Re: [ata] 0568e61225: stress-ng.copy-file.ops_per_sec -15.0% regression

[John Garry]

On 12/08/2022 12:13, John Garry wrote:
> > On Tue, Aug 09, 2022 at 07:55:53AM -0700, Damien Le Moal wrote:
> > > On 2022/08/09 2:58, John Garry wrote:
> > > > On 08/08/2022 15:52, Damien Le Moal wrote:
> > > > > On 2022/08/05 1:05, kernel test robot wrote:
> > > > > > Greeting,
> > > > > >
> > > > > > FYI, we noticed a -15.0% regression of 
> > > > > > stress-ng.copy-file.ops_per_sec due to commit:
> > > > > >
> > > > > >
> > > > > > commit: 0568e6122574dcc1aded2979cd0245038efe22b6 ("ata: 
> > > > > > libata-scsi: cap ata_device->max_sectors according to 
> > > > > > shost->max_sectors")
> > > > > > https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git 
> > > > > > master
> > > > > >
> > > > > > in testcase: stress-ng
> > > > > > on test machine: 96 threads 2 sockets Ice Lake with 256G memory
> > > > > > with following parameters:
> > > > > >
> > > > > >     nr_threads: 10%
> > > > > >     disk: 1HDD
> > > > > >     testtime: 60s
> > > > > >     fs: f2fs
> > > > > >     class: filesystem
> > > > > >     test: copy-file
> > > > > >     cpufreq_governor: performance
> > > > > >     ucode: 0xb000280
> > > > >
> > > > > Without knowing what the device adapter is, hard to say where the 
> > > > > problem is. I
> > > > > suspect that with the patch applied, we may be ending up with a 
> > > > > small default
> > > > > max_sectors value, causing overhead due to more commands than 
> > > > > necessary.
> > > > >
> > > > > Will check what I see with my test rig.
> > > >
> > > > As far as I can see, this patch should not make a difference unless the
> > > > ATA shost driver is setting the max_sectors value unnecessarily low.
> > >
> > > That is my hunch too, hence my question about which host driver is 
> > > being used
> > > for this test... That is not apparent from the problem report.
> >
> > we noticed the commit is already in mainline now, and in our tests, 
> > there is
> > still similar regression and also on other platforms.
> > could you guide us how to check "which host driver is being used for this
> > test"? hope to supply some useful information.
>
> For me, a complete kernel log may help.

and since only 1HDD, the output of the following would be helpful:

/sys/block/sda/queue/max_sectors_kb
/sys/block/sda/queue/max_hw_sectors_kb

And for 5.19, if possible.

Thanks!

> > > >