From b8921c24c47c895ccdf35ff1c6424293b0933764 Mon Sep 17 00:00:00 2001 From: "Costa Tsaousis (ktsaou)" Date: Fri, 28 Oct 2016 21:34:26 +0300 Subject: [PATCH] take into account the chart update frequency to detect that last_collected alarms are CLEAR --- conf.d/health.d/apache.conf | 4 ++-- conf.d/health.d/disks.conf | 8 ++++---- conf.d/health.d/memcached.conf | 4 ++-- conf.d/health.d/mysql.conf | 4 ++-- conf.d/health.d/named.conf | 4 ++-- conf.d/health.d/net.conf | 4 ++-- conf.d/health.d/nginx.conf | 4 ++-- conf.d/health.d/redis.conf | 4 ++-- conf.d/health.d/retroshare.conf | 4 ++-- conf.d/health.d/squid.conf | 4 ++-- conf.d/health.d/tcp_resets.conf | 4 ++-- 11 files changed, 24 insertions(+), 24 deletions(-) diff --git a/conf.d/health.d/apache.conf b/conf.d/health.d/apache.conf index 0aaf0e00..0c98b877 100644 --- a/conf.d/health.d/apache.conf +++ b/conf.d/health.d/apache.conf @@ -6,8 +6,8 @@ template: apache_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection to: webmaster diff --git a/conf.d/health.d/disks.conf b/conf.d/health.d/disks.conf index cc7a4766..c333a303 100644 --- a/conf.d/health.d/disks.conf +++ b/conf.d/health.d/disks.conf @@ -7,8 +7,8 @@ template: disk_space_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection of the mount point to: sysadmin @@ -19,8 +19,8 @@ template: disk_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection of the block device to: sysadmin diff --git a/conf.d/health.d/memcached.conf b/conf.d/health.d/memcached.conf index 46a8ca0e..77be66c5 100644 --- a/conf.d/health.d/memcached.conf +++ b/conf.d/health.d/memcached.conf @@ -6,8 +6,8 @@ template: memcached_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection to: dba diff --git a/conf.d/health.d/mysql.conf b/conf.d/health.d/mysql.conf index a2cfa3ec..f95d7c59 100644 --- a/conf.d/health.d/mysql.conf +++ b/conf.d/health.d/mysql.conf @@ -6,8 +6,8 @@ template: mysql_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection to: dba diff --git a/conf.d/health.d/named.conf b/conf.d/health.d/named.conf index f2eaa83c..4fc65c8e 100644 --- a/conf.d/health.d/named.conf +++ b/conf.d/health.d/named.conf @@ -6,8 +6,8 @@ template: named_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection to: domainadmin diff --git a/conf.d/health.d/net.conf b/conf.d/health.d/net.conf index 7753aa18..6865f55e 100644 --- a/conf.d/health.d/net.conf +++ b/conf.d/health.d/net.conf @@ -6,8 +6,8 @@ template: interface_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection to: sysadmin diff --git a/conf.d/health.d/nginx.conf b/conf.d/health.d/nginx.conf index d70d6a59..a686c3d9 100644 --- a/conf.d/health.d/nginx.conf +++ b/conf.d/health.d/nginx.conf @@ -6,8 +6,8 @@ template: nginx_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection to: webmaster diff --git a/conf.d/health.d/redis.conf b/conf.d/health.d/redis.conf index 3e648d85..5f6d397e 100644 --- a/conf.d/health.d/redis.conf +++ b/conf.d/health.d/redis.conf @@ -6,8 +6,8 @@ template: redis_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection to: dba diff --git a/conf.d/health.d/retroshare.conf b/conf.d/health.d/retroshare.conf index 1af7b468..2344b60e 100644 --- a/conf.d/health.d/retroshare.conf +++ b/conf.d/health.d/retroshare.conf @@ -5,8 +5,8 @@ template: retroshare_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection to: sysadmin diff --git a/conf.d/health.d/squid.conf b/conf.d/health.d/squid.conf index 76143c5d..06cc9678 100644 --- a/conf.d/health.d/squid.conf +++ b/conf.d/health.d/squid.conf @@ -6,8 +6,8 @@ template: squid_last_collected_secs calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection to: proxyadmin diff --git a/conf.d/health.d/tcp_resets.conf b/conf.d/health.d/tcp_resets.conf index fbb7b389..a7cb325f 100644 --- a/conf.d/health.d/tcp_resets.conf +++ b/conf.d/health.d/tcp_resets.conf @@ -5,8 +5,8 @@ calc: $now - $last_collected_t units: seconds ago every: 10s - warn: $this > (($status >= $WARNING) ? (0) : ( 5 * $update_every)) - crit: $this > (($status == $CRITICAL) ? (0) : (60 * $update_every)) + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) delay: up 0 down 5m multiplier 1.5 max 1h info: number of seconds since the last successful data collection to: sysadmin -- 2.39.2