chore: Update reads and reads resources dashs (#12654)

pull/12641/head^2
Salva Corts 1 year ago committed by GitHub
parent 985251c486
commit 5e10d8d689
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
  1. 420
      production/loki-mixin-compiled/dashboards/loki-reads-resources.json
  2. 369
      production/loki-mixin-compiled/dashboards/loki-reads.json
  3. 32
      production/loki-mixin/dashboards/loki-reads-resources.libsonnet
  4. 30
      production/loki-mixin/dashboards/loki-reads.libsonnet

@ -1364,7 +1364,7 @@
},
{
"collapse": false,
"height": "250px",
"collapsed": false,
"panels": [
{
"datasource": "$datasource",
@ -1429,6 +1429,7 @@
}
]
},
"gridPos": { },
"id": 19,
"links": [ ],
"options": {
@ -1440,6 +1441,411 @@
"sort": "none"
}
},
"targets": [
{
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"}[$__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)",
"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\"})",
"format": "time_series",
"legendFormat": "limit",
"legendLink": null
}
],
"title": "CPU",
"tooltip": {
"sort": 2
},
"type": "timeseries"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "bytes"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "request"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#FFC000",
"mode": "fixed"
}
},
{
"id": "custom.fillOpacity",
"value": 0
}
]
},
{
"matcher": {
"id": "byName",
"options": "limit"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E02F44",
"mode": "fixed"
}
},
{
"id": "custom.fillOpacity",
"value": 0
}
]
}
]
},
"gridPos": { },
"id": 20,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"})",
"format": "time_series",
"legendFormat": "{{pod}}",
"legendLink": null
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\", resource=\"memory\"} > 0)",
"format": "time_series",
"legendFormat": "request",
"legendLink": null
},
{
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"} > 0)",
"format": "time_series",
"legendFormat": "limit",
"legendLink": null
}
],
"title": "Memory (workingset)",
"tooltip": {
"sort": 2
},
"type": "timeseries"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "bytes"
},
"overrides": [ ]
},
"gridPos": { },
"id": 21,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/bloom-gateway\"})",
"format": "time_series",
"legendFormat": "{{pod}}",
"legendLink": null
}
],
"title": "Memory (go heap inuse)",
"tooltip": {
"sort": 2
},
"type": "timeseries"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 100,
"lineWidth": 0,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "Bps"
},
"overrides": [ ]
},
"gridPos": { },
"id": 22,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__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\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
"format": "time_series",
"legendFormat": "{{pod}} - {{device}}",
"legendLink": null
}
],
"title": "Disk Writes",
"type": "timeseries"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 100,
"lineWidth": 0,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "Bps"
},
"overrides": [ ]
},
"gridPos": { },
"id": 23,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"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\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
"format": "time_series",
"legendFormat": "{{pod}} - {{device}}",
"legendLink": null
}
],
"title": "Disk Reads",
"type": "timeseries"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "percentunit"
},
"overrides": [ ]
},
"gridPos": { },
"id": 24,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"expr": "max by(persistentvolumeclaim) (kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} / kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}) and count by(persistentvolumeclaim) (kube_persistentvolumeclaim_labels{cluster=~\"$cluster\", namespace=~\"$namespace\",label_name=~\"bloom-gateway.*\"})",
"format": "time_series",
"legendFormat": "{{persistentvolumeclaim}}",
"legendLink": null
}
],
"title": "Disk Space Utilization",
"type": "timeseries"
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Bloom Gateway",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "short"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "request"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#FFC000",
"mode": "fixed"
}
},
{
"id": "custom.fillOpacity",
"value": 0
}
]
},
{
"matcher": {
"id": "byName",
"options": "limit"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E02F44",
"mode": "fixed"
}
},
{
"id": "custom.fillOpacity",
"value": 0
}
]
}
]
},
"id": 25,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"span": 4,
"targets": [
{
@ -1530,7 +1936,7 @@
}
]
},
"id": 20,
"id": 26,
"links": [ ],
"options": {
"legend": {
@ -1592,7 +1998,7 @@
},
"overrides": [ ]
},
"id": 21,
"id": 27,
"links": [ ],
"options": {
"legend": {
@ -1655,7 +2061,7 @@
"overrides": [ ]
},
"gridPos": { },
"id": 22,
"id": 28,
"links": [ ],
"options": {
"legend": {
@ -1741,7 +2147,7 @@
]
},
"gridPos": { },
"id": 23,
"id": 29,
"links": [ ],
"options": {
"legend": {
@ -1842,7 +2248,7 @@
]
},
"gridPos": { },
"id": 24,
"id": 30,
"links": [ ],
"options": {
"legend": {
@ -1904,7 +2310,7 @@
"overrides": [ ]
},
"gridPos": { },
"id": 25,
"id": 31,
"links": [ ],
"options": {
"legend": {

@ -905,7 +905,7 @@
"stack": true,
"targets": [
{
"expr": "sum by (status) (\n label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"expr": "sum by (status) (\n label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"format": "time_series",
"legendFormat": "{{status}}",
"refId": "A"
@ -953,7 +953,7 @@
"span": 4,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"})) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} 99th Percentile",
@ -961,7 +961,7 @@
"step": 10
},
{
"expr": "histogram_quantile(0.50, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"})) * 1e3",
"expr": "histogram_quantile(0.50, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"})) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} 50th Percentile",
@ -969,7 +969,7 @@
"step": 10
},
{
"expr": "1e3 * sum(cluster_job_route:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}) by (route) / sum(cluster_job_route:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}) by (route) ",
"expr": "1e3 * sum(cluster_job_route:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}) by (route) / sum(cluster_job_route:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}) by (route) ",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} Average",
@ -1037,7 +1037,7 @@
"span": 4,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (le,pod)) * 1e3",
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/ingester\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}[$__rate_interval])) by (le,pod)) * 1e3",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
@ -1250,7 +1250,7 @@
"stack": true,
"targets": [
{
"expr": "sum by (status) (\n label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"expr": "sum by (status) (\n label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"format": "time_series",
"legendFormat": "{{status}}",
"refId": "A"
@ -1298,7 +1298,7 @@
"span": 4,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"})) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} 99th Percentile",
@ -1306,7 +1306,7 @@
"step": 10
},
{
"expr": "histogram_quantile(0.50, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"})) * 1e3",
"expr": "histogram_quantile(0.50, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"})) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} 50th Percentile",
@ -1314,7 +1314,7 @@
"step": 10
},
{
"expr": "1e3 * sum(cluster_job_route:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}) by (route) / sum(cluster_job_route:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}) by (route) ",
"expr": "1e3 * sum(cluster_job_route:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}) by (route) / sum(cluster_job_route:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}) by (route) ",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} Average",
@ -1382,7 +1382,7 @@
"span": 4,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (le,pod)) * 1e3",
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/ingester-zone.*\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}[$__rate_interval])) by (le,pod)) * 1e3",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
@ -1934,7 +1934,7 @@
"stack": true,
"targets": [
{
"expr": "sum by (status) (\n label_replace(label_replace(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(querier|index-gateway)\", operation=\"Shipper.Query\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"expr": "sum by (status) (\n label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/bloom-gateway\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"format": "time_series",
"legendFormat": "{{status}}",
"refId": "A"
@ -1980,6 +1980,351 @@
}
},
"span": 4,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/bloom-gateway\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"})) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} 99th Percentile",
"refId": "A",
"step": 10
},
{
"expr": "histogram_quantile(0.50, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/bloom-gateway\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"})) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} 50th Percentile",
"refId": "B",
"step": 10
},
{
"expr": "1e3 * sum(cluster_job_route:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/bloom-gateway\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}) by (route) / sum(cluster_job_route:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/bloom-gateway\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}) by (route) ",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} Average",
"refId": "C",
"step": 10
}
],
"title": "Latency",
"type": "timeseries",
"yaxes": [
{
"format": "ms",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "ms"
},
"overrides": [ ]
},
"id": 18,
"links": [ ],
"nullPointMode": "null as zero",
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"span": 4,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/bloom-gateway\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs\"}[$__rate_interval])) by (le,pod)) * 1e3",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "__auto",
"refId": "A",
"step": 10
}
],
"title": "Per Pod Latency (p99)",
"type": "timeseries"
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Bloom Gateway",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"aliasColors": {
"1xx": "#EAB839",
"2xx": "#7EB26D",
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
},
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 100,
"lineWidth": 0,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
}
},
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "short"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "1xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#EAB839",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "2xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#7EB26D",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "3xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#6ED0E0",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "4xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#EF843C",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "5xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E24D42",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "OK"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#7EB26D",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "cancel"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#A9A9A9",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "error"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E24D42",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "success"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#7EB26D",
"mode": "fixed"
}
}
]
}
]
},
"fill": 10,
"id": 19,
"linewidth": 0,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"span": 4,
"stack": true,
"targets": [
{
"expr": "sum by (status) (\n label_replace(label_replace(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(querier|index-gateway)\", operation=\"Shipper.Query\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"format": "time_series",
"legendFormat": "{{status}}",
"refId": "A"
}
],
"title": "QPS",
"type": "timeseries"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "ms"
},
"overrides": [ ]
},
"id": 20,
"links": [ ],
"nullPointMode": "null as zero",
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"span": 4,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(querier|index-gateway)\", operation=\"Shipper.Query\"}[$__rate_interval])) by (le)) * 1e3",
@ -2045,7 +2390,7 @@
},
"overrides": [ ]
},
"id": 18,
"id": 21,
"links": [ ],
"nullPointMode": "null as zero",
"options": {

