We are using version 8.1.28, with a server configuration of 16 cores and 48GB of memory, running on VMware with no other software running except Ignition.
We have recently encountered frequent clock drift errors, and the server often runs very slowly. By using JMC to analyze the runtime status, we have identified two issues.
1.Under normal circumstances, the CPU usage is consistently around 10%. We suspect that the CPU spikes are caused by certain threads. How can we pinpoint the cause of abnormal CPU spikes?
2.Regarding garbage collection, as shown in the screenshot , a garbage collection occurred at 13:41:50, causing a 2.361 second pause in the program. We allocated a maximum and minimum of 24GB to the JVM, and the JVM's memory usage has never exceeded 8GB. Why were multiple garbage collections triggered at this time, and how can we avoid this issue?We have added -XX:MaxGCPauseMillis=100 to the Ignition.conf file.
Here is the automatically exported JFR file. Could you please help analyze it? Thanks a lot.
automaticallyTriggeredRecording_2024-03-27_13-42-56_2ce427af.zip (3.3 MB)
By the way, could you please explain what the perspective-worker and perspective-queue threads are used for?
