JaegerElasticsearchCassandra

Query Service Latency Degradation

warning
latencyUpdated Feb 7, 2026

High P95/P99 query latencies (>5 seconds) make Jaeger UI unusable during incident troubleshooting, typically caused by slow storage reads, overloaded shards, or inefficient trace queries.

Sources
Frequently Asked Questions | Jaegerwww.jaegertracing.io
Jaeger Monitoring: Essential Metrics and Alerting for Production ...last9.io
Jaeger Metrics: Internal Operations and Service Performance ... - Last9last9.io
Technologies:
JaegerSymptoms of this issue are visible in Jaeger metrics and logs
ElasticsearchThe root cause of this issue originates in Elasticsearch
CassandraThe root cause of this issue originates in Cassandra
How to detect:

Monitor P95 and P99 query latency. Alert when query latency exceeds 5 seconds consistently. Track query success rate; drops below 95% indicate storage or query service issues.

Recommended action:

Check storage backend query performance. For Elasticsearch, verify disk I/O, shard health, and index design. For Cassandra, check read latency and partition key distribution. Break down by query type to identify expensive patterns.