问题
I am running hazelcast (3.7.2). It is split into client node and a server node. A client can upload files, which gets put into an IQueue to be picked up by an Item listener on the server side. The problem is, the item listeners are not picking up those items straight away because the system is "not healthy". I believe this could be due to the way memory is being used and garbage collection is struggling. This is the message I get.
processors=32,
physical.memory.total=295.7G,
physical.memory.free=2.9G,
swap.space.total=16.0G,
swap.space.free=15.7G,
heap.memory.used=112.4G,
heap.memory.free=23.3G,
heap.memory.total=135.8G,
heap.memory.max=135.8G,
heap.memory.used/total=82.82%,
heap.memory.used/max=82.82%,
minor.gc.count=375,
minor.gc.time=512417ms,
major.gc.count=8,
major.gc.time=169878ms,
load.process=0.01%,
load.system=0.01%,
load.systemAverage=20.00%,
thread.count=171,
thread.peakCount=290,
cluster.timeDiff=0,
event.q.size=0,
executor.q.async.size=0,
executor.q.client.size=0,
executor.q.query.size=0,
executor.q.scheduled.size=0,
executor.q.io.size=0,
executor.q.system.size=0,
executor.q.operations.size=0,
executor.q.priorityOperation.size=0,
operations.completed.count=42173798,
executor.q.mapLoad.size=0,
executor.q.mapLoadAllKeys.size=0,
executor.q.cluster.size=0,
executor.q.response.size=0,
operations.running.count=0,
operations.pending.invocations.percentage=0.00%,
operations.pending.invocations.count=0,
proxy.count=0,
clientEndpoint.count=6,
connection.active.count=7,
client.connection.count=6,
connection.count=1
Dec 08, 2017 3:39:39 AM com.hazelcast.internal.diagnostics.HealthMonitor
Can someone show me how I can optimize my configuration or point me in the right direction? Thanks.
来源：https://stackoverflow.com/questions/47711680/configuring-hazelcast-to-prevent-heartbeat-issues