1 files changed, 59 insertions, 0 deletions
diff --git a/src/health/health.d/dbengine.conf b/src/health/health.d/dbengine.conf
new file mode 100644
index 000000000..5585a9533
--- /dev/null
+++ b/src/health/health.d/dbengine.conf
@@ -0,0 +1,59 @@
+# you can disable an alarm notification by setting the 'to' line to: silent
+
+    alarm: 10min_dbengine_global_fs_errors
+       on: netdata.dbengine_global_errors
+    class: Errors
+     type: Netdata
+component: DB engine
+   lookup: sum -10m unaligned of fs_errors
+    units: errors
+    every: 10s
+     crit: $this > 0
+    delay: down 15m multiplier 1.5 max 1h
+  summary: Netdata DBengine filesystem errors
+     info: Number of filesystem errors in the last 10 minutes (too many open files, wrong permissions, etc)
+       to: sysadmin
+
+    alarm: 10min_dbengine_global_io_errors
+       on: netdata.dbengine_global_errors
+    class: Errors
+     type: Netdata
+component: DB engine
+   lookup: sum -10m unaligned of io_errors
+    units: errors
+    every: 10s
+     crit: $this > 0
+    delay: down 1h multiplier 1.5 max 3h
+  summary: Netdata DBengine IO errors
+     info: Number of IO errors in 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
+    class: Errors
+     type: Netdata
+component: DB engine
+   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
+  summary: Netdata DBengine global flushing warnings
+     info: number of times when dbengine dirty pages were over 50% of the instance's page cache in the last 10 minutes. \
+           Metric data are at risk of not being stored in the database. To remedy, reduce disk load or use faster disks.
+       to: sysadmin
+
+    alarm: 10min_dbengine_global_flushing_errors
+       on: netdata.dbengine_long_term_page_stats
+    class: Errors
+     type: Netdata
+component: DB engine
+   lookup: sum -10m unaligned of flushing_pressure_deletions
+    units: pages
+    every: 10s
+     crit: $this != 0
+    delay: down 1h multiplier 1.5 max 3h
+  summary: Netdata DBengine global flushing errors
+     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. To fix, reduce disk load or use faster disks.
+       to: sysadmin