btw. We found an additonal hints about the cache write to disk (480 sec) with an information of settings for sysctl. I have changed the settings to vm.dirty_background_ratio = 5 vm.dirty_ratio = 10 It seems it reduce the occurence of the timeout (480 sec) a little bit. But this is only a opinion. see also page: https://www.blackmoreops.com/2014/09/22/linux-kernel-panic-issue-fix-hung_task_timeout_secs-blocked-120-seconds-problem/ Best regards Holger