https://bugzilla.kernel.org/show_bug.cgi?id=217965 denk@xxxxxxxx changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |denk@xxxxxxxx --- Comment #67 from denk@xxxxxxxx --- Hi, I just stumbled upon this issue, which it seems is the same I am suffering from on a Raspberry Pi 5. Th e OS is Arch Linux ARM and linux-rpi 6.6.20 running on a NVME SSD. After reading this issue, I checked the ext4 mount options and found stripe=8191. As a first test I downgraded linux-rpi to 6.1.69 and my issue of a CPU hogging kworker process, when pulling and creating docker containers did not happen anymore. With kernel 6.6.20 and all earlier 6.6.x versions, docker operations were really slow, in some cases pulling and recreating a container took over 1000 seconds. With kernel 6.1.69 these operations are back to normal speed. As a next step I would like to try to set stripe=0. What is the right approach here, as I am a bit unsure. Is it ok to remount the running system partition with mount -o remount,stripe=0 <dev> without any risks for a first test? And to change permanently to stripe=0,id it ok and sufficient to run tune2fs -f -E stride=0 <dev> on the mounted system partition without any risks? I would be thankful for a helping hand here to not do anything wrong or dangerous. I hope, that this works around my issue for now, until a fix has been found for this. Thank you very much for looking into this! Kind regards denk -- You may reply to this email to add a comment. You are receiving this mail because: You are watching the assignee of the bug.
