiplier 1.5 max 1h

59 - info: storage health status

61 + info: storage health status \

62 + (-1: unknown, 0: green, 1: yellow, 2: orange, 3: red, 4: grey)

63 to: sysadmin

64

65 template: vcsa_mem_health

@@ -67,7 +70,8 @@ template: vcsa_mem_health

70 warn: $this == 1

71 crit: ($this == 2) || ($this == 3)

72 delay: down 1m multiplier 1.5 max 1h

70 - info: mem health status

73 + info: memory health status \

74 + (-1: unknown, 0: green, 1: yellow, 2: orange, 3: red, 4: grey)

75 to: sysadmin

76

77 template: vcsa_load_health

@@ -78,7 +82,8 @@ template: vcsa_load_health

82 warn: $this == 1

83 crit: ($this == 2) || ($this == 3)

84 delay: down 1m multiplier 1.5 max 1h

81 - info: load health status

85 + info: load health status \

86 + (-1: unknown, 0: green, 1: yellow, 2: orange, 3: red, 4: grey)

87 to: sysadmin

88

89 template: vcsa_database_storage_health

@@ -89,7 +94,8 @@ template: vcsa_database_storage_health

94 warn: $this == 1

95 crit: ($this == 2) || ($this == 3)

96 delay: down 1m multiplier 1.5 max 1h

92 - info: database storage health status

97 + info: database storage health status \

98 + (-1: unknown, 0: green, 1: yellow, 2: orange, 3: red, 4: grey)

99 to: sysadmin

100

101 template: vcsa_applmgmt_health

@@ -100,7 +106,8 @@ template: vcsa_applmgmt_health

106 warn: $this == 1

107 crit: ($this == 2) || ($this == 3)

108 delay: down 1m multiplier 1.5 max 1h

103 - info: appl mgmt health status

109 + info: applmgmt health status \

110 + (-1: unknown, 0: green, 1: yellow, 2: orange, 3: red, 4: grey)

111 to: sysadmin

112

113

@@ -118,5 +125,6 @@ template: vcsa_software_updates_health

125 warn: $this == 4

126 crit: $this == 3

127 delay: down 1m multiplier 1.5 max 1h

121 - info: software packages health status

128 + info: software updates availability status \

129 + (-1: unknown, 0: green, 2: orange, 3: red, 4: grey)

130 to: sysadmin

health/health.d/vernemq.conf

+26 -26

@@ -21,7 +21,7 @@ template: vernemq_socket_errors

21 every: 1m

22 warn: $this > (($status >= $WARNING) ? (0) : (5))

23 delay: up 2m down 5m multiplier 1.5 max 2h

24 - info: socket errors in the last minute

24 + info: number of socket errors in the last minute

25 to: sysadmin

26

27 # Queues dropped/expired/unhandled PUBLISH messages

@@ -33,7 +33,7 @@ template: vernemq_queue_message_drop

33 every: 1m

34 warn: $this > (($status >= $WARNING) ? (0) : (5))

35 delay: up 5m down 5m multiplier 1.5 max 2h

36 - info: dropped messaged due to full queues in the last minute

36 + info: number of dropped messaged due to full queues in the last minute

37 to: sysadmin

38

39 template: vernemq_queue_message_expired

@@ -43,7 +43,7 @@ template: vernemq_queue_message_expired

43 every: 1m

44 warn: $this > (($status >= $WARNING) ? (0) : (15))

45 delay: up 5m down 5m multiplier 1.5 max 2h

46 - info: messages which expired before delivery in the last minute

46 + info: number of messages which expired before delivery in the last minute

47 to: sysadmin

48

49 template: vernemq_queue_message_unhandled

@@ -53,7 +53,7 @@ template: vernemq_queue_message_unhandled

53 every: 1m

54 warn: $this > (($status >= $WARNING) ? (0) : (5))

55 delay: up 5m down 5m multiplier 1.5 max 2h

56 - info: unhandled messages (connections with clean session=true) in the last minute

56 + info: number of unhandled messages (connections with clean session=true) in the last minute

57 to: sysadmin

58

59 # Erlang VM

@@ -66,7 +66,7 @@ template: vernemq_average_scheduler_utilization

66 warn: $this > (($status >= $WARNING) ? (75) : (85))

67 crit: $this > (($status == $CRITICAL) ? (85) : (95))

68 delay: down 15m multiplier 1.5 max 1h

69 - info: average scheduler utilization for the last 10 minutes

69 + info: average scheduler utilization over the last 10 minutes

70 to: sysadmin

71

72 # Cluster communication and netsplits

@@ -78,7 +78,7 @@ template: vernemq_cluster_dropped

78 every: 1m

79 warn: $this > 0

80 delay: up 5m down 5m multiplier 1.5 max 1h

81 - info: the amount of traffic dropped during communication with the cluster nodes in the last minute

