From: Ben Hutchings <email@example.com> To: Eric Dumazet <firstname.lastname@example.org> Cc: "Grant Grundler" <email@example.com>, "Freddy Xin" <firstname.lastname@example.org>, "David Miller" <email@example.com>, netdev <firstname.lastname@example.org>, email@example.com, LKML <firstname.lastname@example.org>, "ASIX Louis [蘇威陸]" <email@example.com>, "Allan Chou" <firstname.lastname@example.org> Subject: Re: [PATCH 1/1] TX throttling bug-fixing patch of AX88179_178A Date: Mon, 22 Jul 2013 20:47:51 +0100 [thread overview] Message-ID: <email@example.com> (raw) In-Reply-To: <1374518841.4990.26.camel@edumazet-glaptop> On Mon, 2013-07-22 at 11:47 -0700, Eric Dumazet wrote: > On Mon, 2013-07-22 at 19:38 +0100, Ben Hutchings wrote: > > On Mon, 2013-07-22 at 11:29 -0700, Grant Grundler wrote: > > > On Mon, Jul 22, 2013 at 10:07 AM, Eric Dumazet <firstname.lastname@example.org> wrote: > > > ... > > > > I guess that if a driver does not advertise NETIF_F_SG, this > > > > skb_linearize() call is not needed : All frames reaching your xmit > > > > function should already be linear > > > > > > As Ben Hutchings pointed out, hw_features is still setting this...but > > > I'm not sure how that matters. > > > > > > ax88179_set_features() doesn't allow setting SG or TSO features. But > > > I expect it would be "not too difficult" to add such that ethtool > > > could set those features after boot. > > [...] > > > > It already can. That's what putting feature flags in hw_features does. > > My original concern, that inspired this patch, was to remove SG support, > as this driver does not have SG support at all. > > Linearize a full TSO packet needs order-5 allocations, thats likely to > fail and lead to very slow TCP performance, because it will only rely on > retransmits. The driver could set gso_max_size to reduce that problem. But I rather doubt that TSO followed by skb_linearize() significantly improves throughput or CPU-efficiency. (If the device has a 1G link but is connected to the host through a USB 2.0 port, then USB is the bottleneck and TSO could improve throughput a few percent. But that's a silly configuration.) The real solution would be for someone to add SG support to the usbnet core. Trying to support 1GbE with only linear skbs is not a great idea... and it can only be a matter of time before there is USB ultra speed (or whatever comes after 'super') with 10GbE devices... Ben. -- Ben Hutchings, Staff Engineer, Solarflare Not speaking for my employer; that's the marketing department's job. They asked us to note that Solarflare product names are trademarked.
next prev parent reply other threads:[~2013-07-22 19:47 UTC|newest] Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top 2013-07-20 9:16 freddy 2013-07-22 17:07 ` Eric Dumazet 2013-07-22 17:11 ` Ben Hutchings 2013-07-22 18:29 ` Grant Grundler 2013-07-22 18:38 ` Ben Hutchings 2013-07-22 18:47 ` Eric Dumazet 2013-07-22 19:47 ` Ben Hutchings [this message] [not found] ` <1374522471.1635.48.camel-/LGg1Z1CJKQ+9kgCwbf1HqK4ta4zdZpAajtMo4Cw6ucAvxtiuMwx3w@public.gmane.org> 2013-07-23 6:10 ` Eric Dumazet 2013-07-23 23:46 ` David Miller 2013-07-23 23:56 ` Eric Dumazet 2013-07-24 0:05 ` Eric Dumazet 2013-07-24 0:15 ` [PATCH] usbnet: do not pretend to support SG/TSO Eric Dumazet 2013-07-26 20:48 ` David Miller 2013-07-24 0:17 ` [PATCH 1/1] TX throttling bug-fixing patch of AX88179_178A David Miller 2013-07-24 2:29 ` Grant Grundler [not found] ` <CANEJEGtLavwdPdq_Qojz_x-DQ3KXfZp0vPYr6imKtNxN0Hf_2Q-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org> 2013-07-24 2:32 ` Grant Grundler 2013-07-25 2:28 ` Ming Lei 2013-07-25 5:10 ` Eric Dumazet 2013-07-25 5:25 ` Ming Lei [not found] ` <CACVXFVNyFk0Zpi4tC0ENiq8RcrtrjYW-Dhs+A56+Pw4BKm8y8A-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org> 2013-07-25 11:01 ` Eric Dumazet 2013-07-25 14:52 ` Ming Lei 2013-07-25 15:00 ` Ben Hutchings [not found] ` <CACVXFVNre5SsJhaVqFNRcop7ahqxabWqHZkjBZccj1ZqOAUZ9A-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org> 2013-07-25 15:11 ` Eric Dumazet 2013-07-25 13:34 ` Ben Hutchings
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --subject='Re: [PATCH 1/1] TX throttling bug-fixing patch of AX88179_178A' \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).