Mixin: Follow naming convention for bucketReplicate (thanos-io#4859)

* Follow naming convention for bucketReplicate dashboard and alert Signed-off-by: Jéssica Lins <[email protected]> * Run make docs Signed-off-by: Jéssica Lins <[email protected]> * Examples clean, make docs Signed-off-by: Jéssica Lins <[email protected]> * Remove someAlert from thanos-component-absent test case Signed-off-by: Jéssica Lins <[email protected]> * Add util function to change from snake case to camel case Signed-off-by: Jéssica Lins <[email protected]> * Use snake case for query frontend dashboard file Signed-off-by: Jéssica Lins <[email protected]> * Update links to query frontend and bucket replicate dashhboards Signed-off-by: Jéssica Lins <[email protected]> * Extract to sanitizeComponent function Signed-off-by: Jéssica Lins <[email protected]> * Rename to sanitizeComponentName Signed-off-by: Jéssica Lins <[email protected]>
vinted · Nov 19, 2021 · d2d74da · d2d74da
1 parent b0b853b
commit d2d74da
Show file tree

Hide file tree

Showing 14 changed files with 50 additions and 56 deletions.
diff --git a/examples/alerts/alerts.md b/examples/alerts/alerts.md
@@ -578,7 +578,7 @@ rules:
     description: Thanos Replicate is failing to run, {{$value | humanize}}% of attempts
       failed.
     runbook_url: https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicateerrorrate
-    summary: Thanose Replicate is failing to run.
+    summary: Thanos Replicate is failing to run.
   expr: |
     (
       sum by (job) (rate(thanos_replicate_replication_runs_total{result="error", job=~".*thanos-bucket-replicate.*"}[5m]))
@@ -612,17 +612,6 @@ rules:
 ```yaml mdox-exec="cat examples/tmp/thanos-component-absent.yaml"
 name: thanos-component-absent
 rules:
-- alert: ThanosBucketReplicateIsDown
-  annotations:
-    description: ThanosBucketReplicate has disappeared. Prometheus target for the
-      component cannot be discovered.
-    runbook_url: https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicateisdown
-    summary: Thanos component has disappeared.
-  expr: |
-    absent(up{job=~".*thanos-bucket-replicate.*"} == 1)
-  for: 5m
-  labels:
-    severity: critical
 - alert: ThanosCompactIsDown
   annotations:
     description: ThanosCompact has disappeared. Prometheus target for the component

diff --git a/examples/alerts/alerts.yaml b/examples/alerts/alerts.yaml
@@ -542,7 +542,7 @@ groups:
       description: Thanos Replicate is failing to run, {{$value | humanize}}% of attempts
         failed.
       runbook_url: https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicateerrorrate
-      summary: Thanose Replicate is failing to run.
+      summary: Thanos Replicate is failing to run.
     expr: |
       (
         sum by (job) (rate(thanos_replicate_replication_runs_total{result="error", job=~".*thanos-bucket-replicate.*"}[5m]))
@@ -569,17 +569,6 @@ groups:
       severity: critical
 - name: thanos-component-absent
   rules:
-  - alert: ThanosBucketReplicateIsDown
-    annotations:
-      description: ThanosBucketReplicate has disappeared. Prometheus target for the
-        component cannot be discovered.
-      runbook_url: https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicateisdown
-      summary: Thanos component has disappeared.