81 + info: amount of traffic dropped during communication with the cluster nodes in the last minute

82 to: sysadmin

83

84 template: vernemq_netsplits

@@ -88,7 +88,7 @@ template: vernemq_netsplits

88 every: 10s

89 warn: $this > 0

90 delay: down 5m multiplier 1.5 max 2h

91 - info: detected netsplits in the last minute

91 + info: number of detected netsplits (split brain situation) in the last minute

92 to: sysadmin

93

94 # Unsuccessful CONNACK

@@ -100,7 +100,7 @@ template: vernemq_mqtt_connack_sent_reason_unsuccessful

100 every: 1m

101 warn: $this > (($status >= $WARNING) ? (0) : (5))

102 delay: up 5m down 5m multiplier 1.5 max 2h

103 - info: unsuccessful v3/v5 CONNACK sent in the last minute

103 + info: number of sent unsuccessful v3/v5 CONNACK packets in the last minute

104 to: sysadmin

105

106 # Not normal DISCONNECT

@@ -112,7 +112,7 @@ template: vernemq_mqtt_disconnect_received_reason_not_normal

112 every: 1m

113 warn: $this > (($status >= $WARNING) ? (0) : (5))

114 delay: up 5m down 5m multiplier 1.5 max 2h

115 - info: not normal v5 DISCONNECT received in the last minute

115 + info: number of received not normal v5 DISCONNECT packets in the last minute

116 to: sysadmin

117

118 template: vernemq_mqtt_disconnect_sent_reason_not_normal

@@ -122,7 +122,7 @@ template: vernemq_mqtt_disconnect_sent_reason_not_normal

122 every: 1m

123 warn: $this > (($status >= $WARNING) ? (0) : (5))

124 delay: up 5m down 5m multiplier 1.5 max 2h

125 - info: not normal v5 DISCONNECT sent in the last minute

125 + info: number of sent not normal v5 DISCONNECT packets in the last minute

126 to: sysadmin

127

128 # SUBSCRIBE errors and unauthorized attempts

@@ -134,7 +134,7 @@ template: vernemq_mqtt_subscribe_error

134 every: 1m

135 warn: $this > (($status >= $WARNING) ? (0) : (5))

136 delay: up 5m down 5m multiplier 1.5 max 2h

137 - info: failed v3/v5 SUBSCRIBE operations in the last minute

137 + info: number of failed v3/v5 SUBSCRIBE operations in the last minute

138 to: sysadmin

139

140 template: vernemq_mqtt_subscribe_auth_error

@@ -144,7 +144,7 @@ template: vernemq_mqtt_subscribe_auth_error

144 every: 1m

145 warn: $this > (($status >= $WARNING) ? (0) : (5))

146 delay: up 5m down 5m multiplier 1.5 max 2h

147 - info: unauthorized v3/v5 SUBSCRIBE attempts in the last minute

147 + info: number of unauthorized v3/v5 SUBSCRIBE attempts in the last minute

148 to: sysadmin

149

150 # UNSUBSCRIBE errors

@@ -156,7 +156,7 @@ template: vernemq_mqtt_unsubscribe_error

156 every: 1m

157 warn: $this > (($status >= $WARNING) ? (0) : (5))

158 delay: up 5m down 5m multiplier 1.5 max 2h

159 - info: failed v3/v5 UNSUBSCRIBE operations in the last minute

159 + info: number of failed v3/v5 UNSUBSCRIBE operations in the last minute

160 to: sysadmin

161

162 # PUBLISH errors and unauthorized attempts

@@ -168,7 +168,7 @@ template: vernemq_mqtt_publish_errors

168 every: 1m

169 warn: $this > (($status >= $WARNING) ? (0) : (5))

170 delay: up 5m down 5m multiplier 1.5 max 2h

171 - info: failed v3/v5 PUBLISH operations in the last minute

171 + info: number of failed v3/v5 PUBLISH operations in the last minute

172 to: sysadmin

173

174 template: vernemq_mqtt_publish_auth_errors

@@ -178,7 +178,7 @@ template: vernemq_mqtt_publish_auth_errors

178 every: 1m

179 warn: $this > (($status >= $WARNING) ? (0) : (5))

180 delay: up 5m down 5m multiplier 1.5 max 2h

181 - info: unauthorized v3/v5 PUBLISH attempts in the last minute

181 + info: number of unauthorized v3/v5 PUBLISH attempts in the last minute

182 to: sysadmin

183

184 # Unsuccessful and unexpected PUBACK

@@ -190,7 +190,7 @@ template: vernemq_mqtt_puback_received_reason_unsuccessful

190 every: 1m

191 warn: $this > (($status >= $WARNING) ? (0) : (5))

