netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jarek Poplawski <jarkao2@gmail.com>
To: Tom Herbert <therbert@google.com>
Cc: David Miller <davem@davemloft.net>, netdev@vger.kernel.org
Subject: Re: [PATCH v4 1/1] rps: core implementation
Date: Sat, 21 Nov 2009 01:40:11 +0100	[thread overview]
Message-ID: <4B0736EB.8090406@gmail.com> (raw)
In-Reply-To: <65634d660911201612y12a9b5bnb6685da040ad832d@mail.gmail.com>

Tom Herbert wrote, On 11/21/2009 01:12 AM:

>> I guess my confusion is from the:
>>
>>                                __raise_softirq_irqoff(NET_RX_SOFTIRQ);
>>
>> you are doing as you set the cpus in rps_remote_softirq_cpus.
>>
>> Why do you need to schedule the local RX softirq, when we know we're
>> in a NAPI poll loop and thus that we're in a softirq, and thus that we
>> will fire off the IPIs at the end of net_rx_action()?
>>
>> That's what you're doing, the softirq raising just seems superfluous.
>>
> 
> Ah, right. If RPS can't be used non-NAPI case, this line is now
> superfluous.  It can be removed.

Hmm... mostly right. At least if it's wrt. my previous opinion. I meant
only that non-NAPI case would be handled less optimally without this
dedicated softirq, but __raise_softirq_irqoff(NET_RX_SOFTIRQ) or
napi_schedule(&queue->backlog) could be called from netif_rx().

Jarek P.

  reply	other threads:[~2009-11-21  0:40 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-11-20 23:28 [PATCH v4 1/1] rps: core implementation Tom Herbert
2009-11-20 23:39 ` David Miller
2009-11-20 23:50   ` Tom Herbert
2009-11-21  0:05     ` David Miller
2009-11-21  0:12       ` Tom Herbert
2009-11-21  0:40         ` Jarek Poplawski [this message]
2009-11-20 23:40 ` Stephen Hemminger
2009-11-20 23:53   ` Tom Herbert
2009-11-20 23:56   ` David Miller
2009-12-17 21:04   ` Tom Herbert
2010-01-06  1:32     ` Tom Herbert
2010-01-06  5:54       ` Eric Dumazet
2010-01-06  7:56         ` Tom Herbert
2010-01-06 18:38         ` Eric Dumazet
2010-01-06 21:10           ` [BUG net-next-2.6] Had to revert bonding: allow arp_ip_targets on separate vlans to use arp validation Eric Dumazet
2010-01-06 21:28             ` Jay Vosburgh
2010-01-06 21:34               ` Eric Dumazet
2010-01-06 21:38             ` David Miller
2010-01-06 21:45               ` Andy Gospodarek
2010-01-06 22:56             ` [PATCH net-next-2.6] fix " Andy Gospodarek
2010-01-06 23:53               ` Jay Vosburgh
2010-01-07  8:37                 ` Eric Dumazet
2010-01-07  8:41                   ` David Miller
2010-01-06 22:54           ` [PATCH v4 1/1] rps: core implementation Tom Herbert
2010-01-07  9:15             ` Eric Dumazet
2010-01-07 17:42               ` rps: some comments Eric Dumazet
2010-01-08  0:07                 ` Tom Herbert
2010-01-08  6:27                   ` Eric Dumazet
2010-01-11  6:25               ` [PATCH v4 1/1] rps: core implementation Tom Herbert
2010-01-11  9:00                 ` Eric Dumazet
2010-01-14  4:40                   ` David Miller
2009-11-20 23:42 ` Stephen Hemminger
2009-11-21  0:04   ` Tom Herbert
2009-11-21  8:07 ` Eric Dumazet
2009-11-21  9:03   ` Tom Herbert
2009-11-21  9:31     ` Eric Dumazet

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=4B0736EB.8090406@gmail.com \
    --to=jarkao2@gmail.com \
    --cc=davem@davemloft.net \
    --cc=netdev@vger.kernel.org \
    --cc=therbert@google.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).