netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Zacco <zacco@fw.hu>
To: David Miller <davem@davemloft.net>
Cc: baruch@ev-en.org, netdev@vger.kernel.org
Subject: Re: many sockets, slow sendto
Date: Tue, 20 Mar 2007 22:59:10 +0100	[thread overview]
Message-ID: <4600592E.80605@fw.hu> (raw)
In-Reply-To: <20070319.161611.70218081.davem@davemloft.net>

Hi,

David Miller wrote:
> From: Zacco <zacco@fw.hu>
> Date: Tue, 20 Mar 2007 00:10:19 +0100
>
>   
>> As you recommended, I used oprofile and it turned out that the 
>> __udp4_lib_lookup function spent most of the time. There is a udp hash 
>> table and the sockets are sought based on the 7 LSBs of the destination 
>> port number. So what happened is now quite obvious: I had many thousands 
>> of sockets, all with the same destination port, thus linked in the same 
>> slot of this hash table. I tried using different ports and it
>> was much faster then.
>>     
>
> There isn't much we can do here.  I bet your destination address
> is unchanging just like your destination ports.
>   
As I'm simulating independent users on one host, each user has a 
different IP address, but each with the same port. So unlike the port, 
the address is changing, basically it's a huge A-class range.

> UDP apps can and do bind to specific destination addresses and
> ports, but the source side is usually wild-carded.
>   
Right, usually it is, but in my case the source addresses are also 
bound, otherwise the source address would be the primary address of the 
physical interface; however, I need to simulate users as if they were on 
separate hosts.
> Are both the source address and port fully specified for your
> sockets?  Maybe we can do something using if that's the case...
>   
You made me curious.  :)  What do you have in mind?

thx: Zacco

  reply	other threads:[~2007-03-20 21:58 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-03-06 15:08 many sockets, slow sendto Zaccomer Lajos
2007-03-06 18:20 ` Baruch Even
2007-03-19 23:10   ` Zacco
2007-03-19 23:16     ` David Miller
2007-03-20 21:59       ` Zacco [this message]
2007-03-20 22:48         ` Eric Dumazet
2007-03-21 21:53           ` Zacco
2007-03-21 22:24             ` Eric Dumazet
2007-03-21 23:26             ` Eric Dumazet
2007-03-22  1:14             ` David Miller
2007-03-21 22:12           ` Eric Dumazet
2007-03-22  1:15             ` David Miller
2007-03-22  6:43               ` Eric Dumazet
2007-03-29 19:24             ` Zacco
2007-03-30 13:10               ` Eric Dumazet
2007-04-22 12:34                 ` Zacco
2007-04-30  7:26             ` David Miller
2007-04-30 10:56               ` YOSHIFUJI Hideaki / 吉藤英明
2007-04-30 12:47                 ` Eric Dumazet
2007-04-30 19:43                   ` YOSHIFUJI Hideaki / 吉藤英明
2007-04-30 19:59                     ` Eric Dumazet
2007-03-06 19:23 ` Andi Kleen
2007-03-06 21:28   ` Zacco

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=4600592E.80605@fw.hu \
    --to=zacco@fw.hu \
    --cc=baruch@ev-en.org \
    --cc=davem@davemloft.net \
    --cc=netdev@vger.kernel.org \
    /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).