192 delay: up 5m down 5m multiplier 1.5 max 2h

193 - info: unsuccessful v5 PUBACK received in the last minute

193 + info: number of received unsuccessful v5 PUBACK packets in the last minute

194 to: sysadmin

195

196 template: vernemq_mqtt_puback_sent_reason_unsuccessful

@@ -200,7 +200,7 @@ template: vernemq_mqtt_puback_sent_reason_unsuccessful

200 every: 1m

201 warn: $this > (($status >= $WARNING) ? (0) : (5))

202 delay: up 5m down 5m multiplier 1.5 max 2h

203 - info: unsuccessful v5 PUBACK sent in the last minute

203 + info: number of sent unsuccessful v5 PUBACK packets in the last minute

204 to: sysadmin

205

206 template: vernemq_mqtt_puback_unexpected

@@ -210,7 +210,7 @@ template: vernemq_mqtt_puback_unexpected

210 every: 1m

211 warn: $this > (($status >= $WARNING) ? (0) : (5))

212 delay: up 5m down 5m multiplier 1.5 max 2h

213 - info: unexpected v3/v5 PUBACK received in the last minute

213 + info: number of received unexpected v3/v5 PUBACK packets in the last minute

214 to: sysadmin

215

216 # Unsuccessful and unexpected PUBREC

@@ -222,7 +222,7 @@ template: vernemq_mqtt_pubrec_received_reason_unsuccessful

222 every: 1m

223 warn: $this > (($status >= $WARNING) ? (0) : (5))

224 delay: up 5m down 5m multiplier 1.5 max 2h

225 - info: unsuccessful v5 PUBREC received in the last minute

225 + info: number of received unsuccessful v5 PUBREC packets in the last minute

226 to: sysadmin

227

228 template: vernemq_mqtt_pubrec_sent_reason_unsuccessful

@@ -232,7 +232,7 @@ template: vernemq_mqtt_pubrec_sent_reason_unsuccessful

232 every: 1m

233 warn: $this > (($status >= $WARNING) ? (0) : (5))

234 delay: up 5m down 5m multiplier 1.5 max 2h

235 - info: unsuccessful v5 PUBREC sent in the last minute

235 + info: number of sent unsuccessful v5 PUBREC packets in the last minute

236 to: sysadmin

237

238 template: vernemq_mqtt_pubrec_invalid_error

@@ -242,7 +242,7 @@ template: vernemq_mqtt_pubrec_invalid_error

242 every: 1m

243 warn: $this > (($status >= $WARNING) ? (0) : (5))

244 delay: up 5m down 5m multiplier 1.5 max 2h

245 - info: unexpected v3 PUBREC received in the last minute

245 + info: number of received unexpected v3 PUBREC packets in the last minute

246 to: sysadmin

247

248 # Unsuccessful PUBREL

@@ -254,7 +254,7 @@ template: vernemq_mqtt_pubrel_received_reason_unsuccessful

254 every: 1m

255 warn: $this > (($status >= $WARNING) ? (0) : (5))

256 delay: up 5m down 5m multiplier 1.5 max 2h

257 - info: unsuccessful v5 PUBREL received in the last minute

257 + info: number of received unsuccessful v5 PUBREL packets in the last minute

258 to: sysadmin

259

260 template: vernemq_mqtt_pubrel_sent_reason_unsuccessful

@@ -264,7 +264,7 @@ template: vernemq_mqtt_pubrel_sent_reason_unsuccessful

264 every: 1m

265 warn: $this > (($status >= $WARNING) ? (0) : (5))

266 delay: up 5m down 5m multiplier 1.5 max 2h

267 - info: unsuccessful v5 PUBREL sent in the last minute

267 + info: number of sent unsuccessful v5 PUBREL packets in the last minute

268 to: sysadmin

269

270 # Unsuccessful and unexpected PUBCOMP

@@ -276,7 +276,7 @@ template: vernemq_mqtt_pubcomp_received_reason_unsuccessful

276 every: 1m

277 warn: $this > (($status >= $WARNING) ? (0) : (5))

278 delay: up 5m down 5m multiplier 1.5 max 2h

279 - info: unsuccessful v5 PUBCOMP received in the last minute

279 + info: number of received unsuccessful v5 PUBCOMP packets in the last minute

280 to: sysadmin

281

282 template: vernemq_mqtt_pubcomp_sent_reason_unsuccessful

@@ -286,7 +286,7 @@ template: vernemq_mqtt_pubcomp_sent_reason_unsuccessful

286 every: 1m

287 warn: $this > (($status >= $WARNING) ? (0) : (5))

