Article 4R3SA ext4, the disk performance deteriorates rapidly after a reboot

ext4, the disk performance deteriorates rapidly after a reboot

by
whatsthecraic
from LinuxQuestions.org on (#4R3SA)
Good folks,

I recently requested to my host provider (ovh.ie) to increase the disk space in my personal VPS. After the update, I've aded the extra free space in the existing partition with parted & resize2fs, which seems to be correctly recognised by lsblk & co. The problem is that, now, after a reboot, the VPS becomes quite unresponsible after 4-6 hours of uptime. The CPU usage peaks at 100%, completely consumed by processes such as kworker/u2:0+flush-254:0 and jbd2/vda1-8. Monitoring the VPS with journalctl, iostat and fatrace revealed only mild activity from sshd and exim, still on the normal range. But it's like the partition becomes incredibly slow or unresponsive, with the processes constantly stuck while trying to write in the disk. Here is the output of dmesg: http://ix.io/1WK9. I am not sure how to track down the problem. Running fsck (e2fsck) in rescue mode showed no issues on the partition.

Any suggestion on how to track down the root cause for this behaviour?latest?d=yIl2AUoC8zA latest?i=h_jaa7h6Iyw:txSZ5JKlG3w:F7zBnMy latest?i=h_jaa7h6Iyw:txSZ5JKlG3w:V_sGLiP latest?d=qj6IDK7rITs latest?i=h_jaa7h6Iyw:txSZ5JKlG3w:gIN9vFwh_jaa7h6Iyw
External Content
Source RSS or Atom Feed
Feed Location https://feeds.feedburner.com/linuxquestions/latest
Feed Title LinuxQuestions.org
Feed Link https://www.linuxquestions.org/questions/
Reply 0 comments