From 48087e0e1af855b67c0ce1285bf3b8acbed245a5 Mon Sep 17 00:00:00 2001 From: Periklis Tsirakidis Date: Thu, 12 Oct 2023 14:01:55 +0200 Subject: [PATCH] operator: Add missing marker/sweeper panels in retention dashboard (#10854) Co-authored-by: Joao Marcal --- operator/CHANGELOG.md | 1 + ...grafana-dashboard-lokistack-retention.json | 842 +++++++++++++++++- operator/jsonnet/config.libsonnet | 13 +- 3 files changed, 853 insertions(+), 3 deletions(-) diff --git a/operator/CHANGELOG.md b/operator/CHANGELOG.md index 014a544f114b8..a699e7c4b4811 100644 --- a/operator/CHANGELOG.md +++ b/operator/CHANGELOG.md @@ -1,5 +1,6 @@ ## Main +- [10854](https://github.com/grafana/loki/pull/10854) **periklis**: Add missing marker/sweeper panels in retention dashboard - [10717](https://github.com/grafana/loki/pull/10717) **periklis**: Allow SSE settings in AWS S3 object storage secret - [10715](https://github.com/grafana/loki/pull/10715) **periklis**: Allow endpoint_suffix in azure object storage secret - [10562](https://github.com/grafana/loki/pull/10562) **periklis**: Add memberlist IPv6 support diff --git a/operator/internal/manifests/openshift/internal/dashboards/static/grafana-dashboard-lokistack-retention.json b/operator/internal/manifests/openshift/internal/dashboards/static/grafana-dashboard-lokistack-retention.json index 2023f0623fb29..39f847e9b7588 100644 --- a/operator/internal/manifests/openshift/internal/dashboards/static/grafana-dashboard-lokistack-retention.json +++ b/operator/internal/manifests/openshift/internal/dashboards/static/grafana-dashboard-lokistack-retention.json @@ -395,7 +395,7 @@ "sort": 2, "value_type": "individual" }, - "type": "stat", + "type": "singlestat", "xaxis": { "buckets": null, "mode": "time", @@ -581,6 +581,846 @@ "showTitle": true, "title": "Compact and Mark", "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "count by(action)(loki_boltdb_shipper_retention_marker_table_processed_total{ namespace=~\"$namespace\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{action}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Processed Tables Per Action", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "count by(table,action)(loki_boltdb_shipper_retention_marker_table_processed_total{ namespace=~\"$namespace\" , action=~\"modified|deleted\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{table}}-{{action}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Modified Tables", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (table)(rate(loki_boltdb_shipper_retention_marker_count_total{ namespace=~\"$namespace\"}[$__rate_interval])) >0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{table}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Marks Creation Rate Per Table", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Per Table Marker", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (increase(loki_boltdb_shipper_retention_marker_count_total{ namespace=~\"$namespace\"}[24h]))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Marked Chunks (24h)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_bucket{ namespace=~\"$namespace\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum(rate(loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_bucket{ namespace=~\"$namespace\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(rate(loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_sum{ namespace=~\"$namespace\"}[$__rate_interval])) * 1e3 / sum(rate(loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_count{ namespace=~\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Mark Table Latency", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "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 + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (increase(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_count{ namespace=~\"$namespace\"}[24h]))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Delete Chunks (24h)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_bucket{ namespace=~\"$namespace\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum(rate(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_bucket{ namespace=~\"$namespace\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(rate(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_sum{ namespace=~\"$namespace\"}[$__rate_interval])) * 1e3 / sum(rate(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_count{ namespace=~\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Delete Latency", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Sweeper", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "time() - (loki_boltdb_shipper_retention_sweeper_marker_file_processing_current_time{ namespace=~\"$namespace\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "lag", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Sweeper Lag", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(loki_boltdb_shipper_retention_sweeper_marker_files_current{ namespace=~\"$namespace\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "count", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Marks Files to Process", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status)(rate(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_count{ namespace=~\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Delete Rate Per Status", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" } ], "schemaVersion": 14, diff --git a/operator/jsonnet/config.libsonnet b/operator/jsonnet/config.libsonnet index be75d44e11d39..ec50b795a1de2 100644 --- a/operator/jsonnet/config.libsonnet +++ b/operator/jsonnet/config.libsonnet @@ -56,6 +56,15 @@ local utils = (import 'github.com/grafana/jsonnet-libs/mixin-utils/utils.libsonn ], }, + // replaceType updates the type of a panel. Used to + // transform "stat" graphs in "singlestat" to ensure OCP Console compatibility + local replaceType = function(type, replacement) + function(p) p + ( + if p.type == type then { + type: replacement, + } else {} + ), + // dropPanels removes unnecessary panels from the loki dashboards // that are of obsolete usage on our AWS-based deployment environment. local dropPanels = function(panels, dropList, fn) @@ -135,7 +144,7 @@ local utils = (import 'github.com/grafana/jsonnet-libs/mixin-utils/utils.libsonn grafanaDashboards+: { 'loki-retention.json'+: { - local dropList = ['Logs', 'Per Table Marker', 'Sweeper', ''], + local dropList = ['Logs'], local replacements = [ { from: 'cluster=~"$cluster",', to: '' }, { from: 'container="compactor"', to: 'container=~".+-compactor"' }, @@ -146,7 +155,7 @@ local utils = (import 'github.com/grafana/jsonnet-libs/mixin-utils/utils.libsonn tags: defaultLokiTags(super.tags), rows: [ r { - panels: mapPanels([replaceMatchers(replacements)], r.panels), + panels: mapPanels([replaceMatchers(replacements), replaceType('stat', 'singlestat')], r.panels), } for r in dropPanels(super.rows, dropList, function(p) true) ],