288 delay: up 5m down 5m multiplier 1.5 max 2h

289 - info: unsuccessful v5 PUBCOMP sent in the last minute

289 + info: number of sent unsuccessful v5 PUBCOMP packets in the last minute

290 to: sysadmin

291

292 template: vernemq_mqtt_pubcomp_unexpected

@@ -296,5 +296,5 @@ template: vernemq_mqtt_pubcomp_unexpected

296 every: 1m

297 warn: $this > (($status >= $WARNING) ? (0) : (5))

298 delay: up 5m down 5m multiplier 1.5 max 2h

299 - info: unexpected v3/v5 PUBCOMP received in the last minute

299 + info: number of received unexpected v3/v5 PUBCOMP packets in the last minute

300 to: sysadmin

health/health.d/vsphere.conf

+23 -39

@@ -13,7 +13,7 @@ template: vsphere_vm_mem_usage

13 warn: $this > (($status >= $WARNING) ? (80) : (90))

14 crit: $this > (($status == $CRITICAL) ? (90) : (98))

15 delay: down 15m multiplier 1.5 max 1h

16 - info: used RAM

16 + info: virtual machine memory utilization

17

18 # -----------------------------------------------HOST Specific----------------------------------------------------------

19 # Memory

@@ -27,7 +27,7 @@ template: vsphere_host_mem_usage

27 warn: $this > (($status >= $WARNING) ? (80) : (90))

28 crit: $this > (($status == $CRITICAL) ? (90) : (98))

29 delay: down 15m multiplier 1.5 max 1h

30 - info: used RAM

30 + info: host memory utilization

31

32 # Network errors

33

@@ -38,10 +38,7 @@ families: *

38 lookup: sum -10m unaligned absolute match-names of rx

39 units: packets

40 every: 1m

41 - warn: $this >= 5

42 - delay: down 1h multiplier 1.5 max 2h

43 - info: interface inbound dropped packets in the last 10 minutes

44 - to: sysadmin

41 + info: number of inbound errors for the network interface in the last 10 minutes

42

43 template: vsphere_outbound_packets_errors

44 on: vsphere.net_errors_total

@@ -50,10 +47,7 @@ families: *

47 lookup: sum -10m unaligned absolute match-names of tx

48 units: packets

49 every: 1m

53 - warn: $this >= 5

54 - delay: down 1h multiplier 1.5 max 2h

55 - info: interface outbound dropped packets in the last 10 minutes

56 - to: sysadmin

50 + info: number of outbound errors for the network interface in the last 10 minutes

51

52 # Network errors ratio

53

@@ -62,13 +56,12 @@ template: vsphere_inbound_packets_errors_ratio

56 hosts: *

57 families: *

58 lookup: sum -10m unaligned absolute match-names of rx

65 - calc: (($vsphere_inbound_packets_errors != nan AND $this > 0) ? ($vsphere_inbound_packets_errors * 100 / $this) : (0))

59 + calc: (($vsphere_inbound_packets_errors != nan AND $this > 1000) ? ($vsphere_inbound_packets_errors * 100 / $this) : (0))

60 units: %

61 every: 1m

68 - warn: $this >= 0.1

69 - crit: $this >= 2

70 - delay: down 1h multiplier 1.5 max 2h

71 - info: the ratio of inbound errors vs the total number of received packets of the network interface, during the last 10 minutes

62 + warn: $this >= 2

63 + delay: up 1m down 1h multiplier 1.5 max 2h

64 + info: ratio of inbound errors for the network interface over the last 10 minutes

65 to: sysadmin

66

67 template: vsphere_outbound_packets_errors_ratio

@@ -76,13 +69,12 @@ template: vsphere_outbound_packets_errors_ratio

69 hosts: *

70 families: *

71 lookup: sum -10m unaligned absolute match-names of tx

79 - calc: (($vsphere_outbound_packets_errors != nan AND $this > 0) ? ($vsphere_outbound_packets_errors * 100 / $this) : (0))

72 + calc: (($vsphere_outbound_packets_errors != nan AND $this > 1000) ? ($vsphere_outbound_packets_errors * 100 / $this) : (0))

73 units: %

74 every: 1m

82 - warn: $this >= 0.1

83 - crit: $this >= 2

84 - delay: down 1h multiplier 1.5 max 2h

85 - info: the ratio of outbound errors vs the total number of sent packets of the network interface, during the last 10 minutes

75 + warn: $this >= 2

76 + delay: up 1m down 1h multiplier 1.5 max 2h

77 + info: ratio of outbound errors for the network interface over the last 10 minutes

78 to: sysadmin

79

80 # -----------------------------------------------Common-------------------------------------------------------------------

@@ -97,7 +89,7 @@ template: vsphere_cpu_usage

89 warn: $this > (($status >= $WARNING) ? (75) : (85))

90 crit: $this > (($status == $CRITICAL) ? (85) : (95))

