[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <dc82e53c-c565-460d-b268-26d0d5a9ed68@ti.com>
Date: Fri, 24 Oct 2025 14:13:43 +0530
From: "Malladi, Meghana" <m-malladi@...com>
To: Jacob Keller <jacob.e.keller@...el.com>, <horms@...nel.org>,
<namcao@...utronix.de>, <vadim.fedorenko@...ux.dev>,
<christian.koenig@....com>, <sumit.semwal@...aro.org>,
<sdf@...ichev.me>, <john.fastabend@...il.com>, <hawk@...nel.org>,
<daniel@...earbox.net>, <ast@...nel.org>, <pabeni@...hat.com>,
<kuba@...nel.org>, <edumazet@...gle.com>, <davem@...emloft.net>,
<andrew+netdev@...n.ch>
CC: <linaro-mm-sig@...ts.linaro.org>, <dri-devel@...ts.freedesktop.org>,
<linux-media@...r.kernel.org>, <bpf@...r.kernel.org>,
<linux-kernel@...r.kernel.org>, <netdev@...r.kernel.org>,
<linux-arm-kernel@...ts.infradead.org>, <srk@...com>,
Vignesh Raghavendra
<vigneshr@...com>,
Roger Quadros <rogerq@...nel.org>, <danishanwar@...com>
Subject: Re: [PATCH net-next v4 0/6] Add AF_XDP zero copy support
Hi Jacob,
On 10/24/2025 6:26 AM, Jacob Keller wrote:
>
>
> On 10/23/2025 2:39 AM, Meghana Malladi wrote:
>> This series adds AF_XDP zero coppy support to icssg driver.
>>
>> Tests were performed on AM64x-EVM with xdpsock application [1].
>>
>> A clear improvement is seen Transmit (txonly) and receive (rxdrop)
>> for 64 byte packets. 1500 byte test seems to be limited by line
>> rate (1G link) so no improvement seen there in packet rate
>>
>> Having some issue with l2fwd as the benchmarking numbers show 0
>> for 64 byte packets after forwading first batch packets and I am
>> currently looking into it.
>>
>
> Do you think this means there is an issue with the patches or your test
> setup?
>
> I didn't see anything stand out as a problem to me when reading the series:
>
> Reviewed-by: Jacob Keller <jacob.e.keller@...el.com>
>
The setup is quite simple. I send broadcast traffic to the dut on which
I run l2fwd (with xdpsock) and expect the stats to increase. But after
4096 packets, the stats stop incrementing. And I see this issue only
with 64 byte packet and not with 1500 byte packets. I am suspecting
could be some race condition or some bug in our dma controller. I am
tracking this issue and post a fix for this separately.
--
Thanks,
Meghana Malladi
Powered by blists - more mailing lists