Thread (28 messages) 28 messages, 6 authors, 2014-06-01

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 the
patches 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 much
performance 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 that
support byte alignment,  so it also use one descriptor per MSS.
quoted
Thanks for your suggestion and response. Do you know why highmem cause
much 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
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help