91 delay: down 15m multiplier 1.5 max 1h

100 - info: cpu utilization for the last 10 minutes

92 + info: average CPU utilization

93 to: sysadmin

94

95 # Network drops

@@ -109,10 +101,7 @@ families: *

101 lookup: sum -10m unaligned absolute match-names of rx

102 units: packets

103 every: 1m

112 - warn: $this >= 5

113 - delay: down 1h multiplier 1.5 max 2h

114 - info: interface inbound dropped packets in the last 10 minutes

115 - to: sysadmin

104 + info: number of inbound dropped packets for the network interface in the last 10 minutes

105

106 template: vsphere_outbound_packets_dropped

107 on: vsphere.net_drops_total

@@ -121,10 +110,7 @@ families: *

110 lookup: sum -10m unaligned absolute match-names of tx

111 units: packets

112 every: 1m

124 - warn: $this >= 5

125 - delay: down 1h multiplier 1.5 max 2h

126 - info: interface outbound dropped packets in the last 10 minutes

127 - to: sysadmin

113 + info: number of outbound dropped packets for the network interface in the last 10 minutes

114

115 # Network drops ratio

116

@@ -133,13 +119,12 @@ template: vsphere_inbound_packets_dropped_ratio

119 hosts: *

120 families: *

121 lookup: sum -10m unaligned absolute match-names of rx

136 - calc: (($vsphere_inbound_packets_dropped != nan AND $this > 0) ? ($vsphere_inbound_packets_dropped * 100 / $this) : (0))

122 + calc: (($vsphere_inbound_packets_dropped != nan AND $this > 1000) ? ($vsphere_inbound_packets_dropped * 100 / $this) : (0))

123 units: %

124 every: 1m

139 - warn: $this >= 0.1

140 - crit: $this >= 2

141 - delay: down 1h multiplier 1.5 max 2h

142 - info: the ratio of inbound dropped packets vs the total number of received packets of the network interface, during the last 10 minutes

125 + warn: $this >= 2

126 + delay: up 1m down 1h multiplier 1.5 max 2h

127 + info: ratio of inbound dropped packets for the network interface over the last 10 minutes

128 to: sysadmin

129

130 template: vsphere_outbound_packets_dropped_ratio

@@ -147,11 +132,10 @@ template: vsphere_outbound_packets_dropped_ratio

132 hosts: *

133 families: *

134 lookup: sum -10m unaligned absolute match-names of tx

150 - calc: (($vsphere_outbound_packets_dropped != nan AND $this > 0) ? ($vsphere_outbound_packets_dropped * 100 / $this) : (0))

135 + calc: (($vsphere_outbound_packets_dropped != nan AND $this > 1000) ? ($vsphere_outbound_packets_dropped * 100 / $this) : (0))

136 units: %

137 every: 1m

153 - warn: $this >= 0.1

154 - crit: $this >= 2

155 - delay: down 1h multiplier 1.5 max 2h

156 - info: the ratio of outbound dropped packets vs the total number of sent packets of the network interface, during the last 10 minutes

138 + warn: $this >= 2

139 + delay: up 1m down 1h multiplier 1.5 max 2h

140 + info: ratio of outbound dropped packets for the network interface over the last 10 minutes

141 to: sysadmin

health/health.d/web_log.conf

+25 -25

@@ -31,7 +31,7 @@ families: *

31 calc: ($this == 0)?(1):($this)

32 units: requests

33 every: 10s

34 - info: the sum of all HTTP requests over the last minute

34 + info: number of HTTP requests in the last minute

35

36 template: 1m_successful

37 on: web_log.response_statuses

@@ -43,7 +43,7 @@ families: *

43 warn: ($1m_requests > 120) ? ($this < (($status >= $WARNING ) ? ( 95 ) : ( 85 )) ) : ( 0 )

44 crit: ($1m_requests > 120) ? ($this < (($status == $CRITICAL) ? ( 85 ) : ( 75 )) ) : ( 0 )

45 delay: up 2m down 15m multiplier 1.5 max 1h

46 - info: the ratio of successful HTTP responses (1xx, 2xx, 304, 401) over the last minute

46 + info: ratio of successful HTTP requests over the last minute (1xx, 2xx, 304, 401)

47 to: webmaster

48

49 template: 1m_redirects

@@ -56,7 +56,7 @@ families: *

56 warn: ($1m_requests > 120) ? ($this > (($status >= $WARNING ) ? ( 1 ) : ( 20 )) ) : ( 0 )

57 crit: ($1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 20 ) : ( 30 )) ) : ( 0 )

58 delay: up 2m down 15m multiplier 1.5 max 1h

59 - info: the ratio of HTTP redirects (3xx except 304) over the last minute

59 + info: ratio of redirection HTTP requests over the last minute (3xx except 304)

