netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Felix Fietkau <nbd@openwrt.org>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: netdev@vger.kernel.org, zajec5@gmail.com, hauke@hauke-m.de
Subject: Re: [PATCH 4/4] bgmac: fix DMA rx corruption
Date: Sun, 12 Apr 2015 19:28:48 +0200	[thread overview]
Message-ID: <552AAB50.7010401@openwrt.org> (raw)
In-Reply-To: <1428859488.25985.347.camel@edumazet-glaptop2.roam.corp.google.com>

On 2015-04-12 19:24, Eric Dumazet wrote:
> On Sun, 2015-04-12 at 12:43 +0200, Felix Fietkau wrote:
>> On 2015-04-12 12:31, Eric Dumazet wrote:
> 
>> > This might be better for performance to perform one single bgmac_write()
>> > at the end of bgmac_dma_rx_read(), and leave this one in place as well,
>> > not for performance since this is slow path, but correctness.
>> I intentionally made it write this field for every slot update, because
>> it might potentially allow the hardware to push frames faster when under
>> pressure. The CPU isn't fast enough to handle gigabit speeds anyway.
> 
> If CPU is not fast enough, then it makes sense to optimize this part,
> and save cpu cycles for actual processing.
> 
> You know, even a fast cpu is not able to keep up at 40Gbits.
> 
> You have a clear opportunity to have batching right there, take it.
Already did that in v2. :)

- Felix

  reply	other threads:[~2015-04-12 17:28 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-04-12 10:08 [PATCH 1/4] bgmac: simplify tx ring index handling Felix Fietkau
2015-04-12 10:08 ` [PATCH 2/4] bgmac: leave interrupts disabled as long as there is work to do Felix Fietkau
2015-04-12 10:08 ` [PATCH 3/4] bgmac: set received skb headroom to NET_SKB_PAD Felix Fietkau
2015-04-12 10:08 ` [PATCH 4/4] bgmac: fix DMA rx corruption Felix Fietkau
2015-04-12 10:31   ` Eric Dumazet
2015-04-12 10:43     ` Felix Fietkau
2015-04-12 17:24       ` Eric Dumazet
2015-04-12 17:28         ` Felix Fietkau [this message]
2015-04-12 10:31   ` Jakub Kiciński
2015-04-12 11:11   ` Sergei Shtylyov

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 \
    --in-reply-to=552AAB50.7010401@openwrt.org \
    --to=nbd@openwrt.org \
    --cc=eric.dumazet@gmail.com \
    --cc=hauke@hauke-m.de \
    --cc=netdev@vger.kernel.org \
    --cc=zajec5@gmail.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).