trino.jvm.gc.collection_time

GC time total

Dimensions:None

Available on:Native (1)

Interface Metrics (1)

Native

java.lang.GarbageCollector.CollectionTime

Total time spent in garbage collection

Dimensions:None

Sources

java.lang.GarbageCollector.CollectionTimetrino.io

Technical Annotations (20)

Configuration Parameters (4)

memory.heap-headroom-per-noderecommended: increase if pod OOM-killed

reserves native memory outside JVM heap to prevent k8s OOMKills

-Xmxrecommended: 105G

JVM max heap size; must accommodate query.max-memory-per-node + memory.heap-headroom-per-node with buffer for GC

query.max-memory-per-noderecommended: 85GB

Maximum query memory per node; tight allocation relative to heap can trigger excessive GC

-XX:G1HeapRegionSizerecommended: 32M

G1 GC region size; impacts GC pause behavior for large heaps

Error Signatures (6)

io.trino.operator.PageTransportTimeoutExceptionexception

java.util.concurrent.TimeoutException: Total timeout 10000 ms elapsedexception

io.trino.server.IoExceptionSuppressingWriterInterceptor Could not write to output: EofException(null)log pattern

Expected response code from http://.*:8080/v1/task/.*/status to be 200, but was 408http status

Error 408 Timeout: Timed outhttp status

io.trino.spi.TrinoExceptionexception

Technical References (10)

HttpPageBufferClientcomponent/v1/task/{task-id}/resultscomponentMajor GCconceptOOMKilledconceptcom.oracle.truffle.js.runtime.builtins.JSFunctionObject$Unboundcomponentcom.oracle.truffle.api.strings.TruffleStringcomponentGraalVMcomponentRangercomponentG1 Old Generationcomponent/v1/task/.../statusfile path

Related Insights (4)

PageTransportTimeoutException occurs without worker failure or obvious resource exhaustionwarning

▸

Worker OOM causes pod restarts and query failurescritical

▸

Coordinator crashes from Ranger plugin JavaScript policy memory leakcritical

▸

Long GC pauses cause HTTP 408 task timeout failurescritical

▸