From 00db8da80dcbd2ae3f746b42d6a3d6492259f009 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Luk=C3=A1=C5=A1=20Vl=C4=8Dek?= Date: Fri, 2 Oct 2020 14:20:28 +0200 Subject: [PATCH] Bug 1883719: Bulk statistics are recorded under index threadpool --- files/prometheus_alerts.yml | 8 ++++---- files/prometheus_rules.yml | 12 ++++++------ 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/files/prometheus_alerts.yml b/files/prometheus_alerts.yml index 6082048f6..b21a8fea4 100644 --- a/files/prometheus_alerts.yml +++ b/files/prometheus_alerts.yml @@ -22,12 +22,12 @@ "labels": "severity": "warning" - - "alert": "ElasticsearchBulkRequestsRejectionJumps" + - "alert": "ElasticsearchIndexingRequestsRejectionJumps" "annotations": - "message": "High Bulk Rejection Ratio at {{ $labels.node }} node in {{ $labels.cluster }} cluster. This node may not be keeping up with the indexing speed." - "summary": "High Bulk Rejection Ratio - {{ $value }}%" + "message": "High Indexing Rejection Ratio at {{ $labels.node }} node in {{ $labels.cluster }} cluster. This node may not be keeping up with the indexing speed." + "summary": "High Indexing Rejection Ratio - {{ $value }}%" "expr": | - round( bulk:reject_ratio:rate2m * 100, 0.001 ) > 5 + round( indexing:reject_ratio:rate2m * 100, 0.001 ) > 5 "for": "10m" "labels": "severity": "warning" diff --git a/files/prometheus_rules.yml b/files/prometheus_rules.yml index 8ced15f23..e43ce3830 100644 --- a/files/prometheus_rules.yml +++ b/files/prometheus_rules.yml @@ -3,11 +3,11 @@ - "name": "logging_elasticsearch.rules" "rules": - "expr": | - rate(es_threadpool_threads_count{name="bulk", type="rejected"}[2m]) - "record": "bulk:rejected_requests:rate2m" + rate(es_threadpool_threads_count{name="index", type="rejected"}[2m]) + "record": "indexing:rejected_requests:rate2m" - "expr": | - rate(es_threadpool_threads_count{name="bulk", type="completed"}[2m]) - "record": "bulk:completed_requests:rate2m" + rate(es_threadpool_threads_count{name="index", type="completed"}[2m]) + "record": "indexing:completed_requests:rate2m" - "expr": | - sum by (cluster, instance, node) (bulk:rejected_requests:rate2m) / on (cluster, instance, node) (bulk:completed_requests:rate2m) - "record": "bulk:reject_ratio:rate2m" + sum by (cluster, instance, node) (indexing:rejected_requests:rate2m) / on (cluster, instance, node) (indexing:completed_requests:rate2m) + "record": "indexing:reject_ratio:rate2m"