forked from RemoteSync/grafana-meta-monitoring-chart
Compare commits
29 Commits
add_more_m
...
fix_cluste
| Author | SHA1 | Date | |
|---|---|---|---|
|
291f680c16 | ||
|
1be9bc8d0a | ||
|
|
81d63a4383 | ||
|
|
333ba3a3fd | ||
|
|
7aa091cbf8 | ||
|
|
d309a5bc50 | ||
|
|
346dd4968e | ||
|
|
f5c9fa0593 | ||
|
|
d5e8df856d | ||
|
|
2d85e7e120 | ||
|
|
1a4a1ad885 | ||
|
|
c1ff364c29 | ||
|
|
bd0ef0e2cc | ||
|
|
0216163885 | ||
|
|
c42718649f | ||
|
|
650df8217a | ||
|
|
f7946ff713 | ||
|
|
b312fc37fc | ||
|
|
ad96f09600 | ||
|
|
090f1ef91a | ||
|
|
b2957d90f0 | ||
|
|
f8aea814c5 | ||
|
|
91c19f07d3 | ||
|
|
315b203082 | ||
|
|
caf4eda1be | ||
|
|
21ba3ebe8c | ||
|
|
f0a934a393 | ||
|
|
941420b417 | ||
|
1ea10cdbfa |
@@ -1,7 +1,7 @@
|
||||
dependencies:
|
||||
- name: loki
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
version: 6.5.0
|
||||
version: 6.5.1
|
||||
- name: alloy
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
version: 0.1.1
|
||||
@@ -14,5 +14,5 @@ dependencies:
|
||||
- name: minio
|
||||
repository: https://charts.min.io
|
||||
version: 5.2.0
|
||||
digest: sha256:5328702b5f6b0487aba8f7bc77d6abfcd5e094569e9205cd725971e3e31255dd
|
||||
generated: "2024-05-08T07:03:21.797461955Z"
|
||||
digest: sha256:e0c7af6d328fe35f4b9a3557235f458d92225b84b1366dbb77c4626d3cdb5be9
|
||||
generated: "2024-05-09T07:02:42.911579524Z"
|
||||
|
||||
@@ -13,7 +13,7 @@ type: application
|
||||
# This is the chart version. This version number should be incremented each time you make changes
|
||||
# to the chart and its templates, including the app version.
|
||||
# Versions are expected to follow Semantic Versioning (https://semver.org/)
|
||||
version: 0.0.2
|
||||
version: 0.0.3
|
||||
# This is the version number of the application being deployed. This version number should be
|
||||
# incremented each time you make changes to the application. Versions are not expected to
|
||||
# follow Semantic Versioning. They should reflect the version the application is using.
|
||||
@@ -22,7 +22,7 @@ appVersion: "0.0.1"
|
||||
dependencies:
|
||||
- name: loki
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
version: 6.5.0
|
||||
version: 6.5.1
|
||||
condition: local.logs.enabled
|
||||
- name: alloy
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
|
||||
Binary file not shown.
BIN
charts/meta-monitoring/charts/loki-6.5.1.tgz
Normal file
BIN
charts/meta-monitoring/charts/loki-6.5.1.tgz
Normal file
Binary file not shown.
