PrometheusMetricjvm.memory.heap.used
JVM heap used bytesSummary
Tracks the current amount of JVM heap memory in use. Heap usage directly impacts garbage collection frequency and application performance. The insight about JVM heap pressure cascading failures highlights how sustained high heap usage (>85%) triggers frequent GC pauses, degrading query and indexing performance. Heap exhaustion leads to OutOfMemoryErrors and node failures.
Technical Annotations (2)
Technical References (2)
model cachecomponentJDK 25.0.2+10componentRelated Insights (8)
Long GC pauses halt all ZooKeeper threads including heartbeat processing, causing client sessions to expire. Even well-tuned JVMs can experience occasional long pauses that exceed typical session timeout windows.
When JVM heap usage stays above 85% for extended periods, garbage collection pauses increase dramatically, leading to node unresponsiveness, cluster state propagation failures, and potential split-brain scenarios.
Field data (inverted reverse index for aggregations) loads into JVM heap on first access and persists for segment lifetime. When circuit breaker limit or cache size is too small, frequent evictions cause repeated expensive field data loading, spiking CPU and heap pressure.
Cassandra nodes running on the JVM can experience heap exhaustion where heap usage climbs to 80-90% and stays elevated without dropping after GC, leading to OutOfMemoryError or node instability. This manifests as timeout errors at the application layer before the node crashes.
Circuit breakers trip to prevent operations that would cause OutOfMemoryError by estimating memory requirements and rejecting requests that exceed configured limits. Frequent trips indicate memory pressure or oversized operations.
Improper distribution of shards or unbalanced node roles can cause resource hotspots where some nodes are overloaded while others are underutilized.