Re: Chelsio Forwarding performance and RELENG_13 vs RELENG_12 (solved)

From: mike tancsa <mike_at_sentex.net>
Date: Thu, 03 Nov 2022 18:20:54 UTC
On 10/21/2022 2:45 PM, mike tancsa wrote:
> On 10/21/2022 2:30 PM, Navdeep Parhar wrote:
>> On 10/21/22 11:15 AM, mike tancsa wrote:
>>> On 10/21/2022 2:13 PM, Navdeep Parhar wrote:
>>>>
>>>>>> hw.cxgbe.ntxq=4
>>>>>> hw.cxgbe.nrxq=4
>>>>>>
>>>>> Thanks Navdeep!
>>>>>
>>>>> Unfortunately, still the odd dropped packet :(
>>>>
>>>> Can you try increasing the size of the queues?
>>>>
>>>> hw.cxgbe.qsize_txq=2048
>>>> hw.cxgbe.qsize_rxq=2048
>>>>
>>>> The stats show that you are using MTU 1500.  If you were using MTU 
>>>> 9000 I'd also have suggested setting largest_rx_cluster to 4K.
>>>>
>>>> hw.cxgbe.largest_rx_cluster=4096
>>>>
>>> Thanks again, just 1500 MTU.  Shall I keep nt and nrxq at 4 still ?
>>
>> Yes, I think 4 queues are enough for 10G.
>>
> Sadly, no luck. Still about the same rate of overflows :(
>
>
FYI, I worked around the issue by using two 520-CR NICs instead of the 
one 540-CR NIC and performance is solid again with no dropped packets

     ---Mike