RE: [PATCH v1 6/6] net: fec: Add software TSO support
From: fugang.duan@freescale.com <hidden>
Date: 2014-06-01 02:25:49
From: Eric Dumazet <redacted> Data: Sunday, June 01, 2014 9:40 AM
To: Duan Fugang-B38611 Cc: Li Frank-B20596; davem@davemloft.net; ezequiel.garcia@free- electrons.com; netdev@vger.kernel.org; shawn.guo@linaro.org; bhutchings@solarflare.com; stephen@networkplumber.org Subject: RE: [PATCH v1 6/6] net: fec: Add software TSO support On Sun, 2014-06-01 at 00:55 +0000, fugang.duan@freescale.com wrote:quoted
From: Eric Dumazet <redacted> Data: Saturday, May 31, 2014 12:22 AM So I connect to APPLE MAC book to test again, test result (applied thepatches to our internal kernel 3.10.31):quoted
High mem disable: tx bandwidth 942Mbps, cpu loading is 65%. High mem enable: tx bandwidth 930Mbps, cpu loading is 100%. => I don't know why kernel highmem config enable cause so muchperformance drop ???quoted
For your above suggestion "using one descriptor per MSS, instead of two": Yes, for imx6dl soc, we just do it like this. For imx6sx soc FEC thatsupport byte alignment, so it also use one descriptor per MSS.quoted
Thanks for your suggestion and response. Do you know why highmem causemuch performance drop for SW TSO ? Check NETIF_F_HIGHDMA : your driver might be able to advertise its support.
Indeed, I got the test result after add "NETIF_F_HIGHDMA" feature, otherwise, the performance is worse.
Check your copies, because you might then need kmap() For an example, read efx_skb_copy_bits_to_pio() in drivers/net/ethernet/sfc/tx.c
I will check it. Thanks, Andy