On Wed, 2018-01-31 at 13:22 +1100, Dave Chinner wrote:
> On Tue, Jan 30, 2018 at 11:40:04PM +0500, mikhail wrote:
> > Hi.
> > 
> > I  launched several application which highly use I/O on start and it
> > caused freezing system for several second.
> > 
> > All traces lead to xfs.
> > 
> > Whether there is a useful info in trace or just it means that disk is slow?
> 
> Could be a disk that is slow, or could be many other
> things. More information required:
> 
> http://xfs.org/index.php/XFS_FAQ#Q:_What_information_should_I_include_when_reporting_a_problem.3F


How to be if there is no 100% case and I can catch the hang in the absolutely unknown time?
Can I all time keep running "trace-cmd record -e xfs\*"?
It would take a lot of memory?
Or will be enought enter "echo w > /proc/sysrq-trigger" after boot?

> 
> And everything else is backed up behind it trying to allocate
> inodes. There could be many, many reasons for that, and that's why
> we need more information to begin to isolate the cause.
> 
> Cheers,
> 
> Dave.
> 

Yet another backtrace attached to message.