-    expr: |
-      absent(up{job=~".*thanos-bucket-replicate.*"} == 1)
-    for: 5m
-    labels:
-      severity: critical
   - alert: ThanosCompactIsDown
     annotations:
       description: ThanosCompact has disappeared. Prometheus target for the component

diff --git a/examples/dashboards/dashboards.md b/examples/dashboards/dashboards.md
@@ -5,7 +5,7 @@ There exists Grafana dashboards for each component (not all of them complete) ta
 - [Thanos Overview](overview.json)
 - [Thanos Compact](compact.json)
 - [Thanos Querier](query.json)
-- [Thanos Query Frontend](queryFrontend.json)
+- [Thanos Query Frontend](query_frontend.json)
 - [Thanos Store](store.json)
 - [Thanos Receiver](receive.json)
 - [Thanos Sidecar](sidecar.json)

diff --git a/examples/dashboards/queryFrontend.json → examples/dashboards/query_frontend.json b/examples/dashboards/queryFrontend.json → examples/dashboards/query_frontend.json
@@ -1112,6 +1112,6 @@
    },
    "timezone": "UTC",
    "title": "Thanos / Query Frontend",
-   "uid": "9bc9f8bb21d4d18193c3fe772b36c306",
+   "uid": "303c4e660a475c4c8cf6aee97da3a24a",
    "version": 0
 }
diff --git a/mixin/README.md b/mixin/README.md
@@ -113,8 +113,7 @@ This project is intended to be used as a library. You can extend and customize d
     thanosPrometheusCommonDimensions: 'namespace, pod',
     title: '%(prefix)sSidecar' % $.dashboard.prefix,
   },
-  // TODO(kakkoyun): Fix naming convention: bucketReplicate
-  bucket_replicate+:: {
+  bucketReplicate+:: {
     selector: 'job=~".*thanos-bucket-replicate.*"',
     title: '%(prefix)sBucketReplicate' % $.dashboard.prefix,
   },

diff --git a/mixin/alerts/bucket_replicate.libsonnet b/mixin/alerts/bucket_replicate.libsonnet
@@ -1,13 +1,13 @@
 {
   local thanos = self,
-  bucket_replicate+:: {
+  bucketReplicate+:: {
     selector: error 'must provide selector for Thanos Bucket Replicate dashboard',
     errorThreshold: 10,
     p99LatencyThreshold: 20,
     dimensions: std.join(', ', std.objectFields(thanos.targetGroups) + ['job']),
   },
   prometheusAlerts+:: {
-    groups+: if thanos.bucket_replicate == null then [] else [
+    groups+: if thanos.bucketReplicate == null then [] else [
       local location = if std.length(std.objectFields(thanos.targetGroups)) > 0 then ' in %s' % std.join('/', ['{{$labels.%s}}' % level for level in std.objectFields(thanos.targetGroups)]) else '';
       {
         name: 'thanos-bucket-replicate',
@@ -16,15 +16,15 @@
             alert: 'ThanosBucketReplicateErrorRate',
             annotations: {
               description: 'Thanos Replicate is failing to run%s, {{$value | humanize}}%% of attempts failed.' % location,
-              summary: 'Thanose Replicate is failing to run%s.' % location,
+              summary: 'Thanos Replicate is failing to run%s.' % location,
             },
             expr: |||
               (
                 sum by (%(dimensions)s) (rate(thanos_replicate_replication_runs_total{result="error", %(selector)s}[5m]))
               / on (%(dimensions)s) group_left
                 sum by (%(dimensions)s) (rate(thanos_replicate_replication_runs_total{%(selector)s}[5m]))
               ) * 100 >= %(errorThreshold)s
-            ||| % thanos.bucket_replicate,
+            ||| % thanos.bucketReplicate,
             'for': '5m',
             labels: {
               severity: 'critical',
@@ -42,7 +42,7 @@
               and
                 sum by (%(dimensions)s) (rate(thanos_replicate_replication_run_duration_seconds_bucket{%(selector)s}[5m])) > 0
               )
-            ||| % thanos.bucket_replicate,
+            ||| % thanos.bucketReplicate,
             'for': '5m',
             labels: {
               severity: 'critical',

diff --git a/mixin/config.libsonnet b/mixin/config.libsonnet
@@ -53,8 +53,7 @@
     thanosPrometheusCommonDimensions: 'namespace, pod',
     title: '%(prefix)sSidecar' % $.dashboard.prefix,
   },
-  // TODO(kakkoyun): Fix naming convention: bucketReplicate
-  bucket_replicate+:: {
+  bucketReplicate+:: {
     selector: 'job=~".*thanos-bucket-replicate.*"',
     title: '%(prefix)sBucketReplicate' % $.dashboard.prefix,
   },

diff --git a/mixin/dashboards/bucket_replicate.libsonnet b/mixin/dashboards/bucket_replicate.libsonnet
@@ -2,7 +2,7 @@ local g = import '../lib/thanos-grafana-builder/builder.libsonnet';
 
 {
   local thanos = self,
-  bucket_replicate+:: {
+  bucketReplicate+:: {
     selector: error 'must provide selector for Thanos Bucket Replicate dashboard',
