OpenSearch

Cache Miss Storm Amplifying Latency

warning
latencyUpdated Feb 6, 2026

High Cache_Query_Miss and Cache_Request_Miss rates force expensive query re-execution and document retrieval, amplifying latency and CPU usage. Often follows cache evictions or cluster restarts when caches are cold.

How to detect:

Track Cache_Query_Miss and Cache_Request_Miss rates alongside Cache_Query_Hit and Cache_Request_Hit to calculate hit ratios. Monitor Cache_Request_Eviction and Cache_FieldData_Eviction for premature evictions. Correlate with increased CPU_Utilization and Latency.

Recommended action:

Analyze query patterns to improve cache reuse. Increase cache sizes if evictions are high but heap allows. Implement query result caching strategies. Pre-warm caches after restarts. For persistent cache misses, optimize queries to be more cache-friendly or accept the cache miss rate.