From 2e85f9325a797977eea9dfea0a925775ddd211d9 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 7 Feb 2021 12:49:00 +0100 Subject: Merging upstream version 1.29.0. Signed-off-by: Daniel Baumann --- health/health.d/dbengine.conf | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) (limited to 'health/health.d/dbengine.conf') 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 -- cgit v1.2.3