60 to: webmaster

61

62 template: 1m_bad_requests

@@ -69,7 +69,7 @@ families: *

69 warn: ($1m_requests > 120) ? ($this > (($status >= $WARNING) ? ( 10 ) : ( 30 )) ) : ( 0 )

70 crit: ($1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 30 ) : ( 50 )) ) : ( 0 )

71 delay: up 2m down 15m multiplier 1.5 max 1h

72 - info: the ratio of HTTP bad requests (4xx except 401) over the last minute

72 + info: ratio of client error HTTP requests over the last minute (4xx except 401)

73 to: webmaster

74

75 template: 1m_internal_errors

@@ -82,7 +82,7 @@ families: *

82 warn: ($1m_requests > 120) ? ($this > (($status >= $WARNING) ? ( 1 ) : ( 2 )) ) : ( 0 )

83 crit: ($1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 2 ) : ( 5 )) ) : ( 0 )

84 delay: up 2m down 15m multiplier 1.5 max 1h

85 - info: the ratio of HTTP internal server errors (5xx), over the last minute

85 + info: ratio of server error HTTP requests over the last minute (5xx)

86 to: webmaster

87

88 # unmatched lines

@@ -101,10 +101,10 @@ families: *

101 calc: ($this == 0)?(1):($this)

102 units: requests

103 every: 10s

104 - info: the sum of all HTTP requests over the last minute

104 + info: number of HTTP requests over the last minute

105

106 template: 1m_unmatched

107 -on: web_log.response_codes

107 + on: web_log.response_codes

108 families: *

109 lookup: sum -1m unaligned of unmatched

110 calc: $this * 100 / $1m_total_requests

@@ -112,7 +112,7 @@ families: *

112 every: 10s

113 warn: ($1m_total_requests > 120) ? ($this > 1) : ( 0 )

114 delay: up 1m down 5m multiplier 1.5 max 1h

115 - info: the ratio of unmatched lines, over the last minute

115 + info: percentage of unparsed log lines over the last minute

116 to: webmaster

117

118 # -----------------------------------------------------------------------------

@@ -131,7 +131,7 @@ families: *

131 lookup: average -10m unaligned of avg

132 units: ms

133 every: 30s

134 - info: the average time to respond to HTTP requests, over the last 10 minutes

134 + info: average HTTP response time over the last 10 minutes

135

136 template: web_slow

137 on: web_log.response_time

@@ -144,7 +144,7 @@ families: *

144 warn: ($1m_requests > 120) ? ($this > $green && $this > ($10m_response_time * 2) ) : ( 0 )

145 crit: ($1m_requests > 120) ? ($this > $red && $this > ($10m_response_time * 4) ) : ( 0 )

146 delay: down 15m multiplier 1.5 max 1h

147 - info: the average time to respond to HTTP requests, over the last 1 minute

147 + info: average HTTP response time over the last minute

148 options: no-clear-notification

149 to: webmaster

150

@@ -165,7 +165,7 @@ families: *

165 lookup: average -5m at -5m unaligned of successful_requests

166 units: requests/s

167 every: 30s

168 - info: average rate of successful HTTP requests over the last 5 minutes

168 + info: average number of successful HTTP requests for the 5 minutes starting 10 minutes ago

169

170 template: 5m_successful

171 on: web_log.response_statuses

@@ -173,7 +173,7 @@ families: *

173 lookup: average -5m unaligned of successful_requests

174 units: requests/s

175 every: 30s

176 - info: average successful HTTP requests over the last 5 minutes

176 + info: average number of successful HTTP requests over the last 5 minutes

177

178 template: 5m_requests_ratio

179 on: web_log.response_codes

@@ -185,7 +185,7 @@ families: *

185 crit: ($5m_successful_old > 120) ? ($this > 400 OR $this < 25) : (0)

186 delay: down 15m multiplier 1.5 max 1h

187 options: no-clear-notification

188 - info: the percentage of successful web requests over the last 5 minutes, \

188 + info: ratio of successful HTTP requests over the last 5 minutes, \

189 compared with the previous 5 minutes \

190 (clear notification for this alarm will not be sent)

191 to: webmaster

@@ -224,7 +224,7 @@ families: *

224 calc: ($this == 0)?(1):($this)

225 units: requests

226 every: 10s

227 - info: the sum of all HTTP requests over the last minute

227 + info: number of HTTP requests in the last minute

228

229 template: web_log_1m_unmatched

230 on: web_log.excluded_requests

@@ -235,7 +235,7 @@ families: *

235 every: 10s

236 warn: ($web_log_1m_total_requests > 120) ? ($this > 1) : ( 0 )

237 delay: up 1m down 5m multiplier 1.5 max 1h

238 - info: the ratio of unmatched lines, over the last minute

238 + info: percentage of unparsed log lines over the last minute

239 to: webmaster

240

241 # -----------------------------------------------------------------------------

