A soft lockup isn't necessarily anything 'crashing', it is the symptom of a task or kernel thread using and not releasing a CPU for a longer period of time than allowed; in Check Point the default fault is 10 seconds. This is adjustable by editing the value within /proc/sys/kernel/softlockup_thresh and requires a reboot when change. Changing this value will only extend the threshold for when a softlock trace is triggered. The technical reasons behind a softlock involves CPU interrupts and nmi-watchdog while the CPU is under heavy load. For each online CPU on the system, a watchdog process gets created which will send a non maskable interrupt (NMI) to all CPUs in the system who in turn will (non-intrusively) print the stacktraces of their currently running tasks. Under normal circumstances those messages may go away if the load on the CPU is decreased. The stack traces of those tasks are supposed to give us a first idea what the tasks were doing at the time of the issue. However, to be able to examine the root cause behind the messages, a kernel dump would be needed.