On Wed, Jul 03, 2019 at 12:39:31AM +0200, Andrea Vai wrote:
> On 02/07/19 20:01:13, Ming Lei wrote:
> > On Tue, Jul 02, 2019 at 12:46:45PM +0200, Andrea Vai wrote:
> > > Hi,
> > > I have a problem writing data to a USB pendrive, and it seems
> > > kernel-related. With the help of Greg an Alan (thanks) and some
> > > bisect, I found out the offending commit being
> > >
> > > commit f664a3cc17b7d0a2bc3b3ab96181e1029b0ec0e6
> > >
> > > [...]
> > >
> >
> > One possible reason may be related with too small 'nr_requests', could
> > you apply the following command and see if any difference can be made?
> >
> > echo 32 > /sys/block/sdN/queue/nr_requests
>
> I applied it (echo 32 > /sys/block/sdf/queue/nr_requests), ran the test again, and still failed. I assumed I didn't have to build the kernel again, did I? (sorry but I am not skilled)
>
You don't need to build kernel.
I just run same write test on one slow usb drive in my laptop, which
runs '5.1.11-200.fc29.x86_64', and can't reproduce your issue, maybe it
depends on your drive.
Could you collect the queue limits sysfs log via the following command?
find /sys/block/sdN/queue -type f -exec grep -aH . {} \;
Thanks,
Ming