@@ -255,7 +255,7 @@ families: *

255 calc: ($this == 0)?(1):($this)

256 units: requests

257 every: 10s

258 - info: the sum of all HTTP requests over the last minute

258 + info: number of HTTP requests in the last minute

259

260 template: web_log_1m_successful

261 on: web_log.type_requests

@@ -267,7 +267,7 @@ families: *

267 warn: ($web_log_1m_requests > 120) ? ($this < (($status >= $WARNING ) ? ( 95 ) : ( 85 )) ) : ( 0 )

268 crit: ($web_log_1m_requests > 120) ? ($this < (($status == $CRITICAL) ? ( 85 ) : ( 75 )) ) : ( 0 )

269 delay: up 2m down 15m multiplier 1.5 max 1h

270 - info: the ratio of successful HTTP responses (1xx, 2xx, 304, 401) over the last minute

270 + info: ratio of successful HTTP requests over the last minute (1xx, 2xx, 304, 401)

271 to: webmaster

272

273 template: web_log_1m_redirects

@@ -280,7 +280,7 @@ families: *

280 warn: ($web_log_1m_requests > 120) ? ($this > (($status >= $WARNING ) ? ( 1 ) : ( 20 )) ) : ( 0 )

281 crit: ($web_log_1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 20 ) : ( 30 )) ) : ( 0 )

282 delay: up 2m down 15m multiplier 1.5 max 1h

283 - info: the ratio of HTTP redirects (3xx except 304) over the last minute

283 + info: ratio of redirection HTTP requests over the last minute (3xx except 304)

284 to: webmaster

285

286 template: web_log_1m_bad_requests

@@ -293,7 +293,7 @@ families: *

293 warn: ($web_log_1m_requests > 120) ? ($this > (($status >= $WARNING) ? ( 10 ) : ( 30 )) ) : ( 0 )

294 crit: ($web_log_1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 30 ) : ( 50 )) ) : ( 0 )

295 delay: up 2m down 15m multiplier 1.5 max 1h

296 - info: the ratio of HTTP bad requests (4xx except 401) over the last minute

296 + info: ratio of client error HTTP requests over the last minute (4xx except 401)

297 to: webmaster

298

299 template: web_log_1m_internal_errors

@@ -306,7 +306,7 @@ families: *

306 warn: ($web_log_1m_requests > 120) ? ($this > (($status >= $WARNING) ? ( 1 ) : ( 2 )) ) : ( 0 )

307 crit: ($web_log_1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 2 ) : ( 5 )) ) : ( 0 )

308 delay: up 2m down 15m multiplier 1.5 max 1h

309 - info: the ratio of HTTP internal server errors (5xx), over the last minute

309 + info: ratio of server error HTTP requests over the last minute (5xx)

310 to: webmaster

311

312 # -----------------------------------------------------------------------------

@@ -325,7 +325,7 @@ families: *

325 lookup: average -10m unaligned of avg

326 units: ms

327 every: 30s

328 - info: the average time to respond to HTTP requests, over the last 10 minutes

328 + info: average HTTP response time over the last 10 minutes

329

330 template: web_log_web_slow

331 on: web_log.request_processing_time

@@ -338,7 +338,7 @@ families: *

338 warn: ($web_log_1m_requests > 120) ? ($this > $green && $this > ($web_log_10m_response_time * 2) ) : ( 0 )

339 crit: ($web_log_1m_requests > 120) ? ($this > $red && $this > ($web_log_10m_response_time * 4) ) : ( 0 )

340 delay: down 15m multiplier 1.5 max 1h

341 - info: the average time to respond to HTTP requests, over the last 1 minute

341 + info: average HTTP response time over the last 1 minute

342 options: no-clear-notification

343 to: webmaster

344

@@ -359,7 +359,7 @@ families: *

359 lookup: average -5m at -5m unaligned of success

360 units: requests/s

361 every: 30s

362 - info: average rate of successful HTTP requests over the last 5 minutes

362 + info: average number of successful HTTP requests for the 5 minutes starting 10 minutes ago

363

364 template: web_log_5m_successful

365 on: web_log.type_requests

@@ -367,7 +367,7 @@ families: *

367 lookup: average -5m unaligned of success

368 units: requests/s

369 every: 30s

370 - info: average successful HTTP requests over the last 5 minutes

370 + info: average number of successful HTTP requests over the last 5 minutes

371

372 template: web_log_5m_requests_ratio

373 on: web_log.type_requests

@@ -379,7 +379,7 @@ families: *

379 crit: ($web_log_5m_successful_old > 120) ? ($this > 400 OR $this < 25) : (0)

