On Sat, Aug 9, 2014 at 11:18 AM, Anatol Pomozov <anatol.pomozov@gmail.com> wrote:
Hi
Another way to get more information about this problem is to use kernel traces. Let's enable block and writeback events:
sudo su cd /sys/kernel/debug/tracing echo 1 > events/writeback/enable echo 1 > events/block/enable echo 1 > tracing_on cat trace_pipe
there will some information like processid, inode... Maybe you'll see some pattern in the writes etc..
In any case this problem sounds like an upstream issue and it is better to contact them.
I've emailed the btrfs list and will follow up there. I could not make head nor tail of block/writeback events, seemed similar with the problematic kernel versions and the non-problematic ones. It could be that the kernel upgrade merely exposed an underlying issue. In any case, I uploaded a print screen showing the iotop and perf top readings.... hopefully someone can understand it. https://db.tt/TSh5piq6