     title: error 'must provide title for Thanos Bucket Replicate dashboard',
     dashboard:: {
@@ -11,22 +11,22 @@ local g = import '../lib/thanos-grafana-builder/builder.libsonnet';
     },
   },
   grafanaDashboards+:: {
-    [if thanos.bucket_replicate != null then 'bucket_replicate.json']:
-      g.dashboard(thanos.bucket_replicate.title)
+    [if thanos.bucketReplicate != null then 'bucket_replicate.json']:
+      g.dashboard(thanos.bucketReplicate.title)
       .addRow(
         g.row('Bucket Replicate Runs')
         .addPanel(
           g.panel('Rate') +
           g.qpsErrTotalPanel(
-            'thanos_replicate_replication_runs_total{result="error", %s}' % thanos.bucket_replicate.dashboard.selector,
-            'thanos_replicate_replication_runs_total{%s}' % thanos.bucket_replicate.dashboard.selector,
-            thanos.bucket_replicate.dashboard.dimensions
+            'thanos_replicate_replication_runs_total{result="error", %s}' % thanos.bucketReplicate.dashboard.selector,
+            'thanos_replicate_replication_runs_total{%s}' % thanos.bucketReplicate.dashboard.selector,
+            thanos.bucketReplicate.dashboard.dimensions
           )
         )
         .addPanel(
           g.panel('Errors', 'Shows rate of errors.') +
           g.queryPanel(
-            'sum by (%(dimensions)s, result) (rate(thanos_replicate_replication_runs_total{result="error", %(selector)s}[$interval]))' % thanos.bucket_replicate.dashboard,
+            'sum by (%(dimensions)s, result) (rate(thanos_replicate_replication_runs_total{result="error", %(selector)s}[$interval]))' % thanos.bucketReplicate.dashboard,
             '{{result}}'
           ) +
           { yaxes: g.yaxes('percentunit') } +
@@ -36,8 +36,8 @@ local g = import '../lib/thanos-grafana-builder/builder.libsonnet';
           g.panel('Duration', 'Shows how long has it taken to run a replication cycle.') +
           g.latencyPanel(
             'thanos_replicate_replication_run_duration_seconds',
-            'result="success",  %s' % thanos.bucket_replicate.dashboard.selector,
-            thanos.bucket_replicate.dashboard.dimensions
+            'result="success",  %s' % thanos.bucketReplicate.dashboard.selector,
+            thanos.bucketReplicate.dashboard.dimensions
           )
         )
       )
@@ -47,11 +47,11 @@ local g = import '../lib/thanos-grafana-builder/builder.libsonnet';
           g.panel('Metrics') +
           g.queryPanel(
             [
-              'sum by (%(dimensions)s) (rate(blocks_meta_synced{state="loaded", %(selector)s}[$interval]))' % thanos.bucket_replicate.dashboard,
-              'sum by (%(dimensions)s) (rate(blocks_meta_synced{state="failed", %(selector)s}[$interval]))' % thanos.bucket_replicate.dashboard,
-              'sum by (%(dimensions)s) (rate(thanos_replicate_blocks_already_replicated_total{%(selector)s}[$interval]))' % thanos.bucket_replicate.dashboard,
-              'sum by (%(dimensions)s) (rate(thanos_replicate_blocks_replicated_total{%(selector)s}[$interval]))' % thanos.bucket_replicate.dashboard,
-              'sum by (%(dimensions)s) (rate(thanos_replicate_objects_replicated_total{%(selector)s}[$interval]))' % thanos.bucket_replicate.dashboard,
+              'sum by (%(dimensions)s) (rate(blocks_meta_synced{state="loaded", %(selector)s}[$interval]))' % thanos.bucketReplicate.dashboard,
+              'sum by (%(dimensions)s) (rate(blocks_meta_synced{state="failed", %(selector)s}[$interval]))' % thanos.bucketReplicate.dashboard,
+              'sum by (%(dimensions)s) (rate(thanos_replicate_blocks_already_replicated_total{%(selector)s}[$interval]))' % thanos.bucketReplicate.dashboard,
+              'sum by (%(dimensions)s) (rate(thanos_replicate_blocks_replicated_total{%(selector)s}[$interval]))' % thanos.bucketReplicate.dashboard,
+              'sum by (%(dimensions)s) (rate(thanos_replicate_objects_replicated_total{%(selector)s}[$interval]))' % thanos.bucketReplicate.dashboard,
             ],
             ['meta loads', 'partial meta reads', 'already replicated blocks', 'replicated blocks', 'replicated objects']
           )

diff --git a/mixin/dashboards/defaults.libsonnet b/mixin/dashboards/defaults.libsonnet
@@ -1,3 +1,4 @@
+local utils = import '../lib/utils.libsonnet';
 {
   local thanos = self,
   local grafanaDashboards = super.grafanaDashboards,
@@ -13,7 +14,8 @@
   // Automatically add a uid to each dashboard based on the base64 encoding
   // of the file name and set the timezone to be 'default'.