380 delay: down 15m multiplier 1.5 max 1h

381 options: no-clear-notification

382 - info: the percentage of successful web requests over the last 5 minutes, \

382 + info: ratio of successful HTTP requests over over the last 5 minutes, \

383 compared with the previous 5 minutes \

384 (clear notification for this alarm will not be sent)

385 to: webmaster

health/health.d/whoisquery.conf

+1 -1

@@ -20,5 +20,5 @@ template: whoisquery_days_until_expiration

20 every: 60s

21 warn: $this < $days_until_expiration_warning*24*60*60

22 crit: $this < $days_until_expiration_critical*24*60*60

23 - info: domain time until expiration

23 + info: time until the domain name registration expires

24 to: webmaster

health/health.d/wmi.conf

+8 -8

@@ -26,7 +26,7 @@ template: wmi_10min_cpu_usage

26 warn: $this > (($status >= $WARNING) ? (75) : (85))

27 crit: $this > (($status == $CRITICAL) ? (85) : (95))

28 delay: down 15m multiplier 1.5 max 1h

29 - info: cpu utilization for the last 10 minutes

29 + info: average CPU utilization over the last 10 minutes

30 to: sysadmin

31

32

@@ -42,7 +42,7 @@ template: wmi_ram_in_use

42 warn: $this > (($status >= $WARNING) ? (80) : (90))

43 crit: $this > (($status == $CRITICAL) ? (90) : (98))

44 delay: down 15m multiplier 1.5 max 1h

45 - info: used RAM

45 + info: memory utilization

46 to: sysadmin

47

48 template: wmi_swap_in_use

@@ -55,7 +55,7 @@ template: wmi_swap_in_use

55 warn: $this > (($status >= $WARNING) ? (80) : (90))

56 crit: $this > (($status == $CRITICAL) ? (90) : (98))

57 delay: down 15m multiplier 1.5 max 1h

58 - info: used Swap

58 + info: swap memory utilization

59 to: sysadmin

60

61

@@ -71,7 +71,7 @@ families: *

71 every: 1m

72 warn: $this >= 5

73 delay: down 1h multiplier 1.5 max 2h

74 - info: interface inbound discarded packets in the last 10 minutes

74 + info: number of inbound discarded packets for the network interface in the last 10 minutes

75 to: sysadmin

76

77 template: wmi_outbound_packets_discarded

@@ -84,7 +84,7 @@ families: *

84 every: 1m

85 warn: $this >= 5

86 delay: down 1h multiplier 1.5 max 2h

87 - info: interface outbound discarded packets in the last 10 minutes

87 + info: number of outbound discarded packets for the network interface in the last 10 minutes

88 to: sysadmin

89

90 template: wmi_inbound_packets_errors

@@ -97,7 +97,7 @@ families: *

97 every: 1m

98 warn: $this >= 5

99 delay: down 1h multiplier 1.5 max 2h

100 - info: interface inbound errors in the last 10 minutes

100 + info: number of inbound errors for the network interface in the last 10 minutes

101 to: sysadmin

102

103 template: wmi_outbound_packets_errors

@@ -110,7 +110,7 @@ families: *

110 every: 1m

111 warn: $this >= 5

112 delay: down 1h multiplier 1.5 max 2h

113 - info: interface outbound errors in the last 10 minutes

113 + info: number of outbound errors for the network interface in the last 10 minutes

114 to: sysadmin

115

116

@@ -126,5 +126,5 @@ template: wmi_disk_in_use

126 warn: $this > (($status >= $WARNING) ? (80) : (90))

127 crit: $this > (($status == $CRITICAL) ? (90) : (98))

128 delay: down 15m multiplier 1.5 max 1h

129 - info: used disk space

129 + info: disk space utilization

130 to: sysadmin

health/health.d/x509check.conf

+2 -2

@@ -20,7 +20,7 @@ template: x509check_days_until_expiration

20 every: 60s

21 warn: $this < $days_until_expiration_warning*24*60*60

22 crit: $this < $days_until_expiration_critical*24*60*60

23 - info: certificate time until expiration

23 + info: time until x509 certificate expires

24 to: webmaster

25

26 template: x509check_revocation_status

@@ -28,5 +28,5 @@ template: x509check_revocation_status

28 calc: $revoked

29 every: 60s

30 crit: $this != nan AND $this != 0

31 - info: certificate revocation status

31 + info: x509 certificate revocation status (0: revoked, 1: valid)

32 to: webmaster

health/health.d/zfs.conf

+1 -1

@@ -6,5 +6,5 @@

6 every: 1m

7 warn: $this > 0

8 delay: down 1h multiplier 1.5 max 2h

9 - info: the number of times ZFS had to limit the ARC growth in the last 10 minutes

9 + info: number of times ZFS had to limit the ARC growth in the last 10 minutes

10 to: sysadmin

health: improve alarms infos (#10853)