Message-ID: <21ce3015-b379-056c-e5ca-8763c58c6553@arinc9.com>
Date: Wed, 10 May 2023 10:59:36 +0200
From: Arınç ÜNAL <arinc.unal@...nc9.com>
To: Daniel Golle <daniel@...rotopia.org>, Vladimir Oltean <olteanv@...il.com>
Cc: DENG Qingfang <dqfext@...il.com>, Greg Ungerer <gerg@...nel.org>,
 Richard van Schagen <richard@...terhints.com>,
 Richard van Schagen <vschagen@...com>,
 Frank Wunderlich <frank-w@...lic-files.de>, mithat.guner@...ont.com,
 erkin.bozoglu@...ont.com, bartel.eerdekens@...stell8.be,
 netdev <netdev@...r.kernel.org>
Subject: Re: MT7530 bug, forward broadcast and unknown frames to the correct
 CPU port

On 1.05.2023 12:43, Arınç ÜNAL wrote:
> On 1.05.2023 13:31, Daniel Golle wrote:
>> On Mon, May 01, 2023 at 01:09:30PM +0300, Vladimir Oltean wrote:
>>> On Sat, Apr 29, 2023 at 10:52:12PM +0300, Arınç ÜNAL wrote:
>>>> On 29.04.2023 21:56, Vladimir Oltean wrote:
>>>>> On Sat, Apr 29, 2023 at 09:39:41PM +0300, Arınç ÜNAL wrote:
>>>>>> Are you fine with the preferred port patch now that I mentioned 
>>>>>> port 6
>>>>>> would be preferred for MT7531BE since it's got 2.5G whilst port 5 has
>>>>>> got 1G? Would you like to submit it or leave it to me to send the 
>>>>>> diff
>>>>>> above and this?
>>>>>
>>>>> No, please tell me: what real life difference would it make to a user
>>>>> who doesn't care to analyze which CPU port is used?
>>>>
>>>> They would get 2.5 Gbps download/upload bandwidth in total to the CPU,
>>>> instead of 1 Gbps. 3 computers connected to 3 switch ports would 
>>>> each get
>>>> 833 Mbps download/upload speed to/from the CPU instead of 333 Mbps.
>>>
>>> In theory, theory and practice are the same. In practice, they aren't.
>>> Are you able to obtain 833 Mbps concurrently over 3 user ports?
>>
>> Probably the 2.5 GBit/s won't saturate, but I do manage to get more
>> than 1 Gbit/s total (using the hardware flow offloading capability to
>> NAT-route WAN<->LAN and simultanously have a WiFi client access a NAS
>> device which also connects to a LAN port. I use MT7915E+MT7975D mPCIe
>> module with BPi-R2)
>>
>> Using PHY muxing to directly map the WAN port to GMAC2 is also an
>> option, but would be limiting the bandwidth for those users who just
>> want all 5 ports to be bridged. Hence I do agree with Arınç that the
>> best would be to use the TRGMII link on GMAC1 for the 4 WAN ports and
>> prefer using RGMII link on GMAC2 for the WAN port, but keep using DSA.
> 
> You seem to be rather talking about MT7530 while I think preferring port 6
> would benefit MT7531BE the most.
> 
> Can you test the actual speed with SGMII on MT7531? Route between two 
> ports and
> do a bidirectional iperf3 speed test.
> 
> SGMII should at least provide you with 2 Gbps bandwidth in total in a
> router-on-a-stick scenario which is the current situation until the 
> changing
> DSA conduit support is added.
> 
> If we were to use port 5, download and upload speed would be capped at 500
> Mbps. With SGMII you should get 1000 Mbps on each.

I tested this on Daniel's Banana Pi BPI-R3 which has got an MT7531AE 
switch. I can confirm I get more than 500 Mbps for RX and TX on a 
bidirectional speed test.

[SUM][RX-S]   0.00-18.00  sec  1.50 GBytes   715 Mbits/sec 
    receiver

[SUM][TX-S]   0.00-18.00  sec  1.55 GBytes   742 Mbits/sec  6996 
     sender

The test was run between two computers on different networks, 
192.168.1.0/24 and 192.168.2.0/24, both computers had static routes to 
reach each other. I tried iperf3 as the server and client on both 
computers with similar results.

This concludes preferring port 6 is practically beneficial for MT7531BE.

Arınç

Powered by blists - more mailing lists