@@ -1824,7 +1824,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*distributor.*|(loki|enterprise-logs)-write)\"}[$__rate_interval]))",
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*distributor.*|(loki|enterprise-logs)-write.*|$namespace-[0-9]+)\"}[$__rate_interval]))",
|
||||
"intervalFactor": 3,
|
||||
"legendFormat": "{{pod}}",
|
||||
"refId": "A"
|
||||
@@ -1921,7 +1921,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"(.*/distributor|(loki|enterprise-logs)-write|.*/loki)\"}",
|
||||
"expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"(.*/.*distributor|$namespace/(loki|enterprise-logs)-write|.*/loki|$namespace/loki-single-binary)\"}",
|
||||
"instant": false,
|
||||
"intervalFactor": 3,
|
||||
"legendFormat": "{{pod}}",
|
||||
@@ -2525,7 +2525,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))",
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*ingester.*|(loki|enterprise-logs)-write.*|loki-single-binary|$namespace-[0-9]+)\"}[$__rate_interval]))",
|
||||
"intervalFactor": 3,
|
||||
"legendFormat": "{{pod}}",
|
||||
"refId": "A"
|
||||
@@ -2622,7 +2622,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}",
|
||||
"expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(.*ingester.*|(loki|enterprise-logs)-write.*|loki-single-binary|$namespace-[0-9]+)\"}",
|
||||
"instant": false,
|
||||
"intervalFactor": 3,
|
||||
"legendFormat": "{{pod}}",
|
||||
@@ -3308,7 +3308,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(reason) (rate(loki_ingester_chunks_flushed_total{cluster=~\"$cluster\",job=~\"$namespace/.*ingester.*\", namespace=~\"$namespace\"}[$__rate_interval])) / ignoring(reason) group_left sum(rate(loki_ingester_chunks_flushed_total{cluster=~\"$cluster\",job=~\"$namespace/.*ingester.*\", namespace=~\"$namespace\"}[$__rate_interval]))",
|
||||
"expr": "sum by(reason) (rate(loki_ingester_chunks_flushed_total{cluster=~\"$cluster\",job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\", namespace=~\"$namespace\"}[$__rate_interval])) / ignoring(reason) group_left sum(rate(loki_ingester_chunks_flushed_total{cluster=~\"$cluster\",job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\", namespace=~\"$namespace\"}[$__rate_interval]))",
|
||||
"interval": "",
|
||||
"legendFormat": "{{ reason }}"
|
||||
}
|
||||
@@ -3388,7 +3388,7 @@
|
||||
"reverseYBuckets": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (le) (rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"($namespace)/(ingester|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))",
|
||||
"expr": "sum by (le) (rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))",
|
||||
"format": "heatmap",
|
||||
"instant": false,
|
||||
"interval": "",
|
||||
@@ -3481,7 +3481,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*querier.*|(loki|enterprise-logs)-read|loki-single-binary)\"}[$__rate_interval]))",
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*querier.*|(loki|enterprise-logs)-read.*|loki-single-binary|$namespace-[0-9]+)\"}[$__rate_interval]))",
|
||||
"intervalFactor": 3,
|
||||
"legendFormat": "{{pod}}",
|
||||
"refId": "A"
|
||||
@@ -3578,7 +3578,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(.*querier.*|(loki|enterprise-logs)-read|.*loki-single-binary)\"}",
|
||||
"expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(.*querier.*|(loki|enterprise-logs)-read.*|.*loki-single-binary|$namespace-[0-9]+)\"}",
|
||||
"instant": false,
|
||||
"intervalFactor": 3,
|
||||
"legendFormat": "{{pod}}",
|
||||
|
||||
@@ -104,19 +104,19 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\"}[$__rate_interval]))",
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\", resource=\"cpu\"} > 0)",
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"cpu\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "request",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\"})",
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -206,19 +206,19 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\"})",
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\", resource=\"memory\"} > 0)",
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"memory\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "request",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\"} > 0)",
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -269,7 +269,7 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/.*query-frontend\"})",
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*query-frontend|loki-read|loki-single-binary)\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
@@ -371,19 +371,19 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\"}[$__rate_interval]))",
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\", resource=\"cpu\"} > 0)",
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\", resource=\"cpu\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "request",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\"})",
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -473,19 +473,19 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\"})",
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\", resource=\"memory\"} > 0)",
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\", resource=\"memory\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "request",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\"} > 0)",
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -536,7 +536,7 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/.*query-scheduler\"})",
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*query-scheduler|loki-read|loki-single-binary)\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
