Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Migrate prometheus pre 1.14 rules only when prometheus-operator.kubeTargetVersionOverride is set to 1.13.0-0 #1301

Merged
merged 1 commit into from
Jan 8, 2021
Merged

Migrate prometheus pre 1.14 rules only when prometheus-operator.kubeTargetVersionOverride is set to 1.13.0-0 #1301

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 5 additions & 7 deletions deploy/helm/sumologic/upgrade-2.0.0.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,17 +181,14 @@ function migrate_prometheus_recording_rules() {
fi

local RECORDING_RULES_OVERRIDE
RECORDING_RULES_OVERRIDE=$(yq r "${TEMP_FILE}" -- 'prometheus-operator.kubeTargetVersionOverride')
readonly RECORDING_RULES_OVERRIDE=$(yq r "${TEMP_FILE}" -- 'prometheus-operator.kubeTargetVersionOverride')

if [[ "${RECORDING_RULES_OVERRIDE}" == "1.13.0-0" ]]; then
add_prometheus_pre_1_14_recording_rules "${TEMP_FILE}"
info "Removing prometheus kubeTargetVersionOverride='1.13.0-0'"
yq d -i "${TEMP_FILE}" "prometheus-operator.kubeTargetVersionOverride"
add_prometheus_pre_1_14_recording_rules "${TEMP_FILE}"
elif [[ -z "${RECORDING_RULES_OVERRIDE}" ]]; then
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what about this condition? What if kubeTargetVersionOverride is unset?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We don't want to add pre 1.14 rules then.
As per discussion with @frankreno

add_prometheus_pre_1_14_recording_rules "${TEMP_FILE}"
else
warning "prometheus-operator.kubeTargetVersionOverride should be unset or set to '1.13.0-0'"
warning "Actually it's set to: ${RECORDING_RULES_OVERRIDE}"
elif [[ -n "${RECORDING_RULES_OVERRIDE}" ]]; then
warning "prometheus-operator.kubeTargetVersionOverride should be unset or set to '1.13.0-0' but it's set to: ${RECORDING_RULES_OVERRIDE}"
warning "Please unset it or set it to '1.13.0-0' and rerun this script"
fi
}
Expand Down Expand Up @@ -515,6 +512,7 @@ function add_prometheus_pre_1_14_recording_rules() {
EOF
)

info "Adding 'additionalPrometheusRulesMap.pre-1.14-node-rules' to kube-prometheus-stack chart configuration"
yq w -i "${temp_file}" 'prometheus-operator.additionalPrometheusRulesMap."pre-1.14-node-rules"' \
--from <(echo "${PROMETHEUS_RULES}")
}
Expand Down
1 change: 1 addition & 0 deletions tests/upgrade_v2_script/static/prometheus_operator_valid.log
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
[INFO] Mapping prometheus-operator.prometheusOperator.tlsProxy.enabled into kube-prometheus-stack.prometheusOperator.tls.enabled

