summaryrefslogtreecommitdiffstats
path: root/health/health.d/dbengine.conf
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2021-02-07 11:45:55 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2021-02-07 11:45:55 +0000
commita8220ab2d293bb7f4b014b79d16b2fb05090fa93 (patch)
tree77f0a30f016c0925cf7ee9292e644bba183c2774 /health/health.d/dbengine.conf
parentAdding upstream version 1.19.0. (diff)
downloadnetdata-a8220ab2d293bb7f4b014b79d16b2fb05090fa93.tar.xz
netdata-a8220ab2d293bb7f4b014b79d16b2fb05090fa93.zip
Adding upstream version 1.29.0.upstream/1.29.0
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'health/health.d/dbengine.conf')
-rw-r--r--health/health.d/dbengine.conf26
1 files changed, 19 insertions, 7 deletions
diff --git a/health/health.d/dbengine.conf b/health/health.d/dbengine.conf
index ce9839ef1..274673e3e 100644
--- a/health/health.d/dbengine.conf
+++ b/health/health.d/dbengine.conf
@@ -5,7 +5,7 @@
on: netdata.dbengine_global_errors
os: linux freebsd macos
hosts: *
-lookup: sum -10m unaligned of FS errors
+lookup: sum -10m unaligned of fs_errors
units: errors
every: 10s
crit: $this > 0
@@ -17,7 +17,7 @@ lookup: sum -10m unaligned of FS errors
on: netdata.dbengine_global_errors
os: linux freebsd macos
hosts: *
-lookup: sum -10m unaligned of I/O errors
+lookup: sum -10m unaligned of io_errors
units: errors
every: 10s
crit: $this > 0
@@ -25,14 +25,26 @@ lookup: sum -10m unaligned of I/O errors
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_errors
+ alarm: 10min_dbengine_global_flushing_warnings
on: netdata.dbengine_global_errors
os: linux freebsd macos
hosts: *
-lookup: sum -10m unaligned of flushing errors
+lookup: sum -10m unaligned of pg_cache_over_half_dirty_events
units: errors
- every: 3s
- crit: $this > 0
+ 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 times in the last 10 minutes that the dbengine failed to completely flush data to disk, metric data will not be stored in the database, please reduce disk load or use a faster disk
+ 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