@@ -638,19 +638,19 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\"}[$__rate_interval]))",
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\", resource=\"cpu\"} > 0)",
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"cpu\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "request",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\"})",
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -740,19 +740,19 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\"})",
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\", resource=\"memory\"} > 0)",
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"memory\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "request",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\"} > 0)",
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -803,7 +803,7 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/.*querier\"})",
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*querier|loki-read|loki-single-binary)\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
@@ -854,7 +854,7 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"querier\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
|
||||
"expr": "sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}} - {{device}}",
|
||||
"legendLink": null
|
||||
@@ -902,7 +902,7 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(instance, pod, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"querier\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
|
||||
"expr": "sum by(instance, pod, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}} - {{device}}",
|
||||
"legendLink": null
|
||||
@@ -1462,19 +1462,19 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"}[$__rate_interval]))",
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\", resource=\"cpu\"} > 0)",
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"cpu\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "request",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"})",
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -1564,19 +1564,19 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"})",
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\", resource=\"memory\"} > 0)",
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"memory\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "request",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"} > 0)",
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -1627,7 +1627,7 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/.*bloom-gateway\"})",
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*bloom-gateway|loki-read|loki-single-binary)\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
@@ -1678,7 +1678,7 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"bloom-gateway\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
|
||||
"expr": "sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}} - {{device}}",
|
||||
"legendLink": null
|
||||
@@ -1726,7 +1726,7 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(instance, pod, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"bloom-gateway\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
|
||||
"expr": "sum by(instance, pod, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}} - {{device}}",
|
||||
"legendLink": null
|
||||
@@ -2189,19 +2189,19 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\"}[$__rate_interval]))",
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\", resource=\"cpu\"} > 0)",
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\", resource=\"cpu\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "request",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\"})",
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -2291,19 +2291,19 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\"})",
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\", resource=\"memory\"} > 0)",
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\", resource=\"memory\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "request",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\"} > 0)",
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -2354,7 +2354,7 @@
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/ruler\"})",
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*ruler|loki-backend|loki-single-binary)\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
|
||||
@@ -104,7 +104,7 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor\"}[$__rate_interval]))",
|
||||
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor|loki\", pod=~\"distributor|loki-write-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
@@ -116,7 +116,7 @@
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor\"})",
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor|loki\", pod=~\"distributor|loki-write-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor|loki\", pod=~\"distributor|loki-write-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -206,7 +206,7 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor\"})",
|
||||
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor|loki\", pod=~\"distributor|loki-write-.*|$namespace-[0-9]*\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
@@ -218,7 +218,7 @@
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor\"} > 0)",
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor|loki\", pod=~\"distributor|loki-write-.*|$namespace-[0-9]*\"} > 0)",
|
||||
"format": "time_series",
|
||||
"legendFormat": "limit",
|
||||
"legendLink": null
|
||||
@@ -269,7 +269,7 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/.*distributor\"})",
|
||||