[INFO] Adding 'additionalPrometheusRulesMap.pre-1.14-node-rules' to kube-prometheus-stack chart configuration
[INFO] Removing prometheus kubeTargetVersionOverride='1.13.0-0'
[INFO] Migrating prometheus-config-reloader container to config-reloader in prometheusSpec
[INFO] Migrating from prometheus-operator to kube-prometheus-stack
Expand Down
196 changes: 0 additions & 196 deletions tests/upgrade_v2_script/static/prometheus_remote_write_regexes.output.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,199 +129,3 @@ kube-prometheus-stack:
sourceLabels: [job, __name__]
containers:
- name: config-reloader
additionalPrometheusRulesMap:
pre-1.14-node-rules:
groups:
- name: node-pre-1.14.rules
rules:
- expr: 1 - avg(rate(node_cpu_seconds_total{job="node-exporter",mode="idle"}[1m]))
record: :node_cpu_utilisation:avg1m
- expr: |-
1 - avg by (node) (
rate(node_cpu_seconds_total{job="node-exporter",mode="idle"}[1m])
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:)
record: node:node_cpu_utilisation:avg1m
- expr: |-
1 -
sum(
node_memory_MemFree_bytes{job="node-exporter"} +
node_memory_Cached_bytes{job="node-exporter"} +
node_memory_Buffers_bytes{job="node-exporter"}
)
/
sum(node_memory_MemTotal_bytes{job="node-exporter"})
record: ':node_memory_utilisation:'
- expr: |-
(node:node_memory_bytes_total:sum - node:node_memory_bytes_available:sum)
/
node:node_memory_bytes_total:sum
record: node:node_memory_utilisation:ratio
- expr: |-
1 -
sum by (node) (
(
node_memory_MemFree_bytes{job="node-exporter"} +
node_memory_Cached_bytes{job="node-exporter"} +
node_memory_Buffers_bytes{job="node-exporter"}
)
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
/
sum by (node) (
node_memory_MemTotal_bytes{job="node-exporter"}
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
record: 'node:node_memory_utilisation:'
- expr: 1 - (node:node_memory_bytes_available:sum / node:node_memory_bytes_total:sum)
record: 'node:node_memory_utilisation_2:'
- expr: |-
max by (instance, namespace, pod, device) ((node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}
- node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
/ node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
record: 'node:node_filesystem_usage:'
- expr: |-
sum by (node) (
node_memory_MemTotal_bytes{job="node-exporter"}
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
record: node:node_memory_bytes_total:sum
- expr: |-
sum(irate(node_network_receive_bytes_total{job="node-exporter",device!~"veth.+"}[1m])) +
sum(irate(node_network_transmit_bytes_total{job="node-exporter",device!~"veth.+"}[1m]))
record: :node_net_utilisation:sum_irate
- expr: |-
sum by (node) (
(irate(node_network_receive_bytes_total{job="node-exporter",device!~"veth.+"}[1m]) +
irate(node_network_transmit_bytes_total{job="node-exporter",device!~"veth.+"}[1m]))
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
record: node:node_net_utilisation:sum_irate
- expr: |-
sum(irate(node_network_receive_drop_total{job="node-exporter",device!~"veth.+"}[1m])) +
sum(irate(node_network_transmit_drop_total{job="node-exporter",device!~"veth.+"}[1m]))
record: :node_net_saturation:sum_irate
- expr: |-
sum by (node) (
(irate(node_network_receive_drop_total{job="node-exporter",device!~"veth.+"}[1m]) +
irate(node_network_transmit_drop_total{job="node-exporter",device!~"veth.+"}[1m]))
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
record: node:node_net_saturation:sum_irate
- expr: |-
max by (instance, namespace, pod, device) ((node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}
- node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
/ node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
record: 'node:node_filesystem_usage:'
- expr: |-
sum(node_load1{job="node-exporter"})
/
sum(node:node_num_cpu:sum)
record: ':node_cpu_saturation_load1:'
- expr: |-
sum by (node) (
node_load1{job="node-exporter"}
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
/
node:node_num_cpu:sum
record: 'node:node_cpu_saturation_load1:'
- expr: avg(irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]))
record: :node_disk_saturation:avg_irate
- expr: |-
avg by (node) (
irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m])
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
record: node:node_disk_saturation:avg_irate
- expr: avg(irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]))
record: :node_disk_utilisation:avg_irate
- expr: |-
avg by (node) (
irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m])
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
record: node:node_disk_utilisation:avg_irate
- expr: |-
1e3 * sum(
(rate(node_vmstat_pgpgin{job="node-exporter"}[1m])
+ rate(node_vmstat_pgpgout{job="node-exporter"}[1m]))
)
record: :node_memory_swap_io_bytes:sum_rate
- expr: |-
1e3 * sum by (node) (
(rate(node_vmstat_pgpgin{job="node-exporter"}[1m])
+ rate(node_vmstat_pgpgout{job="node-exporter"}[1m]))
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
record: node:node_memory_swap_io_bytes:sum_rate
- expr: |-
node:node_cpu_utilisation:avg1m
*
node:node_num_cpu:sum
/
scalar(sum(node:node_num_cpu:sum))
record: node:cluster_cpu_utilisation:ratio
- expr: |-
(node:node_memory_bytes_total:sum - node:node_memory_bytes_available:sum)
/
scalar(sum(node:node_memory_bytes_total:sum))
record: node:cluster_memory_utilisation:ratio
- expr: |-
sum by (node) (
node_load1{job="node-exporter"}
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
/
node:node_num_cpu:sum
record: 'node:node_cpu_saturation_load1:'
- expr: |-
max by (instance, namespace, pod, device) (
node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}
/
node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}
)
record: 'node:node_filesystem_avail:'
- expr: |-
max by (instance, namespace, pod, device) ((node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}
- node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
/ node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
record: 'node:node_filesystem_usage:'
- expr: |-
max(
max(
kube_pod_info{job="kube-state-metrics", host_ip!=""}
) by (node, host_ip)
* on (host_ip) group_right (node)
label_replace(
(
max(node_filesystem_files{job="node-exporter", mountpoint="/"})
by (instance)
), "host_ip", "$1", "instance", "(.*):.*"
)
) by (node)
record: 'node:node_inodes_total:'
- expr: |-
max(
max(
kube_pod_info{job="kube-state-metrics", host_ip!=""}
) by (node, host_ip)
* on (host_ip) group_right (node)
label_replace(
(
max(node_filesystem_files_free{job="node-exporter", mountpoint="/"})
by (instance)
), "host_ip", "$1", "instance", "(.*):.*"
)
) by (node)
record: 'node:node_inodes_free:'
Loading