@ -117,6 +117,38 @@ local utils = import 'mixin-utils/utils.libsonnet';
$.containerDiskSpaceUtilizationPanel('Disk Space Utilization', index_gateway_job_matcher),
)
)
.addRowIf(
!$._config.ssd.enabled,
grafana.row.new('Bloom Gateway')
.addPanel(
$.containerCPUUsagePanel('CPU', 'bloom-gateway'),
)
.addPanel(
$.containerMemoryWorkingSetPanel('Memory (workingset)', 'bloom-gateway'),
)
.addPanel(
$.goHeapInUsePanel('Memory (go heap inuse)', 'bloom-gateway'),
)
.addPanel(
$.newQueryPanel('Disk Writes', 'Bps') +
$.queryPanel(
'sum by(%s, %s, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + %s' % [$._config.per_node_label, $._config.per_instance_label, $.filterNodeDiskContainer('bloom-gateway')],
'{{%s}} - {{device}}' % $._config.per_instance_label
) +
$.withStacking,
)
.addPanel(
$.newQueryPanel('Disk Reads', 'Bps') +
$.queryPanel(
'sum by(%s, %s, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + %s' % [$._config.per_node_label, $._config.per_instance_label, $.filterNodeDiskContainer('bloom-gateway')],
'{{%s}} - {{device}}' % $._config.per_instance_label
) +
$.withStacking,
)
.addPanel(
$.containerDiskSpaceUtilizationPanel('Disk Space Utilization', 'bloom-gateway'),
)
)
.addRow(
$.row('Ingester')
.addPanel(

@ -6,7 +6,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
local showBigTable = false,
local http_routes = 'loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values',
local grpc_routes = '/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs',
local grpc_routes = '/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs|/logproto.BloomGateway/FilterChunkRefs',
local latencyPanelWithExtraGrouping(metricName, selector, multiplier='1e3', extra_grouping='') = {
nullPointMode: 'null as zero',
@ -45,6 +45,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
ingester: [utils.selector.re('job', '($namespace)/%s' % (if $._config.ssd.enabled then '%s-write' % $._config.ssd.pod_prefix_matcher else 'ingester'))],
ingesterZoneAware: [utils.selector.re('job', '($namespace)/%s' % (if $._config.ssd.enabled then '%s-write' % $._config.ssd.pod_prefix_matcher else 'ingester-zone.*'))],
querierOrIndexGateway: [utils.selector.re('job', '($namespace)/%s' % (if $._config.ssd.enabled then '%s-read' % $._config.ssd.pod_prefix_matcher else '(querier|index-gateway)'))],
bloomGateway: [utils.selector.re('job', '($namespace)/%s' % (if $._config.ssd.enabled then '%s-backend' % $._config.ssd.pod_prefix_matcher else 'bloom-gateway'))],
},
local selector(matcherId) =
@ -59,6 +60,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
ingesterSelector:: selector('ingester'),
ingesterZoneSelector:: selector('ingesterZoneAware'),
querierOrIndexGatewaySelector:: selector('querierOrIndexGateway'),
bloomGatewaySelector:: selector('bloomGateway'),
} +
$.dashboard('Loki / Reads', uid='reads')
.addCluster()
@ -210,6 +212,32 @@ local utils = import 'mixin-utils/utils.libsonnet';
)
)
)
.addRowIf(
!$._config.ssd.enabled,
$.row('Bloom Gateway')
.addPanel(
$.newQueryPanel('QPS') +
$.newQpsPanel('loki_request_duration_seconds_count{%s route=~"%s"}' % [dashboards['loki-reads.json'].bloomGatewaySelector, grpc_routes])
)
.addPanel(
$.newQueryPanel('Latency', 'ms') +
utils.latencyRecordingRulePanel(
'loki_request_duration_seconds',
dashboards['loki-reads.json'].clusterMatchers + dashboards['loki-reads.json'].matchers.bloomGateway + [utils.selector.re('route', grpc_routes)],
sum_by=['route']
)
)
.addPanel(
p99LatencyByPod(
'loki_request_duration_seconds',
$.toPrometheusSelector(
dashboards['loki-reads.json'].clusterMatchers +
dashboards['loki-reads.json'].matchers.bloomGateway +
[utils.selector.re('route', grpc_routes)]
),
)
)
)
.addRowIf(
showBigTable,
$.row('BigTable')

Loading…
Cancel
Save