On Sun, Sep 15, 2024 at 07:08:35PM +0100, Simon Horman wrote: > On Sat, Sep 14, 2024 at 09:56:24PM -0700, Shradha Gupta wrote: > > Through some experiments, we found out that increasing the default > > RX buffers count from 512 to 1024, gives slightly better throughput > > and significantly reduces the no_wqe_rx errs on the receiver side. > > Along with these, other parameters like cpu usage, retrans seg etc > > also show some improvement with 1024 value. > > > > Following are some snippets from the experiments > > > > ntttcp tests with 512 Rx buffers > > --------------------------------------- > > connections| throughput| no_wqe errs| > > --------------------------------------- > > 1 | 40.93Gbps | 123,211 | > > 16 | 180.15Gbps | 190,120 > > 128 | 180.20Gbps | 173,508 | > > 256 | 180.27Gbps | 189,884 | > > > > ntttcp tests with 1024 Rx buffers > > --------------------------------------- > > connections| throughput| no_wqe errs| > > --------------------------------------- > > 1 | 44.22Gbps | 19,864 | > > 16 | 180.19Gbps | 4,430 | > > 128 | 180.21Gbps | 2,560 | > > 256 | 180.29Gbps | 1,529 | > > > > So, increasing the default RX buffers per queue count to 1024 > > > > Signed-off-by: Shradha Gupta <shradhagupta@xxxxxxxxxxxxxxxxxxx> > > Reviewed-by: Haiyang Zhang <haiyangz@xxxxxxxxxxxxx> > > Hi Shradha, > > net-next is currently closed other than for bug fixes. > Please consider reposting once it re-opens, after v6.12-rc1 > has been released. Noted, thanks Simon > > -- > pw-bot: defer
