blob: 274673e3e3b218cd7aed62af9fd21ab297734572 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
|
# you can disable an alarm notification by setting the 'to' line to: silent
alarm: 10min_dbengine_global_fs_errors
on: netdata.dbengine_global_errors
os: linux freebsd macos
hosts: *
lookup: sum -10m unaligned of fs_errors
units: errors
every: 10s
crit: $this > 0
delay: down 15m multiplier 1.5 max 1h
info: number of File-System errors dbengine came across the last 10 minutes (too many open files, wrong permissions etc)
to: sysadmin
alarm: 10min_dbengine_global_io_errors
on: netdata.dbengine_global_errors
os: linux freebsd macos
hosts: *
lookup: sum -10m unaligned of io_errors
units: errors
every: 10s
crit: $this > 0
delay: down 1h multiplier 1.5 max 3h
info: number of IO errors dbengine came across the last 10 minutes (CRC errors, out of space, bad disk etc)
to: sysadmin
alarm: 10min_dbengine_global_flushing_warnings
on: netdata.dbengine_global_errors
os: linux freebsd macos
hosts: *
lookup: sum -10m unaligned of pg_cache_over_half_dirty_events
units: errors
every: 10s
warn: $this > 0
delay: down 1h multiplier 1.5 max 3h
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
to: sysadmin
alarm: 10min_dbengine_global_flushing_errors
on: netdata.dbengine_long_term_page_stats
os: linux freebsd macos
hosts: *
lookup: sum -10m unaligned of flushing_pressure_deletions
units: pages
every: 10s
crit: $this != 0
delay: down 1h multiplier 1.5 max 3h
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
to: sysadmin
|