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*distributor|loki-write|loki-single-binary)\"})",
|
||||
"format": "time_series",
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null
|
||||
|
||||
@@ -135,6 +135,11 @@ data:
|
||||
}
|
||||
|
||||
prometheus.relabel "filter" {
|
||||
rule {
|
||||
target_label = "cluster"
|
||||
replacement = "{{- .Values.clusterLabelValue -}}"
|
||||
}
|
||||
|
||||
rule {
|
||||
source_labels = ["__name__"]
|
||||
regex = "({{ include "agent.all_metrics" . }})"
|
||||
@@ -330,7 +335,7 @@ data:
|
||||
{{- if .Values.local.logs.enabled }}
|
||||
loki.write "local" {
|
||||
endpoint {
|
||||
url = "http://{{- .Release.Namespace -}}-loki-gateway.{{- .Release.Namespace -}}.svc.cluster.local:80/loki/api/v1/push"
|
||||
url = "http://loki-write.{{- .Release.Namespace -}}.svc.cluster.local:3100/loki/api/v1/push"
|
||||
}
|
||||
}
|
||||
{{- end }}
|
||||
@@ -346,7 +351,7 @@ data:
|
||||
{{- if .Values.local.traces.enabled }}
|
||||
otelcol.exporter.otlphttp "local" {
|
||||
client {
|
||||
endpoint = "http://{{- .Release.Name -}}-tempo-distributor.svc:4318"
|
||||
endpoint = "http://{{- .Release.Name -}}-tempo-distributor.{{- .Release.Namespace -}}.svc:4318"
|
||||
}
|
||||
}
|
||||
{{- end }}
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
namespacesToMonitor:
|
||||
- loki
|
||||
# The name of the cluster where this will be installed
|
||||
clusterLabelValue: "meta-monitoring"
|
||||
clusterLabelValue: "meta"
|
||||
# Set to true to write logs, metrics or traces to Grafana Cloud
|
||||
# The secrets have to be created first
|
||||
cloud:
|
||||
@@ -45,7 +45,12 @@ grafana:
|
||||
paths:
|
||||
- path: /
|
||||
# -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers
|
||||
# pathType: Prefix
|
||||
pathType: Prefix
|
||||
# backend:
|
||||
# service:
|
||||
# name: TODO
|
||||
# port:
|
||||
# number: TODO
|
||||
# -- TLS configuration for the gateway ingress. Hosts passed through the `tpl` function to allow templating
|
||||
#tls:
|
||||
# - secretName: grafana-tls
|
||||
@@ -144,6 +149,7 @@ metrics:
|
||||
- kube_pod_container_resource_requests
|
||||
- kube_pod_container_status_last_terminated_reason
|
||||
- kube_pod_container_status_restarts_total
|
||||
- loki_azure_blob_request_duration_seconds_bucket
|
||||
- loki_boltdb_shipper_compact_tables_operation_duration_seconds
|
||||
- loki_boltdb_shipper_compact_tables_operation_last_successful_run_timestamp_seconds
|
||||
- loki_boltdb_shipper_retention_marker_count_total
|
||||
@@ -169,11 +175,15 @@ metrics:
|
||||
- loki_compactor_deleted_lines
|
||||
- loki_compactor_oldest_pending_delete_request_age_seconds
|
||||
- loki_compactor_pending_delete_requests_count
|
||||
- loki_consul_request_duration_seconds_bucket
|
||||
- loki_discarded_samples_total
|
||||
- loki_discarded_bytes_total
|
||||
- loki_distributor_bytes_received_total
|
||||
- loki_distributor_lines_received_total
|
||||
- loki_distributor_structured_metadata_bytes_received_total
|
||||
- loki_gcs_request_duration_seconds_bucket
|
||||
- loki_gcs_request_duration_seconds_count
|
||||
- loki_index_request_duration_seconds_bucket
|
||||
- loki_index_request_duration_seconds_count
|
||||
- loki_ingester_chunk_age_seconds_bucket
|
||||
- loki_ingester_chunk_age_seconds_count
|
||||
@@ -186,6 +196,7 @@ metrics:
|
||||
- loki_ingester_chunk_entries_sum
|
||||
- loki_ingester_chunk_size_bytes_bucket
|
||||
- loki_ingester_chunk_utilization_bucket
|
||||
- loki_ingester_chunk_utilization_count
|
||||
- loki_ingester_chunk_utilization_sum
|
||||
- loki_ingester_chunks_flushed_total
|
||||
- loki_ingester_flush_queue_length
|
||||
@@ -203,6 +214,8 @@ metrics:
|
||||
- loki_ruler_wal_prometheus_remote_storage_samples_total
|
||||
- loki_ruler_wal_samples_appended_total
|
||||
- loki_ruler_wal_storage_created_series_total
|
||||
- loki_s3_request_duration_seconds_bucket
|
||||
- loki_s3_request_duration_seconds_count
|
||||
- loki_write_batch_retries_total
|
||||
- loki_write_dropped_bytes_total
|
||||
- loki_write_dropped_entries_total
|
||||
|
||||
@@ -187,7 +187,11 @@ For each of the dashboard files in charts/meta-monitoring/src/dashboards folder
|
||||
|
||||
1. JAEGER_ENDPOINT: http address of the mmc-alloy service installed by the meta-monitoring chart, for example "http://mmc-alloy:14268/api/traces"
|
||||
1. JAEGER_AGENT_TAGS: extra tags you would like to add to the spans, for example 'cluster="abc",namespace="def"'
|
||||
1. JAEGER_SAMPLER_TYPE: the sampling strategy, for example to sample all use 'const' with a value of 1 for the next environment variable
|
||||
1. JAEGER_SAMPLER_PARAM: 1
|
||||
1. JAEGER_SAMPLER_TYPE: the sampling strategy, we suggest setting this to `ratelimiting` so at most 1 trace is accepted per second. See these [docs](https://www.jaegertracing.io/docs/1.57/sampling/) for more options.
|
||||
1. JAEGER_SAMPLER_PARAM: 1.0
|
||||
|
||||
1. If Loki is installed in a different namespace you can create an [ExternalName service](https://kubernetes.io/docs/concepts/services-networking/service/#externalname) in Kubernetes to point to the mmc-alloy service in the meta monitoring namespace
|
||||
|
||||
## Configure external access using an Ingress in local mode
|
||||
|
||||
When using local mode by default a Kubernetes [Ingress](https://kubernetes.io/docs/concepts/services-networking/ingress/) object is created to access the Grafana instance. This will need to be adapted to your cloud provider by updating the `grafana.ingress` section of the `values.yaml` file provided to Helm. Check the documentation of your cloud provider for available options.
|
||||
Reference in New Issue
Block a user