Message-ID: <89da4b36-e814-9238-71a6-044af49e8de8@nbd.name>
Date:   Thu, 23 Dec 2021 09:58:44 +0100
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:91.0)
 Gecko/20100101 Thunderbird/91.4.1
Content-Language: en-US
To:     Karthikeyan Periyasamy <quic_periyasa@quicinc.com>,
        ath11k@lists.infradead.org
Cc:     linux-wireless@vger.kernel.org
References: <1640248077-14075-1-git-send-email-quic_periyasa@quicinc.com>
From:   Felix Fietkau <nbd@nbd.name>
Subject: Re: [PATCH] ath11k: Add peer rhash table support
In-Reply-To: <1640248077-14075-1-git-send-email-quic_periyasa@quicinc.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 2021-12-23 09:27, Karthikeyan Periyasamy wrote:
> When more clients (128) are connected, the UL data traffic
> KPI measurement is low compared to single client. This issue
> is due to more CPU cycles spent on the peer lookup operation
> with more clients. So reduce the peer lookup operation by
> modifying the linear based lookup operation into the rhash
> based lookup operation. This improve the peak throughput
> measurement. Since this is a software algorithm change, it is
> applicable for all the platforms.
> 
> TCP UL 128 Clients test case Observation (64bit system):
> Previous: ~550 Mbps
> Now	: ~860 Mbps
> 
> Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.5.0.1-01067-QCAHKSWPL_SILICONZ-1
> 
> Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Why does ath11k keep a separate peer list instead of just using the sta 
entry? That seems ugly and inefficient...

- Felix