[EXT] Re: [dpdk-stable] [PATCH v2] test: avoid hang if queues are full and Tx fails

[Thomas Monjalon]

I'm pretty sure there is something wrong in the driver cnxk,
but you keep insisting and nobody complained,
so I accept the patch for the test application.

Applied


24/05/2022 07:39, Rakesh Kudurumalla:
> ping
> 
> > From: Rakesh Kudurumalla
> > Sent: Monday, May 9, 2022 3:32 PM
> > 
> > Hi Thomas Monjalon,
> > 
> > Same behavior is observed in cnxk driver as well.
> > Can we please get this patch merged ?
> > 
> > > From: Rakesh Kudurumalla
> > > Sent: Monday, February 14, 2022 10:27 AM
> > > >
> > > > octeontx2 driver is removed
> > > > Can we close this patch?
> > > Same behavior is observed with cnxk driver, so we need  this patch
> > > >
> > > > 01/02/2022 07:30, Rakesh Kudurumalla:
> > > > > ping
> > > > >
> > > > > > From: Rakesh Kudurumalla
> > > > > > Sent: Monday, January 10, 2022 2:35 PM
> > > > > >
> > > > > > ping
> > > > > >
> > > > > > > From: Rakesh Kudurumalla
> > > > > > > Sent: Monday, December 13, 2021 12:10 PM
> > > > > > > > From: Thomas Monjalon <thomas at monjalon.net>
> > > > > > > > Sent: Monday, November 29, 2021 2:44 PM
> > > > > > > > 29/11/2021 09:52, Rakesh Kudurumalla:
> > > > > > > > > From: Thomas Monjalon <thomas at monjalon.net>
> > > > > > > > > > 22/11/2021 08:59, Rakesh Kudurumalla:
> > > > > > > > > > > From: Thomas Monjalon <thomas at monjalon.net>
> > > > > > > > > > > > 20/07/2021 18:50, Rakesh Kudurumalla:
> > > > > > > > > > > > > Current pmd_perf_autotest() in continuous mode
> > > > > > > > > > > > > tries to enqueue MAX_TRAFFIC_BURST completely
> > > > > > > > > > > > > before starting the
> > > > > > test.
> > > > > > > > > > > > > Some drivers cannot accept complete
> > > > > > > > > > > > > MAX_TRAFFIC_BURST even though
> > > > > > > > > > rx+tx
> > > > > > > > > > > > > desc
> > > > > > > > > > > > count
> > > > > > > > > > > > > can fit it.
> > > > > > > > > > > >
> > > > > > > > > > > > Which driver is failing to do so?
> > > > > > > > > > > > Why it cannot enqueue 32 packets?
> > > > > > > > > > >
> > > > > > > > > > > Octeontx2 driver is failing to enqueue because
> > > > > > > > > > > hardware buffers are full
> > > > > > > > > > before test.
> > > > > > > >
> > > > > > > > Aren't you stopping the support of octeontx2?
> > > > > > > > Why do you care now?
> > > > > > > >  yes we are not supporting octeontx2,but this  issue is
> > > > > > > > observed in cnxk driver ,current patch fixes the same
> > > > > > > > > >
> > > > > > > > > > Why hardware buffers are full?
> > > > > > > > > Hardware buffers are full because number of number of
> > > > > > > > > descriptors in continuous mode Is less than
> > > > > > > > > MAX_TRAFFIC_BURST, so if enque fails , there is no way
> > > > > > > > > hardware
> > > can drop the Packets .
> > > > > > > > > pmd_per_autotest application evaluates performance after
> > > > > > > > > enqueueing
> > > > > > packets Initially.
> > > > > > > > > >
> > > > > > > > > > > pmd_perf_autotest() in continuous mode tries to
> > > > > > > > > > > enqueue MAX_TRAFFIC_BURST (2048) before starting the
> > test.
> > > > > > > > > > >
> > > > > > > > > > > > > This patch changes behaviour to stop enqueuing
> > > > > > > > > > > > > after few
> > > > > > retries.
> > > > > > > > > > > >
> > > > > > > > > > > > If there is a real limitation, there will be issues
> > > > > > > > > > > > in more places than this test program.
> > > > > > > > > > > > I feel it should be addressed either in the driver
> > > > > > > > > > > > or at ethdev
> > > > level.