   grafanaDashboards:: {
-    local component = std.split(filename, '.')[0],
+    local component = utils.sanitizeComponentName(std.split(filename, '.')[0]),
+
     [filename]: grafanaDashboards[filename] {
       uid: std.md5(filename),
       timezone: thanos.dashboard.timezone,

diff --git a/mixin/dashboards/query_frontend.libsonnet b/mixin/dashboards/query_frontend.libsonnet
@@ -12,7 +12,7 @@ local utils = import '../lib/utils.libsonnet';
     },
   },
   grafanaDashboards+:: {
-    [if thanos.queryFrontend != null then 'queryFrontend.json']:
+    [if thanos.queryFrontend != null then 'query_frontend.json']:
       local queryFrontendHandlerSelector = utils.joinLabels([thanos.queryFrontend.dashboard.selector, 'handler="query-frontend"']);
       local queryFrontendTripperwareSelector = utils.joinLabels([thanos.queryFrontend.dashboard.selector, 'tripperware="query_range"']);
       local queryFrontendOpSelector = utils.joinLabels([thanos.queryFrontend.dashboard.selector, 'op="query_range"']);

diff --git a/mixin/lib/utils.libsonnet b/mixin/lib/utils.libsonnet
@@ -12,4 +12,21 @@
   },
 
   joinLabels(labels): std.join(', ', std.filter(function(x) std.length(std.stripChars(x, ' ')) > 0, labels)),
+
+  firstCharUppercase(parts): std.join(
+    '',
+    [
+      std.join(
+        '',
+        [std.asciiUpper(std.stringChars(part)[0]), std.substr(part, 1, std.length(part) - 1)]
+      )
+      for part in parts[1:std.length(parts)]
+    ]
+  ),
+
+  toCamelCase(parts): std.join('', [parts[0], self.firstCharUppercase(parts)]),
+
+  componentParts(name): std.split(name, '_'),
+
+  sanitizeComponentName(name): if std.length(self.componentParts(name)) > 1 then self.toCamelCase(self.componentParts(name)) else name,
 }
diff --git a/mixin/rules/bucket_replicate.libsonnet b/mixin/rules/bucket_replicate.libsonnet
@@ -1,10 +1,10 @@
 {
   local thanos = self,
-  bucket_replicate+:: {
+  bucketReplicate+:: {
     selector: error 'must provide selector for Thanos Bucket Replicate dashboard',
   },
   prometheusRules+:: {
-    groups+: if thanos.bucket_replicate == null then [] else [
+    groups+: if thanos.bucketReplicate == null then [] else [
       {
         name: 'thanos-bucket-replicate.rules',
         rules: [],

diff --git a/mixin/runbook.md b/mixin/runbook.md
@@ -15,7 +15,7 @@
 
 |Name|Summary|Description|Severity|Runbook|
 |---|---|---|---|---|
-|ThanosBucketReplicateErrorRate|Thanose Replicate is failing to run.|Thanos Replicate is failing to run, {{$value  humanize}}% of attempts failed.|critical|[https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicateerrorrate](https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicateerrorrate)|
+|ThanosBucketReplicateErrorRate|Thanos Replicate is failing to run.|Thanos Replicate is failing to run, {{$value  humanize}}% of attempts failed.|critical|[https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicateerrorrate](https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicateerrorrate)|
 |ThanosBucketReplicateRunLatency|Thanos Replicate has a high latency for replicate operations.|Thanos Replicate {{$labels.job}} has a 99th percentile latency of {{$value}} seconds for the replicate operations.|critical|[https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicaterunlatency](https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicaterunlatency)|
 
 ## thanos-compact
@@ -32,7 +32,6 @@
 
 |Name|Summary|Description|Severity|Runbook|
 |---|---|---|---|---|
-|ThanosBucketReplicateIsDown|Thanos component has disappeared.|ThanosBucketReplicate has disappeared. Prometheus target for the component cannot be discovered.|critical|[https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicateisdown](https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosbucketreplicateisdown)|
 |ThanosCompactIsDown|Thanos component has disappeared.|ThanosCompact has disappeared. Prometheus target for the component cannot be discovered.|critical|[https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanoscompactisdown](https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanoscompactisdown)|
 |ThanosQueryIsDown|Thanos component has disappeared.|ThanosQuery has disappeared. Prometheus target for the component cannot be discovered.|critical|[https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosqueryisdown](https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosqueryisdown)|
 |ThanosReceiveIsDown|Thanos component has disappeared.|ThanosReceive has disappeared. Prometheus target for the component cannot be discovered.|critical|[https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosreceiveisdown](https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosreceiveisdown)|

diff --git a/pkg/rules/rules_test.go b/pkg/rules/rules_test.go
@@ -50,7 +50,7 @@ func testRulesAgainstExamples(t *testing.T, dir string, server rulespb.RulesServ
 		{
 			Name:                    "thanos-component-absent",
 			File:                    filepath.Join(dir, "alerts.yaml"),
-			Rules:                   []*rulespb.Rule{someAlert, someAlert, someAlert, someAlert, someAlert, someAlert, someAlert},
+			Rules:                   []*rulespb.Rule{someAlert, someAlert, someAlert, someAlert, someAlert, someAlert},
 			Interval:                60,
 			PartialResponseStrategy: storepb.PartialResponseStrategy_ABORT,
 		},