[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1335926703.22133.39.camel@edumazet-glaptop>
Date: Wed, 02 May 2012 04:45:03 +0200
From: Eric Dumazet <eric.dumazet@...il.com>
To: Alexander Duyck <alexander.h.duyck@...el.com>
Cc: Alexander Duyck <alexander.duyck@...il.com>,
David Miller <davem@...emloft.net>,
netdev <netdev@...r.kernel.org>,
Neal Cardwell <ncardwell@...gle.com>,
Tom Herbert <therbert@...gle.com>,
Jeff Kirsher <jeffrey.t.kirsher@...el.com>,
Michael Chan <mchan@...adcom.com>,
Matt Carlson <mcarlson@...adcom.com>,
Herbert Xu <herbert@...dor.apana.org.au>,
Ben Hutchings <bhutchings@...arflare.com>,
Ilpo Järvinen <ilpo.jarvinen@...sinki.fi>,
Maciej Żenczykowski <maze@...gle.com>
Subject: Re: [PATCH 3/4 v2 net-next] net: make GRO aware of skb->head_frag
On Tue, 2012-05-01 at 12:45 -0700, Alexander Duyck wrote:
> I wasn't worried about the kfree vs put_page, I was worried about the
> coalesce case. However, it looks like you are correct and I am not
> seeing any issues so everything seems to be working fine.
>
> I have a hacked together ixgbe up and running now with the new build_skb
> logic and RSC/LRO disabled. It looks like it is giving me a 5%
> performance boost for small packet routing, but I am using more CPU for
> netperf TCP receive tests and I was wondering if you had seen anything
> similar on the tg3 driver?
>
Hmm, tg3 perf for small packets is not changed, because tg3 uses
copybreak anyway.
#define TG3_RX_COPY_THRESHOLD 256
For big packets, I have no changes in netperf because GRO cannot really
provide big enough skbs at 1Gb speed.
The changes are noticeable when BDP (Bandwidth*Delay Product) is large
and some packet losses happen : You notice lower latencies in TCP stack,
because of less collapses (big copies)
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists