Compare commits

..

18 Commits

Author SHA1 Message Date
Michel Hollands
618ab3778b Add kube-state-metrics documentation
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-14 10:31:11 +01:00
Michel Hollands
89d9bdb5e2 Merge pull request #119 from grafana/fix_cluster_name
Use shorter name for cluster
2024-05-14 08:47:56 +01:00
Michel Hollands
291f680c16 Use shorter name for cluster
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-14 08:46:45 +01:00
Michel Hollands
1be9bc8d0a Merge pull request #118 from grafana/fix_dashboards
Fix dashboards a bit more
2024-05-13 17:04:45 +01:00
Michel Hollands
81d63a4383 Fix CPU usage of ssd querier
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 16:59:05 +01:00
Michel Hollands
333ba3a3fd Add cluster to kube state metrics
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 16:58:07 +01:00
Michel Hollands
7aa091cbf8 Merge pull request #117 from grafana/fix_dashboards
Fix dashboards
2024-05-13 14:48:45 +01:00
Michel Hollands
d309a5bc50 Fix mistakes
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 14:44:08 +01:00
Michel Hollands
346dd4968e Make reads-resources work for all 3 deployment modes
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 14:36:53 +01:00
Michel Hollands
f5c9fa0593 Update operation so it works with all types of deployment
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 14:07:59 +01:00
Michel Hollands
d5e8df856d Update writes dashboard work with all types
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 14:06:41 +01:00
Michel Hollands
2d85e7e120 Update dashboards so they work with single binary
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 10:56:35 +01:00
Michel Hollands
1a4a1ad885 Fix ruler panel
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 10:17:55 +01:00
Michel Hollands
c1ff364c29 Add missing metric in reads dashboard
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 09:45:37 +01:00
Michel Hollands
bd0ef0e2cc Add missing values
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 09:21:05 +01:00
Michel Hollands
0216163885 Add chunk reason
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 09:11:20 +01:00
Michel Hollands
c42718649f Fix distributor memory panel
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2024-05-13 09:03:02 +01:00
Michel Hollands
650df8217a Merge pull request #116 from grafana/fix_loki_write_endpoint
Fix local write end point
2024-05-13 08:24:18 +01:00
6 changed files with 71 additions and 54 deletions

View File

@@ -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}}",

View File

@@ -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

View File

@@ -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

View File

@@ -135,6 +135,11 @@ data:
}
prometheus.relabel "filter" {
rule {
target_label = "cluster"
replacement = "{{- .Values.clusterLabelValue -}}"
}
rule {
source_labels = ["__name__"]
regex = "({{ include "agent.all_metrics" . }})"

View File

@@ -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:
@@ -149,6 +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
@@ -174,11 +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
@@ -191,6 +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
@@ -208,6 +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

View File

@@ -194,4 +194,8 @@ For each of the dashboard files in charts/meta-monitoring/src/dashboards folder
## 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.
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.
## Kube-state-metrics
Metrics about Kubernetes objects are scraped from [kube-state-metrics](https://github.com/kubernetes/kube-state-metrics). This needs to be installed in the cluster. The `kubeStateMetrics.endpoint` entry in values.yaml should be set to it's address (without the `/metrics` part in the URL).