diff options
Diffstat (limited to 'health/health.d/kubelet.conf')
| -rw-r--r-- | health/health.d/kubelet.conf | 43 |
1 files changed, 23 insertions, 20 deletions
diff --git a/health/health.d/kubelet.conf b/health/health.d/kubelet.conf index d2ef24b58..5eda59b2c 100644 --- a/health/health.d/kubelet.conf +++ b/health/health.d/kubelet.conf @@ -4,26 +4,26 @@ # True (1) if the node is experiencing a configuration-related error, false (0) otherwise. - template: node_config_error + template: kubelet_node_config_error on: k8s_kubelet.kubelet_node_config_error calc: $kubelet_node_config_error units: bool every: 10s warn: $this == 1 delay: down 1m multiplier 1.5 max 2h - info: the node is experiencing a configuration-related error + info: the node is experiencing a configuration-related error (0: false, 1: true) to: sysadmin # Failed Token() requests to the alternate token source - template: token_requests + template: kubelet_token_requests lookup: sum -10s of token_fail_count on: k8s_kubelet.kubelet_token_requests units: failed requests every: 10s warn: $this > 0 delay: down 1m multiplier 1.5 max 2h - info: failed token requests to alternate token source + info: number of failed Token() requests to the alternate token source to: sysadmin # Docker and runtime operation errors @@ -35,7 +35,7 @@ every: 10s warn: $this > (($status >= $WARNING) ? (0) : (20)) delay: up 30s down 1m multiplier 1.5 max 2h - info: operations error + info: number of Docker or runtime operation errors to: sysadmin # ----------------------------------------------------------------------------- @@ -53,63 +53,66 @@ # quantile 0.5 -template: 1m_kubelet_pleg_relist_latency_quantile_05 +template: kubelet_1m_pleg_relist_latency_quantile_05 on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds lookup: average -1m unaligned of kubelet_pleg_relist_latency_05 units: microseconds every: 10s - info: the average value of pleg relisting latency during the last minute (quantile 0.5) + info: average Pod Lifecycle Event Generator relisting latency over the last minute (quantile 0.5) -template: 10s_kubelet_pleg_relist_latency_quantile_05 +template: kubelet_10s_pleg_relist_latency_quantile_05 on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds lookup: average -10s unaligned of kubelet_pleg_relist_latency_05 - calc: $this * 100 / (($1m_kubelet_pleg_relist_latency_quantile_05 < 1000)?(1000):($1m_kubelet_pleg_relist_latency_quantile_05)) + calc: $this * 100 / (($kubelet_1m_pleg_relist_latency_quantile_05 < 1000)?(1000):($kubelet_1m_pleg_relist_latency_quantile_05)) every: 10s units: % warn: $this > (($status >= $WARNING)?(100):(200)) crit: $this > (($status >= $WARNING)?(200):(400)) delay: down 1m multiplier 1.5 max 2h - info: the % of the pleg relisting latency in the last 10 seconds, compared to the last minute (quantile 0.5) + info: ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \ + compared to the last minute (quantile 0.5) to: sysadmin # quantile 0.9 -template: 1m_kubelet_pleg_relist_latency_quantile_09 +template: kubelet_1m_pleg_relist_latency_quantile_09 on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds lookup: average -1m unaligned of kubelet_pleg_relist_latency_09 units: microseconds every: 10s - info: the average value of pleg relisting latency during the last minute (quantile 0.9) + info: average Pod Lifecycle Event Generator relisting latency over the last minute (quantile 0.9) -template: 10s_kubelet_pleg_relist_latency_quantile_09 +template: kubelet_10s_pleg_relist_latency_quantile_09 on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds lookup: average -10s unaligned of kubelet_pleg_relist_latency_09 - calc: $this * 100 / (($1m_kubelet_pleg_relist_latency_quantile_09 < 1000)?(1000):($1m_kubelet_pleg_relist_latency_quantile_09)) + calc: $this * 100 / (($kubelet_1m_pleg_relist_latency_quantile_09 < 1000)?(1000):($kubelet_1m_pleg_relist_latency_quantile_09)) every: 10s units: % warn: $this > (($status >= $WARNING)?(200):(400)) crit: $this > (($status >= $WARNING)?(400):(800)) delay: down 1m multiplier 1.5 max 2h - info: the % of the pleg relisting latency in the last 10 seconds, compared to the last minute (quantile 0.9) + info: ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \ + compared to the last minute (quantile 0.9) to: sysadmin # quantile 0.99 -template: 1m_kubelet_pleg_relist_latency_quantile_099 +template: kubelet_1m_pleg_relist_latency_quantile_099 on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds lookup: average -1m unaligned of kubelet_pleg_relist_latency_099 units: microseconds every: 10s - info: the average value of pleg relisting latency during the last minute (quantile 0.99) + info: average Pod Lifecycle Event Generator relisting latency over the last minute (quantile 0.99) -template: 10s_kubelet_pleg_relist_latency_quantile_099 +template: kubelet_10s_pleg_relist_latency_quantile_099 on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds lookup: average -10s unaligned of kubelet_pleg_relist_latency_099 - calc: $this * 100 / (($1m_kubelet_pleg_relist_latency_quantile_099 < 1000)?(1000):($1m_kubelet_pleg_relist_latency_quantile_099)) + calc: $this * 100 / (($kubelet_1m_pleg_relist_latency_quantile_099 < 1000)?(1000):($kubelet_1m_pleg_relist_latency_quantile_099)) every: 10s units: % warn: $this > (($status >= $WARNING)?(400):(800)) crit: $this > (($status >= $WARNING)?(800):(1200)) delay: down 1m multiplier 1.5 max 2h - info: the % of the pleg relisting latency in the last 10 seconds, compared to the last minute (quantile 0.99) + info: ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \ + compared to the last minute (quantile 0.99) to: sysadmin |