| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | alarm: 10min_dbengine_global_fs_errors |
| 4 | on: netdata.dbengine_global_errors |
| 5 | class: Errors |
| 6 | type: Netdata |
| 7 | component: DB engine |
| 8 | lookup: sum -10m unaligned of fs_errors |
| 9 | units: errors |
| 10 | every: 10s |
| 11 | crit: $this > 0 |
| 12 | delay: down 15m multiplier 1.5 max 1h |
| 13 | summary: Netdata DBengine filesystem errors |
| 14 | info: Number of filesystem errors in the last 10 minutes (too many open files, wrong permissions, etc) |
| 15 | to: sysadmin |
| 16 | |
| 17 | alarm: 10min_dbengine_global_io_errors |
| 18 | on: netdata.dbengine_global_errors |
| 19 | class: Errors |
| 20 | type: Netdata |
| 21 | component: DB engine |
| 22 | lookup: sum -10m unaligned of io_errors |
| 23 | units: errors |
| 24 | every: 10s |
| 25 | crit: $this > 0 |
| 26 | delay: down 1h multiplier 1.5 max 3h |
| 27 | summary: Netdata DBengine IO errors |
| 28 | info: Number of IO errors in the last 10 minutes (CRC errors, out of space, bad disk, etc) |
| 29 | to: sysadmin |
| 30 | |
| 31 | alarm: 10min_dbengine_global_flushing_warnings |
| 32 | on: netdata.dbengine_global_errors |
| 33 | class: Errors |
| 34 | type: Netdata |
| 35 | component: DB engine |
| 36 | lookup: sum -10m unaligned of pg_cache_over_half_dirty_events |
| 37 | units: errors |
| 38 | every: 10s |
| 39 | warn: $this > 0 |
| 40 | delay: down 1h multiplier 1.5 max 3h |
| 41 | summary: Netdata DBengine global flushing warnings |
| 42 | info: number of times when dbengine dirty pages were over 50% of the instance's page cache in the last 10 minutes. \ |
| 43 | Metric data are at risk of not being stored in the database. To remedy, reduce disk load or use faster disks. |
| 44 | to: sysadmin |
| 45 | |
| 46 | alarm: 10min_dbengine_global_flushing_errors |
| 47 | on: netdata.dbengine_long_term_page_stats |
| 48 | class: Errors |
| 49 | type: Netdata |
| 50 | component: DB engine |
| 51 | lookup: sum -10m unaligned of flushing_pressure_deletions |
| 52 | units: pages |
| 53 | every: 10s |
| 54 | crit: $this != 0 |
| 55 | delay: down 1h multiplier 1.5 max 3h |
| 56 | summary: Netdata DBengine global flushing errors |
| 57 | info: Number of pages deleted due to failure to flush data to disk in the last 10 minutes. \ |
| 58 | Metric data were lost to unblock data collection. To fix, reduce disk load or use faster disks. |
| 59 | to: sysadmin |